hh.sePublications
Change search
Refine search result
123 51 - 100 of 145
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 51.
    Lundström, Jens
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent Systems´ laboratory.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent Systems´ laboratory.
    System for Assessing, Exploring and Monitoring Offset Print Quality2011In: Recent Researches in Circuits, Systems, Communications & Computers: Proc. of 2nd European Conference of Communications (ECCOM'11), Athens: World Scientific and Engineering Academy and Society, 2011, p. 28-33Conference paper (Refereed)
    Abstract [en]

    Variations in offset print quality relate to numerous parameter of printing press and paper. To maintain constant quality of products, press operators need to assess, explore and monitor print quality. This paper presents a novel system for assessing and predicting values of print quality attributes, where the adopted, random forests (RF)-based, modeling approach also allows quantifying the influence of different parameters. In contrast to other print quality assessment systems, this system utilizes common print marks known as double grey-bars. A novel virtual sensor for assessing the mis-registration degree of printing plates using images of double grey-bars is presented. The inferred influence of paper and printing press parameters on print quality shows correlation with known print quality conditions.

  • 52.
    Lundström, Jens
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent Systems´ laboratory.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent Systems´ laboratory. Kaunas University of Technology, Kaunas, Lithuania.
    Tullander, E.
    Hylte Mill, Hyltebruk, Sweden.
    Larsson, B.
    V-TAB, Hisingsbacka, Sweden.
    Assessing, exploring, and monitoring quality of offset colour prints2013In: Measurement, ISSN 0263-2241, E-ISSN 1873-412X, Vol. 46, no 4, p. 1427-1441Article in journal (Refereed)
    Abstract [en]

    Variations in offset print quality relate to numerous parameters of printing press and paper. To maintain a constant high print quality press operators need to assess, explore and monitor quality of prints. Today assessment is mainly done manually. This paper presents a novel system for assessing and predicting values of print quality attributes, where the adopted, random forests (RFs)-based, modeling approach also allows quantifying the influence of different paper and press parameters on print quality. In contrast to other print quality assessment systems the proposed system utilises common, simple print marks known as double grey-bars. Novel virtual sensors assessing print quality attributes using images of double grey-bars are presented. The inferred influence of paper and printing press parameters on quality of colour prints shows clear relation with known print quality conditions. Thorough analysis and categorisation of related work is also given in the paper. (C) 2012 Elsevier Ltd. All rights reserved.

  • 53.
    Malmqvist, K.
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
    Malmqvist, L.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
    Bergman, L.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
    A new method for colour measurements in multicolour newspaper pictures and its use for ink feed control1996In: 1996 INTERNATIONAL PRINTING & GRAPHIC ARTS CONFERENCE, 1996, p. 181-185Conference paper (Refereed)
  • 54.
    Menezes, Maria Luiza Recena
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).
    Samara, A.
    School of Computing and Mathematics, Ulster University Belfast, Belfast, United Kingdom.
    Galway, L.
    School of Computing and Mathematics, Ulster University Belfast, Belfast, United Kingdom.
    Pinheiro Sant'Anna, Anita
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Alonso-Fernandez, Fernando
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Wang, H.
    School of Computing and Mathematics, Ulster University Belfast, Belfast, United Kingdom.
    Bond, R.
    School of Computing and Mathematics, Ulster University Belfast, Belfast, United Kingdom.
    Towards emotion recognition for virtual environments: an evaluation of eeg features on benchmark dataset2017In: Personal and Ubiquitous Computing, ISSN 1617-4909, E-ISSN 1617-4917, Vol. 21, no 6, p. 1003-1013Article in journal (Refereed)
    Abstract [en]

    One of the challenges in virtual environments is the difficulty users have in interacting with these increasingly complex systems. Ultimately, endowing machines with the ability to perceive users emotions will enable a more intuitive and reliable interaction. Consequently, using the electroencephalogram as a bio-signal sensor, the affective state of a user can be modelled and subsequently utilised in order to achieve a system that can recognise and react to the user’s emotions. This paper investigates features extracted from electroencephalogram signals for the purpose of affective state modelling based on Russell’s Circumplex Model. Investigations are presented that aim to provide the foundation for future work in modelling user affect to enhance interaction experience in virtual environments. The DEAP dataset was used within this work, along with a Support Vector Machine and Random Forest, which yielded reasonable classification accuracies for Valence and Arousal using feature vectors based on statistical measurements and band power from the and waves and High Order Crossing of the EEG signal. © 2017, The Author(s).

  • 55.
    Minelga, Jonas
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Lithuania.
    Vaiciukynas, Evaldas
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab). Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Kaunas University of Technology, Kaunas, Lithuania.
    Padervinskis, Evaldas
    Department of Otolaryngology, Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Uloza, Virgilijus
    Department of Otolaryngology, Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Comparing Throat and Acoustic Microphones for Laryngeal Pathology Detection from Human Voice2014In: Electrical and Control Technologies: Proceedings of the 9th International Conference on Electrical and Control Technologies ECT-2014 / [ed] A. Navickas (general editor), A. Sauhats, A. Virbalis, M. Ažubalis, V. Galvanauskas, K. Brazauskas & A. Jonaitis, Kaunas: Kaunas University of Technology , 2014, p. 50-53Conference paper (Refereed)
    Abstract [en]

    The aim of this study was to compare acoustic and throat microphones in the voice pathology detection task. Recordings of sustained phonation /a/ were used in the study. Each recording was characterized by a rather large set of diverse features, 1051 features in total. Classification into two classes, namely normal and pathological, was performed using random forest committees. Models trained using data obtained from the throat microphone provided lower classification accuracy. This is probably due to a narrower frequency range of the throat microphone leading to loss of important information. © Kaunas University of Technology, 2014.

  • 56.
    Minelga, Jonas
    et al.
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Vaiciukynas, Evaldas
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    A Transparent Decision Support Tool in Screening for Laryngeal Disorders Using Voice and Query Data2017In: Applied Sciences: APPS, ISSN 1454-5101, E-ISSN 1454-5101, Vol. 7, no 10, p. 1-15, article id 1096Article in journal (Refereed)
    Abstract [en]

    The aim of this study is a transparent tool for analysis of voice (sustained phonation /a/) and query data capable of providing support in screening for laryngeal disorders. In this work, screening is concerned with identification of potentially pathological cases by classifying subject’s data into ’healthy’ and ’pathological’ classes as well as visual exploration of data and automatic decisions. A set of association rules and a decision tree, techniques lending themselves for exploration, were generated for pathology detection. Data pairwise similarities, estimated in a novel way, were mapped onto a 2D metric space for visual inspection and analysis. Accurate identification of pathological cases was observed on unseen subjects using the most discriminative query parameter and six audio parameters routinely used by otolaryngologists in a clinical practice: equal error rate (EER) of 11.1% was achieved using association rules and 10.2% using the decision tree. The EER was further reduced to 9.5% by combining results from these two classifiers. The developed solution can be a useful tool for Otolaryngology departments in diagnostics, education and exploratory tasks. © 2017 by the authors.

  • 57.
    Olenina, Irina
    et al.
    Marine Science and Technology Centre, Klaipėda University, Klaipėda, Lithuania & Department of Marine Research, Environmental Protection Agency, Lithuania.
    Vaiciukynas, Evaldas
    Department of Information Systems, Kaunas University of Technology, Lithuania & Department of Electrical Power Systems, Kaunas University of Technology, Lithuania .
    Sulcius, Sigitas
    Marine Science and Technology Centre, Klaipėda University, Klaipėda, Lithuania & Laboratory of Algology and Microbial Ecology, Nature Research Centre, Lithuania.
    Paskauskas, Ricardas
    Marine Science and Technology Centre, Klaipėda University, Klaipėda, Lithuania & Laboratory of Algology and Microbial Ecology, Nature Research Centre, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Department of Electrical Power Systems, Kaunas University of Technology, Lithuania.
    Gelzinis, Adas
    Department of Electrical Power Systems, Kaunas University of Technology, Lithuania.
    Bacauskiene, Marija
    Department of Electrical Power Systems, Kaunas University of Technology, Lithuania.
    Bertasiute, Vilma
    Marine Science and Technology Centre, Klaipėda University, Klaipėda, Lithuania.
    Olenin, Sergej
    Marine Science and Technology Centre, Klaipėda University, Klaipėda, Lithuania.
    The dinoflagellate Prorocentrum cordatum at the edge of the salinity tolerance: The growth is slower but cells are larger2016In: Estuarine, Coastal and Shelf Science, ISSN 0272-7714, E-ISSN 1096-0015, Vol. 168, no 5, p. 71-79Article in journal (Refereed)
    Abstract [en]

    In this study we examine how the projected climate change driven decrease in the Baltic Sea salinity can impact the growth, cell size and shape of the recently invaded dinoflagellate Prorocentrum cordatum. In laboratory treatments we mimicked salinity conditions at the edge of the mesohaline south-eastern Baltic and oligohaline-to-limnic Curonian Lagoon. We used an innovative computer-based method allowing detection of P. cordatum cells and quantitative characterization of cell contours in phytoplankton images. This method also made available robust indicators of the morphometric changes, which are not accessible for an expert studying cells under light microscope. We found that the salinity tolerance limit of P. cordatum ranges between 1.8 and 3.6, and that the mean cell size of its population is inversely proportional to both salinity and nutrient content. Under ambient south-eastern Baltic salinity (7.2) the nutrients were stimulating the growth of P. cordatum; while at the edge of its salinity tolerance the nutrient availability did not have such effect. We suggest that in the future Baltic the decline insalinity and increase in nutrient loads may result in larger cells of P. cordatum and extended duration of their presence in plankton, causing longer periods of algal blooms.

  • 58.
    Razanskas, Petras
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Olsson, Charlotte
    Halmstad University, School of Business, Engineering and Science, Biological and Environmental Systems (BLESS).
    Wiberg, Per-Arne
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Time Domain Features of Multi-channel EMG Applied to Prediction of Physiological Parameters in Fatiguing Bicycling Exercises2015In: Frontiers in Artificial Intelligence and Applications, ISSN 0922-6389, E-ISSN 1879-8314, Vol. 278, p. 118-127Article in journal (Refereed)
    Abstract [en]

    A set of novel time-domain features characterizing multi-channel surface EMG (sEMG) signals of six muscles (rectus femoris, vastus lateralis, and semitendinosus of each leg) is proposed for prediction of physiological parameters considered important in cycling: blood lactate concentration and oxygen uptake. Fifty one different features, including phase shifts between muscles, active time percentages, sEMG amplitudes, as well as symmetry measures between both legs, were defined from sEMG data and used to train linear and random forest models. The random forests models achieved the coefficient of determination R2 = 0:962 (lactate) and R2 = 0:980 (oxygen). The linear models were less accurate. Feature pruning applied enabled creating accurate random forest models (R2 >0:9) using as few as 7 (lactate) or 4 (oxygen) time-domain features. sEMG amplitude was important for both types of models. Models to predict lactate also relied on measurements describing interaction between front and back muscles, while models to predict oxygen uptake relied on front muscles only, but also included interactions between the two legs. © 2015 The authors and IOS Press. All rights reserved.

  • 59.
    Ražanskas, Petras
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Kaunas University of Technology, Kaunas, Lithuania.
    Olsson, Charlotte
    Halmstad University, School of Business, Engineering and Science, Biological and Environmental Systems (BLESS).
    Wiberg, Per-Arne
    Swedish Adrenaline, Halmstad, Sweden.
    Predicting Blood Lactate Concentration and Oxygen Uptake from sEMG Data during Fatiguing Cycling Exercise2015In: Sensors, ISSN 1424-8220, E-ISSN 1424-8220, Vol. 15, no 8, p. 20480-20500Article in journal (Refereed)
    Abstract [en]

    This article presents a study of the relationship between electromyographic (EMG) signals from vastus lateralis, rectus femoris, biceps femoris and semitendinosus muscles, collected during fatiguing cycling exercises, and other physiological measurements, such as blood lactate concentration and oxygen consumption. In contrast to the usual practice of picking one particular characteristic of the signal, e.g., the median or mean frequency, multiple variables were used to obtain a thorough characterization of EMG signals in the spectral domain. Based on these variables, linear and non-linear (random forest) models were built to predict blood lactate concentration and oxygen consumption. The results showed that mean and median frequencies are sub-optimal choices for predicting these physiological quantities in dynamic exercises, as they did not exhibit significant changes over the course of our protocol and only weakly correlated with blood lactate concentration or oxygen uptake. Instead, the root mean square of the original signal and backward difference, as well as parameters describing the tails of the EMG power distribution were the most important variables for these models. Coefficients of determination ranging from R2 = 0:77 to R2 = 0:98 (for blood lactate) and from R2 = 0:81 to R2 = 0:97 (for oxygen uptake) were obtained when using random forest regressors.

  • 60.
    Ražanskas, Petras
    et al.
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Department of Electrical Power Systems, Kaunas University of Technology, Lithuania.
    Viberg, Per-Arne
    Swedish Adrenaline, Halmstad, Sweden.
    Olsson, Charlotte M.
    Halmstad University, School of Business, Engineering and Science, The Rydberg Laboratory for Applied Sciences (RLAS).
    Predicting physiological parameters in fatiguing bicycling exercises using muscle activation timing2017In: Biomedical Signal Processing and Control, ISSN 1746-8094, E-ISSN 1746-8108, Vol. 35, p. 19-29Article in journal (Refereed)
    Abstract [en]

    This article is concerned with a novel technique for prediction of blood lactate concentration level and oxygen uptake rate from multi-channel surface electromyography (sEMG) signals. The approach is built on predictive models exploiting a set of novel time-domain variables computed from sEMG signals. Signals from three muscles of each leg, namely, vastus lateralis, rectus femoris, and semitendinosus were used in this study. The feature set includes parameters reflecting asymmetry between legs, phase shifts between activation of different muscles, active time percentages, and sEMG amplitude. Prediction ability of both linear and non-linear (random forests-based) models was explored. The random forests models showed very good prediction accuracy and attained the coefficient of determination R2 = 0.962 for lactate concentration level and R2 = 0.980 for oxygen uptake rate. The linear models showed lower prediction accuracy. Comparable results were obtained also when sEMG amplitude data were removed from the training sets. A feature elimination algorithm allowed to build accurate random forests (R2 > 0.9) using just six (lactate concentration level) or four (oxygen uptake rate) time-domain variables. Models created to predict blood lactate concentration rate relied on variables reflecting interaction between front and back leg muscles, while parameters computed from front muscles and interactions between two legs were the most important variables for models created to predict oxygen uptake rate.© 2017 Elsevier Ltd.

  • 61.
    Rimavičius, Tadas
    et al.
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Gelžinis, Adas
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Vaiciukynas, Evaldas
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Bačauskiene, Marija
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Šaškov, Aleksėj
    Open Access Centre for Marine Research, Klaipeda University, Klaipeda, Lithuania.
    Automatic benthic imagery recognition using a hierarchical two-stage approach2018In: Signal, Image and Video Processing, ISSN 1863-1703, E-ISSN 1863-1711, Vol. 12, no 6, p. 1107-1114Article in journal (Refereed)
    Abstract [en]

    The main objective of this work is to establish an automated classification system of seabed images. A novel two-stage approach to solving the image region classification task is presented. The first stage is based on information characterizing geometry, colour and texture of the region being analysed. Random forests and support vector machines are considered as classifiers in this work. In the second stage, additional information characterizing image regions surrounding the region being analysed is used. The reliability of decisions made in the first stage regarding the surrounding regions is taken into account when constructing a feature vector for the second stage. The proposed technique was tested in an image region recognition task including five benthic classes: red algae, sponge, sand, lithothamnium and kelp. The task was solved with the average accuracy of 90.11% using a data set consisting of 4589 image regions and the tenfold cross-validation to assess the performance. The two-stage approach allowed increasing the classification accuracy for all the five classes, more than 27% for the “difficult” to recognize “kelp” class. © 2018, Springer-Verlag London Ltd., part of Springer Nature.

  • 62.
    Signahl, Mikael
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Fuzzy combination schemes for modular neural networks1997In: SCIA '97, the 10th Scandinavian conference on image analysis: proceedings / [ed] Frydrych, M; Parkkinen, J; Visa, A, Lappeenranta: Pattern Recognition Society of Finland , 1997, p. 419-424Conference paper (Refereed)
    Abstract [en]

    In this paper, we discuss some new methods for combining different outputs from several feed forward neural networks into a final output. We generalize the BADD defuzzification method (G-BADD) to obtain substantial improvement in system output. It is compared with the ordinary BADD-, Sugeno- and the MOM-methods. The use of the fuzzy integral, as a selection tool when deciding which networks are to be used in the combination, is introduced.

  • 63.
    Stasiunas, Antanas
    et al.
    Kaunas University of Technology.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Kaunas University of Technology.
    Miliauskas, As
    Kaunas University of Medicine.
    An adaptive functional model of the filtering system of the cochlea of the inner ear2011In: Proceedings of the 4th Imternational Symposium on Applied Sciences in Biomedical and Communication Technologies, ISABEL 2011, ACM Press, 2011, p. -6Conference paper (Refereed)
    Abstract [en]

    Outer hair cells (OHC) in the cochlea of the inner ear, together with the local structures of the basilar membrane, reticular lamina and tectorial membrane, constitute the adaptive primary filters (PF) of the second order. We used them for designing a serial-parallel signal filtering system. We determined a rational number of PF included in Gaussian channels of the system, summation weights of the output signals, and distribution of PF along the basilar membrane. A Gaussian channel consisting of five PF is presented as an example, and properties of the channel operating in the linear and non-linear mode are determined during adaptation and under efferent control. The results suggest that application of biological filtering principles can be useful for designing of cochlear implants with new strategies of speech encoding.

  • 64.
    Stasiunas, Antanas
    et al.
    Kaunas University of Technology, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Bacauskiene, Marija
    Kaunas University of Technology, Lithuania.
    Miliauskas, Rimvydas
    Lithuanian University of Health Sciences, Lithuania.
    A Serial-Parallel Panoramic Filter Bank as a Model of Frequency Decomposition of Complex Sounds in the Human Inner Ear2011In: Informatica (Vilnius), ISSN 0868-4952, E-ISSN 1822-8844, Vol. 22, no 2, p. 259-278Article in journal (Refereed)
    Abstract [en]

    We consider that the outer hair cells of the inner ear together with the local structuresof the basilar membrane, reticular lamina and tectorial membrane form the primary filters (PF) ofthe second order. Taking into account a delay in transmission of the excitation signal in the cochleaand the influence of the Reissner membrane, we design a signal filtering system consisting of thePF with the common PF of the neighboring channels. We assess the distribution of the centralfrequencies of the channels along the cochlea, optimal number of the PF constituting a channel,natural frequencies of the channels, damping factors and summation weights of the outputs of thePF. As an example, we present a filter bank comprising 20 Gaussian-type channels each consistingof five PF. The proposed filtering system can be useful for designing cochlear implants based onbiological principles of signal processing in the cochlea.

  • 65.
    Stasiunas, Antanas
    et al.
    Department of Electrical and Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Bacauskiene, Marija
    Department of Electrical and Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Miliauskas, Rimvydas
    Department of Physiology, Lithuanian University of Health Sciences, Kaunas, Lithuania.
    An adaptive panoramic filter bank as a qualitative model of the filtering system of the cochlea: The peculiarities in linear and nonlinear mode2012In: Medical Engineering and Physics, ISSN 1350-4533, E-ISSN 1873-4030, Vol. 34, no 2, p. 187-194Article in journal (Refereed)
    Abstract [en]

    Outer hair cells in the cochlea of the ear, together with the local structures of the basilar membrane, reticular lamina and tectorial membrane constitute the adaptive primary filters (PF) of the second order. We used them for designing a serial-parallel signal filtering system. We determined a rational number of the PF included in Gaussian channels of the system, summation weights of the output signals, and distribution of the PF along the basilar membrane. A Gaussian panoramic filter bank each channel of which consists of five PF is presented as an example. The properties of the PF, the channel and the filter bank operating in the linear and nonlinear modes are determined during adaptation and under efferent control. The results suggest that application of biological filtering principles can be useful for designing cochlear implants with new speech encoding strategies. © 2011 IPEM.

  • 66.
    Stasiunas, Antanas
    et al.
    Department of Applied Electronics, Kaunas University of Technology, LT-3031 Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Department of Applied Electronics, Kaunas University of Technology, LT-3031 Kaunas, Lithuania.
    Miliauskas, Rimvydas
    Department of Physiology, Kaunas University of Medicine, LT-3000 Kaunas, Lithuania.
    Stasiuniene, Natalija
    Department of Biochemistry, Kaunas University of Medicine, LT-3000 Kaunas, Lithuania.
    Malmqvist, Kerstin
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Compression, adaptation and efferent control in a revised outer hair cell functional model2005In: Medical Engineering and Physics, ISSN 1350-4533, E-ISSN 1873-4030, Vol. 27, no 9, p. 780-789Article in journal (Refereed)
    Abstract [en]

    In the cochlea of the inner ear, outer hair cells (OHC) together with the local passive structures of the tectorial and basilar membranes comprise non-linear resonance circuits with the local and central (afferent–efferent) feedback. The characteristics of these circuits and their control possibilities depend on the mechanomotility of the OHC. The main element of our functional model of the OHC is the mechanomotility circuit with the general transfer characteristic y = k tanh(x − a). The parameter k of this characteristic reflects the axial stiffness of the OHC, and the parameter a working position of the hair bundle. The efferent synaptic signals act on the parameter k directly and on the parameter a indirectly through changes in the membrane potential. The dependences of the sensitivity and selectivity on changes in the parameters a and k are obtained by the computer simulation. Functioning of the model at low-level input signals is linear. Due to the non-linearity of the transfer characteristic of the mechanomotility circuit the high-level signals are compressed. For the adaptation and efferent control, however, the transfer characteristic with respect to the initial operating point should be asymmetrical (a > 0). The asymmetry relies on the deflection of the hair bundle from the axis of the OHC.

  • 67.
    Stasiunas, Antanas
    et al.
    Department of Applied Electronics, Kaunas University of Technology, LT-3031, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Kemesis, Povilas
    Department of Applied Electronics, Kaunas University of Technology, LT-3031, Kaunas, Lithuania.
    Bacauskiene, Marija
    Department of Applied Electronics, Kaunas University of Technology, LT-3031, Kaunas, Lithuania.
    Miliauskas, Rimvydas
    Laboratory of Neurophysiology, Kaunas University of Medicine, LT-3000, Kaunas, Lithuania.
    Stasiuniene, Natalija
    Department of Biochemistry, Kaunas University of Medicine, LT-3000, Kaunas, Lithuania.
    Malmqvist, Kerstin
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    A non-linear circuit for simulating OHC of the cochlea2003In: Medical Engineering and Physics, ISSN 1350-4533, E-ISSN 1873-4030, Vol. 25, no 7, p. 591-601Article in journal (Refereed)
    Abstract [en]

    In the present paper, referring to known characteristics of the outer hair cells functioning in the cochlea of the inner ear, a functional model of the outer hair cells is constructed. It consists of a linear feed-forward circuit and a non-linear positive feedback circuit. The feed-forward circuit reflects the contribution of local basilar and tectorial membrane areas and passive outer hair cells’ physical parameters to the forming of low-selectivity resonance characteristics. The non-linear positive feedback circuit reflects the non-linear outer hair cell signal transduction processes and the active role of efferents from the medial superior olive in altering circuit sensitivity and selectivity.

    Referring to an analytical description of the circuit model and computer simulation results, an explanation is given over the biological meaning of the outer hair cells’ non-linearities in signal transduction processes and the role of the non-linearities in achieving the following: signal compression, the dependency of circuit sensitivity and frequency selectivity upon the input signal amplitude, the compatibility of high-frequency selectivity and short transient response of the biological filtering circuits.

  • 68.
    Stasiunas, Antanas
    et al.
    a Department of Applied Electronics, Kaunas University of Technology, Lithuania .
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Miliauskas, Rimvydas
    Department of Physiology, Kaunas University of Medicine, Lithuania.
    Stasiuniene, Natalija
    Department of Biochemistry, Kaunas University of Medicine, Lithuania.
    An adaptive model simulating the somatic motility and the active hair bundle motion of the OHC2009In: Computers in Biology and Medicine, ISSN 0010-4825, E-ISSN 1879-0534, Vol. 39, no 9, p. 800-809Article in journal (Refereed)
    Abstract [en]

    The outer hair cells (OHC) of the mammalian inner ear change the sensitivity and frequency selectivity of the filtering system of the cochlea using two kinds of mechanical activity: the somatic motility and the active hair bundle motion. We designed a non-linear adaptive model of the OHC employing both mechanisms of the mechanical activity. The modeling results show that the high sensitivity and frequency selectivity of the filtering system of the cochlea depend on the somatic motility of the OHC. However, both mechanisms of mechanical activity are involved in the adaptation to sound intensity and efferent-synaptic influence. The fast (alternating) component (AC) of the mechanical–electrical transduction signal controls the motor protein prestin and fast changes in axial length of the cell. The slow (direct) component (DC) appearing at high signal intensity affects the axial stiffness, the cell length and the position of the hair bundle. The efferent influence is realized by the same mechanism.

  • 69.
    Stasiunas, Antanas
    et al.
    Department of Applied Electronics, Kaunas University of Technology, LT-51368 Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Miliauskas, Rimvydas
    Department of Physiology, Kaunas University of Medicine, LT-44307 Kaunas, Lithuania.
    Stasiuniene, Natalija
    Department of Biochemistry, Kaunas University of Medicine, LT-44307 Kaunas, Lithuania.
    Bacauskiene, Marija
    Department of Applied Electronics, Kaunas University of Technology, LT-51368 Kaunas, Lithuania.
    Physiologically inspired signal preprocessing for auditory prostheses: Insights from the electro-motility of the OHC2008In: Medical Engineering and Physics, ISSN 1350-4533, E-ISSN 1873-4030, Vol. 30, no 2, p. 171-181Article in journal (Refereed)
    Abstract [en]

    We designed a non-linear functional model of the outer hair cell (OHC) functioning in the filtering system of the cochlea and then isolated from it two second-order structures, one employing the mechanism of the somatic motility and the other the hair bundle motion of the OHC. The investigation of these circuits showed that the main mechanism increasing the sensitivity and frequency selectivity of the filtering system is the somatic motility. The mechanism of the active hair bundle motion appeared less suitable for realization of the band-pass filtering structures due to the dependence of the sensitivity, natural frequency and selectivity on the signal intensity. We combined three second-order filtering structures employing the mechanism of the somatic motility and the lateral inhibition to form a parallel-type filtering channel of the sixth order with the frequency characteristics of the Butterworth-type and Gaussian-type. The investigation of these channels showed that the Gaussian-type channel has the advantage over the Butterworth-type channel. It is more suitable for realization of a filter bank with common lateral circuits and has less distorted frequency characteristic in the nonlinear mode.

  • 70.
    Stasiunas, tanas
    et al.
    Kaunas University of Technology.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Kemesis, povilas
    Kaunas University of Technology.
    Bacauskiene, Marija
    Kaunas University of Technology.
    Miliauskas, Rimvydas
    Kaunas University of Medicine.
    Stasiuniene, Natalija
    Kaunas University of Medicine.
    Malmqvist, Kerstin
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    A multi-channel adaptive nonlinear filtering structure realizingsome properties of the hearing system2005In: Computers in Biology and Medicine, ISSN 0010-4825, E-ISSN 1879-0534, Vol. 35, no 6, p. 495-510Article in journal (Refereed)
    Abstract [en]

    An adaptive nonlinear signal-filtering model of the cochlea is proposed based on the functional properties of the inner ear. The model consists of the cochlear filtering segments taking into account the longitudinal, transverse and radial pressure wave propagation. On the basis of an analytical description of different parts of the model and the results of computer modeling, the biological significance of the nonlinearity of signal transduction processes in the outer hair cells, their role in signal compression and adaptation, the efferent control over the characteristics of the filtering structures (frequency selectivity and sensitivity) are explained. © 2004 Elsevier Ltd. All rights reserved.

  • 71.
    Uloza, Virgilijus
    et al.
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Padervinskis, Evaldas
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Uloziene, Ingrida
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Saferis, Viktoras
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Kaunas University of Technology, Kaunas, Lithuania.
    Combined Use of Standard and Throat Microphones for Measurement of Acoustic Voice Parameters and Voice Categorization2015In: Journal of Voice, ISSN 0892-1997, E-ISSN 1873-4588, Vol. 29, no 5, p. 552-559Article in journal (Refereed)
    Abstract [en]

    Summary: Objective. The aim of the present study was to evaluate the reliability of the measurements of acoustic voice parameters obtained simultaneously using oral and contact (throat) microphones and to investigate utility of combined use of these microphones for voice categorization.

    Materials and Methods. Voice samples of sustained vowel /a/ obtained from 157 subjects (105 healthy and 52 pathological voices) were recorded in a soundproof booth simultaneously through two microphones: oral AKG Perception 220 microphone (AKG Acoustics, Vienna, Austria) and contact (throat) Triumph PC microphone (Clearer Communications, Inc, Burnaby, Canada) placed on the lamina of thyroid cartilage. Acoustic voice signal data were measured for fundamental frequency, percent of jitter and shimmer, normalized noise energy, signal-to-noise ratio, and harmonic-to-noise ratio using Dr. Speech software (Tiger Electronics, Seattle, WA).

    Results. The correlations of acoustic voice parameters in vocal performance were statistically significant and strong (r = 0.71–1.0) for the entire functional measurements obtained for the two microphones. When classifying into healthy-pathological voice classes, the oral-shimmer revealed the correct classification rate (CCR) of 75.2% and the throat-jitter revealed CCR of 70.7%. However, combination of both throat and oral microphones allowed identifying a set of three voice parameters: throat-signal-to-noise ratio, oral-shimmer, and oral-normalized noise energy, which provided the CCR of 80.3%.

    Conclusions. The measurements of acoustic voice parameters using a combination of oral and throat microphones showed to be reliable in clinical settings and demonstrated high CCRs when distinguishing the healthy and pathological voice patient groups. Our study validates the suitability of the throat microphone signal for the task of automatic voice analysis for the purpose of voice screening. Copyright © 2014 The Voice Foundation.

  • 72.
    Uloza, Virgilijus
    et al.
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Padervinskis, Evaldas
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Vegiene, Aurelija
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Pribuisiene, Ruta
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Saferis, Viktoras
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Vaiciukynas, Evaldas
    Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Exploring the feasibility of smart phone microphone for measurement of acoustic voice parameters and voice pathology screening2015In: European Archives of Oto-Rhino-Laryngology, ISSN 0937-4477, E-ISSN 1434-4726, Vol. 272, no 11, p. 3391-3399Article in journal (Refereed)
    Abstract [en]

    The objective of this study is to evaluate the reliability of acoustic voice parameters obtained using smart phone (SP) microphones and investigate the utility of use of SP voice recordings for voice screening. Voice samples of sustained vowel/a/obtained from 118 subjects (34 normal and 84 pathological voices) were recorded simultaneously through two microphones: oral AKG Perception 220 microphone and SP Samsung Galaxy Note3 microphone. Acoustic voice signal data were measured for fundamental frequency, jitter and shimmer, normalized noise energy (NNE), signal to noise ratio and harmonic to noise ratio using Dr. Speech software. Discriminant analysis-based Correct Classification Rate (CCR) and Random Forest Classifier (RFC) based Equal Error Rate (EER) were used to evaluate the feasibility of acoustic voice parameters classifying normal and pathological voice classes. Lithuanian version of Glottal Function Index (LT_GFI) questionnaire was utilized for self-assessment of the severity of voice disorder. The correlations of acoustic voice parameters obtained with two types of microphones were statistically significant and strong (r = 0.73–1.0) for the entire measurements. When classifying into normal/pathological voice classes, the Oral-NNE revealed the CCR of 73.7 % and the pair of SP-NNE and SP-shimmer parameters revealed CCR of 79.5 %. However, fusion of the results obtained from SP voice recordings and GFI data provided the CCR of 84.60 % and RFC revealed the EER of 7.9 %, respectively. In conclusion, measurements of acoustic voice parameters using SP microphone were shown to be reliable in clinical settings demonstrating high CCR and low EER when distinguishing normal and pathological voice classes, and validated the suitability of the SP microphone signal for the task of automatic voice analysis and screening.

  • 73.
    Uloza, Virgilijus
    et al.
    Department of Otolaryngology, Kaunas University of Medicine, Eiveniu 2, LT-50009 Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Bacauskiene, Marija
    Department of Electrical and Control Instrumentation, Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Department of Electrical and Control Instrumentation, Kaunas University of Technology, Kaunas, Lithuania.
    Pribuisiene, Ruta
    Department of Otolaryngology, Kaunas University of Medicine, Eiveniu 2, LT-50009 Kaunas, Lithuania.
    Kaseta, Marius
    Department of Otolaryngology, Kaunas University of Medicine, Eiveniu 2, LT-50009 Kaunas, Lithuania.
    Saferis, Viktoras
    Department of Physics, Mathematics and Biophysics, Kaunas University of Medicine, Kaunas, Lithuania.
    Categorizing Normal and Pathological Voices: Automated and Perceptual Categorization2011In: Journal of Voice, ISSN 0892-1997, E-ISSN 1873-4588, Vol. 25, no 6, p. 700-708Article in journal (Refereed)
    Abstract [en]

    Objectives: The aims of the present study were to evaluate the accuracy of an elaborated automated voice categorization system that classified voice signal samples into healthy and pathological classes and to compare it with classification accuracy that was attained by human experts. Material and Methods: We investigated the effectiveness of 10 different feature sets in the classification of voice recordings of the sustained phonation of the vowel sound /a/ into the healthy and two pathological voice classes, and proposed a new approach to building a sequential committee of support vector machines (SVMs) for the classification. By applying “genetic search” (a search technique used to find solutions to optimization problems), we determined the optimal values of hyper-parameters of the committee and the feature sets that provided the best performance. Four experienced clinical voice specialists who evaluated the same voice recordings served as experts. The “gold standard” for classification was clinically and histologically proven diagnosis. Results: A considerable improvement in the classification accuracy was obtained from the committee when compared with the single feature type-based classifiers. In the experimental investigations that were performed using 444 voice recordings coming from 148 subjects, three recordings from each subject, we obtained the correct classification rate (CCR) of over 92% when classifying into the healthy-pathological voice classes, and over 90% when classifying into three classes (healthy voice and two nodular or diffuse lesion voice classes). The CCR obtained from human experts was about 74% and 60%, respectively. Conclusion: When operating under the same experimental conditions, the automated voice discrimination technique based on sequential committee of SVM was considerably more effective than the human experts.

  • 74.
    Ungh, Jörgen
    et al.
    StoraEnso, Falun Research Centre, Sweden.
    Nilsson, Carl Magnus
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Analysis of paper, print and press interaction from online measurements in a press room2007In: Nordic Pulp & Paper Research Journal, ISSN 0283-2631, E-ISSN 2000-0669, Vol. 22, no 3, p. 383-387Article in journal (Refereed)
    Abstract [en]

    A measurement platform for online studies of print runnability in a full-scale four-high web offset printing press is described. Results from two trial runs showed no effect of reel tightness on print runnability. Differences were, however, found for so called edge reels.

  • 75.
    Vaiciukynas, Evaldas
    et al.
    Kaunas University of Technology.
    Gelzinis, Adas
    Kaunas University of Technology.
    Bacauskiene, Marija
    Kaunas University of Technology.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent Systems´ laboratory.
    Vegiene, Aurelija
    Kaunas University of Medicine.
    Exploring Kernels in SVM-Based Classification of Larynx Pathology from Human Voice2010In: Proceedings of the 5th International Conference on Electrical and Control Technologies ECT-2010, May 6-7, 2010, Kaunas, Lithuania, Kaunas: KUT , 2010, p. 67-72Conference paper (Refereed)
    Abstract [en]

    In this paper identification of laryngeal disorders using cepstral parameters of human voice is investigated. Mel-frequency cepstral coefficients (MFCC), extracted from audio recordings, are further approximated, using 3 strategies: sampling, averaging, and estimation. SVM and LS-SVM categorize pre-processed data into normal, nodular, and diffuse classes. Since it is a three-class problem, various combination schemes are explored.  Constructed custom kernels outperformed a popular non-linear RBF kernel. Features, estimated with GMM, and SVM kernels, designed to exploit this information, is an interesting fusion of probabilistic and discriminative models for human voice-based classification of larynx pathology.

  • 76.
    Vaiciukynas, Evaldas
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Kaunas University of Technology, Kaunas, Lithuania.
    Parkinson’s Disease Detection from Speech Using Convolutional Neural Networks2018In: Smart objects and technologies for social good: Third International Conference, GOODTECHS 2017, Pisa, Italy, November 29-30, 2017, Proceedings / [ed] Guidi, B., Ricci, L., Calafate, C., Gaggi, O., Marquez-Barja, J., Cham: Springer, 2018, Vol. 233, p. 206-215Conference paper (Refereed)
    Abstract [en]

    Application of deep learning tends to outperform hand-crafted features in many domains. This study uses convolutional neural networks to explore effectiveness of various segments of a speech signal,? – text-dependent pronunciation of a short sentence, – in Parkinson’s disease detection task. Besides the common Mel-frequency spectrogram and its first and second derivatives, inclusion of various other input feature maps is also considered. Image interpolation is investigated as a solution to obtain a spectrogram of fixed length. The equal error rate (EER) for sentence segments varied from 20.3% to 29.5%. Fusion of decisions from sentence segments achieved EER of 14.1%, whereas the best result when using the full sentence exhibited EER of 16.8%. Therefore, splitting speech into segments could be recommended for Parkinson’s disease detection. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018.

  • 77.
    Vaiciukynas, Evaldas
    et al.
    Kaunas University of Technology, Kaunas, Litauen.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Kaunas University of Technology, Kaunas, Litauen.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Litauen.
    Kons, Zvi
    IBM, Haifa, Israel.
    Enhancing decision-level fusion through cluster-based partitioning of feature set2014In: The MENDEL Soft Computing journal : International Conference on Soft Computing MENDEL, ISSN 1803-3814, p. 259-264Article in journal (Refereed)
    Abstract [en]

    Feature set decomposition through cluster-based partitioning is the subject of this study. Approach is applied for the detection of mild laryngeal disorder from acoustic parameters of human voice using random forest (RF) as a base classier. Observations of sustained phonation (audio recordings of vowel /a/) had clinical diagnosis and severity level (from 0 to 3), but only healthy (severity 0) and mildly pathological (severity 1) cases were used. Diverse feature set (made of 26 variously sized subsets) was extracted from the voice signal. Feature-and decision-level fusions showed improvement over the best individual feature subset, but accuracy of fusion strategies did not differ signicantly. To boost accuracy of decision-level fusion, unsupervised decomposition for ensemble design was proposed. Decomposition was obtained by feature-space re-partitioning through clustering. Algorithms tested: a) basic k-Means; b) non-parametric MeanNN; c) adaptive anity propagation. Clustering by k-Means signicantly outperformed feature- and decision-level fusions.

  • 78.
    Vaiciukynas, Evaldas
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Kaunas University of Technology, Kaunas, Lithuania.
    Detecting Parkinson's disease from sustained phonation and speech signals2017In: PLoS ONE, ISSN 1932-6203, E-ISSN 1932-6203, Vol. 12, no 10, article id e0185613Article in journal (Refereed)
    Abstract [en]

    This study investigates signals from sustained phonation and text-dependent speech modalities for Parkinson’s disease screening. Phonation corresponds to the vowel /a/ voicing task and speech to the pronunciation of a short sentence in Lithuanian language. Signals were recorded through two channels simultaneously, namely, acoustic cardioid (AC) and smart phone (SP) microphones. Additional modalities were obtained by splitting speech recording into voiced and unvoiced parts. Information in each modality is summarized by 18 well-known audio feature sets. Random forest (RF) is used as a machine learning algorithm, both for individual feature sets and for decision-level fusion. Detection performance is measured by the out-of-bag equal error rate (EER) and the cost of log-likelihood-ratio. Essentia audio feature set was the best using the AC speech modality and YAAFE audio feature set was the best using the SP unvoiced modality, achieving EER of 20.30% and 25.57%, respectively. Fusion of all feature sets and modalities resulted in EER of 19.27% for the AC and 23.00% for the SP channel. Non-linear projection of a RF-based proximity matrix into the 2D space enriched medical decision support by visualization. © 2017 Vaiciukynas et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

  • 79.
    Vaiciukynas, Evaldas
    et al.
    Department of Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Department of Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Department of Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Department of Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Kons, Zvi
    IBM Haifa Research Laboratory, Haifa University, Haifa, Israel.
    Satt, Aharon
    IBM Haifa Research Laboratory, Haifa University, Haifa, Israel.
    Hoory, Ron
    IBM Haifa Research Laboratory, Haifa University, Haifa, Israel.
    Fusion of voice signal information for detection of mild laryngeal pathology2014In: Applied Soft Computing, ISSN 1568-4946, E-ISSN 1872-9681, Vol. 18, no May 2014, p. 91-103Article in journal (Refereed)
    Abstract [en]

    Detection of mild laryngeal disorders using acoustic parameters of human voice is the main objective in this study. Observations of sustained phonation (audio recordings of vocalized /a/) are labeled by clinical diagnosis and rated by severity (from 0 to 3). Research is exclusively constrained to healthy (severity 0) and mildly pathological (severity 1) cases - two the most difficult classes to distinguish between. Comprehensive voice signal characterization and information fusion constitute the approach adopted here. Characterization is obtained through diverse feature set, containing 26 feature subsets of varying size, extracted from the voice signal. Usefulness of feature-level and decision-level fusion is explored using support vector machine (SVM) and random forest (RF) as basic classifiers. For both types of fusion we also investigate the influence of feature selection on model accuracy. To improve the decision-level fusion we introduce a simple unsupervised technique for ensemble design, which is based on partitioning the feature set by k-means clustering, where the parameter k controls the size and diversity of the prospective ensemble. All types of the fusion resulted in an evident improvement over the best individual feature subset. However, none of the types, including fusion setups comprising feature selection, proved to be significantly superior over the rest. The proposed ensemble design by feature set decomposition discernibly enhanced decision-level and significantly outperformed feature-level fusion. Ensemble of RF classifiers, induced from a cluster-based partitioning of the feature set, achieved equal error rate of 13.1 ± 1.8% in the detection of mildly pathological larynx. This is a very encouraging result, considering that detection of mild laryngeal disorder is a more challenging task than a common discrimination between healthy and a wide spectrum of pathological cases. © 2014 Elsevier B.V.

  • 80.
    Vaiciukynas, Evaldas
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Kaunas University of Technology, Kaunas, Lithuania.
    Minelga, Jonas
    Kaunas University of Technology, Kaunas, Lithuania.
    Hållander, Magnus
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Padervinskis, Evaldas
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Uloza, Virgilijus
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Fusing voice and query data for non-invasive detection of laryngeal disorders2015In: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 42, no 22, p. 8445-8453Article in journal (Refereed)
    Abstract [en]

    Topic of this study is exploration and fusion o fnon-invasive measurements for an accurate detection of pathological larynx. Measurements for human subject encompass answers to items of a specific survey and information extracted by the openSMILE toolkit from several audio recordings of sustained phonation (vowel/a/).

  • 81.
    Vaiciukynas, Evaldas
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Kaunas University of Technology, Kaunas, Lithuania.
    Minelga, Jonas
    Kaunas University of Technology, Kaunas, Lithuania.
    Hållander, Magnus
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Padervinskis, Evaldas
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Uloza, Virgilijus
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Towards Voice and Query Data-based Non-invasive Screening for Laryngeal Disorders2015In: Advances in Electrical and Computer Engineering: Proceedings of the 17th International Conference on Automatic Control, Modelling & Simulation (ACMOS '15): Proceedings of the 14th International Conference on Artificial Intelligence, Knowledge Engineering and Data Bases (AIKED '15): Proceedings of the 6th International Conference on Circuits, Systems, Control, Signals (CSCS '15): Tenerife, Canary Islands, Spain, January 10-12, 2015 / [ed] Nikos E. Mastorakis & Imre J. Rudas, Athens: WSEAS Press , 2015, p. 32-39Conference paper (Refereed)
    Abstract [en]

    Topic of the research is exploration and fusion of non-invasive measurements for an accurate detection of pathological larynx. Measurements for human subject encompass results of a specific survey and information extracted by openSMILE toolkit from several audio recordings of sustained phonation (vowel/a/). Clinical diagnosis, assigned by medical specialist, is a target attribute for binary classification into healthy and pathological cases. Random forest (RF) is used here as a base-learner and also as a meta-learner for decision-level fusion. Fusion combines decisions from ensemble of 5 RF classifiers built on 3 variants of audio recording data (raw and after two types of voice activity detection) and 2 variants of questionnaire (with 9 and 26 questions) data. Out-of-bag equal error rate (EER) was found to be higher for audio data and lower for querry, but each variant was outperformed by the fusion where the lowest EER of 4.8% was achieved. Finally, due to noteworthy performance of the querry data, 22 association rules (11 healthy + 11 pathological) using 17 questions were obtained for comprehensible insights.

  • 82.
    Vaiciukynas, Evaldas
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Kaunas University of Technology, Kaunas, Lithuania.
    Olenina, Irina
    Klaipeda University, Klaipeda, Lithuania & Environmental Protection Agency, Klaipeda, Lithuania.
    Exploiting statistical energy test for comparison of multiple groups in morphometric and chemometric data2015In: Chemometrics and Intelligent Laboratory Systems, ISSN 0169-7439, E-ISSN 1873-3239, Vol. 146, p. 10-23Article in journal (Refereed)
    Abstract [en]

    Multivariate permutation-based energy test of equal distributions is considered here. Approach is attributable to the emerging field of ε-statistics and uses natural logarithm of Euclidean distance for within-sample and between-sample components. Result from permutations is enhanced by a tail approximation through generalized Pareto distribution to boost precision of obtained p-values. Generalization from two-sample case to multiple samples is achieved by combining p-values through meta-analysis. Several strategies of varied statistical power are possible, while a maximum of all pairwise p-values is chosen here. Proposed approach is tested on several morphometric and chemometric data sets. Each data set is additionally transformed by principal component analysis for the purpose of dimensionality reduction and visualization in 2D space. Variable selection, namely, sequential search and multi-cluster feature selection, is applied to reveal in what aspects the groups differ most.

    Morphometric data sets used: 1) survival data of house sparrows Passer domesticus; 2) orange and blue varieties of rock crabs Leptograpsus variegatus; 3) ontogenetic stages of trilobite species Trimerocephalus lelievrei; 4) marine phytoplankton species Prorocentrum minimum.

    Chemometric data sets used: 1) essential oils composition of medicinal plant Hyptis suaveolensspecimens; 2) chemical information of olive oil samples; 3) elemental composition of biomass ash; 4) exchangeable cations of earth metals in forest soil samples.

    Statistically significant differences between groups were successfully indicated, but the selection of variables had a profound effect on the result. Permutation-based energy test and it’s multi-sample generalization through meta-analysis proved useful as an unbalanced non-parametric MANOVA approach. Introduced solution is simple, yet flexible and powerful, and by no means is confined to morphometrics or chemometrics alone, but has a wide range of potential applications. Copyright © 2015 Elsevier B.V.

  • 83.
    Vaiciukynas, Evaldas
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Kaunas University of Technology, Kaunas, Lithuania.
    Sulcius, Sigitas
    Klaipeda University, Klaipeda, Lithuania.
    Paskauskas, Ricardas
    Klaipeda University, Klaipeda, Lithuania.
    Olenina, Irina
    Klaipeda University, Klaipeda, Lithuania.
    Prototype-Based Contour Detection Applied to Segmentation of Phytoplankton Images2013In: AWERProcedia Information Technology and Computer Science: 3rd World Conference on Information Technology (WCIT-2012) / [ed] Hafize Keser and Meltem Hakiz, 2013, p. 1285-1292Conference paper (Refereed)
    Abstract [en]

    Novel prototype-based framework for image segmentation is introduced and successfully applied for cell segmentation in microscopy imagery. This study is concerned with precise contour detection for objects representing the Prorocentrum minimum species in phytoplankton images. The framework requires a single object with the ground truth contour as a prototype to perform detection of the contour for the remaining objects. The level set method is chosen as a segmentation algorithm and its parameters are tuned by differential evolution. The fitness function is based on the distance between pixels near contour in the prototype image and pixels near detected contour in the target image. Pixels “of interest correspond to several concentric bands of various width in outer and inner areas, relative to the contour. Usefulness of the introduced approach was demonstrated by comparing it to the basic level set and advanced Weka segmentation techniques. Solving the parameter selection problem of the level set algorithm considerably improved segmentation accuracy.

  • 84.
    Vaiciukynas, Evaldas
    et al.
    Department of Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Gelzinis, Adas
    Department of Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Department of Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Uloza, Virgilijus
    Department of Otolaryngology, Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Exploring similarity-based classification of larynx disorders from human voice2012In: Speech Communication, ISSN 0167-6393, E-ISSN 1872-7182, Vol. 54, no 5, p. 601-610Article in journal (Refereed)
    Abstract [en]

    In this paper identification of laryngeal disorders using cepstral parameters of human voice is researched. Mel-frequency cepstral coefficients (MFCCs), extracted from audio recordings of patient's voice, are further approximated, using various strategies (sampling, averaging, and clustering by Gaussian mixture model). The effectiveness of similarity-based classification techniques in categorizing such pre-processed data into normal voice, nodular, and diffuse vocal fold lesion classes is explored and schemes to combine binary decisions of support vector machines (SVMs) are evaluated. Most practiced RBF kernel was compared to several constructed custom kernels: (i) a sequence kernel, defined over a pair of matrices, rather than over a pair of vectors and calculating the kernelized principal angle (KPA) between subspaces; (ii) a simple supervector kernel using only means of patient's GMM; (iii) two distance kernels, specifically tailored to exploit covariance matrices of GMM and using the approximation of the Kullback-Leibler divergence from the Monte-Carlo sampling (KL-MCS), and the Kullback-Leibler divergence combined with the Earth mover's distance (KL-EMD) as similarity metrics. The sequence kernel and the distance kernels both outperformed the popular RBF kernel, but the difference is statistically significant only in the distance kernels case. When tested on voice recordings, collected from 410 subjects (130 normal voice, 140 diffuse, and 140 nodular vocal fold lesions), the KL-MCS kernel, using GMM with full covariance matrices, and the KL-EMD kernel, using GMM with diagonal covariance matrices, provided the best overall performance. In most cases, SVM reached higher accuracy than least squares SVM, except for common binary classification using distance kernels. The results indicate that features, modeled with GMM, and kernel methods, exploiting this information, is an interesting fusion of generative (probabilistic) and discriminative (hyperplane) models for similarity-based classification. (C) 2011 Elsevier B.V. All rights reserved.

  • 85.
    Vaiciukynas, Evaldas
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Kaunas University of Technology, Kaunas, Lithuania.
    Vaskevicius, Kestutis
    Kaunas University of Technology, Kaunas, Lithuania.
    Uloza, Virgilijus
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Padervinskis, Evaldas
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Ciceliene, Jolita
    Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Fusing Various Audio Feature Sets for Detection of Parkinson’s Disease from Sustained Voice and Speech Recordings2016In: Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349, Vol. 9811, p. 328-337Article in journal (Refereed)
    Abstract [en]

    The aim of this study is the analysis of voice and speech recordings for the task of Parkinson’s disease detection. Voice modality corresponds to sustained phonation /a/ and speech modality to a short sentence in Lithuanian language. Diverse information from recordings is extracted by 22 well-known audio feature sets. Random forest is used as a learner, both for individual feature sets and for decision-level fusion. Essentia descriptors were found as the best individual feature set, achieving equal error rate of 16.3 % for voice and 13.3 % for speech. Fusion of feature sets and modalities improved detection and achieved equal error rate of 10.8 %. Variable importance in fusion revealed speech modality as more important than voice. © Springer International Publishing Switzerland 2016

  • 86.
    Valincius, Donatas
    et al.
    Kaunas University of Technology.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Gelzinis, Adas
    Kaunas University of Technology.
    Bacauskiene, Marija
    Kaunas University of Technology.
    Image analysis based categorization of laryngeal diseases2006In: Proceedings of the 1st International Conference on Electrical and Control Technologies, 2006, 2006, p. 300-305Conference paper (Refereed)
    Abstract [en]

    This paper concentrates on an automated analysis of laryngeal images aiming to categorize the images into three decision classes, namely healthy, nodular and diffuse. The problem is treated as an amage analysis and classification task. To obtain a comprehensive description of laryngeal images, multiple feature sets exploiting information on image colour, texture, geometry, image intensity gradient direction, and frequency content are extracted. A separate support vector machine (SVM) is used to categorize features of each type into decision classes. The final image categorization is then obtained which is based on the decisions provided by a committee of support vector machines. Bearing in mind a high similarity of the decision classes, the correct classification rate of over 94 % is obtained while testing the system on 785 laryngeal images that are recorded by the Department of Otolaryngology, Kaunas University of Medicine is rather promising.

  • 87.
    Valinicius, D.
    et al.
    Kaunas University of Technology, Department of Applied Electronics, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Kaunas University of Technology, Department of Electrical and Control Equipment, Kaunas, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Department of Electrical and Control Equipment, Kaunas, Lithuania.
    Evolving Committees of Support Vector Machines2007In: Machine Learning and Data Mining in Pattern Recognition, Proceedings / [ed] Perner, P, Berlin: Springer Berlin/Heidelberg, 2007, p. 263-275Conference paper (Refereed)
    Abstract [en]

    The main emphasis of the technique developed in this work for evolving committees of support vector machines (SVM) is on a two phase procedure to select salient features. In the first phase, clearly redundant features are eliminated based on the paired t-test comparing the SVM output sensitivity-based saliency of the candidate and the noise feature. In the second phase, the genetic search integrating the steps of training, aggregation of committee members, and hyper-parameter as well as feature selection into the same learning process is employed. A small number of genetic iterations needed to find a solution is the characteristic feature of the genetic search procedure developed. The experimental tests performed on five real world problems have shown that significant improvements in correct classification rate can be obtained in a small number of iterations if compared to the case of using all the features available.

  • 88.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, M.
    Department of Applied Electronics, Kaunas University of Technology, Kaunas, Lithuania.
    Using artificial neural networks for process and system modelling2003In: Chemometrics and Intelligent Laboratory Systems, ISSN 0169-7439, E-ISSN 1873-3239, Vol. 67, no 2, p. 187-191Article in journal (Refereed)
    Abstract [en]

    This letter concerns several papers, devoted to neural network-based process and system modelling, recently published in the Chemometrics and Intelligent Laboratory Systems journal. Artificial neural networks have proved themselves to be very useful in various modelling applications, because they can represent complex mapping functions and discover the representations using powerful learning algorithms. An optimal set of parameters for defining the functions is learned from examples by minimizing an error functional. In various practical applications, the number of examples available for estimating parameters of the models is rather limited. Moreover, to discover the best model, numerous candidate models must be trained and evaluated. In such thin-data situations, special precautions are to be taken to avoid erroneous conclusions. In this letter, we discuss three important issues, namely network initialization, over-fitting, and model selection, the right consideration of which can be of tremendous help in successful network design and can make neural modelling results more valuable.

  • 89.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Bacauskiene, M.
    Department of Applied Electronics, Kaunas University of Technology, Kaunas, Lithuania.
    Dosinas, A.
    Department of Applied Electronics, Kaunas University of Technology, Kaunas, Lithuania.
    Bartkevicius, V.
    Department of Applied Electronics, Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, A.
    Department of Applied Electronics, Kaunas University of Technology, Kaunas, Lithuania.
    Vaitkunas, M.
    Department of Applied Electronics, Kaunas University of Technology, Kaunas, Lithuania.
    Lipnickas, A.
    Department of Applied Electronics, Kaunas University of Technology, Kaunas, Lithuania.
    An intelligent system for tuning magnetic field of a cathode ray tube deflection yoke2003In: Knowledge-Based Systems, ISSN 0950-7051, E-ISSN 1872-7409, Vol. 16, no 3, p. 161-164Article in journal (Refereed)
    Abstract [en]

    This short communication concerns identification of the number of magnetic correction shunts and their positions for deflection yoke tuning to correct the misconvergence of colours of a cathode ray tube. The misconvergence of colours is characterised by the distances measured between the traces of red and blue beams. The method proposed consists of two phases, namely, learning and optimisation. In the learning phase, the radial basis function neural network is trained to learn a mapping: correction shunt position→changes in misconvergence. In the optimisation phase, the trained neural network is used to predict changes in misconvergence depending on a correction shunt position. An optimisation procedure based on the predictions returned by the neural net is then executed in order to find the minimal number of correction shunts needed and their positions. During the experimental investigations, 98% of the deflection yokes analysed have been tuned successfully using the technique proposed.

  • 90.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Bacauskiene, M.
    Department of Applied Electronics, Kaunas University of Technology Kaunas, Lithuania.
    Malmqvist, Kerstin
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Learning an Adaptive Dissimilarity Measure for Nearest Neighbour Classification2003In: Neural computing & applications (Print), ISSN 0941-0643, E-ISSN 1433-3058, Vol. 11, no 3-4, p. 203-209Article in journal (Refereed)
    Abstract [en]

    In this paper, an approach to weighting features for classification based on the nearest-neighbour rules is proposed. The weights are adaptive in the sense that the weight values are different in various regions of the feature space. The values of the weights are found by performing a random search in the weight space. A correct classification rate is the criterion maximised during the search. Experimentally, we have shown that the proposed approach is useful for classification. The weight values obtained during the experiments show that the importance of features may be different in different regions of the feature space

  • 91.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-51368 Kaunas, Lithuania.
    Estimating ink density from colour camera RGB values by the local kernel ridge regression2008In: Engineering applications of artificial intelligence, ISSN 0952-1976, E-ISSN 1873-6769, Vol. 21, no 1, p. 35-42Article in journal (Refereed)
    Abstract [en]

    We present an option for CCD colour camera based ink density measurements in newspaper printing. To solve the task, first, a reflectance spectrum is reconstructed from the CCD colour camera RGB values and then a well-known relation between ink density and the reflectance spectrum of a sample being measured is used to compute the density. To achieve an acceptable spectral reconstruction accuracy, the local kernel ridge regression is employed. The superiority of the local kernel ridge regression over the global regression and the popular ordinary polynomial regression is demonstrated by experimental comparisons. For a database consisting of 250 colour patches printed on newsprint by an ordinary offset printing press, the average spectrum reconstruction error of and the maximum error ΔEmax=3.29 was obtained. Such an error proved to be low enough for achieving the average ink density measuring error lower than 0.01D.

  • 92.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Department of Applied Electronics, Kaunas University of Technology, LT-3031, Kaunas, Lithuania.
    Feature Selection with Neural Networks2002In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 23, no 11, p. 1323-1335Article in journal (Refereed)
    Abstract [en]

    We present a neural network based approach for identifying salient features for classification in feedforward neural networks. Our approach involves neural network training with an augmented cross-entropy error function. The augmented error function forces the neural network to keep low derivatives of the transfer functions of neurons when learning a classification task. Such an approach reduces output sensitivity to the input changes. Feature selection is based on the reaction of the cross-validation data set classification error due to the removal of the individual features. We demonstrate the usefulness of the proposed approach on one artificial and three real-world classification problems. We compared the approach with five other feature selection methods, each of which banks on a different concept. The algorithm developed outperformed the other methods by achieving higher classification accuracy on all the problems tested.

  • 93.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Department of Applied Electronics, Kaunas University of Technology, Kaunas, Lithuania.
    Image analysis and fuzzy integration applied to print quality assessment2005In: Cybernetics and systems, ISSN 0196-9722, E-ISSN 1087-6553, Vol. 36, no 6, p. 549-564Article in journal (Refereed)
    Abstract [en]

    We present an image analysis and fuzzy integration based option for the assessment of print quality in rotogravure printing. Values of several print distortion attributes are evaluated employing image analysis procedures and then are aggregated into an overall print quality measure using fuzzy integration. The experimental investigations performed have shown that the print quality evaluations provided by the measure correlate well with the print quality rankings obtained from the expert. The developed tools are successfully used in printing shops for routine print quality control.

  • 94.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-3031 Kaunas, Lithuania.
    Dosinas, A.
    Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-3031 Kaunas, Lithuania.
    Bartkevicius, V.
    Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-3031 Kaunas, Lithuania.
    Gelzinis, Adas
    Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-3031 Kaunas, Lithuania.
    Vaitkunas, M.
    Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-3031 Kaunas, Lithuania.
    Lipnickas, Arunas
    Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-3031 Kaunas, Lithuania.
    Intelligent deflection yoke magnetic field tuning2004In: Journal of Intelligent Manufacturing, ISSN 0956-5515, E-ISSN 1572-8145, Vol. 15, no 3, p. 275-286Article in journal (Refereed)
    Abstract [en]

    This paper presents a method and a system to identify the number of magnetic correction shunts and their positions for deflection yoke tuning to correct the misconvergence of colors of a cathode ray tube. The method proposed consists of two phases, namely, learning and optimization. In the learning phase, the radial basis function neural network is trained to learn a mapping: correction shunt position --> changes in misconvergence. In the optimization phase, the trained neural network is used to predict changes in misconvergence depending on a correction shunt position. An optimization procedure based on the predictions returned by the neural net is then executed in order to find the minimal number of correction shunts needed and their positions. During the experimental investigations, 98% of the deflection yokes analyzed have been tuned successfully using the technique proposed.

  • 95.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Kaunas University of Technology, Lithuania.
    Gelzinis, Adas
    Kaunas University of Technology, Lithuania.
    Leverages Based Neural Networks Fusion2004In: Neural information processing, 2004, p. 446-451Conference paper (Refereed)
    Abstract [en]

    To improve estimation results, outputs of multiple neural networks can be aggregated into a committee output. In this paper, we study the usefulness of the leverages based information for creating accurate neural network committees. Based on the approximate leave-one-out error and the suggested, generalization error based, diversity test, accurate and diverse networks are selected and fused into a committee using data dependent aggregation weights. Four data dependent aggregation schemes – based on local variance, covariance, Choquet integral, and the generalized Choquet integral – are investigated. The effectiveness of the approaches is tested on one artificial and three real world data sets.

  • 96.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Bacauskiene, Marija
    Kaunas University of Technology.
    Gelzinis, Adas
    Kaunas University of Technology.
    Uloza, Virgilijus
    Kaunas University of Medicine.
    Monitoring Human Larynx by Random Forests Using Questionnaire Data2011In: Proceedings of the 11th International Conference on Intelligent Systems Design and Applications, ISDA, Cordoba, 22-24 november, 2011, IEEE Computer Society, 2011, p. 914-919Conference paper (Refereed)
    Abstract [en]

    This paper is concerned with noninvasive monitoring of human larynx using subject’s questionnaire data. By applying random forests (RF), questionnaire data arecategorized into a healthy class and several classes of disorders including: cancerous, noncancerous, diffuse, nodular, paralysis, and an overall pathological class. The most important questionnaire statements are determined using RF variable importance evaluations. To explore multidimensional data, t-Distributed Stochastic Neighbor Embedding (t-SNE) and multidimensionalscaling (MDS) are applied to the RF data proximity matrix.When testing the developed tools on a set of data collectedfrom 109 subjects, 100% classification accuracy was obtainedon unseen data coming from two—healthy and pathological—classes. The accuracy of 80.7% was achieved when classifyingthe data into the healthy, cancerous, and noncancerous classes.The t-SNE and MDS mapping techniques facilitate data explorationaimed at identifying subjects belonging to a ”riskgroup”. It is expected that the developed tools will be of greathelp in preventive health care in laryngology.

  • 97.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    Bacauskiene, Marija
    Department of Electrical and Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Gelzinis, Adas
    Department of Electrical and Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Vaiciukynas, Evaldas
    Department of Electrical and Control Equipment, Kaunas University of Technology, Kaunas, Lithuania.
    Uloza, Virgilijus
    Department of Otolaryngology, Kaunas University of Medicine, Kaunas, Lithuania.
    Questionnaire- versus voice-based screening for laryngeal disorders2012In: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 39, no 6, p. 6254-6262Article in journal (Refereed)
    Abstract [en]

    The usefulness of questionnaire and voice data to screen for laryngeal disorders is explored. Answers to 14 questions form a questionnaire data vector. Twenty-three variables computed by the commercial "Dr.Speech" software from a digital voice recording of a sustained phonation of the vowel sound/a/constitute a voice data vector. Categorization of the data into a healthy class and two classes of disorders, namely diffuse and nodular mass lesions of vocal folds is the task pursued in this work. Visualization of data and automated decisions is also an important aspect of this work. To make the categorization, a support vector machine (SVM) is designed based on genetic search. Linear as well as nonlinear canonical correlation analysis (CCA) is employed, to study relations between the questionnaire and voice data sets. The curvilinear component analysis, performing nonlinear mapping into a two-dimensional space, is used for visualizing data and decisions. Data from 240 patients were used in the experimental studies. It was found that the questionnaire data provide more information for the categorization than the voice data. There are 3-4 common directions along which the statistically significant variations of the questionnaire and voice data occur. However, the linear relations between the variations occurring in the two data sets are not strong. On the other hand, very strong linear relations were observed between the nonlinear variates obtained from the questionnaire data and linear ones computed from the voice data. Questionnaire data carry great potential for preventive health care in laryngology. © 2011 Elsevier Ltd. All rights reserved.

  • 98.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Bacauskiene, Marija
    Kaunas University of Technology, Department of Electric Power Systems, Kaunas, Lithuania.
    Malmqvist, Kerstin
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Selecting features for neural network committees2002In: Proceedings of the International Joint Conference on Neural Networks, Piscataway: IEEE, 2002, p. 215-220Conference paper (Refereed)
    Abstract [en]

    We present a neural network based approach for identifying salient features for classification in neural network committees. Our approach involves neural network training with an augmented cross-entropy error function. The augmented error function forces the neural network to keep low derivatives of the transfer functions of neurons of the network when learning a classification task. Such an approach reduces output sensitivity to the input changes. Feature selection is based on the reaction of the cross-validation data set classification error due to the removal of the individual features. We compared the approach with two other neural network based feature selection methods. The algorithm developed outperformed the methods by achieving a higher classification accuracy on three real world problems tested. ©2002 IEEE

  • 99.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).
    Bacauskiene, Marija
    Malmqvist, Kerstin
    Selecting features with neural networks2001In: Neural Information Precessing: ICONIP-2001 proceedings / [ed] Liming Zhang; Fanji Gu, Shanghai: Fudan University Press, 2001, p. 63-68Conference paper (Refereed)
    Abstract [en]

    We present a neural network based approach for identifying salient features for classification in feed-forward neural networks. Our approach involves neural network training with an augmented cross-entropy error function. The augmented error function forces the neural network to keep low derivatives of the transfer functions of neurons when learning a classification task. Such an approach reduces output sensitivity to the input changes. Feature selection is based on the reaction of the cross-validation data set classification error due to the removal of the individual features. We compared the approach with five other feature selection methods, each of which banks on different concept. The algorithm developed outperformed the other methods by achieving a higher classification accuracy on all the problems tested.

  • 100.
    Verikas, Antanas
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Bacauskiene, Marija
    Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-3031, Kaunas, Lithuania.
    Malmqvist, Kerstin
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).
    Selecting salient features for classification committees2003In: Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003 / [ed] Kaynak, O Alpaydin, E Oja, E Xu, L, Heidelberg: Springer Berlin/Heidelberg, 2003, Vol. 2714, p. 35-42Conference paper (Refereed)
    Abstract [en]

    We present a neural network based approach for identifying salient features for classification in neural network committees. Our approach involves neural network training with an augmented cross-entropy error function. The augmented error function forces the neural network to keep low derivatives of the transfer functions of neurons of the network when learning a classification task. Feature selection is based on two criteria, namely the reaction of the cross-validation data set classification error due to the removal of the individual features and the diversity of neural networks comprising the committee. The algorithm developed removed a large number of features from the original data sets without reducing the classification accuracy of the committees. By contrast, the accuracy of the committees utilizing the reduced feature sets was higher than those exploiting all the original features. © Springer-Verlag Berlin Heidelberg 2003.

123 51 - 100 of 145
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf