Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery

Dingrong Wang, Deep Shankar Pandey, Krishna Prasad Neupane, Zhiwei Yu, Ervine Zheng, Zhi Zheng, Qi Yu
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36205-36223, 2023.

Abstract

Machine learning-driven human behavior analysis is gaining attention in behavioral/mental healthcare, due to its potential to identify behavioral patterns that cannot be recognized by traditional assessments. Real-life applications, such as digital behavioral biomarker identification, often require the discovery of complex spatiotemporal patterns in multimodal data, which is largely under-explored. To fill this gap, we propose a novel model that integrates uniquely designed Deep Temporal Sets (DTS) with Evidential Reinforced Attentions (ERA). DTS captures complex temporal relationships in the input and generates a set-based representation, while ERA captures the policy network’s uncertainty and conducts evidence-aware exploration to locate attentive regions in behavioral data. Using child-computer interaction data as a testing platform, we demonstrate the effectiveness of DTS-ERA in differentiating children with Autism Spectrum Disorder and typically developing children based on sequential multimodal visual and touch behaviors. Comparisons with baseline methods show that our model achieves superior performance and has the potential to provide objective, quantitative, and precise analysis of complex human behaviors.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-wang23ab, title = {Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery}, author = {Wang, Dingrong and Pandey, Deep Shankar and Neupane, Krishna Prasad and Yu, Zhiwei and Zheng, Ervine and Zheng, Zhi and Yu, Qi}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {36205--36223}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/wang23ab/wang23ab.pdf}, url = {https://proceedings.mlr.press/v202/wang23ab.html}, abstract = {Machine learning-driven human behavior analysis is gaining attention in behavioral/mental healthcare, due to its potential to identify behavioral patterns that cannot be recognized by traditional assessments. Real-life applications, such as digital behavioral biomarker identification, often require the discovery of complex spatiotemporal patterns in multimodal data, which is largely under-explored. To fill this gap, we propose a novel model that integrates uniquely designed Deep Temporal Sets (DTS) with Evidential Reinforced Attentions (ERA). DTS captures complex temporal relationships in the input and generates a set-based representation, while ERA captures the policy network’s uncertainty and conducts evidence-aware exploration to locate attentive regions in behavioral data. Using child-computer interaction data as a testing platform, we demonstrate the effectiveness of DTS-ERA in differentiating children with Autism Spectrum Disorder and typically developing children based on sequential multimodal visual and touch behaviors. Comparisons with baseline methods show that our model achieves superior performance and has the potential to provide objective, quantitative, and precise analysis of complex human behaviors.} }
Endnote
%0 Conference Paper %T Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery %A Dingrong Wang %A Deep Shankar Pandey %A Krishna Prasad Neupane %A Zhiwei Yu %A Ervine Zheng %A Zhi Zheng %A Qi Yu %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-wang23ab %I PMLR %P 36205--36223 %U https://proceedings.mlr.press/v202/wang23ab.html %V 202 %X Machine learning-driven human behavior analysis is gaining attention in behavioral/mental healthcare, due to its potential to identify behavioral patterns that cannot be recognized by traditional assessments. Real-life applications, such as digital behavioral biomarker identification, often require the discovery of complex spatiotemporal patterns in multimodal data, which is largely under-explored. To fill this gap, we propose a novel model that integrates uniquely designed Deep Temporal Sets (DTS) with Evidential Reinforced Attentions (ERA). DTS captures complex temporal relationships in the input and generates a set-based representation, while ERA captures the policy network’s uncertainty and conducts evidence-aware exploration to locate attentive regions in behavioral data. Using child-computer interaction data as a testing platform, we demonstrate the effectiveness of DTS-ERA in differentiating children with Autism Spectrum Disorder and typically developing children based on sequential multimodal visual and touch behaviors. Comparisons with baseline methods show that our model achieves superior performance and has the potential to provide objective, quantitative, and precise analysis of complex human behaviors.
APA
Wang, D., Pandey, D.S., Neupane, K.P., Yu, Z., Zheng, E., Zheng, Z. & Yu, Q.. (2023). Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:36205-36223 Available from https://proceedings.mlr.press/v202/wang23ab.html.

Related Material