Dr Bjorn Jensen

  • Honorary Research Fellow (School of Computing Science)

email: Bjorn.Jensen@glasgow.ac.uk

SAWB, Room 306, School of Computing Science

ORCID iDhttps://orcid.org/0000-0001-8074-228X

Biography

I (Bjørn Sand Jensen) was a Lecturer in the Information, Data and Analysis Section in the School of Computing Science, University of Glasgow, from May 2016 to October 2021. 

As of 1st November 2021, I am an Associate Professor at the Technical University of Denmark and an Honorary Research Fellow at the University of Glasgow.

 

Research interests

  • Probabilistic (/Bayesian) machine learning
  • Planning/sequential decision-making under uncertainty (using principles from reinforcement learning, including Bayesian optimisation)
  • Audio processing and modelling
  • Eliciting and modelling human decision-making
  • Bayesian non-parametrics (especially Gaussian processes)
  • Uncertainty quantification in scientific inquiry (e.g. biological image analysis and digital humanities)

 

Publications

List by: Type | Date

Jump to: 2023 | 2022 | 2021 | 2020 | 2019 | 2015 | 2014 | 2013 | 2012 | 2011 | 2010 | 2008
Number of items: 30.

2023

Aggarwal, A. , Jensen, B. S. , Pant, S. and Lee, C.-H. (2023) Strain energy density as a Gaussian process and its utilization in stochastic finite element analysis: application to planar soft tissues. Computer Methods in Applied Mechanics and Engineering, 404, 115812. (doi: 10.1016/j.cma.2022.115812)

2022

Zimmerer, D. et al. (2022) MOOD 2020: a public benchmark for out-of-distribution detection and localization on medical images. IEEE Transactions on Medical Imaging, 41(10), pp. 2728-2738. (doi: 10.1109/tmi.2022.3170077)

Kascenas, A., Young, R., Jensen, B. S. , Pugeault, N. and O’Neil, A. Q. (2022) Anomaly Detection via Context and Local Feature Matching. In: IEEE International Symposium on Biomedical Imaging (ISBI) 2022, Kolkata, India, 28-31 Mar 2022, ISBN 9781665429238 (doi: 10.1109/ISBI52829.2022.9761524)

2021

Pitsillos, N., Pore, A., Jensen, B. S. and Aragon Camarasa, G. (2021) Intrinsic Robotic Introspection: Learning Internal States From Neuron Activations. In: IEEE International Conference on Development and Learning (ICDL 2021), Beijing, China, 23-26 Aug 2021, ISBN 9781728162423 (doi: 10.1109/ICDL49984.2021.9515672)

Uhrenholt, A. K. , Charvet, V. and Jensen, B. S. (2021) Probabilistic selection of inducing points in sparse gaussian processes. In: 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021), 27-29 Jul 2021, pp. 1035-1044.

2020

Laux, L., Cutiongco, M. F.A. , Gadegaard, N. and Jensen, B. S. (2020) Interactive machine learning for fast and robust cell profiling. PLoS ONE, 15(9), e0237972. (doi: 10.1371/journal.pone.0237972) (PMID:32915784) (PMCID:PMC7485821)

Cutiongco, M. F.A. , Jensen, B. S. , Reynolds, P. M. and Gadegaard, N. (2020) Predicting gene expression using morphological cell responses to nanotopography. Nature Communications, 11, 1384. (doi: 10.1038/s41467-020-15114-1) (PMID:32170111) (PMCID:PMC7070086)

Mohammadi, S., Uhrenholt, A. K. and Jensen, B. S. (2020) Odd-One-Out Representation Learning. Object Representations for Learning and Reasoning, 11 Dec 2020.

2019

Tonolini, F., Jensen, B. S. and Murray-Smith, R. (2019) Variational Sparse Coding. In: Conference on Uncertainty in Artificial Intelligence (UAI 2019), Tel Aviv, Israel, 22-25 July 2019,

Uhrenholt, A. K. and Jensen, B. S. (2019) Efficient Bayesian Optimization for Target Vector Estimation. In: The 22nd International Conference on Artificial Intelligence and Statistics, Naha, Okinawa, Japan, 16-18 Apr 2019, pp. 2661-2670.

Sablotny, M., Jensen, B. S. and Johnson, C. W. (2019) Recurrent neural networks for fuzz testing web browsers. In: Lee, K. (ed.) Information Security and Cryptology – ICISC 2018. Series: Lecture Notes in Computer Science (11396). Springer, pp. 354-370. ISBN 9783030121457 (doi: 10.1007/978-3-030-12146-4_22)

Uhrenholt, A. and Jensen, B. S. (2019) Efficient Bayesian Optimization for Target Vector Estimation. In: 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Okinawa, Japan, 16-18 April 2019, pp. 2661-2670.

2015

Madsen, J., Sand Jensen, B. and Larson, J. (2015) Learning Combinations of Multiple Feature Representations for Music Emotion Prediction. In: ASM '15: 1st International Workshop on Affect and Sentiment in Multimedia, Brisbane, Australia, 26-30 Oct 2015, pp. 3-8. ISBN 9781450337502 (doi: 10.1145/2813524.2813534)

Sand Jensen, B. , Nielsen, J. B. and Larsen, J. (2015) Perspectives on Bayesian Optimization for HCI. In: CHI 2015: Workshop on Principles, Techniques and Perspectives on Optimization and HCI, Seoul, Republic of Korea, 18-23 Apr 2015,

2014

Madsen, J., Sand Jensen, B. and Larsen, J. (2014) Modeling Temporal Structure in Music for Emotion Prediction using Pairwise Comparisons. In: ISMIR 2014: 15th International Society of Music Information Retrieval Conference, Taipei, Taiwan, 27-31 Oct 2014,

2013

Nielsen, J. B., Sand Jensen, B. , Hansen, T. J. and Larsen, J. (2013) Personalized audio systems - a Bayesian approach. In: 135th International AES Convention, New York City, NY, USA, 17-20 Oct 2013,

Madsen, J., Sand Jensen, B. and Larsen, J. (2013) Predictive modeling of expressed emotions in music using pairwise comparisons. Lecture Notes in Computer Science, 7900, pp. 253-277. (doi: 10.1007/978-3-642-41248-6_14)

Nielsen, J. B., Nielsen, J., Sand Jensen, B. and Larsen, J. (2013) Hearing Aid Personalization. In: 3rd NIPS Workshop on Machine Learning and Interpretation in Neuroimaging 2013, Lake Tahoe, NV, USA, 5-10 Dec 2013,

Sand Jensen, B. , Troelsgaard, R., Larsen, J. and Hansen, L. K. (2013) Towards a universal representation for audio information retrieval and analysis. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, Canada, 26-31 May 2013, pp. 3168-3172. ISBN 9781479903566 (doi: 10.1109/ICASSP.2013.6638242)

Sand Jensen, B. , Nielsen, J. B. and Larsen, J. (2013) Bounded Gaussian Process Regression. In: 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Southampton, UK, 22-25 Sept 2013, pp. 1-6. ISBN 9781479911806 (doi: 10.1109/MLSP.2013.6661916)

2012

Alstrøm, T. S., Sand Jensen, B. , Schmidt, M. N., Kostesha, N. V. and Larsen, J. (2012) Haussdorff and hellinger for colorimetric sensor array classification. In: 2012 IEEE International Workshop on Machine Learning for Signal Processing, Santander, Spain, 23-26 Sep 2012, pp. 1-6. ISBN 9781467310246 (doi: 10.1109/MLSP.2012.6349724)

Madsen, J., Nielsen, J. B., Sand Jensen, B. and Larsen, J. (2012) Modeling expressed emotions in music using pairwise comparisons. In: 9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012), London, UK, 19-22 Jun 2012, pp. 526-533.

Madsen, J., Sand Jensen, B. , Larsen, J. and Nielsen, J. B. (2012) Towards predicting expressed emotion in music from pairwise comparisons. In: 9th Sound and Music Computing Conference (SMC 2012), Copenhagen, Denmark, 11-14 Jul 2012, pp. 350-357.

Nielsen, J. B., Sand Jensen, B. and Larsen, J. (2012) Pseudo inputs for pairwise learning with Gaussian processes. In: 2012 IEEE International Workshop on Machine Learning for Signal Processing, Santander, Spain, 23-26 Sep 2012, pp. 1-6. ISBN 9781467310246 (doi: 10.1109/MLSP.2012.6349812)

Sand Jensen, B. , Saez Gallego, J. and Larsen, J. (2012) A predictive model of music preference using pairwise comparisons. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, 25-30 Mar 2012, pp. 1977-1980. ISBN 9781467300452 (doi: 10.1109/ICASSP.2012.6288294)

2011

Nielsen, J. B., Sand Jensen, B. and Larsen, J. (2011) On sparse multi-task Gaussian process priors for music preference learning. In: 25th Annual Conference on Neural Information Processing Systems : CMPL workshop, Granada, Spain, 12-17 Dec 2011, pp. 1-8.

Sand Jensen, B. , Nielsen, J. B. and Larsen, J. (2011) Efficient preference learning with pairwise continuous observations and Gaussian processes. In: 2011 IEEE International Workshop on Machine Learning for Signal Processing, Santander, Spain, 18-21 Sep 2011, pp. 1-6. ISBN 9781457716218 (doi: 10.1109/MLSP.2011.6064616)

2010

Sand Jensen, B. , Larsen, J. E., Jensen, K., Larsen, J. and Hansen, L. K. (2010) Estimating human predictability from mobile sensor data. In: 2010 IEEE International Workshop on Machine Learning for Signal Processing, Kittilä, Finland, 29 Aug - 01 Sep 2010, pp. 196-201. ISBN 9781424478750 (doi: 10.1109/MLSP.2010.5588997)

Sand Jensen, B. , Larsen, J., Jensen, K., Larsen, J. E. and Hansen, L. K. (2010) Predictability of mobile phone associations. In: 21st European Conference on Machine Learning : Mining Ubiquitous and Social Environments Workshop, Barcelona, Spain, 20-24 Sep 2010, pp. 91-105.

2008

Tranberg-Hansen, A. S., Madsen, J. and Sand Jensen, B. (2008) A service based estimation method for MPSoC performance modelling. In: Third International Symposium on Industrial Embedded Systems (SIES 2008), Montpellier, France, 11-13 Jun 2008, pp. 43-50. ISBN 9781424419944 (doi: 10.1109/SIES.2008.4577679)

This list was generated on Wed Mar 29 16:06:42 2023 BST.
Jump to: Articles | Book Sections | Conference or Workshop Item | Conference Proceedings
Number of items: 30.

Articles

Aggarwal, A. , Jensen, B. S. , Pant, S. and Lee, C.-H. (2023) Strain energy density as a Gaussian process and its utilization in stochastic finite element analysis: application to planar soft tissues. Computer Methods in Applied Mechanics and Engineering, 404, 115812. (doi: 10.1016/j.cma.2022.115812)

Zimmerer, D. et al. (2022) MOOD 2020: a public benchmark for out-of-distribution detection and localization on medical images. IEEE Transactions on Medical Imaging, 41(10), pp. 2728-2738. (doi: 10.1109/tmi.2022.3170077)

Laux, L., Cutiongco, M. F.A. , Gadegaard, N. and Jensen, B. S. (2020) Interactive machine learning for fast and robust cell profiling. PLoS ONE, 15(9), e0237972. (doi: 10.1371/journal.pone.0237972) (PMID:32915784) (PMCID:PMC7485821)

Cutiongco, M. F.A. , Jensen, B. S. , Reynolds, P. M. and Gadegaard, N. (2020) Predicting gene expression using morphological cell responses to nanotopography. Nature Communications, 11, 1384. (doi: 10.1038/s41467-020-15114-1) (PMID:32170111) (PMCID:PMC7070086)

Madsen, J., Sand Jensen, B. and Larsen, J. (2013) Predictive modeling of expressed emotions in music using pairwise comparisons. Lecture Notes in Computer Science, 7900, pp. 253-277. (doi: 10.1007/978-3-642-41248-6_14)

Book Sections

Sablotny, M., Jensen, B. S. and Johnson, C. W. (2019) Recurrent neural networks for fuzz testing web browsers. In: Lee, K. (ed.) Information Security and Cryptology – ICISC 2018. Series: Lecture Notes in Computer Science (11396). Springer, pp. 354-370. ISBN 9783030121457 (doi: 10.1007/978-3-030-12146-4_22)

Conference or Workshop Item

Mohammadi, S., Uhrenholt, A. K. and Jensen, B. S. (2020) Odd-One-Out Representation Learning. Object Representations for Learning and Reasoning, 11 Dec 2020.

Conference Proceedings

Kascenas, A., Young, R., Jensen, B. S. , Pugeault, N. and O’Neil, A. Q. (2022) Anomaly Detection via Context and Local Feature Matching. In: IEEE International Symposium on Biomedical Imaging (ISBI) 2022, Kolkata, India, 28-31 Mar 2022, ISBN 9781665429238 (doi: 10.1109/ISBI52829.2022.9761524)

Pitsillos, N., Pore, A., Jensen, B. S. and Aragon Camarasa, G. (2021) Intrinsic Robotic Introspection: Learning Internal States From Neuron Activations. In: IEEE International Conference on Development and Learning (ICDL 2021), Beijing, China, 23-26 Aug 2021, ISBN 9781728162423 (doi: 10.1109/ICDL49984.2021.9515672)

Uhrenholt, A. K. , Charvet, V. and Jensen, B. S. (2021) Probabilistic selection of inducing points in sparse gaussian processes. In: 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021), 27-29 Jul 2021, pp. 1035-1044.

Tonolini, F., Jensen, B. S. and Murray-Smith, R. (2019) Variational Sparse Coding. In: Conference on Uncertainty in Artificial Intelligence (UAI 2019), Tel Aviv, Israel, 22-25 July 2019,

Uhrenholt, A. K. and Jensen, B. S. (2019) Efficient Bayesian Optimization for Target Vector Estimation. In: The 22nd International Conference on Artificial Intelligence and Statistics, Naha, Okinawa, Japan, 16-18 Apr 2019, pp. 2661-2670.

Uhrenholt, A. and Jensen, B. S. (2019) Efficient Bayesian Optimization for Target Vector Estimation. In: 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Okinawa, Japan, 16-18 April 2019, pp. 2661-2670.

Madsen, J., Sand Jensen, B. and Larson, J. (2015) Learning Combinations of Multiple Feature Representations for Music Emotion Prediction. In: ASM '15: 1st International Workshop on Affect and Sentiment in Multimedia, Brisbane, Australia, 26-30 Oct 2015, pp. 3-8. ISBN 9781450337502 (doi: 10.1145/2813524.2813534)

Sand Jensen, B. , Nielsen, J. B. and Larsen, J. (2015) Perspectives on Bayesian Optimization for HCI. In: CHI 2015: Workshop on Principles, Techniques and Perspectives on Optimization and HCI, Seoul, Republic of Korea, 18-23 Apr 2015,

Madsen, J., Sand Jensen, B. and Larsen, J. (2014) Modeling Temporal Structure in Music for Emotion Prediction using Pairwise Comparisons. In: ISMIR 2014: 15th International Society of Music Information Retrieval Conference, Taipei, Taiwan, 27-31 Oct 2014,

Nielsen, J. B., Sand Jensen, B. , Hansen, T. J. and Larsen, J. (2013) Personalized audio systems - a Bayesian approach. In: 135th International AES Convention, New York City, NY, USA, 17-20 Oct 2013,

Nielsen, J. B., Nielsen, J., Sand Jensen, B. and Larsen, J. (2013) Hearing Aid Personalization. In: 3rd NIPS Workshop on Machine Learning and Interpretation in Neuroimaging 2013, Lake Tahoe, NV, USA, 5-10 Dec 2013,

Sand Jensen, B. , Troelsgaard, R., Larsen, J. and Hansen, L. K. (2013) Towards a universal representation for audio information retrieval and analysis. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, Canada, 26-31 May 2013, pp. 3168-3172. ISBN 9781479903566 (doi: 10.1109/ICASSP.2013.6638242)

Sand Jensen, B. , Nielsen, J. B. and Larsen, J. (2013) Bounded Gaussian Process Regression. In: 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Southampton, UK, 22-25 Sept 2013, pp. 1-6. ISBN 9781479911806 (doi: 10.1109/MLSP.2013.6661916)

Alstrøm, T. S., Sand Jensen, B. , Schmidt, M. N., Kostesha, N. V. and Larsen, J. (2012) Haussdorff and hellinger for colorimetric sensor array classification. In: 2012 IEEE International Workshop on Machine Learning for Signal Processing, Santander, Spain, 23-26 Sep 2012, pp. 1-6. ISBN 9781467310246 (doi: 10.1109/MLSP.2012.6349724)

Madsen, J., Nielsen, J. B., Sand Jensen, B. and Larsen, J. (2012) Modeling expressed emotions in music using pairwise comparisons. In: 9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012), London, UK, 19-22 Jun 2012, pp. 526-533.

Madsen, J., Sand Jensen, B. , Larsen, J. and Nielsen, J. B. (2012) Towards predicting expressed emotion in music from pairwise comparisons. In: 9th Sound and Music Computing Conference (SMC 2012), Copenhagen, Denmark, 11-14 Jul 2012, pp. 350-357.

Nielsen, J. B., Sand Jensen, B. and Larsen, J. (2012) Pseudo inputs for pairwise learning with Gaussian processes. In: 2012 IEEE International Workshop on Machine Learning for Signal Processing, Santander, Spain, 23-26 Sep 2012, pp. 1-6. ISBN 9781467310246 (doi: 10.1109/MLSP.2012.6349812)

Sand Jensen, B. , Saez Gallego, J. and Larsen, J. (2012) A predictive model of music preference using pairwise comparisons. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, 25-30 Mar 2012, pp. 1977-1980. ISBN 9781467300452 (doi: 10.1109/ICASSP.2012.6288294)

Nielsen, J. B., Sand Jensen, B. and Larsen, J. (2011) On sparse multi-task Gaussian process priors for music preference learning. In: 25th Annual Conference on Neural Information Processing Systems : CMPL workshop, Granada, Spain, 12-17 Dec 2011, pp. 1-8.

Sand Jensen, B. , Nielsen, J. B. and Larsen, J. (2011) Efficient preference learning with pairwise continuous observations and Gaussian processes. In: 2011 IEEE International Workshop on Machine Learning for Signal Processing, Santander, Spain, 18-21 Sep 2011, pp. 1-6. ISBN 9781457716218 (doi: 10.1109/MLSP.2011.6064616)

Sand Jensen, B. , Larsen, J. E., Jensen, K., Larsen, J. and Hansen, L. K. (2010) Estimating human predictability from mobile sensor data. In: 2010 IEEE International Workshop on Machine Learning for Signal Processing, Kittilä, Finland, 29 Aug - 01 Sep 2010, pp. 196-201. ISBN 9781424478750 (doi: 10.1109/MLSP.2010.5588997)

Sand Jensen, B. , Larsen, J., Jensen, K., Larsen, J. E. and Hansen, L. K. (2010) Predictability of mobile phone associations. In: 21st European Conference on Machine Learning : Mining Ubiquitous and Social Environments Workshop, Barcelona, Spain, 20-24 Sep 2010, pp. 91-105.

Tranberg-Hansen, A. S., Madsen, J. and Sand Jensen, B. (2008) A service based estimation method for MPSoC performance modelling. In: Third International Symposium on Industrial Embedded Systems (SIES 2008), Montpellier, France, 11-13 Jun 2008, pp. 43-50. ISBN 9781424419944 (doi: 10.1109/SIES.2008.4577679)

This list was generated on Wed Mar 29 16:06:42 2023 BST.

Grants

Current funding (as of November 2021):

- KTP (Innovate UK) project, £178k with industry partner Qumodo, Frank Pollick and Paul Siebert.

- CRUK-funded project: A high-content platform for cellular mechanobiology in cancer research (PI: Nikolaj Gadegaard, ~£200k, my ownership 30%).

- EPSRC-funded project: Closed-loop data science (PI: Roderick Murray-Smith,  total ~£3M, my ownership: 4%)) https://www.gla.ac.uk/schools/computing/research/researchsections/ida-section/closedloop/ 

 

 

Supervision

Prospective PhD Students: I am currently an Honorary Research Fellow and I am NOT accepting students at the University of Glasgow. I would encourage you to visit the School's PGR website to find other potential supervisors/projects.

 

I am currently co-supervising the following postgraduate research students at UofG:

  • Yanni Ji 2019- (PhD) funded by the CSC (with Dr Ke Yuan).
  • Ogechi Onuoha 2021- (PhD) (with Paul Siebert and Frank Pollick)
  • Charvet, Valentin
    Reinforcement Learning in Closed-loop data science
  • He, Zhuo
    Generalized Machine Learning with limited Training Data

Completed postgraduate research projects (PhD and MSc by research):

  • Anders Kirk Uhrenholt, 2017-2021 (primary supervisor), funded by the College of Science and Engineering. 
  • Marie F. Cutiongco, 2019, PhD (co-supervisor, Biomedical engineering, main supervisor: Nikolaj Gadegaard), Correlating single cell form and function under the influence of nanotopography.
  • Jasper Kirton-Wingate, October 2018-2019 (MSc by Research with Widex a/s)
  • Fatma A.I. Elsafoury, 2019, joint supervisor (with Simon Rogers and Chris Claassen), Measuring and Accounting for Spatial and Temporal Trends in Electoral Violence.

Teaching

Standard modules:

  • 2020-2021: Artificial Intelligence COMPSCI4004 H (Semester 1)
  • 2019-2020: Introduction to Data Science and System COMPSCI 5087 (M) (Semester 1), with Dr Jeff Dalton and Dr Nikos Ntarmos.
  • 2019-2020: Artificial Intelligence COMPSCI4004 / COMPCI5987 M/H (Semester 1)
  • 2018-2019: Artificial Intelligence COMPSCI4004 (Semester 2)
  • 2018-2019: Music Curation and Analysis (H) ARTMED4038 (Semester 1, three lectures), with Dr Tim Duguid
  • 2018-2019: Software Engineering (M) COMPSCI5059 (Semester 2), with Dr Ke Yuan
  • 2017-2018: Artificial Intelligence COMPSCI4004 (Semester 1)
  • 2017-2018: Software Engineering (M) COMPSCI5059 (Semester 2), with Dr Ke Yuan
  • 2016-2017: Artificial Intelligence COMPSCI4004 (Semester 1)

 

MSci projects (representative examples):

  • Variational Inference in Bayesian Inverse Reinforcement Learning, P.D., 2018-2019.
  • Machine learning for understanding human decision-making, P.C., 2017-2018.
  • Data-efficient reinforcement learning, G.R., 2017-2018.

 

MSc projects (representative examples):

  • Representation Learning with Sparse VAE for Single-Cell Images, A.R. 2020
  • Tangent propagation for environmental sound classification, B.H., 2020
  • Accelerating Image-Based Cell Profiling with Machine Learning, L.L, 2018 [best project award]
  • Perceptual Embeddings of Music Objects using Machine Learning, H. W., 2017
  • A toolbox for performance modelling and selection of dense neural network architectures, F. B., 2017

 

Honors projects (i.e. final year projects - representative examples)

  • Preference Elicitation for Music using Spoken Dialogue Systems, M.B, 2017-2018.
  • Hybrid Music Recommendation, A.G., 2017-2018
  • Interactive Machine Learning for Time Series Prediction, B.A., 2017-2018
  • Neural Networks for Dialogue Systems, Z.I, 2017-2018

 

Summer internships (representative examples):

  • Generative modelling and representation learning for audio, S.M., Summer 2019 (funded by SoCS)
  • Deep Learning for Image Analysis of Biological Cells, M.D., 2017

Additional information

Local activities (UofG)

  • 2016-2021 : Member of the Research Student Committee in the School of Computing Science.

 

Reviewer / programme committee:

  • I am a recurrent reviewer for NeurIPS (formerly NIPS), AISTATS, ICML, ICLR, UAI, MLSP, ICASSP, ICMI, IEEE Affective Computing.