hh.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Malmqvist, Kerstin
Publications (10 of 10) Show all publications
Stasiunas, t., Verikas, A., Kemesis, p., Bacauskiene, M., Miliauskas, R., Stasiuniene, N. & Malmqvist, K. (2005). A multi-channel adaptive nonlinear filtering structure realizingsome properties of the hearing system. Computers in Biology and Medicine, 35(6), 495-510
Open this publication in new window or tab >>A multi-channel adaptive nonlinear filtering structure realizingsome properties of the hearing system
Show others...
2005 (English)In: Computers in Biology and Medicine, ISSN 0010-4825, E-ISSN 1879-0534, Vol. 35, no 6, p. 495-510Article in journal (Refereed) Published
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.

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2005
Keywords
Cochlear model, Hair cells, Filtering circuits with feedback
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-20134 (URN)10.1016/j.compbiomed.2004.04.004 (DOI)000230573700003 ()15780861 (PubMedID)2-s2.0-15744389647 (Scopus ID)
Available from: 2012-12-14 Created: 2012-12-14 Last updated: 2018-03-22Bibliographically approved
Stasiunas, A., Verikas, A., Bacauskiene, M., Miliauskas, R., Stasiuniene, N. & Malmqvist, K. (2005). Compression, adaptation and efferent control in a revised outer hair cell functional model. Medical Engineering and Physics, 27(9), 780-789
Open this publication in new window or tab >>Compression, adaptation and efferent control in a revised outer hair cell functional model
Show others...
2005 (English)In: Medical Engineering and Physics, ISSN 1350-4533, E-ISSN 1873-4030, Vol. 27, no 9, p. 780-789Article in journal (Refereed) Published
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.

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2005
Keywords
Cochlea, Outer hair cell, Mechanomotility, Motor protein prestin, Efferent synapse
National Category
Medical Biotechnology
Identifiers
urn:nbn:se:hh:diva-257 (URN)10.1016/j.medengphy.2005.03.002 (DOI)000232377700007 ()16171738 (PubMedID)2-s2.0-24944546619 (Scopus ID)2082/552 (Local ID)2082/552 (Archive number)2082/552 (OAI)
Available from: 2006-11-24 Created: 2006-11-24 Last updated: 2018-03-23Bibliographically approved
Verikas, A., Malmqvist, K. & Bergman, L. (2005). Detecting and measuring rings in banknote images. Engineering applications of artificial intelligence, 18(3), 363-371
Open this publication in new window or tab >>Detecting and measuring rings in banknote images
2005 (English)In: Engineering applications of artificial intelligence, ISSN 0952-1976, E-ISSN 1873-6769, Vol. 18, no 3, p. 363-371Article in journal (Refereed) Published
Abstract [en]

Various intelligent systems show a rapidly growing potential use of visual information processing technologies. This paper presents an example of employing visual information processing technologies for detecting and measuring rings in banknote images. The size of the rings is one of parameters used to inspect the banknote printing quality. The approach developed consists of two phases. In the first phase, based on histogram processing and data clustering, image areas containing rings are localized and edges of the rings are detected. Then, in the second phase, applying the hard and possibilistic spherical shell clustering to the extracted edge pixels the ring centre and radii are estimated. The experimental investigations performed have shown that even highly occluded rings are robustly detected. Several prototypes of the system developed have been installed in two banknote printing shops in Europe.

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2005
Keywords
Quality inspection, Colour image processing, Fuzzy clustering, Histogram processing
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-261 (URN)10.1016/j.engappai.2004.09.014 (DOI)000228264400010 ()2-s2.0-14844285749 (Scopus ID)2082/556 (Local ID)2082/556 (Archive number)2082/556 (OAI)
Available from: 2006-11-24 Created: 2006-11-24 Last updated: 2018-03-23Bibliographically approved
Verikas, A., Bacauskiene, M. & Malmqvist, K. (2002). Selecting features for neural network committees. In: Proceedings of the International Joint Conference on Neural Networks: . Paper presented at International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States, 12-17 May, 2002 (pp. 215-220). Piscataway: IEEE
Open this publication in new window or tab >>Selecting features for neural network committees
2002 (English)In: Proceedings of the International Joint Conference on Neural Networks, Piscataway: IEEE, 2002, p. 215-220Conference paper, Published 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

Place, publisher, year, edition, pages
Piscataway: IEEE, 2002
National Category
Telecommunications
Identifiers
urn:nbn:se:hh:diva-38119 (URN)10.1109/IJCNN.2002.1005472 (DOI)000177402800040 ()2-s2.0-0036076592 (Scopus ID)0-7803-7278-6 (ISBN)
Conference
International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States, 12-17 May, 2002
Available from: 2018-10-09 Created: 2018-10-09 Last updated: 2018-10-09Bibliographically approved
Verikas, A., Malmqvist, K. & Bacauskiene, M. (2000). Combining neural networks, fuzzy sets, and evidence theory based approaches for analysing colour images. In: Shun Ichi-Amari, C. Lee Giles, Marco Gori & Vincenzo Piuri (Ed.), IJCNN 2000: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, Como, Italy, 24-27 July 2000, Vol. 2. Paper presented at International Joint Conference on Neural Networks (IJCNN'2000), Como, Italy, July 24-27, 2000 (pp. 297-302). Los Alamitos: IEEE Computer Society
Open this publication in new window or tab >>Combining neural networks, fuzzy sets, and evidence theory based approaches for analysing colour images
2000 (English)In: IJCNN 2000: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, Como, Italy, 24-27 July 2000, Vol. 2 / [ed] Shun Ichi-Amari, C. Lee Giles, Marco Gori & Vincenzo Piuri, Los Alamitos: IEEE Computer Society, 2000, p. 297-302Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents an approach to determining colours of specks in an image taken from a pulp sample. The task is solved through colour classification by an artificial neural network. The network is trained using possibilistic target values. The problem of post-processing of a pixelwise-classified image is addressed from the point of view of the Dempster-Shafer theory of evidence. Each neighbour of a pixel being analysed is considered as an item of evidence supporting particular hypotheses regarding the class label of that pixel. The experiments performed have shown that the colour classification results correspond well with the human perception of colours of the specks.

Place, publisher, year, edition, pages
Los Alamitos: IEEE Computer Society, 2000
Series
IEEE International Joint Conference on Neural Networks (IJCNN), ISSN 1098-7576
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-18783 (URN)10.1109/IJCNN.2000.857912 (DOI)000089240200047 ()2-s2.0-0033681952 (Scopus ID)9780769506197 (ISBN)0769506194 (ISBN)0780365410 (ISBN)9780780365414 (ISBN)0769506216 (ISBN)9780769506210 (ISBN)
Conference
International Joint Conference on Neural Networks (IJCNN'2000), Como, Italy, July 24-27, 2000
Available from: 2012-07-13 Created: 2012-06-25 Last updated: 2018-03-22Bibliographically approved
Verikas, A., Gelzinis, A. & Malmqvist, K. (1999). Using Labelled and Unlabelled Data to Train a Multilayer Perceptron for Colour Classification in Graphic Arts. In: Ibrahim Imam, Yves Kodratoff, Ayman El-Dessouki and Moonis Ali (Ed.), Multiple approaches to intelligent systems: 12th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA/AIE-99, Cairo, Egypt, May 31 - June 3, 1999. Proceedings. Paper presented at 12th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA/AIE -99, Cairo, Egypt, May 31 - June 3, 1999 (pp. 550-559). Berlin: Springer Berlin/Heidelberg
Open this publication in new window or tab >>Using Labelled and Unlabelled Data to Train a Multilayer Perceptron for Colour Classification in Graphic Arts
1999 (English)In: Multiple approaches to intelligent systems: 12th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA/AIE-99, Cairo, Egypt, May 31 - June 3, 1999. Proceedings / [ed] Ibrahim Imam, Yves Kodratoff, Ayman El-Dessouki and Moonis Ali, Berlin: Springer Berlin/Heidelberg, 1999, p. 550-559Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents an approach to using both labelled and unlabelled data to train a multi-layer perceptron. The unlabelled data are iteratively pre-processed by a perceptron being trained to obtain the soft class label estimates. It is demonstrated that substantial gains in classification performance may be achieved from the use of the approach when the labelled data do not adequately represent the entire class distributions. The experimental investigations performed have shown that the approach proposed may be successfully used to train networks for colour classification in graphic arts.

Place, publisher, year, edition, pages
Berlin: Springer Berlin/Heidelberg, 1999
Series
Lecture notes in computer science, ISSN 0302-9743 ; 1611
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:hh:diva-3326 (URN)10.1007/978-3-540-48765-4_59 (DOI)000086482000059 ()978-3-540-66076-7 (ISBN)978-3-540-48765-4 (ISBN)
Conference
12th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA/AIE -99, Cairo, Egypt, May 31 - June 3, 1999
Available from: 2010-02-25 Created: 2009-12-01 Last updated: 2018-03-23Bibliographically approved
Verikas, A., Malmqvist, K., Bacauskiene, M. & Lipnickas, A. (1998). Soft fusion of neural classifiers. In: Shiro Usui, Takashi Omori (Ed.), ICONIP'98: The Fifth International Conference on Neural Information Processing, jointly with JNNS'98, the 1998 annual conference of the Japanese Neural Network Society : Kitakyushu, Japan, October 21-23, 1998 : proceedings, Volume 1. Paper presented at 5th International Conference on Neural Information Processing (ICONIP 98) / 1998 Annual Conference of the Japanese-Neural-Network-Society (JNNS 98), Kitakyushu, Japan, Oct. 21-23, 1998 (pp. 195-198). Burke, VA: IOS Press
Open this publication in new window or tab >>Soft fusion of neural classifiers
1998 (English)In: ICONIP'98: The Fifth International Conference on Neural Information Processing, jointly with JNNS'98, the 1998 annual conference of the Japanese Neural Network Society : Kitakyushu, Japan, October 21-23, 1998 : proceedings, Volume 1 / [ed] Shiro Usui, Takashi Omori, Burke, VA: IOS Press, 1998, p. 195-198Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents three schemes for soft fusion of outputs of multiple neural classifiers. The weights assigned to classifiers or groups of them are data dependent. The first scheme performs linear combination of outputs of classifiers and, in fact, is the BADD defuzzification strategy. The second approach involves calculation of fuzzy integrals. The last scheme performs weighted averaging with data dependent weights. An empirical evaluation using widely accessible data sets substantiates the validity of the approaches with data dependent weights compared to various existing combination schemes of multiple classifiers. The majority rule, combination by averaging, the weighted averaging, the Borda count, and the fuzzy integral have been used for the comparison.

Place, publisher, year, edition, pages
Burke, VA: IOS Press, 1998
Keywords
classification, multiple networks, fuzzy integral, fusion
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-18804 (URN)000079630400044 ()4-274-90259-5 (ISBN)
Conference
5th International Conference on Neural Information Processing (ICONIP 98) / 1998 Annual Conference of the Japanese-Neural-Network-Society (JNNS 98), Kitakyushu, Japan, Oct. 21-23, 1998
Available from: 2012-08-16 Created: 2012-06-25 Last updated: 2018-03-22Bibliographically approved
Verikas, A. & Malmqvist, K. (1995). Increasing colour image segmentation accuracy by means of fuzzy post-processing. In: 1995 IEEE International Conference on Neural Networks: Proceedings, the University of Western Australia, Perth, Western Australia, 27 November-1 December 1995 (Vol. 4). Paper presented at 1995 IEEE International Conference on Neural Networks, the University of Western Australia, Perth, Western Australia, 27 November-1 December 1995 (pp. 1713-1718). Piscataway, NJ: IEEE Press
Open this publication in new window or tab >>Increasing colour image segmentation accuracy by means of fuzzy post-processing
1995 (English)In: 1995 IEEE International Conference on Neural Networks: Proceedings, the University of Western Australia, Perth, Western Australia, 27 November-1 December 1995 (Vol. 4), Piscataway, NJ: IEEE Press, 1995, p. 1713-1718Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a colour image segmentation method which attains a high segmentation accuracy even when regions of the image that have to be separated are very similar in colour. The proposed method classifies pixels into colour classes. Competitive learning with `conscience' is used to learn reference patterns for the different colour classes. A nearest neighbour classification rule followed by a block of fuzzy post-processing attains a high classification accuracy even for very similar colour classes. A correct classification rate of 97.8% has been achieved when classifying two very similar black colours, namely, the black printed with a black ink and the black printed with a mixture of cyan, magenta and yellow inks.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Press, 1995
Series
IEEE International Conference on Neural Networks - Conference Proceedings, ISSN 1098-7576 ; 1995
Keywords
Color image processing, Fuzzy sets, Image segmentation, Learning systems, Pattern recognition
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-18827 (URN)10.1109/ICNN.1995.488878 (DOI)A1995BF46H00331 ()2-s2.0-0029516889 (Scopus ID)0-7803-2769-1 (ISBN)
Conference
1995 IEEE International Conference on Neural Networks, the University of Western Australia, Perth, Western Australia, 27 November-1 December 1995
Available from: 2012-08-15 Created: 2012-06-25 Last updated: 2018-03-22Bibliographically approved
Verikas, A., Malmqvist, K., Bacauskiene, M., Bergman, L. & Nilsson, K. (1994). Hierarchical neural network for color classification. In: IEEE (Ed.), The 1994 IEEE International Conference on Neural Networks: IEEE World Congress on Computational Intelligence, June 27-June 29, 1994, Walt Disney World Dolphin Hotel, Orlando, Florida, Vol. 5. Paper presented at 1994 IEEE International Conference on Neural Networks (ICNN 94) - 1st IEEE World Congress on Computational Intelligence, Orlando, FL, June 26-29, 1994 (pp. 2938-2941). Piscataway, NJ: IEEE Press
Open this publication in new window or tab >>Hierarchical neural network for color classification
Show others...
1994 (English)In: The 1994 IEEE International Conference on Neural Networks: IEEE World Congress on Computational Intelligence, June 27-June 29, 1994, Walt Disney World Dolphin Hotel, Orlando, Florida, Vol. 5 / [ed] IEEE, Piscataway, NJ: IEEE Press, 1994, p. 2938-2941Conference paper, Published paper (Refereed)
Abstract [en]

To make the hierarchical architecture, the neural networks of different type and different unsupervised learning techniques were combined. The classification accuracy obtained from such architecture is high enough to use it in the print quality control.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Press, 1994
Series
IEEE International Conference on Neural Networks - Conference Proceedings, ISSN 1098-7576
Keywords
Color, Color printing, Hierarchical systems, Iterative methods, Learning systems, Quality control
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-18829 (URN)10.1109/ICNN.1994.374699 (DOI)A1994BC54C00548 ()2-s2.0-0028734903 (Scopus ID)0-7803-1901-X (ISBN)
Conference
1994 IEEE International Conference on Neural Networks (ICNN 94) - 1st IEEE World Congress on Computational Intelligence, Orlando, FL, June 26-29, 1994
Available from: 2012-08-15 Created: 2012-06-25 Last updated: 2018-03-22Bibliographically approved
Verikas, A., Malmqvist, K. & Busk, H. (1994). Image analysis and artificial neural network for colour classification in multicolour newspaper printing. In: 1994 International Printing and Graphic Arts Conference: October 17-20, 1994 Chateau Halifax Hotel, Halifax, Canada. Paper presented at 1994 International Printing and Graphic Arts Conference, Halifax, Canada, 17-20 October 1994 (pp. 89-92). Atlanta: TAPPI Press
Open this publication in new window or tab >>Image analysis and artificial neural network for colour classification in multicolour newspaper printing
1994 (English)In: 1994 International Printing and Graphic Arts Conference: October 17-20, 1994 Chateau Halifax Hotel, Halifax, Canada, Atlanta: TAPPI Press , 1994, p. 89-92Conference paper, Published paper (Refereed)
Abstract [en]

Automatic inspection of printed multicoloured screen pictures demands methods for colour classification of screen dots and pans of screen dots directly in an arbitrary picture. The paper describes a technique using colour image analysis and artificial neural network for inverse colour separation. For every arbitrary small part of a coloured picture it is determined which coloured inks that have been printed in that part. Special attention is paid to the problem of seperating between black colour produced by black ink and black colour produced by combining cyan, magenta and yellow ink. The technique is tested on multicoloured newsprint and a high correct colour classification rate has been demonstrated.

Place, publisher, year, edition, pages
Atlanta: TAPPI Press, 1994
Keywords
Algorithms, Color image processing, Data structures, Image analysis, Mathematical models, Neural networks, Newsprint
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-18831 (URN)A1994BB99A00013 ()2-s2.0-0028755278 (Scopus ID)1-895288-66-5 (ISBN)
Conference
1994 International Printing and Graphic Arts Conference, Halifax, Canada, 17-20 October 1994
Available from: 2012-08-15 Created: 2012-06-25 Last updated: 2018-03-22Bibliographically approved
Organisations

Search in DiVA

Show all publications