Optimal sensor channel selection for resource-efficient deep activity recognition

dc.contributorAalto Universityen
dc.contributor.authorLeite, Clayton Frederick Souzaen_US
dc.contributor.authorXiao, Yuen_US
dc.contributor.departmentMobile Cloud Computingen_US
dc.contributor.departmentDepartment of Communications and Networkingen_US
dc.descriptionFunding Information: This work was funded by Business Finland (grant number: 1573/31/2020). Publisher Copyright: © 2021 ACM.
dc.description.abstractDeep learning has permitted unprecedented performance in sensor-based human activity recognition (HAR). However, deep learning models often present high computational overheads, which poses challenges to their implementation on resource-constraint devices such as microcontrollers. Usually, the computational overhead increases with the input size. One way to reduce the input size is by constraining the number of sensor channels. We refer to sensor channel as a specific data modality (e.g. accelerometer) placed on a specific body location (e.g. chest). Identifying and removing irrelevant and redundant sensor channels is feasible via exhaustive search only in cases where few candidates exist. In this paper, we propose a smarter and more efficient way to optimize the sensor channel selection during the training of deep neural networks for HAR. Firstly, we propose a light-weight deep neural network architecture that learns to minimize the use of redundant and irrelevant information in the classification task, while achieving high performance. Secondly, we propose a sensor channel selection algorithm that utilizes the knowledge learned by the neural network to rank the sensor channels by their contribution to the classification task. The neural network is then trimmed by removing the sensor channels with the least contribution from the input and pruning the corresponding weights involved in processing them. The pipeline that consists of the above two steps iterates until the optimal set of sensor channels has been found to balance the trade-off between resource consumption and classification performance. Compared with other selection methods in the literature, experiments on 5 public datasets showed that our proposal achieved significantly higher F1-scores at the same time as utilizing from 76% to 93% less memory, with up to 75% faster inference time and as far as 76% lower energy consumption.en
dc.description.versionPeer revieweden
dc.identifier.citationLeite , C F S & Xiao , Y 2021 , Optimal sensor channel selection for resource-efficient deep activity recognition . in Proceedings of the 20th International Conference on Information Processing in Sensor Networks, IPSN 2021 . , 3458278 , ACM , pp. 371-383 , International Conference on Information Processing in Sensor Networks , Virtual, Online , United States , 18/05/2021 . https://doi.org/10.1145/3412382.3458278en
dc.identifier.otherPURE UUID: b5a5725e-6684-4140-9546-1e8c5f22e695en_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/b5a5725e-6684-4140-9546-1e8c5f22e695en_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85106472709&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/64950790/ELEC_Souza_Leite_Xiao_Optimal_Sensor_Channel_IPSN_2021_acceptedauthormanuscript.pdfen_US
dc.relation.ispartofInternational Conference on Information Processing in Sensor Networksen
dc.relation.ispartofseriesProceedings of the 20th International Conference on Information Processing in Sensor Networks, IPSN 2021en
dc.subject.keyworddeep learningen_US
dc.subject.keywordhuman activity recognitionen_US
dc.subject.keywordSensor channel selectionen_US
dc.titleOptimal sensor channel selection for resource-efficient deep activity recognitionen
dc.typeConference article in proceedingsfi