Related references
Note: Only part of the references are listed.
Article
Automation & Control Systems
Yin Tang et al.
Summary: This article proposes a new CNN that uses a hierarchical-split idea to enhance multiscale feature representation ability in wearable human activity recognition. The experiments demonstrate that the proposed method outperforms baseline models and achieves higher recognition performance without increasing resource consumption. Ablation studies are conducted to evaluate the effect of receptive field variations on classification performance, and it is shown that multiscale receptive fields can help learn discriminative features.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Review
Chemistry, Analytical
Shibo Zhang et al.
Summary: The development of mobile and wearable devices has enabled various applications that measure and improve our daily lives, such as activity tracking, wellness monitoring, and human-computer interaction. Many of these applications rely on low-power sensors in these devices to perform human activity recognition (HAR). In recent years, deep learning has made significant advancements in HAR on mobile and wearable devices. This paper categorizes and summarizes existing work on deep learning methods for wearables-based HAR, and provides an analysis of the current advancements, developing trends, and major challenges. The paper also presents cutting-edge frontiers and future directions for deep learning-based HAR.
Article
Computer Science, Artificial Intelligence
Zhengyang Feng et al.
Summary: Recent semi-supervised learning methods have used pseudo supervision, particularly self-training methods, which generate unreliable pseudo labels. This paper proposes a new approach called Dynamic Mutual Training (DMT) that leverages inter-model disagreement to locate pseudo label errors and achieve state-of-the-art performance in image classification and semantic segmentation.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Mohamed Abdel-Basset et al.
Summary: With the development of wireless sensing technology, the Internet of Things (IoT) has been widely applied in various fields. Human activity recognition (HAR) is an important component in intelligent systems for continuous monitoring of human behaviors. In this research, smartphone inertial sensors are used as a case study, and HAR is treated as an image classification problem. A lightweight model called multiscale image-encoded HHAR (MS-IE-HHAR) is proposed and achieves high accuracy in modeling HAR from heterogeneous data sources.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Hardware & Architecture
Wenbo Huang et al.
ACM Transactions on Embedded Computing Systems
(2022)
Article
Computer Science, Artificial Intelligence
Chaolei Han et al.
Summary: This research focuses on enhancing the application of vanilla convolution in human activity recognition without adjusting the model architectures. Inspired by grouped convolution, a novel heterogeneous convolution is proposed to augment the receptive field of sensor signals for activity recognition. Experimental results demonstrate significant improvements in the performance of sensor-based activity recognition models.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Shenghuan Miao et al.
Summary: This paper proposes a lightweight and efficient GCN-based framework called DynamicWHAR for automatically learning the dynamic correlations between sensors in multi-sensor-based wearable human activity recognition. It models the feature extraction and information interaction between sensors, and extensive experiments validate its superior recognition performance and computational complexity compared to existing models.
PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT
(2022)
Article
Computer Science, Artificial Intelligence
Yin Tang et al.
Summary: Efficiently identifying activities of daily living (ADL) is crucial for improving sports tracking and healthcare applications. Existing attention mechanisms in sensor-based human activity recognition (HAR) have achieved remarkable performance, but they overlook the cross-interaction between different dimensions. This paper proposes a triplet cross-dimension attention method that captures the interaction between sensor dimension, temporal dimension, and channel dimension, leading to improved classification performance.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Yinan Guo et al.
Summary: A dual-ensemble class imbalance learning method is proposed in this research, which uses multimodal evolutionary algorithms to find the optimal combination, providing the simplest ensemble structure and best accuracy in imbalanced data.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Zhengyang Feng et al.
Summary: This paper points out that leveraging inter-model disagreement between different models is key to locating pseudo label errors. By proposing Dynamic Mutual Training (DMT) with a dynamically re-weighted loss function, state-of-the-art performance has been achieved in tasks like image classification and semantic segmentation.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Wesllen Sousa Lima et al.
Summary: This paper introduces a novel algorithm NOHAR for human activity recognition, focusing on continuous data analysis and using symbolic data for online classification. A new framework called DISTAR is proposed to standardize online algorithms for symbolic data. Experimental results show that NOHAR is 33 times faster than the state of the art and can reduce memory consumption by 99.97%.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Wenbo Huang et al.
Summary: This paper explores the use of shallow convolutional neural networks with channel-selectivity for sensor based human activity recognition tasks. Experimental results show that channel-selectivity CNN can achieve lower test errors than traditional static layers, improving the performance of deep HAR without additional costs.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Kun Wang et al.
Summary: The article introduces a recurrent attention network for handling sequential weakly labeled multiactivity recognition and location tasks, effectively inferring multiple activity types and determining specific locations of each target activity, as well as reducing the burden of manual labeling.
IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS
(2021)
Proceedings Paper
Acoustics
Haoyi Fan et al.
Summary: By proposing a method called SemiTime, this work effectively utilizes unlabeled data to capture useful representations of unlabeled time series data, outperforming state-of-the-art methods in various real-world datasets.
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)
(2021)
Article
Computer Science, Theory & Methods
Fuqiang Gu et al.
Summary: This study provides a comprehensive survey on recent advances and challenges in human activity recognition (HAR) with deep learning, highlighting the lack of in-depth research on deep learning methods in HAR.
ACM COMPUTING SURVEYS
(2021)
Article
Computer Science, Artificial Intelligence
Kaixuan Chen et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2020)
Review
Computer Science, Artificial Intelligence
Yan Wang et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2019)
Article
Computer Science, Artificial Intelligence
Haishuai Wang et al.
PATTERN RECOGNITION
(2019)
Review
Computer Science, Artificial Intelligence
Henry Friday Nweke et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Chihiro Ito et al.
PROCEEDINGS OF THE 2018 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2018 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS (UBICOMP/ISWC'18 ADJUNCT)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuta Yuki et al.
PROCEEDINGS OF THE 2018 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2018 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS (UBICOMP/ISWC'18 ADJUNCT)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Shoya Ishimaru et al.
PROCEEDINGS OF THE 2017 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2017 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS (UBICOMP/ISWC '17 ADJUNCT)
(2017)
Article
Chemistry, Analytical
Francisco Javier Ordonez et al.