Högskolan i Skövde

his.sePublications
Change search
Refine search result
1 - 24 of 24
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Darwish, Amena
    et al.
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Learning Individual Driver’s Mental Models Using POMDPs and BToM2020In: DHM2020: Proceedings of the 6th International Digital Human Modeling Symposium, August 31 – September 2, 2020 / [ed] Lars Hanson, Dan Högberg, Erik Brolin, Amsterdam: IOS Press, 2020, p. 51-60Conference paper (Refereed)
    Abstract [en]

    Advanced driver assistant systems are supposed to assist the driver and ensure their safety while at the same time providing a fulfilling driving experience that suits their individual driving styles. What a driver will do in any given traffic situation depends on the driver’s mental model which describes how the driver perceives the observable aspects of the environment, interprets these aspects, and on the driver’s goals and beliefs of applicable actions for the current situation. Understanding the driver’s mental model has hence received great attention from researchers, where defining the driver’s beliefs and goals is one of the greatest challenges. In this paper we present an approach to establish individual drivers’ temporal-spatial mental models by considering driving to be a continuous Partially Observable Markov Decision Process (POMDP) wherein the driver’s mental model can be represented as a graph structure following the Bayesian Theory of Mind (BToM). The individual’s mental model can then be automatically obtained through deep reinforcement learning. Using the driving simulator CARLA and deep Q-learning, we demonstrate our approach through the scenario of keeping the optimal time gap between the own vehicle and the vehicle in front.

    Download full text (pdf)
    fulltext
  • 2.
    Hamed, Omar
    et al.
    University of Skövde, School of Informatics.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Pedestrian Intention Recognition and Action Prediction Using a Feature Fusion Deep Learning Approach2021In: USB Proceedings The 18th International Conference on Modeling Decisions for Artificial Intelligence: MDAI 2021, Umeå / [ed] Vicenç Torra; Yasuo Narukawa, 2021, p. 89-100Conference paper (Refereed)
    Abstract [en]

    Recognizing Pedestrians intention to cross a street and predicting their imminent crossing action are major challenges for advanced driver assistance systems (ADAS) and Autonomous Vehicles (AV). In this paper we address these problems by proposing a new neural network architecture that uses feature fusion. The approach is used to recog[1]nise/predict the pedestrians intention/action 1.5 sec (45 frames) ahead. We evaluate our approach on the recently suggested benchmark by Rasouli et al. and show that our approach outperforms current state of the art models. We observe further improved results when the model is trained and tested on a stronger balanced subset of the PIE dataset.

  • 3.
    Hamed, Omar
    et al.
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Pedestrian’s Intention Recognition, Fusion of Handcrafted Features in a Deep Learning Approach2021In: AAAI-21 / IAAI-21 / EAAI-21 Proceedings: A virtual conference February 2-9, 2021: Thirty-Fifth AAAI Conference on Artificial Intelligence, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, The Eleventh Symposium on Educational Advances in Artificial Intelligence, Palo Alto: AAAI Press, 2021, p. 15795-15796Conference paper (Refereed)
    Abstract [en]

    The safety of vulnerable road users (VRU) is a major concernfor both advanced driver assistance systems (ADAS) and autonomousvehicle manufacturers. To guarantee people safetyon roads, autonomous vehicles must be able to detect thepresence of pedestrians, track them, and predict their intentionto cross the road. Most of the earlier work on pedestrianintention recognition focused on using either handcraftedfeatures or an end-to-end deep learning approach. In thisproject, we investigate the impact of fusing handcrafted featureswith auto learned features by using a two-stream neuralnetwork architecture. Our results show that the combined approachimproves the performance. Furthermore, the proposedmethod achieved very good results on the JAAD dataset. Dependingon whether we considered the immediate frames beforethe crossing or only half a second before that point, wereceived prediction accuracy of 91%, and 84%, respectively.

  • 4.
    Helldin, Tove
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Mathiason, Gunnar
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Situation Awareness in Telecommunication Networks Using Topic Modeling2018In: 2018 21st International Conference on Information Fusion, FUSION 2018, IEEE, 2018, p. 549-556Conference paper (Refereed)
    Abstract [en]

    For an operator of wireless telecommunication networks to make timely interventions in the network before minor faults escalate into issues that can lead to substandard system performance, good situation awareness is of high importance. Due to the increasing complexity of such networks, as well as the explosion of traffic load, it has become necessary to aid human operators to reach a good level of situation awareness through the use of exploratory data analysis and information fusion techniques. However, to understand the results of such techniques is often cognitively challenging and time consuming. In this paper, we present how telecommunication operators can be aided in their data analysis and sense-making processes through the usage and visualization of topic modeling results. We present how topic modeling can be used to extract knowledge from base station counter readings and make design suggestions for how to visualize the analysis results to a telecommunication operator.

  • 5.
    Huhnstock, Nikolas Alexander
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Riveiro, Maria
    Högskolan i Jönköping, JTH, Datateknik och informatik.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    An Infinite Replicated Softmax Model for Topic Modeling2019In: Modeling Decisions for Artificial Intelligence: 16th International Conference, MDAI 2019, Milan, Italy, September 4–6, 2019, Proceedings / [ed] Vicenç Torra, Yasuo Narukawa, Gabriella Pasi, Marco Viviani, Springer, 2019, p. 307-318Conference paper (Refereed)
    Abstract [en]

    In this paper, we describe the infinite replicated Softmax model (iRSM) as an adaptive topic model, utilizing the combination of the infinite restricted Boltzmann machine (iRBM) and the replicated Softmax model (RSM). In our approach, the iRBM extends the RBM by enabling its hidden layer to adapt to the data at hand, while the RSM allows for modeling low-dimensional latent semantic representation from a corpus. The combination of the two results is a method that is able to self-adapt to the number of topics within the document corpus and hence, renders manual identification of the correct number of topics superfluous. We propose a hybrid training approach to effectively improve the performance of the iRSM. An empirical evaluation is performed on a standard data set and the results are compared to the results of a baseline topic model. The results show that the iRSM adapts its hidden layer size to the data and when trained in the proposed hybrid manner outperforms the base RSM model.

    Download full text (pdf)
    fulltext
  • 6.
    Huhnstock, Nikolas Alexander
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Riveiro, Maria
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    On the behavior of the infinite restricted boltzmann machine for clustering2018In: SAC '18 Proceedings of the 33rd Annual ACM Symposium on Applied Computing / [ed] Hisham M. Haddad, Roger L. Wainwright, Richard Chbeir, New York, NY, USA: Association for Computing Machinery (ACM), 2018, p. 461-470Conference paper (Refereed)
    Abstract [en]

    Clustering is a core problem within a wide range of research disciplines ranging from machine learning and data mining to classical statistics. A group of clustering approaches so-called nonparametric methods, aims to cluster a set of entities into a beforehand unspecified and unknown number of clusters, making potentially expensive pre-analysis of data obsolete. In this paper, the recently, by Cote and Larochelle introduced infinite Restricted Boltzmann Machine that has the ability to self-regulate its number of hidden parameters is adapted to the problem of clustering by the introduction of two basic cluster membership assumptions. A descriptive study of the influence of several regularization and sparsity settings on the clustering behavior is presented and results are discussed. The results show that sparsity is a key adaption when using the iRBM for clustering that improves both the clustering performances as well as the number of identified clusters.

  • 7.
    Karlsson, Alexander
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Hammarfelt, Björn
    Swedish School of Library and Information Science (SSLIS), University of Borås, Sweden.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Falkman, Göran
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Olson, Nasrine
    Swedish School of Library and Information Science (SSLIS), University of Borås, Sweden.
    Nelhans, Gustaf
    Swedish School of Library and Information Science (SSLIS), University of Borås, Sweden.
    Nolin, Jan
    Swedish School of Library and Information Science (SSLIS), University of Borås, Sweden.
    Modeling uncertainty in bibliometrics and information retrieval: an information fusion approach2015In: Scientometrics, ISSN 0138-9130, E-ISSN 1588-2861, Vol. 102, no 3, p. 2255-2274Article in journal (Refereed)
  • 8.
    Karlsson, Alexander
    et al.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Steinhauer, H. Joe
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Evaluation of Evidential Combination Operators2013In: / [ed] Fabio Cozman; Thierry Denœux; Sébastien Destercke; Teddy Seidenfeld, 2013, p. 179-189Conference paper (Refereed)
    Abstract [en]

    We present an experiment for evaluating precise and imprecise evidential combination operators. The experiment design is based on the assumption that only limited statistical information is available in the form of multinomial observations. We evaluate three different evidential combination operators; one precise, the Bayesian combination operator, and two imprecise, the credal and Dempster’s combination operator, for combining independent pieces of evidence regarding some discrete state space of interest. The evaluation is performed by using a score function that takes imprecision into account. The results show that the precise framework seems to perform equally well as the imprecise frameworks.

  • 9.
    Olson, Nasrine
    et al.
    University of Borås.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Nelhans, Gustaf
    University of Borås.
    Falkman, Göran
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Nolin, Jan
    University of Borås.
    Little Scientist, Big Data Information fusion towards meeting the information needs of scholars2014In: Assessing Libraries and Library Users and Use, 2014Conference paper (Other academic)
  • 10.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Helldin, Tove
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Mathiason, Gunnar
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Topic Modeling for Situation Understanding in Telecommunication Networks2017In: 2017 27th International Telecommunication Networks and Applications Conference (ITNAC), IEEE, 2017, p. 73-78Conference paper (Refereed)
  • 11.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Helldin, Tove
    University of Skövde, The Informatics Research Centre. University of Skövde, School of Informatics.
    Mathiason, Gunnar
    University of Skövde, The Informatics Research Centre. University of Skövde, School of Informatics.
    Spatio-Temporal Awareness for Wireless Telecommunication Networks2018In: Working Papers and Documents of the IJCAI-ECAI-2018 Workshop on Learning and Reasoning: Principles & Applications to Everyday Spatial and Temporal Knowledge, 2018, p. 49-50Conference paper (Refereed)
  • 12.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Helldin, Tove
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Mathiason, Gunnar
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Anomaly Detection in Telecommunication Networks using Topic Models2018Conference paper (Refereed)
  • 13.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Helldin, Tove
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Mathiason, Gunnar
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Topic modeling for anomaly detection in telecommunication networks2023In: Journal of Ambient Intelligence and Humanized Computing, ISSN 1868-5137, E-ISSN 1868-5145, Vol. 14, no 11, p. 15085-15096Article in journal (Refereed)
    Abstract [en]

    To ensure reliable network performance, anomaly detection is an important part of the telecommunication operators’ work. This includes that operators need to timely intervene with the network, should they encounter indications of network performance degradation. In this paper, we describe the results of an initial experiment for anomaly detection with regard to network performance, using topic modeling on base station run-time variable data collected from live Radio Access Networks (RANs). The results show that topic modeling clusters semantically related data in the same way as human experts would and that the anomalies in our test cases could be identified in latent Dirichlet allocation (LDA) topic models. Our experiment further reveals which information provided by the topic model is particularly usable to support human anomaly detection in this application domain.

    Download full text (pdf)
    fulltext
  • 14.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Information Fusion2019In: Data science in Practice / [ed] Alan Said, Vicenç Torra, Springer, 2019, p. 61-78Chapter in book (Refereed)
    Abstract [en]

    The study of information fusion comprises methods and techniques to automatically or semi-automatically combine information stemming from homogeneous or heterogeneous sources into a representation that supports a human user’s situation awareness for the purposes of decision making. Information fusion is not an end in itself but studies, adapts, applies and combines methods, techniques and algorithms provided by many other research areas, such as artificial intelligence, data mining, machine learning and optimization, in order to customize solutions for specific tasks. There are many different models for information fusion that describe the overall process as tasks building upon each other on different levels of abstraction. Information fusion includes the analysis of information, the inference of new information and the evaluation of uncertainty within the information. Hence, uncertainty management plays a vital role within the information fusion process. Uncertainty can be expressed by probability theory or, in the form of non-specificity and discord, by, for example, evidence theory.

  • 15.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Traceable Uncertainty for Threat Evaluation in Air to Ground Scenarios2013In: Twelfth Scandinavian Conference on Artificial Intelligence: SCAI 2013 / [ed] Manfred Jaeger; Thomas Dyhre Nielsen; Paolo Viappiani, IOS Press, 2013, p. 255-264Conference paper (Refereed)
    Abstract [en]

    In this paper we apply our method for traceable uncertainty to the application scenario of threat evaluation. The paper shows how the uncertainty within a decision support process can be traced and used to include a human decision maker in the decision making process by pointing to situations within the process where unusually high uncertainty is encountered. The human decision maker can then contribute with context information or expert knowledge to resolve the situation.

  • 16.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Andler, Sten F.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Traceable Uncertainty2013In: Proceedings of the 16th International Conference on Information Fusion, FUSION 2013, 2013, p. 1582-1589, article id 6641191Conference paper (Refereed)
  • 17.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Mathiason, Gunnar
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Helldin, Tove
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Root-Cause Localization using Restricted Boltzmann Machines2016In: 2016 19th International Conference on Information Fusion Proceedings, IEEE Computer Society, 2016, p. 248-255Conference paper (Refereed)
  • 18.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
    Marsland, Stephen
    School of Engineering and Advanced Technology, Massey University, New Zealand.
    Guesgen, Hans W.
    School of Engineering and Advanced Technology, Massey University, New Zealand.
    Context Awareness for a Smart Environment Utilizing Context Maps and Dempster-Shafer Theory2012In: Impact Analysis of Solutions for Chronic Disease Prevention and Management: 10th International Conference on Smart Homes and Health Telematics, ICOST 2012, Artiminio, Italy, June 12-15, 2012. Proceedings / [ed] Mark Donnelly; Cristiano Paggetti; Chris Nugent; Mounir Mokhtari, Springer Berlin/Heidelberg, 2012, p. 270-273Conference paper (Refereed)
    Abstract [en]

    In this paper we describe context awareness for a smart home using previously collected qualitative data. Based on this, context experts estimate to what extent a behavior is likely to occur in the given situation. The experts’ estimations are then combined using Dempster-Shafer Theory. The result can be used to (a) predict the most likely behavior and (b) to verify to what extent a behavior that has been detected is usual in the given situation.

  • 19.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Mellin, Jonas
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Automatic Early Risk Detection of Possible Medical Conditions for Usage Within an AMI-System2015In: Ambient Intelligence - Software and Applications / [ed] Amr Mohamed, Paulo Novais, António Pereira, Gabriel Villarrubia González, Antonio Fernández-Caballero, Springer Berlin/Heidelberg, 2015, p. 13-21Conference paper (Refereed)
    Abstract [en]

    Using hyperglycemia as an example, we present how Bayesian networks can be utilized for automatic early detection of a person’s possible medical risks based on information provided by un obtrusive sensors in their living environments. The network’s outcome can be used as a basis on which an automated AMI-system decides whether to interact with the person, their caregiver, or any other appropriate party. The networks’ design is established through expert elicitation and validated using a half-automated validation process that allows the medical expert to specify validation rules. To interpret the networks’ results we use an output dictionary which is automatically generated for each individual network and translates the output probability into the different risk classes (e.g.,no risk, risk).

    Download full text (pdf)
    fulltext
  • 20.
    Steinhauer, H. Joe
    et al.
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Åhlén, Anders
    Huawei Technologies Sweden.
    Helldin, Tove
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Mathiason, Gunnar
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Increased Network Monitoring Support through Topic Modeling2020In: International Journal of Information, Communication Technology and Applications, E-ISSN 2205-0930, Vol. 6, no 1Article in journal (Refereed)
    Abstract [en]

    To ensure that a wireless telecommunication system is reliably functioning at all times, root-causes of potential network failures need to be identified and remedied, ideally before a noticeable network performance degradation occurs. Network operators are today observing a multitude of key performance indicators (KPIs) and are notified of possible network problems through alarms issued by different parts of the network. However, the number of cascading alarms together with the number of observable KPIs are easily overwhelming the operator’s cognitive capacity. In this paper we show how exploratory data analysis and machine learning, in particular topic modelling, can assist the operator when monitoring network performance and identifying anomalous network behaviour as well as supporting the operator’s analysis of the anomaly and identification of its root-cause. 

    Download full text (pdf)
    fulltext
  • 21.
    Torra, Vicenç
    et al.
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre.
    Berglund, Stefan
    University of Skövde, School of Bioscience. University of Skövde, The Systems Biology Research Centre.
    Artificial Intelligence2019In: Data Science in Practice / [ed] Alan Said, Vicenç Torra, Springer, 2019, p. 9-26Chapter in book (Refereed)
    Abstract [en]

    This chapter gives a brief introduction to what artificial intelligence is. We begin discussing some of the alternative definitions for artificial intelligence and introduce the four major areas of the field. Then, in subsequent sections we present these areas. They are problem solving and search, knowledge representation and knowledge-based systems, machine learning, and distributed artificial intelligence. The chapter follows with a discussion on some ethical dilemma we find in relation to artificial intelligence. A summary closes this chapter.

  • 22.
    Vellenga, Koen
    et al.
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment. Volvo Car Corporation Sweden.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Falkman, Göran
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Sjögren, Anders
    Volvo Car Corporation Sweden.
    Surrogate Deep Learning to Estimate Uncertainties for Driver Intention Recognition2023In: ICMLC 2023: Proceedings of 2023 15th International Conference on Machine Learning and Computing, Zhuhai, China, February 17-20, 2023, New York, NY, USA: Association for Computing Machinery (ACM), 2023, p. 252-258Conference paper (Refereed)
    Abstract [en]

    Real-world applications of artificial intelligence that can potentially harm human beings should be able to express uncertainty about the made predictions. Probabilistic deep learning (DL) methods (e.g., variational inference [VI], VI last layer [VI-LL], Monte-Carlo [MC] dropout, stochastic weight averaging - Gaussian [SWA-G], and deep ensembles) can produce a predictive uncertainty but require expensive MC sampling techniques. Therefore, we evaluated if the probabilistic DL methods are uncertain when making incorrect predictions for an open-source driver intention recognition dataset and if a surrogate DL model can reproduce the uncertainty estimates. We found that all probabilistic DL methods are significantly more uncertain when making incorrect predictions at test time, but there are still instances where the models are very certain but completely incorrect. The surrogate DL models trained on the MC dropout and VI uncertainty estimates were capable of reproducing a significantly higher uncertainty estimate when making incorrect predictions.

    Download full text (pdf)
    fulltext
  • 23.
    Vellenga, Koen
    et al.
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment. Department of Data Analytics and Engineering, R&D, Volvo Car Corporation, Sweden.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Falkman, Göran
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Björklund, Tomas
    Department of Data Analytics and Engineering, R&D, Volvo Car Corporation, Sweden.
    Evaluation of Video Masked Autoencoders' Performance and Uncertainty Estimations for Driver Action and Intention Recognition2024In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE, 2024, p. 7429-7437Conference paper (Refereed)
    Abstract [en]

    Traffic fatalities remain among the leading death causes worldwide. To reduce this figure, car safety is listed as one of the most important factors. To actively support human drivers, it is essential for advanced driving assistance systems to be able to recognize the driver's actions and intentions. Prior studies have demonstrated various approaches to recognize driving actions and intentions based on in-cabin and external video footage. Given the performance of self-supervised video pre-trained (SSVP) Video Masked Autoencoders (VMAEs) on multiple action recognition datasets, we evaluate the performance of SSVP VMAEs on the Honda Research Institute Driving Dataset for driver action recognition (DAR) and on the Brain4Cars dataset for driver intention recognition (DIR). Besides the performance, the application of an artificial intelligence system in a safety-critical environment must be capable to express when it is uncertain about the produced results. Therefore, we also analyze uncertainty estimations produced by a Bayes-by-Backprop last-layer (BBB-LL) and Monte-Carlo (MC) dropout variants of an VMAE. Our experiments show that an VMAE achieves a higher overall performance for both offline DAR and end-to-end DIR compared to the state-of-the-art. The analysis of the BBB-LL and MC dropout models show higher uncertainty estimates for incorrectly classified test instances compared to correctly predicted test instances.

    Download full text (pdf)
    fulltext
  • 24.
    Vellenga, Koen
    et al.
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment. Department of Complete Vehicle Data Science, R&D, Volvo Car Corporation, Gothenburg, Sweden.
    Steinhauer, H. Joe
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Karlsson, Alexander
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Falkman, Göran
    University of Skövde, School of Informatics. University of Skövde, Informatics Research Environment.
    Rhodin, Asli
    Department of Complete Vehicle Data Science, R&D, Volvo Car Corporation, Gothenburg, Sweden.
    Koppisetty, Ashok Chaitanya
    Department of Complete Vehicle Data Science, R&D, Volvo Car Corporation, Gothenburg, Sweden.
    Driver intention recognition: state-of-the-art review2022In: IEEE Open Journal of Intelligent Transportation Systems, E-ISSN 2687-7813, Vol. 3, p. 602-616Article, review/survey (Refereed)
    Abstract [en]

    Every year worldwide more than one million people die and a further 50 million people are injured in traffic accidents. Therefore, the development of car safety features that actively support the driver in preventing accidents, is of utmost importance to reduce the number of injuries and fatalities. However, to establish this support it is necessary that the advanced driver assistance system (ADAS) understands the driver’s intended behavior in advance. The growing variety of sensors available for vehicles together with improved computer vision techniques, hence led to increased research directed towards inferring the driver’s intentions. This article reviews 64 driver intention recognition studies with regard to the maneuvers considered, the driving features included, the AI methods utilized, the achieved performance within the presented experiments, and the open challenges identified by the respected researchers. The article provides a high level analysis of the current technology readiness level of driver intention recognition technology to address the challenges to enable reliable driver intention recognition, such as the system architecture, implementation, and the purpose of the technology.

    Download full text (pdf)
    fulltext
1 - 24 of 24
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf