Related references
Note: Only part of the references are listed.
Article
Engineering, Electrical & Electronic
Shu Shen et al.
Summary: As a promising technology in HCI, deep learning shows good potential for gesture recognition using sEMG signals. However, existing complex network structures cannot be deployed on edge devices. Lightweight neural networks face challenges in achieving both accuracy and limited computing power. To address this, we propose a flexible and modular method based on sEMG and acceleration signals for gesture recognition. With the improved channel attention mechanism, the lightweight ICA-CNN achieves satisfactory performance in accuracy and inference speed. Experimental results demonstrate a recognition accuracy of 94.24% for 49 gestures using sEMG and acceleration signals, higher than using sEMG signals alone. Additionally, a single inference of the proposed method takes only 38.6 ms on the CPU.
IEEE SENSORS JOURNAL
(2023)
Article
Computer Science, Information Systems
Swardiantara Silalahi et al.
Summary: The increase in drone usage has led to a rise in drone incidents and attacks, necessitating the development of preventive measures and post-incident procedures. While previous research has focused on framework proposal, case studies, and tool evaluation, there is a lack of research on utilizing specific data artifacts from drone forensic images. This study proposes using a deep learning-based NLP technique, named entity recognition (NER), to extract incident-related information from log message data. The proposed method outperforms previous baseline models with a 91.348% F1 score.
Article
Computer Science, Information Systems
Jing Chi et al.
Summary: A lightweight image recognition model, L-GhostNet, based on improved GhostNet, is proposed to address the problems of extensive computation and high storage cost of deep convolutional neural networks. The model incorporates learning group convolution and improved CA into GhostNet to reduce calculation and parameters, and improve network flexibility. Experimental results show that compared to GhostNet, L-GhostNet has slightly improved accuracy, reduced computation by more than 44%, decreased the number of parameters by more than 33%, and improved FPS by 26% on various datasets.
Article
Thermodynamics
Zhizhong Xing et al.
Summary: In this study, we propose a method for segmenting the point cloud of coal mining face (CMF) based on the advanced dynamic graph convolution neural network (DGCNN) in harsh environments and obtaining the information of the coal cutting roof line. The results show that the multi-level and series pooling DGCNN (ML & SP-DGCNN) performs the best. The coal cutting roof line obtained by segmenting the CMF point cloud provides a crucial basis for dynamically correcting the underground geological model and straightening the CMF, and the established CMF point cloud segmentation model lays a foundation for perceiving the underground environment and achieving sustainable green production of coal resources.
Article
Computer Science, Information Systems
Hongsheng Xu et al.
Summary: To ensure the security of computer systems and networks, designing and implementing intrusion detection systems that can identify and mitigate network attacks and threats is crucial. Deep learning has significant advantages in processing complex, high-dimensional, and large-scale traffic data, thus leading to better detection results in intrusion detection systems.
Article
Physics, Multidisciplinary
Ching-Hsun Tseng et al.
Summary: This work proposes an efficient and robust backbone, UPANets, which utilizes channel and spatial direction attentions to expand the receptive fields in shallow convolutional layers. Experimental results show that UPANets achieve better performance with fewer resources on CIFAR-{10, 100} than existing state-of-the-art methods.
Proceedings Paper
Acoustics
Jun Chen et al.
Summary: This paper proposes an extended single-channel real-time speech enhancement framework called FullSubNet+, with improvements including a lightweight multi-scale time sensitive channel attention module, utilizing phase information, and a more efficient full-band module.
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2022)
Article
Computer Science, Artificial Intelligence
Ramprasaath R. Selvaraju et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Article
Computer Science, Interdisciplinary Applications
Abhijit Guha Roy et al.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2019)
Article
Computer Science, Artificial Intelligence
Liang-Chieh Chen et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Dongyoon Han et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Computer Science, Hardware & Architecture
Alex Krizhevsky et al.
COMMUNICATIONS OF THE ACM
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Jifeng Dai et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Francois Chollet
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Computer Science, Artificial Intelligence
Antonio Torralba et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2008)
Review
Neurosciences
M Corbetta et al.
NATURE REVIEWS NEUROSCIENCE
(2002)