hh.sePublikationer
Ändra sökning
Avgränsa sökresultatet
123456 51 - 100 av 270
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 51.
    Alonso-Fernandez, Fernando
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Raja, Kiran B.
    Norwegian University of Science and Technology, Gjøvik, Norway.
    Raghavendra, R.
    Norwegian University of Science and Technology, Gjøvik, Norway.
    Busch, Christoph
    Norwegian University of Science and Technology, Gjøvik, Norway.
    Bigun, Josef
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Vera-Rodriguez, Ruben
    Universidad Autónoma de Madrid, Madrid, Spain.
    Fierrez, Julian
    Universidad Autónoma de Madrid, Madrid, Spain.
    Cross-sensor periocular biometrics in a global pandemic: Comparative benchmark and novel multialgorithmic approach2022Ingår i: Information Fusion, ISSN 1566-2535, E-ISSN 1872-6305, Vol. 83-84, s. 110-130Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The massive availability of cameras and personal devices results in a wide variability between imaging conditions, producing large intra-class variations and a significant performance drop if images from heterogeneous environments are compared for person recognition purposes. However, as biometric solutions are extensively deployed, it will be common to replace acquisition hardware as it is damaged or newer designs appear or to exchange information between agencies or applications operating in different environments. Furthermore, variations in imaging spectral bands can also occur. For example, face images are typically acquired in the visible (VIS) spectrum, while iris images are usually captured in the near-infrared (NIR) spectrum. However, cross-spectrum comparison may be needed if, for example, a face image obtained from a surveillance camera needs to be compared against a legacy database of iris imagery. Here, we propose a multialgorithmic approach to cope with periocular images captured with different sensors. With face masks in the front line to fight against the COVID-19 pandemic, periocular recognition is regaining popularity since it is the only region of the face that remains visible. As a solution to the mentioned cross-sensor issues, we integrate different biometric comparators using a score fusion scheme based on linear logistic regression This approach is trained to improve the discriminating ability and, at the same time, to encourage that fused scores are represented by log-likelihood ratios. This allows easy interpretation of output scores and the use of Bayes thresholds for optimal decision-making since scores from different comparators are in the same probabilistic range. We evaluate our approach in the context of the 1st Cross-Spectral Iris/Periocular Competition, whose aim was to compare person recognition approaches when periocular data from visible and near-infrared images is matched. The proposed fusion approach achieves reductions in the error rates of up to 30%–40% in cross-spectral NIR–VIS comparisons with respect to the best individual system, leading to an EER of 0.2% and a FRR of just 0.47% at FAR = 0.01%. It also represents the best overall approach of the mentioned competition. Experiments are also reported with a database of VIS images from two different smartphones as well, achieving even bigger relative improvements and similar performance numbers. We also discuss the proposed approach from the point of view of template size and computation times, with the most computationally heavy comparator playing an important role in the results. Lastly, the proposed method is shown to outperform other popular fusion approaches in multibiometrics, such as the average of scores, Support Vector Machines, or Random Forest. © 2022 The Authors

  • 52.
    Alonso-Fernandez, Fernando
    et al.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Roli, F.
    University of Cagliari, Italy.
    Marcialis, G. L.
    University of Cagliari, Italy.
    Fierrez, J.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Ortega-Garcia, J.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Comparison of fingerprint quality measures using an optical and a capacitive sensor2007Ingår i: Biometrics: Theory, Applications, and Systems, 2007. BTAS 2007. First IEEE International Conference on, Piscataway, N.J.: IEEE Press, 2007, s. 133-138Konferensbidrag (Refereegranskat)
    Abstract [en]

    Although several image quality measures have been proposed for fingerprints, no work has taken into account the differences among capture devices, and how these differences impact on the image quality. In this paper, several representative measures for assessing the quality fingerprint images are compared using an optical and a capacitive sensor. The capability to discriminate between images of different quality and its relationship with the verification performance is studied. We report differences depending on the sensor, and interesting relationships between sensor technology and features used for quality assessment are also pointed out. ©2007 IEEE.

    Ladda ner fulltext (pdf)
    fulltext
  • 53.
    Alonso-Fernandez, Fernando
    et al.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Roli, Fabio
    Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy.
    Marcialis, Gian Luca
    Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy.
    Fierrez, Julian
    Escuela Politecnica Superior, Univ Autonoma Madrid, Madrid, Spain.
    Ortega-Garcia, Javier
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Performance of Fingerprint Quality Measures Depending on Sensor Technology2008Ingår i: Journal of Electronic Imaging (JEI), ISSN 1017-9909, E-ISSN 1560-229X, Vol. 17, nr 1, artikel-id 011008Artikel i tidskrift (Refereegranskat)
    Ladda ner fulltext (pdf)
    fulltext
  • 54.
    Alonso-Fernandez, Fernando
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Sharon Belvisi, Nicole Mariah
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Hernandez-Diaz, Kevin
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Muhammad, Naveed
    Institute of Computer Science, University of Tartu, Tartu , Estonia.
    Bigun, Josef
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Writer Identification Using Microblogging Texts for Social Media Forensics2021Ingår i: IEEE Transactions on Biometrics, Behavior, and Identity Science, E-ISSN 2637-6407, Vol. 3, nr 3, s. 405-426Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Establishing authorship of online texts is fundamental to combat cybercrimes. Unfortunately, text length is limited on some platforms, making the challenge harder. We aim at identifying the authorship of Twitter messages limited to 140 characters. We evaluate popular stylometric features, widely used in literary analysis, and specific Twitter features like URLs, hashtags, replies or quotes. We use two databases with 93 and 3957 authors, respectively. We test varying sized author sets and varying amounts of training/test texts per author. Performance is further improved by feature combination via automatic selection. With a large amount of training Tweets (>500), a good accuracy (Rank-5>80%) is achievable with only a few dozens of test Tweets, even with several thousands of authors. With smaller sample sizes (10-20 training Tweets), the search space can be diminished by 9-15% while keeping a high chance that the correct author is retrieved among the candidates. In such cases, automatic attribution can provide significant time savings to experts in suspect search. For completeness, we report verification results. With few training/test Tweets, the EER is above 20-25%, which is reduced to < 15% if hundreds of training Tweets are available. We also quantify the computational complexity and time permanence of the employed features. © 2019 IEEE.

    Ladda ner fulltext (pdf)
    fulltext
  • 55.
    Alonso-Fernandez, Fernando
    et al.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Tome-Gonzalez, P.
    Universidad Autonoma de Madrid, Spain.
    Ruiz-Albacete, V.
    Universidad Autonoma de Madrid, Spain.
    Ortega-Garcia, J.
    Universidad Autonoma de Madrid, Spain.
    Iris Recognition Based on SIFT Features2009Ingår i: 2009 First IEEE International Conference on Biometrics, Identity and Securit, 2009, s. 1-8Konferensbidrag (Refereegranskat)
    Abstract [en]

    Biometric methods based on iris images are believed to allow very high accuracy, and there has been an explosion of interest in iris biometrics in recent years. In this paper, we use the Scale Invariant Feature Transformation (SIFT) for recognition using iris images. Contrarily to traditional iris recognition systems, the SIFT approach does not rely on the transformation of the iris pattern to polar coordinates or on highly accurate segmentation, allowing less constrained image acquisition conditions. We extract characteristic SIFT feature points in scale space and perform matching based on the texture information around the feature points using the SIFT operator. Experiments are done using the BioSec multimodal database, which includes 3,200 iris images from 200 individuals acquired in two different sessions. We contribute with the analysis of the influence of different SIFT parameters on the recognition performance. We also show the complementarity between the SIFT approach and a popular matching approach based on transformation to polar coordinates and Log-Gabor wavelets. The combination of the two approaches achieves significantly better performance than either of the individual schemes, with a performance improvement of 24% in the Equal Error Rate.

    Ladda ner fulltext (pdf)
    fulltext
  • 56.
    Alonso-Fernandez, Fernando
    et al.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Veldhuis, R. N. J.
    University of Twente, The Netherlands.
    Bazen, A. M.
    University of Twente, The Netherlands.
    Fierrez-Aguilar, J.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Ortega-Garcia, J.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    On the relation between biometric quality and user-dependent score distributions in fingerprint verification2006Konferensbidrag (Refereegranskat)
    Ladda ner fulltext (pdf)
    fulltext
  • 57.
    Alonso-Fernandez, Fernando
    et al.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Veldhuis, R. N. J.
    University of Twente, The Netherlands.
    Bazen, A. M.
    University of Twente, The Netherlands.
    Fierrez-Aguilar, J.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Ortega-Garcia, J.
    Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain.
    Sensor Interoperability and Fusion in Fingerprint Verification: A Case Study Using Minutiae- and Ridge-based Matchers2006Ingår i: 2006 9th International Conference on Control, Automation, Robotics and Vision, Vols 1- 5, Piscataway, N.J.: IEEE Press, 2006, s. 422-427Konferensbidrag (Refereegranskat)
    Abstract [en]

    Information fusion in fingerprint recognition has been studied in several papers. However, only a few papers have been focused on sensor interoperability and sensor fusion. In this paper, these two topics are studied using a multisensor database acquired with three different fingerprint sensors. Authentication experiments using minutiae and ridge-based matchers are reported. Results show that the performance drops dramatically when matching images from different sensors. We have also observed that fusing scores from different sensors results in better performance than fusing different instances from the same sensor. © 2006 IEEE.

    Ladda ner fulltext (pdf)
    fulltext
  • 58.
    ALRimawi, Mohammed
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Doppler Wheel for Emulation of Automotive Radar Target2019Självständigt arbete på avancerad nivå (magisterexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Automotive radar is an emerging field of research and development. Technological ‎advancements in this field will improve safety for vehicles, pedestrians, and ‎bicyclists, and enable the development of autonomous vehicles. Usage of the ‎Automotive radar is expanding ‎in car and road areas to reduce collisions and ‎accident. Automotive radar ‎developers face a problem to test their radar sensor in ‎the street since there are a lot of interferences ‎signals, noise and unpredicted ‎situations. This thesis provides a part of the solution for this problem by designing a ‎device can demonstrate a different speeds value. This device will help the developer ‎to test their radar sensor inside an anechoic chamber room that provides accurate ‎control of the environmental conditions. This report shows how to ‎build the ‎measuring setup device, step by step to demonstrate the people and vehicle’s speed ‎‎in the street by a Doppler emulator using the wheel for millimetre FWMC radar. ‎Linear speed system needs a large space for testing, but using the rotational wheel ‎allow the developer to test the radar sensor in a small area. It begins with the wheel ‎design specifications and the relation between the ‎rotational speed (RPM) of the ‎wheel and the Doppler frequency. The Doppler ‎frequency is changed by varying the ‎speed of the wheel. Control and power circuit ‎was carefully designed to control the ‎wheel speed accurately. All the measuring ‎setup device parts were assembled in one ‎box. Also, signal processing was done by ‎MATLAB to measure the Doppler frequency ‎using millimetre FMCW radar sensor. ‎The measuring setup device was tested in the ‎anechoic chamber room for different speeds. the ‎manual and automatic tests show ‎good results to measure the different wheel speeds ‎with high accuracy.‎

    Ladda ner fulltext (pdf)
    fulltext
    Ladda ner (wmv)
    Automotive Testing result
    Ladda ner (zip)
    Circuit board (OrCAD files)
    Ladda ner (zip)
    C programming file (mikroC)
  • 59.
    Altarabichi, Mohammed Ghaith
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Evolving intelligence: Overcoming challenges for Evolutionary Deep Learning2024Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    Deep Learning (DL) has achieved remarkable results in both academic and industrial fields over the last few years. However, DL models are often hard to design and require proper selection of features and tuning of hyper-parameters to achieve high performance. These selections are tedious for human experts and require substantial time and resources. A difficulty that encouraged a growing number of researchers to use Evolutionary Computation (EC) algorithms to optimize Deep Neural Networks (DNN); a research branch called Evolutionary Deep Learning (EDL).

    This thesis is a two-fold exploration within the domains of EDL, and more broadly Evolutionary Machine Learning (EML). The first goal is to makeEDL/EML algorithms more practical by reducing the high computational costassociated with EC methods. In particular, we have proposed methods to alleviate the computation burden using approximate models. We show that surrogate-models can speed up EC methods by three times without compromising the quality of the final solutions. Our surrogate-assisted approach allows EC methods to scale better for both, expensive learning algorithms and large datasets with over 100K instances. Our second objective is to leverage EC methods for advancing our understanding of Deep Neural Network (DNN) design. We identify a knowledge gap in DL algorithms and introduce an EC algorithm precisely designed to optimize this uncharted aspect of DL design. Our analytical focus revolves around revealing avant-garde concepts and acquiring novel insights. In our study of randomness techniques in DNN, we offer insights into the design and training of more robust and generalizable neural networks. We also propose, in another study, a novel survival regression loss function discovered based on evolutionary search.

    Ladda ner fulltext (pdf)
    fulltext
  • 60.
    Alves, Dimas Irion
    et al.
    Instituto Tecnológico De Aeronáutica, Sao Jose dos Campos, Brazil.
    Palm, Bruna Gregory
    Blekinge Institute Of Technology, Karlskrona, Sweden.
    Hellsten, Hans
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Machado, Renato
    Instituto Tecnológico De Aeronáutica, Sao Jose dos Campos, Brazil.
    Vu, Viet Thuy
    Blekinge Institute Of Technology, Karlskrona, Sweden.
    Pettersson, Mats I.
    Blekinge Institute Of Technology, Karlskrona, Sweden.
    Dammert, Patrik
    Saab Ab, Stockholm, Sweden.
    Change Detection Method for Wavelength-Resolution SAR Images Based on Bayes’ Theorem: An Iterative Approach2023Ingår i: IEEE Access, E-ISSN 2169-3536, Vol. 11, s. 84734-84743Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This paper presents an iterative change detection (CD) method based on Bayes&#x2019; theorem for very high-frequency (VHF) ultra-wideband (UWB) SAR images considering commonly used clutter-plus-noise statistical models. The proposed detection technique uses the information of the detected changes to iteratively update the data and distribution information, obtaining more accurate clutter-plus-noise statistics resulting in false alarm reduction. The Bivariate Rayleigh and Bivariate Gaussian distributions are investigated as candidates to model the clutter-plus-noise, and the Anderson-Darling goodness-of-fit test is used to investigate three scenarios of interest. Different aspects related to the distributions are discussed, the observed mismatches are analyzed, and the impact of the distribution chosen for the proposed iterative change detection method is analyzed. Finally, the proposed iterative method performance is assessed in terms of the probability of detection and false alarm rate and compared with other competitive solutions. The experimental evaluation uses data from real measurements obtained using the CARABAS II SAR system. Results show that the proposed iterative CD algorithm performs better than the other methods.

  • 61.
    Amirhossein, Berenji
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Taghiyarrenani, Zahra
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Nowaczyk, Sławomir
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    curr2vib: Modality Embedding Translation for Broken-Rotor Bar Detection2023Ingår i: Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2022, Grenoble, France, September 19–23, 2022, Proceedings, Part II / [ed] Irena Koprinska et al., Cham: Springer Nature, 2023, Vol. 1753, s. 423-437Konferensbidrag (Refereegranskat)
    Abstract [en]

    Recently and due to the advances in sensor technology and Internet-of-Things, the operation of machinery can be monitored, using a higher number of sources and modalities. In this study, we demonstrate that Multi-Modal Translation is capable of transferring knowledge from a modality with higher level of applicability (more usefulness to solve an specific task) but lower level of accessibility (how easy and affordable it is to collect information from this modality) to another one with higher level of accessibility but lower level of applicability. Unlike the fusion of multiple modalities which requires all of the modalities to be available during the deployment stage, our proposed method depends only on the more accessible one; which results in the reduction of the costs regarding instrumentation equipment. The presented case study demonstrates that by the employment of the proposed method we are capable of replacing five acceleration sensors with three current sensors, while the classification accuracy is also increased by more than 1%.

    Ladda ner fulltext (pdf)
    fulltext
  • 62. Andersson, Emil
    et al.
    Schedin, Niklas
    Räkning av Personer i Rörelse med Bildtolkning2016Självständigt arbete på grundnivå (högskoleexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    I dagens samhälle är företag beroende av markadsundersökningar för att forsatt kunna växa. En undersökning kan vara att se personflödet i varuhus. Det här projektet riktar sig till att skapa en bildtolkningsalgoritm som klarar av att räkna antalet personer som passerar förbi en kamera. Systemet består av två stycken räknare, en för de personer som går in och en för de som går ut. För att lösa denna uppgift så har projektet delats in i två faser, en utbildningsfas och en utvecklingsfas. Utbildningsfasen är till för att få kunskap om bildtolkning, eftersom projektmedlemarna inte har någon tidigare erfarenhet om det området. Utvecklingsfasen är då den slutliga algoritmen utvecklas utifrån de kunskaper som utbildningsfasen har givit. Det slutliga resultatet visar att vid låg belastning är algoritmen pålitlig, men när den belastas med allt fler personer börjar räknarna avvika ifrån de faktiska värdena.

    Ladda ner fulltext (pdf)
    fulltext
  • 63.
    Andreasson, Henrik
    et al.
    Örebro University, Örebro, Sweden.
    Bouguerra, Abdelbaki
    Örebro University, Örebro, Sweden.
    Åstrand, Björn
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Rögnvaldsson, Thorsteinn
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Gold-fish SLAM: An application of SLAM to localize AGVs2014Ingår i: Field and Service Robotics: Results of the 8th International Conference / [ed] Kazuya Yoshida & Satoshi Tadokoro, Heidelberg: Springer, 2014, s. 585-598Konferensbidrag (Refereegranskat)
    Abstract [en]

    The main focus of this paper is to present a case study of a SLAM solution for Automated Guided Vehicles (AGVs) operating in real-world industrial environments. The studied solution, called Gold-fish SLAM, was implemented to provide localization estimates in dynamic industrial environments, where there are static landmarks that are only rarely perceived by the AGVs. The main idea of Gold-fish SLAM is to consider the goods that enter and leave the environment as temporary landmarks that can be used in combination with the rarely seen static landmarks to compute online estimates of AGV poses. The solution is tested and verified in a factory of paper using an eight ton diesel-truck retrofitted with an AGV control system running at speeds up to 3m/s. The paper includes also a general discussion on how SLAM can be used in industrial applications with AGVs. © Springer-Verlag Berlin Heidelberg 2014.

  • 64.
    Aramrattana, Maytheewat
    et al.
    The Swedish National Road and Transport Research Institute (VTI), Linköping, Sweden.
    Larsson, Tony
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), Centrum för forskning om inbyggda system (CERES).
    Englund, Cristofer
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab). RISE Viktoria, Gothenburg, Sweden.
    Jansson, Jonas
    The Swedish National Road and Transport Research Institute (VTI), Linköping, Sweden.
    Nåbo, Arne
    The Swedish National Road and Transport Research Institute (VTI), Linköping, Sweden.
    A Novel Risk Indicator for Cut-In Situations2020Ingår i: 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Piscataway, NJ: IEEE, 2020, artikel-id 9294315Konferensbidrag (Refereegranskat)
    Abstract [en]

    Cut-in situations occurs when a vehicle intention- ally changes lane and ends up in front of another vehicle or in-between two vehicles. In such situations, having a method to indicate the collision risk prior to making the cut-in maneuver could potentially reduce the number of sideswipe and rear end collisions caused by the cut-in maneuvers. This paper propose a new risk indicator, namely cut-in risk indicator (CRI), as a way to indicate and potentially foresee collision risks in cut-in situations. As an example use case, we applied CRI on data from a driving simulation experiment involving a manually driven vehicle and an automated platoon in a highway merging situation. We then compared the results with time-to-collision (TTC), and suggest that CRI could correctly indicate collision risks in a more effective way. CRI can be computed on all vehicles involved in the cut-in situations, not only for the vehicle that is cutting in. Making it possible for other vehicles to estimate the collision risk, for example if a cut-in from another vehicle occurs, the surrounding vehicles could be warned and have the possibility to react in order to potentially avoid or mitigate accidents. © 2020 IEEE.

  • 65.
    Aramrattana, Maytheewat
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Larsson, Tony
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Englund, Cristofer
    Högskolan i Halmstad, Akademin för informationsteknologi. RISE Viktoria, Gothenburg, Sweden.
    Jansson, Jonas
    Swedish National Road and Transport Research Institute (VTI), Sweden.
    Nåbo, Arne
    Swedish National Road and Transport Research Institute (VTI), Sweden.
    A Simulation Study on Effects of Platooning Gaps on Drivers of Conventional Vehicles in Highway Merging Situations2022Ingår i: IEEE transactions on intelligent transportation systems (Print), ISSN 1524-9050, E-ISSN 1558-0016, Vol. 23, nr 4, s. 3790-3796Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Platooning refers to a group of vehicles that--enabled by wireless vehicle-to-vehicle (V2V) communication and vehicle automation--drives with short inter-vehicular distances. Before its deployment on public roads, several challenging traffic situations need to be handled. Among the challenges are cut-in situations, where a conventional vehicle--a vehicle that has no automation or V2V communication--changes lane and ends up between vehicles in a platoon. This paper presents results from a simulation study of a scenario, where a conventional vehicle, approaching from an on-ramp, merges into a platoon of five cars on a highway. We created the scenario with four platooning gaps: 15, 22.5, 30, and 42.5 meters. During the study, the conventional vehicle was driven by 37 test persons, who experienced all the platooning gaps using a driving simulator. The participants' opinions towards safety, comfort, and ease of driving between the platoon in each gap setting were also collected through a questionnaire. The results suggest that a 15-meter gap prevents most participants from cutting in, while causing potentially dangerous maneuvers and collisions when cut-in occurs. A platooning gap of at least 30 meters yield positive opinions from the participants, and facilitating more smooth cut-in maneuvers while less collisions were observed.

  • 66.
    Arvidsson, Moa
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Sawirot, Sithichot
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Englund, Cristofer
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Alonso-Fernandez, Fernando
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Torstensson, Martin
    RISE Viktoria, Gothenburg, Sweden.
    Duran, Boris
    RISE Viktoria, Gothenburg, Sweden.
    Drone navigation and license place detection for vehicle location in indoor spaces2023Ingår i: Progress in Artificial Intelligence and Pattern Recognition / [ed] Yanio Hernández Heredia; Vladimir Milián Núñez; José Ruiz Shulcloper, Heidelberg: Springer, 2023, s. 362-374Konferensbidrag (Refereegranskat)
    Abstract [en]

    Millions of vehicles are transported every year, tightly parked in vessels or boats. To reduce the risks of associated safety issues like fires, knowing the location of vehicles is essential, since different vehicles may need different mitigation measures, e.g. electric cars. This work is aimed at creating a solution based on a nano-drone that navigates across rows of parked vehicles and detects their license plates. We do so via a wall-following algorithm, and a CNN trained to detect license plates. All computations are done in real-time on the drone, which just sends position and detected images that allow the creation of a 2D map with the position of the plates. Our solution is capable of reading all plates across eight test cases (with several rows of plates, different drone speeds, or low light) by aggregation of measurements across several drone journeys. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

    Ladda ner fulltext (pdf)
    fulltext
  • 67.
    Asplund, Martin
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Landin, Robin
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Steering of the second front axle in Volvo trucks2020Självständigt arbete på grundnivå (högskoleexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Med några års mellanrum får moderna tunga fordon en ny design och kan frakta mer gods än tidigare. Men att öka mängden gods innebär att öka vikten, vilket leder till mer tryck på ingenjörerna för att designa förbättrade fordonsramar och axlar för att fördela denna last bättre. Nyligen har en andra framaxel lagts till. Denna axel har styrts med en mekanisk länk sedan den infördes, men tack vare de senaste lagändringarna finns nu möjligheten att styra denna axel med ett elektro-hydrauliskt system. Syftet med projektet är just det, att skapa ett elektro-hydrauliskt styrsystem, kan även kallas steer-by-wire (SBW). Genom möten med ingenjörer på Volvo GTT kunde det första utkastet till några koncept uppnås. Koncepten bestod av en CAD-konstruktion av styrningen, kompletterad med en hydraulisk styrning. Genom att återanvända befintliga delar i den nya designen uppnåddes en liknande styrfunktion. Men att ha ett SBW-system som kan kopplas direkt till den nya axeln, det är inte längre begränsat med en anslutning till den första axeln, nu sätter bara fantasin gränserna. Vikten minskas, bränsle- och energiförbrukning minskas, men kanske viktigast av allt. Flexibiliteten i detta system ökar, vilket gör det möjligt att ha oberoende styrning från den första axeln och till och med ändra axelns placering på själva ramen. Ett system som det här kan ha en stor inverkan på miljöeffekterna av lastbilar, eftersom det kan minska antalet fordon på vägen. Tack vare den ökade mängden dom nu kan frakta.

    Ladda ner fulltext (pdf)
    fulltext
  • 68.
    Aydogdu, Canan
    et al.
    Chalmers University of Technology, Gothenburg, Sweden.
    Keskin, Musa Furkan
    Chalmers University of Technology, Gothenburg, Sweden.
    Carvajal, Gisela K.
    QAMCOM Research, Gothenburg, Sweden.
    Eriksson, Olof
    Veoneer Sweden AB, Vårgårda, Sweden.
    Hellsten, Hans
    Saab Surveillance, Linköping, Sweden.
    Herbertsson, Hans
    Chalmers University of Technology, Gothenburg, Sweden.
    Nilsson, Emil
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS).
    Rydström, Mats
    Chalmers University of Technology, Gothenburg, Sweden.
    Vanäs, Karl
    Volvo Car Corporation, Gothenburg, Sweden.
    Wymeersch, Henk
    Communications Systems, Chalmers University of Technology, Gothenburg, Sweden.
    Radar Interference Mitigation for Automated Driving: Exploring Proactive Strategies2020Ingår i: IEEE signal processing magazine (Print), ISSN 1053-5888, E-ISSN 1558-0792, Vol. 37, nr 4, s. 72-84, artikel-id 9127843Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Autonomous driving relies on a variety of sensors, especially radars, which have unique robustness under heavy rain/fog/snow and poor light conditions. With the rapid increase of the amount of radars used on modern vehicles, where most radars operate in the same frequency band, the risk of radar interference becomes a compelling issue. This article analyzes automotive radar interference and proposes several new approaches that combine industrial and academic expertise toward the goal of achieving interference-free autonomous driving (AD). © IEEE.

  • 69.
    Baaz, August
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Yonan, Yonan
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Hernandez-Diaz, Kevin
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Alonso-Fernandez, Fernando
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Nilsson, Felix
    HMS Industrial Networks AB, Halmstad, Sweden.
    Synthetic Data for Object Classification in Industrial Applications2023Ingår i: Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods ICPRAM / [ed] Maria De Marsico; Gabriella Sanniti di Baja; Ana Fred, SciTePress, 2023, Vol. 1, s. 387-394Konferensbidrag (Refereegranskat)
    Abstract [en]

    One of the biggest challenges in machine learning is data collection. Training data is an important part since it determines how the model will behave. In object classification, capturing a large number of images per object and in different conditions is not always possible and can be very time-consuming and tedious. Accordingly, this work explores the creation of artificial images using a game engine to cope with limited data in the training dataset. We combine real and synthetic data to train the object classification engine, a strategy that has shown to be beneficial to increase confidence in the decisions made by the classifier, which is often critical in industrial setups. To combine real and synthetic data, we first train the classifier on a massive amount of synthetic data, and then we fine-tune it on real images. Another important result is that the amount of real images needed for fine-tuning is not very high, reaching top accuracy with just 12 or 24 images per class. This substantially reduces the requirements of capturing a great amount of real data. © 2023 by SCITEPRESS-Science and Technology Publications, Lda.

    Ladda ner fulltext (pdf)
    fulltext
  • 70.
    Baerveldt, Albert-Jan
    et al.
    Högskolan i Halmstad, Sektionen för ekonomi och teknik (SET).
    Klang, Robert
    Högskolan i Halmstad, Sektionen för ekonomi och teknik (SET).
    A low-cost and low-weight attitude estimation system for an autonomous helicopter1997Ingår i: IEEE International Conference on Intelligent Engineering Systems, Proceedings, INES / [ed] Imre J Rudas, Piscataway, N.J.: IEEE Press, 1997, s. 391-395Konferensbidrag (Övrigt vetenskapligt)
    Abstract [en]

    In this paper a low-cost and low-weight attitude estimation system for an autonomous helicopter is presented. The system is based on an inclinometer and a rate gyro. The data coming from the sensors is fused through a complementary filter. In this way the slow dynamics of the inclinometer can be effectively compensated. Tests have shown that we obtained a very effective attitude estimation system.

  • 71.
    Belvisi, Nicole Mariah Sharon
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Muhammad, Naveed
    Institute of Computer Science, University of Tartu, Tartu, Estonia.
    Alonso-Fernandez, Fernando
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Forensic Authorship Analysis of Microblogging Texts Using -Grams and Stylometric Features2020Ingår i: 2020 8th International Workshop on Biometrics and Forensics (IWBF), Piscataway: IEEE, 2020, artikel-id 9107953Konferensbidrag (Refereegranskat)
    Abstract [en]

    In recent years, messages and text posted on the Internet are used in criminal investigations. Unfortunately, the authorship of many of them remains unknown. In some channels, the problem of establishing authorship may be even harder, since the length of digital texts is limited to a certain number of characters. In this work, we aim at identifying authors of tweet messages, which are limited to 280 characters. We evaluate popular features employed traditionally in authorship attribution which capture properties of the writing style at different levels. We use for our experiments a self-captured database of 40 users, with 120 to 200 tweets per user. Results using this small set are promising, with the different features providing a classification accuracy between 92% and 98.5%. These results are competitive in comparison to existing studies which employ short texts such as tweets or SMS. ©2020 IEEE 

  • 72.
    Belyaev, Evgeny
    et al.
    Department of Signal Processing, Tampere University of Technology, Tampere, Finland.
    Molchanov, Pavlo
    Department of Signal Processing, Tampere University of Technology, Tampere, Finland.
    Vinel, Alexey
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), Centrum för forskning om inbyggda system (CERES). Department of Electronics and Communication Engineering, Tampere University of Technology, Tampere, Finland.
    Koucheryavy, Yevgeni
    Department of Electronics and Communication Engineering, Tampere University of Technology, Tampere, Finland.
    The Use of Automotive Radars in Video-Based Overtaking Assistance Applications2013Ingår i: IEEE transactions on intelligent transportation systems (Print), ISSN 1524-9050, E-ISSN 1558-0016, Vol. 14, nr 3, s. 1035-1042, artikel-id 649464Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Overtaking on rural roads may cause severe accidents when oncoming traffic is detected by a driver too late, or its speed is underestimated. Recently proposed cooperative overtaking assistance systems are based on real-time video transmission, where a video stream captured with a camera installed at the windshield of a vehicle is compressed, broadcast through the wireless channel, and displayed to the drivers of vehicles driving behind. In such a system, it is of ultimate importance to deliver video information about the opposite lane with low end-to-end latency and good visual quality. In this paper, we propose reallocating the wireless channel resources in favor of the part of the captured video frame containing the image of the oncoming vehicle. To achieve this goal, we apply automotive radar for oncoming vehicle detection, and we use the image of this vehicle as a region-of-interest (ROI) for the video rate control. We present the theoretical framework, which describes the basics of such an approach and can serve as a useful guideline for the future practical implementation of the overtaking assistance systems. The benefits of our proposal are demonstrated in relation to the practical scenario of H.264/Advance Video Coding (AVC), IEEE 802.11p/Wireless Access for Vehicular Environments (WAVE) intervehicle communication standards, and currently used automotive radars.

  • 73.
    Bengtsson, Ola
    Chalmers tekniska högskola Göteborg.
    Robust self-localization of mobile robots in dynamic environments using scan matching algorithms2006Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    The most fundamental task for any mobile robot is to perform self-localization in the world in which it is currently active, i.e. determine its position relative its world. Encoders that count wheel rotations are often used, which can be turned into relative position estimates by mean of integration. This process is commonly referred to as dead reckoning. Unfortunately, the errors in such position estimates grow over time due to the underlying measurements errors, which means that the errors in the dead reckoning estimates must be regularly corrected by absolute postion estimates provided by other sensors. The goal of this thesis is to evaluate the possibilities of using so called scan mathing algorithms for robust position estimation of a mobile robot, especially in environments that change over time. A scan is a set o range measurements of the environment provided by e.g. a laser scanner. By comparing a scan taken at the actual poition of the robot with a scan previously taken and stored in a map of the environment, an estimate of the absolute position of the robot can be obtained. It is important that scan matching algorithms are robust against changes in the environments, are robust against different types of environments and can judge their own results.

    The main contributions of the thesis are threefold. First, two new sector-based scan matching algorithms are presented that are based on two existing scan-matching algorithms known as the Cox's and IDC algorithm. The sector-based variants, Cox-S and IDC-S, increase the performance of the existing algorithms, especially in environments containing severe changes. Second, two new methods are presented for estimating the uncertainty of the IDC algorithm. These methods improve the self-judgment of the IDC and IDC-S significantly, as the existing method for estimating the uncertainty was not reliable. Third, the new sector-based scan matching algorithms are evaluated and compared to the existing algorithms on the basis of simulations and real world experiments made with two different mobile robots. The experiments focus on the performance of the algorithms in hanging environments, and on their performance as part of a complete loalization system, i.e. fusing the outcome with dead reckoning. The experiments show a clear advantage of using sector-based scan matching algorithms in terms of increased robustness against changed environments. The experiments show that use especially of a combination of the two sector based algorithms Cox-S and IDC-S, while also using the new method for estimating the uncertainty of the IDC-S, achieves significantly better performance in changing environments compared to the existing algorithms.

  • 74.
    Bengtsson, Ola
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS).
    Baerveldt, Albert-Jan
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS).
    Localization in changing environments - Estimation of a covariance matrix for the IDC algorithm2001Ingår i: Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180): Volume 4 of 4, Piscataway, N.J.: IEEE, 2001, s. 1931-1937Konferensbidrag (Refereegranskat)
    Abstract [en]

    Previously we have presented a new scan-matching algorithm, based on the IDC - Iterative Dual Correspondence- algorithm, which showed a good localization performance even in the case of severe changes in the environment. The Problem of the IDC-algorithm is that there is no good way to estimate the covariance matrix of the position estimate, which prohibits an effective fusion with other position estimates from other sensors, e.g by means of the Kalman filter. In this paper we present a new way to estimate the covariance matrix, by estimating the Hessian matrix of the error function that is minimized by the IDC scan-matching algorithm. Simulation results show that the estimated covariance matrix correspond well to the real one.

  • 75.
    Bergström, Edwin
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Investigate options with spectrum scanning applications2024Självständigt arbete på grundnivå (kandidatexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [en]

    This thesis investigates the possibilities of Software-defined radios as a surveillance system by monitoring the electromagnetic spectrum. The surveillance system monitors the Bluetooth bandwidth with a multi-channel receiver that passively listens to Bluetooth packets. Furthermore, this thesis investigates the possibility of implementing an automatic k-means clustering algorithm to count unique devices in the vicinity. The Background explains the fundamental technologies used in Bluetooth and explains how devices communicate with each other. The Background also explains the proposed receiver architecture and its technologies. Section Related work and similar products investigate different approaches to detecting mobile devices and the effectiveness of the k-means algorithm. The Method explains how the receiver is modeled, how the Python script identifies Bluetooth packets in the bit stream, and how the physical imperfections are collected for the automatic k-means algorithm. Lastly, the Method explains how the labs were conducted. The Result section shows the performance of the receiver and the k-means algorithm. The Discussion section analyzes the results and discusses some design flaws and how to fix them potentially. Lastly, the Conclusion section compares the goals with the results and presents future work for further development.  

    Ladda ner fulltext (pdf)
    fulltext
  • 76.
    Bigun, Josef
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Alonso-Fernandez, Fernando
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Analytic Signal Phase in Ν − D by Linear Symmetry Tensor – fingerprint modelingIngår i: Artikel i tidskrift (Övrigt vetenskapligt)
    Abstract [en]

    We reveal that the Analytic Signal phase, and its gradient have a hitherto unstudied discontinuity in 2−D and higher dimensions. The shortcoming can result in severe artifacts whereas the problem does not exist in 1−D signals. Direct use of Gabor phase, or its gradient, in computer vision and biometric recognition e.g., as done in influential studies, may produce undesired results that will go unnoticed unless special images similar to ours reveal them. Instead of the Analytic Signal phase, we suggest the use of Linear Symmetry phase, relying on more than one set of Gabor filters, but with a negligible computational add-on, as a remedy. Gradient magnitudes of this phase are continuous in contrast to that of the analytic signal whereas continuity of the gradient direction of the phase is guaranteed if Linear Symmetry Tensor replaces gradient vector. The suggested phase has also a built-in automatic scale estimator, useful for robust detection of patterns by multi-scale processing. We show crucial concepts on synthesized fingerprint images, where ground truth regarding instantaneous frequency, (scale \& direction), and phase are known with favorable results. A comparison to a baseline alternative is also reported. To that end, a novel multi-scale minutia model where location, direction, and scale of minutia parameters are steerable, without the creation of uncontrollable minutia is also presented. This is a useful tool, to reduce development times of minutia detection methods with explainable behavior. A revealed consequence is that minutia directions are not determined by the linear phase alone, but also by each other and the influence must be corrected to obtain steerability and accurate ground truths. Essential conclusions are readily transferable to ND, and unrelated applications, e.g. optical flow or disparity estimation in stereo.

  • 77.
    Bigun, Josef
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligenta system (IS-lab).
    Fierrez-Aguilar, J.
    Universidad Politecnica de Madrid, Spain.
    Ortega-Garcia, J.
    Universidad Politecnica de Madrid, Spain.
    Gonzalez-Rodriguez, J.
    Universidad Politecnica de Madrid, Spain.
    Combining Biometric Evidence for Person Authentication2005Ingår i: Advanced Studies in Biometrics: Summer School on Biometrics, Alghero, Italy, June 2-6, 2003 / [ed] Tistarelli, Massimo; Bigun, Josef; Grosso, Enrico, Berlin: Springer Berlin/Heidelberg, 2005, s. 1-18Konferensbidrag (Övrigt vetenskapligt)
    Abstract [en]

    Humans are excellent experts in person recognition and yet they do not perform excessively well in recognizing others only based on one modality such as single facial image. Experimental evidence of this fact is reported concluding that even human authentication relies on multimodal signal analysis. The elements of automatic multimodal authentication along with system models are then presented. These include the machine experts as well as machine supervisors. In particular, fingerprint and speech based systems will serve as illustration. A signal adaptive supervisor based on the input biometric signal quality is evaluated.

  • 78.
    Bigun, Josef
    et al.
    Högskolan i Halmstad, Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Karlsson, Stefan M.
    Högskolan i Halmstad, Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Histogram of directions by the structure tensor2011Ingår i: Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies, New York, NY: Association for Computing Machinery (ACM), 2011Konferensbidrag (Refereegranskat)
    Abstract [en]

    Many low-level features, as well as varying methods of extraction and interpretation rely on directionality analysis (for example the Hough transform, Gabor filters, SIFT descriptors and the structure tensor). The theory of the gradient based structure tensor (a.k.a. the second moment matrix) is a very well suited theoretical platform in which to analyze and explain the similarities and connections (indeed often equivalence) of supposedly different methods and features that deal with image directionality. Of special interest to this study is the SIFT descriptors (histogram of oriented gradients, HOGs). Our analysis of interrelationships of prominent directionality analysis tools offers the possibility of computation of HOGs without binning, in an algorithm of comparative time complexity.

    Ladda ner fulltext (pdf)
    fulltext
  • 79.
    Bigun, Josef
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Mikaelyan, Anna
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS).
    Frequency map by Structure Tensor in Logarithmic Scale Space and Forensic Fingerprints2016Ingår i: PROCEEDINGS OF 29TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, (CVPRW 2016), Piscataway, NJ: IEEE, 2016, s. 204-213, artikel-id 7789522Konferensbidrag (Refereegranskat)
    Abstract [en]

    Increasingly, absolute frequency and orientation maps are needed, e.g. for forensics. We introduce a non-linear scale space via the logarithm of trace of the Structure Tensor. Therein, frequency estimation becomes an orientation estimation problem. We show that this offers significant advantages, including construction of efficient isotropic estimations of dense maps of frequency. In fingerprints, both maps are shown to improve each other in an enhancement scheme via Gabor filtering. We suggest a novel continuous ridge counting method, relying only on dense absolute frequency and orientation maps, without ridge detection, thinning, etc. Furthermore, we present new evidence that frequency maps are useful attributes of minutiae. We verify that the suggested method compares favorably with state of the art using forensic fingerprints as test bed, and test images where the ground truth is known. In evaluations, we use public data sets and published methods only.

  • 80.
    Bouguelia, Mohamed-Rafik
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Nowaczyk, Sławomir
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Payberah, Amir H.
    Swedish Institute of Computer Science, Stockholm, Sweden.
    An adaptive algorithm for anomaly and novelty detection in evolving data streams2018Ingår i: Data mining and knowledge discovery, ISSN 1384-5810, E-ISSN 1573-756X, Vol. 32, nr 6, s. 1597-1633Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In the era of big data, considerable research focus is being put on designing efficient algorithms capable of learning and extracting high-level knowledge from ubiquitous data streams in an online fashion. While, most existing algorithms assume that data samples are drawn from a stationary distribution, several complex environments deal with data streams that are subject to change over time. Taking this aspect into consideration is an important step towards building truly aware and intelligent systems. In this paper, we propose GNG-A, an adaptive method for incremental unsupervised learning from evolving data streams experiencing various types of change. The proposed method maintains a continuously updated network (graph) of neurons by extending the Growing Neural Gas algorithm with three complementary mechanisms, allowing it to closely track both gradual and sudden changes in the data distribution. First, an adaptation mechanism handles local changes where the distribution is only non-stationary in some regions of the feature space. Second, an adaptive forgetting mechanism identifies and removes neurons that become irrelevant due to the evolving nature of the stream. Finally, a probabilistic evolution mechanism creates new neurons when there is a need to represent data in new regions of the feature space. The proposed method is demonstrated for anomaly and novelty detection in non-stationary environments. Results show that the method handles different data distributions and efficiently reacts to various types of change. © 2018 The Author(s)

    Ladda ner fulltext (pdf)
    bouguelia-dami-gnga
  • 81.
    Bouguelia, Mohamed-Rafik
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Nowaczyk, Sławomir
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Santosh, K. C.
    The University of South Dakota, Vermillion, South Dakota, USA.
    Verikas, Antanas
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Agreeing to disagree: active learning with noisy labels without crowdsourcing2018Ingår i: International Journal of Machine Learning and Cybernetics, ISSN 1868-8071, E-ISSN 1868-808X, Vol. 9, nr 8, s. 1307-1319Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We propose a new active learning method for classification, which handles label noise without relying on multiple oracles (i.e., crowdsourcing). We propose a strategy that selects (for labeling) instances with a high influence on the learned model. An instance x is said to have a high influence on the model h, if training h on x (with label y = h(x)) would result in a model that greatly disagrees with h on labeling other instances. Then, we propose another strategy that selects (for labeling) instances that are highly influenced by changes in the learned model. An instance x is said to be highly influenced, if training h with a set of instances would result in a committee of models that agree on a common label for x but disagree with h(x). We compare the two strategies and we show, on different publicly available datasets, that selecting instances according to the first strategy while eliminating noisy labels according to the second strategy, greatly improves the accuracy compared to several benchmarking methods, even when a significant amount of instances are mislabeled. © Springer-Verlag Berlin Heidelberg 2017

    Ladda ner fulltext (pdf)
    BougueliaAL
  • 82.
    Bouguelia, Mohamed-Rafik
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Pashami, Sepideh
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Nowaczyk, Sławomir
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Multi-Task Representation Learning2017Ingår i: 30th Annual Workshop ofthe Swedish Artificial Intelligence Society SAIS 2017: May 15–16, 2017, Karlskrona, Sweden / [ed] Niklas Lavesson, Linköping: Linköping University Electronic Press, 2017, s. 53-59Konferensbidrag (Refereegranskat)
    Abstract [en]

    The majority of existing machine learning algorithms assume that training examples are already represented with sufficiently good features, in practice ones that are designed manually. This traditional way of preprocessing the data is not only tedious and time consuming, but also not sufficient to capture all the different aspects of the available information. With big data phenomenon, this issue is only going to grow, as the data is rarely collected and analyzed with a specific purpose in mind, and more often re-used for solving different problems. Moreover, the expert knowledge about the problem which allows them to come up with good representations does not necessarily generalize to other tasks. Therefore, much focus has been put on designing methods that can automatically learn features or representations of the data instead of learning from handcrafted features. However, a lot of this work used ad hoc methods and the theoretical understanding in this area is lacking.

    Ladda ner fulltext (pdf)
    fulltext
  • 83.
    Busch, Christoph
    et al.
    Norwegian University of Science and Technology, Gjøvik, Norway.
    Deravi, Farzin
    University of Kent, Canterbury, United Kingdom.
    Frings, Dinusha
    European Association for Biometrics (EAB), Amsterdam, Netherlands.
    Alonso-Fernandez, Fernando
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Bigun, Josef
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Facilitating free travel in the Schengen area—A position paper by the European Association for Biometrics2023Ingår i: IET Biometrics, ISSN 2047-4938, E-ISSN 2047-4946, Vol. 12, nr 2, s. 112-128Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Due to migration, terror-threats and the viral pandemic, various EU member states have re-established internal border control or even closed their borders. European Association for Biometrics (EAB), a non-profit organisation, solicited the views of its members on ways which biometric technologies and services may be used to help with re-establishing open borders within the Schengen area while at the same time mitigating any adverse effects. From the responses received, this position paper was composed to identify ideas to re-establish free travel between the member states in the Schengen area. The paper covers the contending needs for security, open borders and fundamental rights as well as legal constraints that any technological solution must consider. A range of specific technologies for direct biometric recognition alongside complementary measures are outlined. The interrelated issues of ethical and societal considerations are also highlighted. Provided a holistic approach is adopted, it may be possible to reach a more optimal trade-off with regards to open borders while maintaining a high-level of security and protection of fundamental rights. European Association for Biometrics and its members can play an important role in fostering a shared understanding of security and mobility challenges and their solutions. © 2023 The Authors. IET Biometrics published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

    Ladda ner fulltext (pdf)
    fulltext
  • 84.
    Byttner, Stefan
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Nowaczyk, Sławomir
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Prytz, Rune
    Volvo Group Trucks Technology, Gothenburg, Sweden.
    Rögnvaldsson, Thorsteinn
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    A field test with self-organized modeling for knowledge discovery in a fleet of city buses2013Ingår i: 2013 IEEE International Conference on Mechatronics and Automation (ICMA 2013) / [ed] Shuxiang Guo, Piscataway, NJ: IEEE Press, 2013, s. 896-901, artikel-id 6618034Konferensbidrag (Refereegranskat)
    Abstract [en]

    Fleets of commercial vehicles represent an excellent real life setting for ubiquitous knowledge discovery. There are many electronic control units onboard a modern bus or truck, with hundreds of signals being transmitted between them on the controller area network. The growing complexity of the vehicles has lead to a significant desire to have systems for fault detection, remote diagnostics and maintenance prediction. This paper aims to show that it is possible to discover useful diagnostic knowledge by a self-organized algorithm in the scenario of a fleet of city buses. The approach is demonstrated as a process consisting of two parts; Unsupervised modeling (where interesting features are discovered) and Guided search (where the previously found features are coupled to additional information sources). The modeling part searches for simple linear models in a group of vehicles, where interesting features are selected based on both non-randomness in relations and variability in the group. It is shown in an eight months long data collection study that this approach was able to discover features related to broken wheelspeed sensors. Strikingly, deviations in these features (for the vehicles with broken sensors) can be observed up to several months before a breakdown occur. This potentially allows for sufficient time to schedule the vehicle for maintenance and prepare the workshop with relevant components. © 2013 IEEE.

  • 85.
    Caizzone, Stefano
    et al.
    German Aerosp Ctr DLR, Inst Commun & Nav, Wessling, Germany.
    Elmarissi, W.
    German Aerosp Ctr DLR, Inst Commun & Nav, Wessling, Germany.
    Marinho, Marco
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS).
    Antreich, F.
    Fed Univ Ceara UFC, Dept Teleinformat Engn, Fortaleza, Ceara, Brazil.
    Direction of arrival estimation performance for compact antenna arrays with adjustable size2017Ingår i: 2017 IEEE MTT-S INTERNATIONAL MICROWAVE SYMPOSIUM (IMS), Piscataway: IEEE, 2017, s. 666-669, artikel-id 8058657Konferensbidrag (Refereegranskat)
    Abstract [en]

    The quest for compact antenna arrays able to perform robust beamforming and high resolution direction of arrival (DOA) estimation is pushing the antenna array dimensions to progressively shrink, with effects in terms of reduced performance not only for the antenna but also for beamforming and DOA estimation algorithms, for which their assumptions about the antenna properties do not hold anymore. This work shows the design and development of an antenna array with adjustable mutual distance between the single elements: such setup will allow to scientifically analyse the effects that progressive miniaturization, i.e. progressively smaller mutual distances between the antennas, have on the DOA estimation algorithms, as well as show the improvements obtained by using array interpolation methods, i.e. techniques able to create a virtual array response out of the actual array one, such as to comply with the algorithms’ requirements on the antenna response. © 2017 IEEE.

  • 86.
    Carvajal, Gisela K.
    et al.
    Qamcom Research & Technology, Gothenburg, Sweden.
    Keskin, Musa Furkan
    Chalmers University of Technology, Gothenburg, Sweden.
    Aydogdu, Canan
    Chalmers University of Technology, Gothenburg, Sweden.
    Eriksson, Olof
    Veoneer, Vårgårda, Sweden.
    Herbertsson, Hans
    Veoneer, Vårgårda, Sweden.
    Hellsten, Hans
    Saab, Linköping, Sweden | Veoneer, Vårgårda, Sweden.
    Nilsson, Emil
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS).
    Rydström, Mats
    Veoneer, Vårgårda, Sweden.
    Vanäs, Karl
    Volvo Cars, Gothenburg, Sweden.
    Wymeersch, Henk
    Chalmers University of Technology, Gothenburg, Sweden.
    Comparison of Automotive FMCW and OFDM Radar Under Interference2020Ingår i: 2020 IEEE Radar Conference (RadarConf20), New York, NY: IEEE, 2020, s. 1-6Konferensbidrag (Refereegranskat)
    Abstract [en]

    Automotive radars are subject to interference in spectrally congested environments. To mitigate this interference, various waveforms have been proposed. We compare two waveforms (FMCW and OFDM) in terms of their radar performance and robustness to interference, under similar parameter settings. Our results indicate that under proper windowing both waveforms can achieve similar performance, but OFDM is more sensitive to interference. ©2020 IEEE

  • 87.
    Chen, Kunru
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Centrum för forskning om tillämpade intelligenta system (CAISR).
    Pashami, Sepideh
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Nowaczyk, Sławomir
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Johansson, Emilia
    Toyota Material Handling Europe, Mjölby, Sweden.
    Sternelöv, Gustav
    Toyota Material Handling Europe, Mjölby, Sweden.
    Rögnvaldsson, Thorsteinn
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Forklift Truck Activity Recognition from CAN Data2021Ingår i: IoT Streams for Data-Driven Predictive Maintenance and IoT, Edge, and Mobile for Embedded Machine Learning: Second International Workshop, IoT Streams 2020, and First International Workshop, ITEM 2020, Co-located with ECML/PKDD 2020, Ghent, Belgium, September 14-18, 2020, Revised Selected Papers / [ed] Joao Gama, Sepideh Pashami, Albert Bifet, Moamar Sayed-Mouchawe, Holger Fröning, Franz Pernkopf, Gregor Schiele, Michaela Blott, Heidelberg: Springer, 2021, s. 119-126Konferensbidrag (Refereegranskat)
    Abstract [en]

    Machine activity recognition is important for accurately esti- mating machine productivity and machine maintenance needs. In this paper, we present ongoing work on how to recognize activities of forklift trucks from on-board data streaming on the controller area network. We show that such recognition works across different sites. We first demon- strate the baseline classification performance of a Random Forest that uses 14 signals over 20 time steps, for a 280-dimensional input. Next, we show how a deep neural network can learn low-dimensional representa- tions that, with fine-tuning, achieve comparable accuracy. The proposed representation achieves machine activity recognition. Also, it visualizes the forklift operation over time and illustrates the relationships across different activities. © Springer Nature Switzerland AG 2020

    Ladda ner fulltext (pdf)
    fulltext
  • 88.
    Chen, Lei
    et al.
    RISE Research Institutes of Sweden, Gothenburg, Sweden.
    Torstensson, Martin
    RISE Research Institutes of Sweden, Gothenburg, Sweden.
    Englund, Cristofer
    RISE Research Institutes of Sweden, Gothenburg, Sweden.
    Federated learning to enable automotive collaborative ecosystem: opportunities and challenges2020Konferensbidrag (Refereegranskat)
    Abstract [en]

    Despite the strong interests in creating data economy, automotive industries are creating data silos with each stakeholder maintaining its own data cloud. Federated learning (FL), designed for privacy-preserving collaborative Machine Learning (ML), offers a promising method that allows multiple stakeholders to share information through ML models without the exposure of raw data, thus natively protecting privacy. Motivated by the strong need for automotive collaboration and the advancement of FL, this paper investigates how FL could enable privacy-preserving information sharing for automotive industries. We first introduce the statuses and challenges for automotive data sharing, followed by a brief introduction to FL. We then present a comprehensive discussion on potential applications of federated learning to enable an automotive collaborative ecosystem. To illustrate the benefits, we apply FL for driver action classification and demonstrate the potential for collaborative machine learning without data sharing. 

  • 89.
    Cortinhal, Tiago
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Tzelepi, George
    Volvo Technology AB, Volvo Group Trucks Technology, Gothenburg, Sweden.
    Erdal Aksoy, Eren
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), Centrum för forskning om inbyggda system (CERES). Volvo Technology AB, Volvo Group Trucks Technology, Gothenburg, Sweden.
    SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving2021Ingår i: Advances in Visual Computing: 15th International Symposium, ISVC 2020, San Diego, CA, USA, October 5–7, 2020, Proceedings, Part II / [ed] Bebis, G., Yin, Z., Kim, E., Bender, J., Subr, K., Kwon, B.C., Zhao, J., Kalkofen, D., Baciu, G., Cham: Springer, 2021, Vol. 12510, s. 207-222Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a full 3D LiDAR point cloud in real-time. SalsaNext is the next version of SalsaNet which has an encoder-decoder architecture where the encoder unit has a set of ResNet blocks and the decoder part combines upsampled features from the residual blocks. In contrast to SalsaNet, we introduce a new context module, replace the ResNet encoder blocks with a new residual dilated convolution stack with gradually increasing receptive fields and add the pixel-shuffle layer in the decoder. Additionally, we switch from stride convolution to average pooling and also apply central dropout treatment. To directly optimize the Jaccard index, we further combine the weighted cross entropy loss with Lovász-Softmax loss. We finally inject a Bayesian treatment to compute the epistemic and aleatoric uncertainties for each point in the cloud. We provide a thorough quantitative evaluation on the Semantic-KITTI dataset, which demonstrates that the proposed SalsaNext outperforms other published semantic segmentation networks and achieves 3.6% more accuracy over the previous state-of-the-art method. We also release our source code1. © 2020, Springer Nature Switzerland AG.

    [1] https://github.com/TiagoCortinhal/SalsaNext

    Ladda ner fulltext (pdf)
    fulltext
  • 90.
    Davari, Narjes
    et al.
    INESC TEC, Porto, Portugal.
    Pashami, Sepideh
    Högskolan i Halmstad, Akademin för informationsteknologi. RISE Research Institute of Sweden, Kista, Sweden.
    Veloso, Bruno
    INESC TEC, Porto, Portugal; University of Porto, Porto, Portugal; University Portucalense, Porto, Portugal.
    Nowaczyk, Sławomir
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Fan, Yuantao
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Mota Pereira, Pedro
    Metro of Porto, Porto, Portugal.
    Ribeiro, Rita P.
    INESC TEC, Porto, Portugal; University of Porto, Porto, Portugal.
    Gama, João
    INESC TEC, Porto, Portugal; University of Porto, Porto, Portugal.
    A Fault Detection Framework Based on LSTM Autoencoder: A Case Study for Volvo Bus Data Set2022Ingår i: Advances in Intelligent Data Analysis XX: 20th International Symposium on Intelligent Data Analysis, IDA 2022 Rennes, France, April 20–22, 2022: Proceedings / [ed] Tassadit Bouadi; Elisa Fromont; Eyke Hüllermeier, Cham: Springer, 2022, s. 39-52Konferensbidrag (Refereegranskat)
    Abstract [en]

    This study applies a data-driven anomaly detection framework based on a Long Short-Term Memory (LSTM) autoencoder network for several subsystems of a public transport bus. The proposed framework efficiently detects abnormal data, significantly reducing the false alarm rate compared to available alternatives. Using historical repair records, we demonstrate how detection of abnormal sequences in the signals can be used for predicting equipment failures. The deviations from normal operation patterns are detected by analysing the data collected from several on-board sensors (e.g., wet tank air pressure, engine speed, engine load) installed on the bus. The performance of LSTM autoencoder (LSTM-AE) is compared against the multi-layer autoencoder (mlAE) network in the same anomaly detection framework. The experimental results show that the performance indicators of the LSTM-AE network, in terms of F1 Score, Recall, and Precision, are better than those of the mlAE network. © 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

    Ladda ner fulltext (pdf)
    fulltext
  • 91.
    Davidsson, Adam
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Lindbom, Fredrik
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Slow-response generator2015Självständigt arbete på grundnivå (högskoleexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Because of environmental pollution, forces the automotive industry constantly reduced emissions requirements legislated by the authorities. Improved techniques for engine control are a must for bringing down emissions. The use of an Exhaust Gas Recirculation (EGR) reduces NOx emissions significantly. Faulty EGR valves affect the emissions negative and therefore needs to be eliminated.

    It is possible to create malfunctions on the EGR valve by modifying the software of the control unit (ECU), but it does not create realistic malfunctions. The problem by modifying the software is that flags and various parameters are set to confirm the malfunction of the ECU. To create actual failure of the EGR valve an external tool to modify the control signal is needed.

    The project's main objective is on a flexible way creating malfunctions on the EGR valve in a truck engine. By investigating engine behavior in a realistic and credible way, one can eliminate malfunctions on the EGR valve. The aim was achieved by a model that has been developed that can, using electronics and a microprocessor read and create a control signal.

    The electronic circuit is controlled by the microprocessor, which can modify the signal and create malfunctions in the form of a slow valve "slow-response". A graphical user interface is used to change and influence the error signal. The circuit with the microprocessor is placed safely in a box to both protect and preserve the components.

    Simulation of Slow response has resulted in an incorrect operated valve being created. Using two different methods a Slow-response can be created. One method is a delay in time, which occurs when the new position is given, the second method is a ramp function when the control signal is gradually increasing. The software can also create an error that mimics a stuck valve of a fixed value. With the above listed methods it is possible in theory to find unknown malfunctions on the EGR valve that influence emissions negatively. 

    Ladda ner fulltext (pdf)
    fulltext
  • 92.
    Ding, Yijie
    et al.
    University of Electronic Science and Technology of China, Quzhou, China.
    Guo, Fei
    Central South University, Changsha, China.
    Tiwari, Prayag
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Zou, Quan
    University of Electronic Science and Technology of China, Chengdu, China.
    Identification of Drug-Side Effect Association Via Multi-View Semi-Supervised Sparse Model2023Ingår i: IEEE Transactions on Artificial Intelligence, E-ISSN 2691-4581Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The association between drugs and side effects encompasses information about approved medications and their documented adverse drug reactions. Traditional experimental approaches for studying this association tend to be time-consuming and expensive. To represent all drug-side effect associations, a bipartite network framework is employed. Consequently, numerous computational methods have been devised to tackle this problem, focusing on predicting new potential associations. However, a significant gap lies in the neglect of the Multi-View Learning (MVL) algorithm, which has the ability to integrate diverse information sources and enhance prediction accuracy. In our study, we have developed a novel predictor named Multi-View Semi-Supervised Sparse Model (Mv3SM) to address the drug side effect prediction problem. Our approach aims to explore the distinctive characteristics of various view features obtained from fully paired multi-view data and mitigate the influence of noisy data. To test the performance of Mv3SM and other computational approaches, we conducted experiments using three benchmark datasets. The obtained results clearly demonstrate that our proposed method achieves superior predictive performance compared to alternative approaches. © IEEE

  • 93.
    Ejnarsson, Marcus
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS).
    Data Mining and Analysis for Characterizing Paper from On-line Multisensor Measurements2008Licentiatavhandling, monografi (Övrigt vetenskapligt)
    Abstract [en]

    The objective of this thesis is to develop a multi-resolution tool for screening paper formation variations, aiming to detect abnormalities in various frequency regions ranging from millimeters to several meters. The abnormalities detected in different frequency regions give an indication for the paper maker about specific disturbances in the paper production process. A paper web, running at a speed of 30 m/s, is illuminated by two red diode lasers and the reflected light are recorded as two time series of high resolution measurements constitutes the input signal to the papermaking process monitoring system. The time series are divided into blocks and each block is analyzed separately. The task is treated as a kernel based novelty detection applied to a multi-resolution time series representation obtained from the frequency bands of the Fourier power spectra of the blocks. The frequency content of each frequency region is characterized by a feature vector, which is transformed using the canonical correlation analysis and then categorized into the inlier or outlier class by the novelty detector. The ratio of outlying data points, significantly exceeding the predetermined value, indicates abnormalities in the paper formation. The experimental investigations performed have shown that the presented paper formation deficiencies monitoring technique and the system can be used for on-line monitoring of paper deficiencies manifesting themselves in a broad frequency range. A software, implementing the technique, was developed and used for online paper formation monitoring at a Swedish paper mill.

  • 94.
    Ekstrand, Joel
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Exercise Classification with Machine Learning2023Självständigt arbete på grundnivå (kandidatexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Innowearable AB har utvecklat en produkt som heter Inno-XTM som räknar ut muskeltröttheten vid 3  övningar: upphopp, jägarvila och benextensioner. Inno-X använder en accelerometer och en yt-elektromyografi-sensor. Målet med projektet var att skapa signalprocesseringsdelen av en machine learning (ML) pipelinesom klassificerar dessa övningar i realtid. Data samlades in från sensorerna för att skapa en träningsmiljö som sedan kunde gå  över i realtidsmiljö genom attanvända en sliding-window teknik. Savitsky-Golay (SG) filter, högpassfilter, och lågpassfilter användes för att reducera brus i sensorsignalerna. SG filtret presterade bäst. Features från både tids- och frekvensdomän användes i feature extraction. Slutprodukten använde 24 features kombinerat från båda domänen. Dessa metoder tillsammans med ML algoritmer som togs fram i ett partnerprojekt gav ett resultat i träningsmiljön på 98.62% i klassificeringsnoggrannhet och 90% för realtidsmiljön. Genom att samla större mängd data med mer diversitet och lösa problemetatiken i att jägarvila och benextensioner  är för lika, kommer realtidsklas-sifikationen förbättras vilket hade gjort att ML pipelinen blir användbar för Innowearables kunder.

    Ladda ner fulltext (pdf)
    fulltext
  • 95.
    Emanuelsson, Herman
    et al.
    Högskolan i Halmstad, Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE).
    Sjunnesson, Emil
    Högskolan i Halmstad, Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE).
    Fjärrstyrt kamerafäste: HE Remote2013Självständigt arbete på grundnivå (högskoleexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Vid tillfällen då det inte lämpar sig att stå vid en videokamera kan det lösas med ett fjärrstyrt kamerafäste. Exempel på tillfällen är på grund av platsbrist på en konsert, en högtidsceremoni där någon måste stå konstigt till för att få bra bild, ute i naturen där djur ska filmas utan att bli ivägskrämda eller vid personalbrist, en tight budget och måste styra flera kameror samtidigt. De system som finns tillgängliga på amatörmarknaden idag har antingen annan funktionalitet och passar sig inte för ovanstående problem eller har väldigt begränsad räckvidd och går inte att sammankoppla med en mobilapplikation.

    Detta projekt går ut på att ta fram en kostnadseffektiv och skräddarsydd lösning för ovanstående problem genom att utveckla ett fjärrstyrt kamerafäste i semiproffssegmentet där det via en handkontroll och vid senare skede med en mobilapplikation styr kamerans lutning och rotation även kallad tiltning och panorering.

    Skillnaderna mellan denna och befintliga lösningar är att med hjälp av Bluetooth-tekniken kan styra både med handkontroll och senare även med en mobilapplikation, anledningen till att det skall kunna styra med båda är att det inte alltid är tillåtet att använda sig av mobiltelefoner i alla miljöer där man vill filma och därför får ett bredare användningsområde för kamerafästet.

    Ladda ner fulltext (pdf)
    Examensrapport_HE_Remote_Emil_Sjunnesson_Herman_Emanuelsson
  • 96.
    Englund, Cristofer
    et al.
    RISE Viktoria, Gothenburg, Sweden.
    Engdahl, Henrik
    Nimling AB, Askim, Sweden.
    Habibi, Shiva
    Chalmers University of Technology, Gothenburg, Sweden.
    Pettersson, Stefan
    RISE Viktoria, Gothenburg, Sweden.
    Sprei, Frances
    Chalmers University of Technology, Gothenburg, Sweden.
    Voronov, Alexey
    RISE Viktoria, Gothenburg, Sweden.
    Wedlin, Johan
    RISE Viktoria, Gothenburg, Sweden.
    Method for prediction of Utilization Rate of Electric Vehicle Free-Floating Car Sharing Services using Data Mining2018Ingår i: 31st International Electric Vehicles Symposium & Exhibition (EVS 31) & International Electric Vehicle Technology Conference 2018 (EVTeC 2018), 2018Konferensbidrag (Refereegranskat)
    Abstract [en]

    Free-floating car sharing is a form of car rental used by people for short periods of time where the cars can be picked up and returned anywhere within a given area. In this paper, we have collected free-floating car sharing data, for electric as well as fossil fueled cars, and data regarding e.g. size of the city, number of cars in the service, etc. The utilization rates of the free-floating car sharing services vary much between the cities, greatly influencing the success of the services. This paper presents the most important factors influencing the utilization rate, and also a methodology to predict the utilization rate for new cities, using data mining based on Random Forests.© EVS 31 & EVTeC 2018.

  • 97.
    Ericson, Stefan K.
    et al.
    University of Skövde, Skövde, Sweden.
    Åstrand, Björn
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Analysis of two visual odometry systems for use in an agricultural field environment2018Ingår i: Biosystems Engineering, ISSN 1537-5110, E-ISSN 1537-5129, Vol. 166, s. 116-125Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This paper analyses two visual odometry systems for use in an agricultural field environment. The impact of various design parameters and camera setups are evaluated in a simulation environment. Four real field experiments were conducted using a mobile robot operating in an agricultural field. The robot was controlled to travel in a regular back-and-forth pattern with headland turns. The experimental runs were 1.8–3.1 km long and consisted of 32–63,000 frames. The results indicate that a camera angle of 75° gives the best results with the least error. An increased camera resolution only improves the result slightly. The algorithm must be able to reduce error accumulation by adapting the frame rate to minimise error. The results also illustrate the difficulties of estimating roll and pitch using a downward-facing camera. The best results for full 6-DOF position estimation were obtained on a 1.8-km run using 6680 frames captured from the forward-facing cameras. The translation error (x, y, z) is 3.76% and the rotational error (i.e., roll, pitch, and yaw) is 0.0482 deg m−1. The main contributions of this paper are an analysis of design option impacts on visual odometry results and a comparison of two state-of-the-art visual odometry algorithms, applied to agricultural field data. © 2017 IAgrE

    Ladda ner fulltext (pdf)
    fulltext
  • 98.
    Fan, Yuantao
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Nowaczyk, Sławomir
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), Laboratoriet för intelligenta system.
    Rögnvaldsson, Thorsteinn
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Evaluation of Self-Organized Approach for Predicting Compressor Faults in a City Bus Fleet2015Ingår i: Procedia Computer Science, E-ISSN 1877-0509, Vol. 53, s. 447-456Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Managing the maintenance of a commercial vehicle fleet is an attractive application domain of ubiquitous knowledge discovery. Cost effective methods for predictive maintenance are progressively demanded in the automotive industry. The traditional diagnostic paradigm that requires human experts to define models is not scalable to today's vehicles with hundreds of computing units and thousands of control and sensor signals streaming through the on-board controller area network. A more autonomous approach must be developed. In this paper we evaluate the performance of the COSMO approach for automatic detection of air pressure related faults on a fleet of city buses. The method is both generic and robust. Histograms of a single pressure signal are collected and compared across the fleet and deviations are matched against workshop maintenance and repair records. It is shown that the method can detect several of the cases when compressors fail on the road, well before the failure. The work is based on data from a three year long field study involving 19 buses operating in and around a city on the west coast of Sweden. © The Authors. Published by Elsevier B.V.

    Ladda ner fulltext (pdf)
    fulltext
  • 99.
    Fan, Yuantao
    et al.
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Nowaczyk, Sławomir
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Rögnvaldsson, Thorsteinn
    Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
    Using Histograms to Find Compressor Deviations in Bus Fleet Data2014Ingår i: The SAIS Workshop 2014 Proceedings, Swedish Artificial Intelligence Society (SAIS) , 2014, s. 123-132Konferensbidrag (Refereegranskat)
    Abstract [en]

    Cost effective methods for predictive maintenance are increasingly demanded in the automotive industry. One solution is to utilize the on-board signals streams on each vehicle and build self-organizing systems that discover data deviations within a fleet. In this paper we evaluate histograms as features for describing and comparing individual vehicles. The results are based on a long-term field test with nineteen city buses operating around Kungsbacka in Halland. The purpose of this work is to investigate ways of discovering abnormal behaviors and irregularities between histograms of on-board signals, here specifically focusing on air pressure. We compare a number of distance measures and analyze the variability of histograms collected over different time spans. Clustering algorithms are used to discover structure in the data and track how this changes over time. As data are compared across the fleet, observed deviations should be matched against (often imperfect) reference data coming from workshop maintenance and repair databases.

    Ladda ner fulltext (pdf)
    fulltext
  • 100.
    Fanaee Tork, Hadi
    Högskolan i Halmstad, Akademin för informationsteknologi.
    Tensor Completion Post-Correction2022Ingår i: Advances in Intelligent Data Analysis XX: 20th International Symposium on Intelligent Data Analysis, IDA 2022, Rennes, France, April 20–22, 2022, Proceedings / [ed] Tassadit Bouadi; Elisa Fromont; Eyke Hüllermeier, Cham: Springer, 2022, Vol. 13205, s. 89-101Konferensbidrag (Refereegranskat)
    Abstract [en]

    Many real-world tensors come with missing values. The task of estimation of such missing elements is called tensor completion (TC). It is a fundamental problem with a wide range of applications in data mining, machine learning, signal processing, and computer vision. In the last decade, several different algorithms have been developed, couple of them have shown high-quality performance in diverse domains. However, our investigation shows that even state-of-the-art TC algorithms sometimes make poor estimations for few cases that are not noticeable if we look at their overall performance. However, such wrong estimates might have a severe effect on some decisions. It becomes a crucial issue in applications where humans are involved. Making bad decisions based on such poor estimations can harm fairness. We propose the first algorithm for tensor completion post-correction, called TCPC, to identify some of such poor estimates from the output of any TC algorithm and refine them with more realistic estimations. Our initial experiments with five real-life tensor datasets show that TCPC is an effective post-correction method. © 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

123456 51 - 100 av 270
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf