دورية أكاديمية

DTCM: Deep Transformer Capsule Mutual Distillation for Multivariate Time Series Classification

التفاصيل البيبلوغرافية
العنوان: DTCM: Deep Transformer Capsule Mutual Distillation for Multivariate Time Series Classification
المؤلفون: Xiao, Zhiwen, Xu, Xin, Xing, Huanlai, Zhao, Bowen, Wang, Xinhan, Song, Fuhong, Qu, Rong, Feng, Li
بيانات النشر: Institute of Electrical and Electronics Engineers
سنة النشر: 2024
المجموعة: University of Nottingham: Repository@Nottingham
مصطلحات موضوعية: Feature extraction, Classification algorithms, Time series analysis, Data mining, Transformers, Routing, Knowledge transfer, Capsule Network, Deep Learning, Knowledge Distillation, Multivariate Time Series Classification, Mutual L
الوصف: This paper proposes a dual-network-based feature extractor, perceptive capsule network (PCapN), for multivariate time series classification (MTSC), including a local feature network (LFN) and a global relation network (GRN). The LFN has two heads (i.e., Head_A and Head_B), each containing two squash CNN blocks and one dynamic routing block to extract the local features from the data and mine the connections among them. The GRN consists of two capsule-based transformer blocks and one dynamic routing block to capture the global patterns of each variable and correlate the useful information of multiple variables. Unfortunately, it is difficult to directly deploy PCapN on mobile devices due to its strict requirement for computing resources. So, this paper designs a lightweight capsule network (LCapN) to mimic the cumbersome PCapN. To promote knowledge transfer from PCapN to LCapN, this paper proposes a deep transformer capsule mutual (DTCM) distillation method. It is targeted and offline, using one- and two-way operations to supervise the knowledge distillation process for the dual-network-based student and teacher models. Experimental results show that the proposed PCapN and DTCM achieve excellent performance on UEA2018 datasets regarding top-1 accuracy.
نوع الوثيقة: article in journal/newspaper
اللغة: unknown
تدمد: 2379-8920
العلاقة: https://nottingham-repository.worktribe.com/output/32450554Test; IEEE Transactions on Cognitive and Developmental Systems; https://nottingham-repository.worktribe.com/file/32450554/1/TCDS24-HuanlaiTest
DOI: 10.1109/tcds.2024.3370219
الإتاحة: https://doi.org/10.1109/tcds.2024.3370219Test
https://nottingham-repository.worktribe.com/file/32450554/1/TCDS24-HuanlaiTest
https://nottingham-repository.worktribe.com/output/32450554Test
حقوق: openAccess
رقم الانضمام: edsbas.31715B52
قاعدة البيانات: BASE
الوصف
تدمد:23798920
DOI:10.1109/tcds.2024.3370219