Högskolan i Skövde

his.sePublications
Change search
Link to record
Permanent link

Direct link
Publications (10 of 100) Show all publications
Vellenga, K., Steinhauer, H. J., Falkman, G. & Björklund, T. (2024). Evaluation of Video Masked Autoencoders' Performance and Uncertainty Estimations for Driver Action and Intention Recognition. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): . Paper presented at IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 4-8, 2024, Waikoloha, Hawaii, USA (pp. 7429-7437). IEEE
Open this publication in new window or tab >>Evaluation of Video Masked Autoencoders' Performance and Uncertainty Estimations for Driver Action and Intention Recognition
2024 (English)In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE, 2024, p. 7429-7437Conference paper, Published 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.

Place, publisher, year, edition, pages
IEEE, 2024
Series
Proceedings IEEE Workshop on Applications of Computer Vision, ISSN 2472-6737, E-ISSN 2642-9381
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Skövde Artificial Intelligence Lab (SAIL)
Identifiers
urn:nbn:se:his:diva-23540 (URN)10.1109/WACV57701.2024.00726 (DOI)2-s2.0-85191986920 (Scopus ID)979-8-3503-1893-7 (ISBN)979-8-3503-1892-0 (ISBN)
Conference
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 4-8, 2024, Waikoloha, Hawaii, USA
Funder
Vinnova, 2018-05012
Available from: 2024-01-16 Created: 2024-01-16 Last updated: 2024-05-13Bibliographically approved
Vellenga, K., Karlsson, A., Steinhauer, H. J., Falkman, G. & Sjögren, A. (2023). Surrogate Deep Learning to Estimate Uncertainties for Driver Intention Recognition. In: ICMLC 2023: Proceedings of 2023 15th International Conference on Machine Learning and Computing, Zhuhai, China, February 17-20, 2023. Paper presented at 15th International Conference on Machine Learning and Computing, Zhuhai, China, February 17-20, 2023 (pp. 252-258). New York, NY, USA: Association for Computing Machinery (ACM)
Open this publication in new window or tab >>Surrogate Deep Learning to Estimate Uncertainties for Driver Intention Recognition
Show others...
2023 (English)In: 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, Published 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.

Place, publisher, year, edition, pages
New York, NY, USA: Association for Computing Machinery (ACM), 2023
Keywords
Driver intention recognition, probabilistic deep learning, surrogate modeling, uncertainty quantification
National Category
Information Systems Other Computer and Information Science
Research subject
Skövde Artificial Intelligence Lab (SAIL)
Identifiers
urn:nbn:se:his:diva-22851 (URN)10.1145/3587716.3587758 (DOI)2-s2.0-85173817744 (Scopus ID)978-1-4503-9841-1 (ISBN)
Conference
15th International Conference on Machine Learning and Computing, Zhuhai, China, February 17-20, 2023
Projects
Intention recognition for real-time automotive 3D situation awareness
Funder
Vinnova, 2018-05012
Note

CC BY-NC-SA 4.0

CORRESPONDING AUTHOR: K. VELLENGA (e-mail: koen.vellenga@volvocars.com)

This work was supported by the Intention Recognition in Real Time for Automotive 3D Situation Awareness (IRRA) Project (https://www.vinnova.se/p/intention-recognition-i-realtid-for-automotive-3d-situation-awareness-irra/).

Available from: 2023-06-27 Created: 2023-06-27 Last updated: 2024-04-17Bibliographically approved
Ohlander, U., Alfredson, J., Riveiro, M., Helldin, T. & Falkman, G. (2023). The Effects of Varying Degrees of Information on Teamwork: a Study on Fighter Pilots. Paper presented at International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2023 Columbia 23 October 2023 through 27 October 2023. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 67(1), 1965-1970
Open this publication in new window or tab >>The Effects of Varying Degrees of Information on Teamwork: a Study on Fighter Pilots
Show others...
2023 (English)In: Proceedings of the Human Factors and Ergonomics Society Annual Meeting, ISSN 1071-1813, E-ISSN 2169-5067, Vol. 67, no 1, p. 1965-1970Article in journal (Refereed) Published
Abstract [en]

A team of fighter pilots in a distributed environment with limited access to information rely on technology to pursue teamwork. In order to design systems that support distributed teamwork, it is, therefore, necessary to understand how access to information affects the team members. Certain factors, such as mutual performance monitoring, shared mental models, adaptability, and backup behavior are considered essential for effective teamwork. We investigate these factors in this work, focusing on how visually communicated information affects fighter pilots’ perception of these factors. For that, a questionnaire including the teamwork factors in relation to certain defined scenarios that contain various levels of information was distributed to fighter pilots. We show that the studied factors are affected by the level of information available to the pilots. Especially, mutual performance monitoring increases with the degree of available information. © 2023 Human Factors and Ergonomics Society.

Place, publisher, year, edition, pages
Sage Publications, 2023
Keywords
fighter pilots, information variation, teamwork
National Category
Information Systems Information Systems, Social aspects Interaction Technologies
Research subject
Skövde Artificial Intelligence Lab (SAIL)
Identifiers
urn:nbn:se:his:diva-23797 (URN)10.1177/21695067231192607 (DOI)2-s2.0-85190953101 (Scopus ID)
Conference
International Annual Meeting of the Human Factors and Ergonomics Society, HFES 2023 Columbia 23 October 2023 through 27 October 2023
Note

Correspondence Address: U. Ohlander; Saab Aeronautics, Saab AB, Linköping, Bröderna Ugglas gata, 58188, Sweden; email: ulrika.ohlander@saabgroup.com; CODEN: PHFSD

Available from: 2024-05-02 Created: 2024-05-02 Last updated: 2024-05-06
Vellenga, K., Steinhauer, H. J., Karlsson, A., Falkman, G., Rhodin, A. & Koppisetty, A. C. (2022). Driver intention recognition: state-of-the-art review. IEEE Open Journal of Intelligent Transportation Systems, 3, 602-616
Open this publication in new window or tab >>Driver intention recognition: state-of-the-art review
Show others...
2022 (English)In: IEEE Open Journal of Intelligent Transportation Systems, E-ISSN 2687-7813, Vol. 3, p. 602-616Article, review/survey (Refereed) Published
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.

Place, publisher, year, edition, pages
IEEE, 2022
Keywords
Driver intentions, intention recognition, driver behavior, driving maneuvers
National Category
Computer Systems
Research subject
Skövde Artificial Intelligence Lab (SAIL)
Identifiers
urn:nbn:se:his:diva-21812 (URN)10.1109/ojits.2022.3197296 (DOI)000853832800001 ()2-s2.0-85147393634 (Scopus ID)
Projects
Intention recognition for real-time automotive 3D situation awareness
Funder
Vinnova, 2018-05012
Note

CC BY-NC-ND 4.0

CORRESPONDING AUTHOR: K. VELLENGA (e-mail: koen.vellenga@volvocars.com)

This work was supported by the Intention Recognition in Real Time for Automotive 3D Situation Awareness (IRRA) Project (https://www.vinnova.se/p/intention-recognition-i-realtid-for-automotive-3d-situation-awareness-irra/).

Available from: 2022-09-12 Created: 2022-09-12 Last updated: 2024-04-17Bibliographically approved
Ståhl, N., Falkman, G., Karlsson, A. & Mathiason, G. (2020). Evaluation of Uncertainty Quantification in Deep Learning. In: Marie-Jeanne Lesot, Susana Vieira, Marek Z. Reformat, João Paulo Carvalho, Anna Wilbik, Bernadette Bouchon-Meunier, Ronald R. Yager (Ed.), Marie-Jeanne Lesot, Susana Vieira, Marek Z. Reformat, João Paulo Carvalho, Anna Wilbik, Bernadette Bouchon-Meunier, Ronald R. Yager (Ed.), Information Processing and Management of Uncertainty in Knowledge-Based Systems: 18th International Conference, IPMU 2020, Lisbon, Portugal, June 15–19, 2020, Proceedings, Part I. Paper presented at 18th International Conference, IPMU 2020, Lisbon, Portugal, June 15–19, 2020 (pp. 556-568). Cham: Springer
Open this publication in new window or tab >>Evaluation of Uncertainty Quantification in Deep Learning
2020 (English)In: Information Processing and Management of Uncertainty in Knowledge-Based Systems: 18th International Conference, IPMU 2020, Lisbon, Portugal, June 15–19, 2020, Proceedings, Part I / [ed] Marie-Jeanne Lesot, Susana Vieira, Marek Z. Reformat, João Paulo Carvalho, Anna Wilbik, Bernadette Bouchon-Meunier, Ronald R. Yager, Cham: Springer, 2020, p. 556-568Conference paper, Published paper (Refereed)
Abstract [en]

Artificial intelligence (AI) is nowadays included into an increasing number of critical systems. Inclusion of AI in such systems may, however, pose a risk, since it is, still, infeasible to build AI systems that know how to function well in situations that differ greatly from what the AI has seen before. Therefore, it is crucial that future AI systems have the ability to not only function well in known domains, but also understand and show when they are uncertain when facing something unknown. In this paper, we evaluate four different methods that have been proposed to correctly quantifying uncertainty when the AI model is faced with new samples. We investigate the behaviour of these models when they are applied to samples far from what these models have seen before, and if they correctly attribute those samples with high uncertainty. We also examine if incorrectly classified samples are attributed with an higher uncertainty than correctly classified samples. The major finding from this simple experiment is, surprisingly, that the evaluated methods capture the uncertainty differently and the correlation between the quantified uncertainty of the models is low. This inconsistency is something that needs to be further understood and solved before AI can be used in critical applications in a trustworthy and safe manner. © 2020, Springer Nature Switzerland AG.

Place, publisher, year, edition, pages
Cham: Springer, 2020
Series
Communications in Computer and Information Science, ISSN 1865-0929, E-ISSN 1865-0937 ; 1237
Keywords
Function evaluation, Information management, Knowledge based systems, Technology transfer, Uncertainty analysis, AI systems, Critical applications, Critical systems, Uncertainty quantifications, Deep learning
National Category
Computer Sciences
Research subject
Skövde Artificial Intelligence Lab (SAIL)
Identifiers
urn:nbn:se:his:diva-18555 (URN)10.1007/978-3-030-50146-4_41 (DOI)2-s2.0-85086272108 (Scopus ID)978-3-030-50145-7 (ISBN)978-3-030-50146-4 (ISBN)
Conference
18th International Conference, IPMU 2020, Lisbon, Portugal, June 15–19, 2020
Available from: 2020-06-18 Created: 2020-06-18 Last updated: 2021-04-19Bibliographically approved
Bae, J., Helldin, T., Riveiro, M., Nowaczyk, S., Bouguelia, M.-R. & Falkman, G. (2020). Interactive clustering: A comprehensive review. ACM Computing Surveys, 53(1), Article ID 1.
Open this publication in new window or tab >>Interactive clustering: A comprehensive review
Show others...
2020 (English)In: ACM Computing Surveys, ISSN 0360-0300, E-ISSN 1557-7341, Vol. 53, no 1, article id 1Article in journal (Refereed) Published
Abstract [en]

In this survey, 105 papers related to interactive clustering were reviewed according to seven perspectives: (1) on what level is the interaction happening, (2) which interactive operations are involved, (3) how user feedback is incorporated, (4) how interactive clustering is evaluated, (5) which data and (6) which clustering methods have been used, and (7) what outlined challenges there are. This article serves as a comprehensive overview of the field and outlines the state of the art within the area as well as identifies challenges and future research needs.

Place, publisher, year, edition, pages
Association for Computing Machinery (ACM), 2020
Keywords
Clustering, Evaluation, Feedback, Interaction, Interactive, User, Surveys, Computer science
National Category
Computer Sciences Human Computer Interaction
Research subject
Skövde Artificial Intelligence Lab (SAIL)
Identifiers
urn:nbn:se:his:diva-18266 (URN)10.1145/3340960 (DOI)000582585800001 ()2-s2.0-85079573488 (Scopus ID)
Note

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s). © 2020 Copyright held by the owner/author(s).

Available from: 2020-02-28 Created: 2020-02-28 Last updated: 2020-11-17Bibliographically approved
Ståhl, N., Falkman, G., Karlsson, A., Mathiason, G. & Boström, J. (2019). Deep Reinforcement Learning for Multiparameter Optimization in de novo Drug Design. Journal of Chemical Information and Modeling, 59(7), 3166-3176
Open this publication in new window or tab >>Deep Reinforcement Learning for Multiparameter Optimization in de novo Drug Design
Show others...
2019 (English)In: Journal of Chemical Information and Modeling, ISSN 1549-9596, E-ISSN 1549-960X, Vol. 59, no 7, p. 3166-3176Article in journal (Refereed) Published
Abstract [en]

In medicinal chemistry programs it is key to design and make compounds that are efficacious and safe. This is a long, complex, and difficult multiparameter optimization process, often including several properties with orthogonal trends. New methods for the automated design of compounds against profiles of multiple properties are thus of great value. Here we present a fragment-based reinforcement learning approach based on an actor-critic model, for the generation of novel molecules with optimal properties. The actor and the critic are both modeled with bidirectional long short-term memory (LSTM) networks. The AI method learns how to generate new compounds with desired properties by starting from an initial set of lead molecules and then improving these by replacing some of their fragments. A balanced binary tree based on the similarity of fragments is used in the generative process to bias the output toward structurally similar molecules. The method is demonstrated by a case study showing that 93% of the generated molecules are chemically valid and more than a third satisfy the targeted objectives, while there were none in the initial set.

Place, publisher, year, edition, pages
American Chemical Society (ACS), 2019
Keywords
algorithms, molecules
National Category
Computer Sciences
Research subject
Skövde Artificial Intelligence Lab (SAIL)
Identifiers
urn:nbn:se:his:diva-17503 (URN)10.1021/acs.jcim.9b00325 (DOI)000477074900010 ()31273995 (PubMedID)2-s2.0-85070180995 (Scopus ID)
Available from: 2019-08-08 Created: 2019-08-08 Last updated: 2021-04-19Bibliographically approved
Holst, A., Bouguelia, M.-R., Görnerup, O., Pashami, S., Al-Shishtawy, A., Falkman, G., . . . Soliman, A. (2019). Eliciting structure in data. In: Christoph Trattner, Denis Parra, Nathalie Riche (Ed.), CEUR Workshop Proceedings: . Paper presented at 2019 Joint ACM IUI Workshops, ACMIUI-WS 2019, Los Angeles, United States, 20 March 2019. CEUR-WS, 2327
Open this publication in new window or tab >>Eliciting structure in data
Show others...
2019 (English)In: CEUR Workshop Proceedings / [ed] Christoph Trattner, Denis Parra, Nathalie Riche, CEUR-WS , 2019, Vol. 2327Conference paper, Published paper (Refereed)
Abstract [en]

This paper demonstrates how to explore and visualize different types of structure in data, including clusters, anomalies, causal relations, and higher order relations. The methods are developed with the goal of being as automatic as possible and applicable to massive, streaming, and distributed data. Finally, a decentralized learning scheme is discussed, enabling finding structure in the data without collecting the data centrally. 

Place, publisher, year, edition, pages
CEUR-WS, 2019
Series
CEUR Workshop Proceedings, ISSN 1613-0073 ; 2327
Keywords
Anomaly detection, Causal inference, Clustering, Distributed analytics, Higher-order structure, Information visualization, Information systems, User interfaces, Causal inferences, Data acquisition
National Category
Computer Sciences Human Computer Interaction
Research subject
Skövde Artificial Intelligence Lab (SAIL)
Identifiers
urn:nbn:se:his:diva-16748 (URN)2-s2.0-85063227224 (Scopus ID)
Conference
2019 Joint ACM IUI Workshops, ACMIUI-WS 2019, Los Angeles, United States, 20 March 2019
Available from: 2019-04-05 Created: 2019-04-05 Last updated: 2020-06-18Bibliographically approved
Ohlander, U., Alfredson, J., Riveiro, M. & Falkman, G. (2019). Fighter pilots' teamwork: a descriptive study. Ergonomics, 62(7), 880-890
Open this publication in new window or tab >>Fighter pilots' teamwork: a descriptive study
2019 (English)In: Ergonomics, ISSN 0014-0139, E-ISSN 1366-5847, Vol. 62, no 7, p. 880-890Article in journal (Refereed) Published
Abstract [en]

The execution of teamwork varies widely depending on the domain and task in question. Despite the considerable diversity of teams and their operation, researchers tend to aim for unified theories and models regardless of field. However, we argue that there is a need for translation and adaptation of the theoretical models to each specific domain. To this end, a case study was carried out on fighter pilots and it was investigated how teamwork is performed in this specialised and challenging environment, with a specific focus on the dependence on technology for these teams. The collaboration between the fighter pilots is described and analysed using a generic theoretical model for effective teamwork from the literature. The results show that domain-specific application and modification is needed in order for the model to capture fighter pilot's teamwork. The study provides deeper understanding of the working conditions for teams of pilots and gives design implications for how tactical support systems can enhance teamwork in the domain. Practitioner summary: This article presents a qualitative interview study with fighter pilots based on a generic theoretical teamwork model applied to the fighter domain. The purpose is to understand the conditions under which teams of fighter pilots work and to provide guidance for the design of future technological aids.

Place, publisher, year, edition, pages
Taylor & Francis Group, 2019
Keywords
Teamwork, team effectiveness, fighter pilot, fighter aircraft
National Category
Production Engineering, Human Work Science and Ergonomics Information Systems, Social aspects
Research subject
Skövde Artificial Intelligence Lab (SAIL)
Identifiers
urn:nbn:se:his:diva-16880 (URN)10.1080/00140139.2019.1596319 (DOI)000465935600001 ()31002026 (PubMedID)2-s2.0-85064645549 (Scopus ID)
Available from: 2019-05-10 Created: 2019-05-10 Last updated: 2022-12-28Bibliographically approved
Ståhl, N., Falkman, G., Karlsson, A., Mathiason, G. & Boström, J. (2019). Improving the use of deep convolutional neural networks for the prediction of molecular properties. In: Florentino Fdez-Riverola, Mohd Saberi Mohamad, Miguel Rocha, Juan F. De Paz, Pascual González (Ed.), Practical Applications of Computational Biology and Bioinformatics, 12th International Conference: . Paper presented at PACBB2018: International Conference on Practical Applications of Computational Biology & Bioinformatics, Toledo, June 20-22, 2018 (pp. 71-79). Cham: Springer, 803
Open this publication in new window or tab >>Improving the use of deep convolutional neural networks for the prediction of molecular properties
Show others...
2019 (English)In: Practical Applications of Computational Biology and Bioinformatics, 12th International Conference / [ed] Florentino Fdez-Riverola, Mohd Saberi Mohamad, Miguel Rocha, Juan F. De Paz, Pascual González, Cham: Springer, 2019, Vol. 803, p. 71-79Conference paper, Published paper (Refereed)
Abstract [en]

We present a flexible deep convolutional neural network method for the analyse of arbitrary sized graph structures representing molecules. The method makes use of RDKit, an open-source cheminformatics software, allowing the incorporation of any global molecular (such as molecular charge) and local (such as atom type) information. We evaluate the method on the Side Effect Resource (SIDER) v4.1 dataset and show that it significantly outperforms another recently proposed method based on deep convolutional neural networks. We also reflect on how different types of information and input data affect the predictive power of our model. This reflection highlights several open problems that should be solved to further improve the use of deep learning within cheminformatics.

Place, publisher, year, edition, pages
Cham: Springer, 2019
Series
Advances in Intelligent Systems and Computing, ISSN 2194-5357, E-ISSN 2194-5365 ; 803
Keywords
drug discovery, graph convolutional neural network, molecular property prediction, bioinformatics, convolution, neural networks, open source software, open systems, cheminformatics, convolutional neural network, deep convolutional neural networks, graph structures, molecular charge, molecular properties, predictive power, deep neural networks
National Category
Computer Sciences
Research subject
Skövde Artificial Intelligence Lab (SAIL); INF301 Data Science
Identifiers
urn:nbn:se:his:diva-16230 (URN)10.1007/978-3-319-98702-6_9 (DOI)000468071900009 ()2-s2.0-85052956812 (Scopus ID)978-3-319-98701-9 (ISBN)978-3-319-98702-6 (ISBN)
Conference
PACBB2018: International Conference on Practical Applications of Computational Biology & Bioinformatics, Toledo, June 20-22, 2018
Available from: 2018-09-25 Created: 2018-09-25 Last updated: 2021-04-19Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-8884-2154

Search in DiVA

Show all publications