Jacob Kamminga completed his Ph.D. in animal activity recognition at the University of Twente in 2020. He used machine learning models as activity classifiers to recognize various activities of animals using motion data on resource-constrained devices (edge-AI). Currently, he is studying active learning and human-in-the-loop AI training. Furthermore, he is interested in unsupervised representation learning to exploit unlabeled data. Other areas of his expertise are data acquisition, processing, and annotation. 

Since 2021 Jacob has been the digital species identification team leader within the ARISE biodiversity project. The digital species identification team builds services that support developing and deploying AI algorithms that detect and identify species from various digital media such as sound, images, and radar.

Expertise

  • Computer Science

    • Activity Recognition
    • Annotation
    • Classifier
    • Accuracy
    • Active Learning
  • Earth and Planetary Sciences

    • State of the Art
    • Recognition
    • Detection

Organisations

Publications

2024

M-MOVE-IT: Multimodal Machine Observation and Video-Enhanced Integration Tool for Data Annotation (2024)In UbiComp Companion 2024 - Companion of the 2024 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 911-915). Association for Computing Machinery. Kamminga, J., van der Duim, R. & ten Hove, E.https://doi.org/10.1145/3675094.3678479COOD: Combined out-of-distribution detection using multiple measures for anomaly & novel class detection in large-scale hierarchical classification (2024)In Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 (pp. 3971-3980) (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE. Hogeweg, L. E., Gangireddy, R., Brunink, D., Kalkman, V. J., Cornelissen, L. & Kamminga, J. W.https://doi.org/10.1109/CVPRW63382.2024.00401COOD: Combined out-of-distribution detection using multiple measures for anomaly & novel class detection in large-scale hierarchical classification (2024)[Working paper › Preprint]. ArXiv.org. Hogeweg, L., Gangireddy, R., Brunink, D., Kalkman, V., Cornelissen, L. & Kamminga, J. W.https://doi.org/10.48550/arXiv.2403.06874M-MOVE-IT: Multimodal Machine Observation and Video-Enhanced Integration Tool for Data Annotation (2024)[Non-textual form › Software]. GitHub. Kamminga, J. W.https://github.com/AI-Sensus/M-MOVE-IT

2022

ARISE: Building an infrastructure for species recognition and biodiversity monitoring in the Netherlands (2022)[Contribution to conference › Abstract] Biodiversity Information Standards, TDWG 2022. van Ommen Kloeke, E., Huijbers, C., Beentjes, K., Kamminga, J. W., Bakker, P. A. J. & Kissling, W. D.https://doi.org/10.3897/biss.6.93613Improving the Annotation Efficiency for Animal Activity Recognition using Active Learning (2022)In Measuring Behavior 2022: 12th International Conference on Methods and Techniques in Behavioral Research, and 6th Seminar on Behavioral Methods (pp. 51-58). Spink, S., Kamminga, J. W. & Kamilaris, A.https://doi.org/10.6084/m9.figshare.20066849

2020

Hiding in the Deep: Online Animal Activity Recognition using Motion Sensors and Machine Learning (2020)[Thesis › PhD Thesis - Research UT, graduation UT]. University of Twente. Kamminga, J. W.https://doi.org/10.3990/1.9789036550550Towards Deep Unsupervised Representation Learning from Accelerometer Time Series for Animal Activity Recognition (2020)[Contribution to conference › Paper] 6th Workshop on Mining and Learning from Time Series, MiLeTS 2020. Kamminga, J. W., Meratnia, N., Le, D. V. & Havinga, P. J. M.

Research profiles

Courses academic year 2024/2025

Courses in the current academic year are added at the moment they are finalised in the Osiris system. Therefore it is possible that the list is not yet complete for the whole academic year.

Courses academic year 2023/2024

Address

University of Twente

Zilverling (building no. 11)
Hallenweg 19
7522 NH Enschede
Netherlands

Navigate to location

Organisations

Scan the QR code or
Download vCard