检索结果-内蒙古大学图书馆

Emotion Recognition Using EEG Signals in Human Brain Waves and Deep Learning Approaches

Emotion Recognition Using EEG Signals in Human Brain Waves a...

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Sakorn Mekruksavanich Narit Hnoohom Wikanda Phaphan Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Thailand Department of Computer Engineering Faculty of Engineering Image Information and Intelligence Laboratory Mahidol University Nakhon Pathom Thailand Department of Applied Statistics Faculty of Applied Science Research Group in Statistical Learning and Inference King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

Emotion recognition using EEG signals has gained growing attention in recent years due to its promising applications in human-computer interaction, affective computing, and mental health assessment. This study investigates the performance of various deep learning architectures in classifying emotional states from EEG recordings. We utilize the Emotion EEG dataset as a benchmark and evaluate five prominent deep learning models. The classification task targets three emotion categories: neu-tral, positive, and negative. Experimental results reveal notable differences in model performance. Among the tested models, BiGRU achieves the highest classification accuracy of 97.70% (±0.69%), followed closely by BiLSTM with 97.37% (±0.17%). These bidirectional architectures significantly outperform the CNN model, which attains an accuracy of only 61.59% (±1.22%). The LSTM and GRU models yield intermediate results, nearing 92% accuracy. The findings highlight the effectiveness of bidirectional recurrent neural networks in modeling the temporal characteristics of EEG signals for emotion detection. This research contributes to advancing EEG-based emotion recognition by identifying the most suitable deep learning strategies, thus supporting the development of more intelligent and emotion-aware computing systems.

关键词： Deep learning Emotion recognition Accuracy Computational modeling Bidirectional long short term memory Mental health computer architecture Brain modeling Electroencephalography Recording

来源：评论

学校读者我要写书评

暂无评论

Orthopedic Walker Fall Detection and Motion Classification Using Bidirectional Gated Recurrent Unit Neural Network 10

Orthopedic Walker Fall Detection and Motion Classification U...

引用

10th International Conference on Digital Arts, Media and Technology and 8th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2025

作者： Mekruksavanich, Sakorn Hnoohom, Narit Phaphan, Wikanda Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Research Group in Statistical Learning and Inference Department of Applied Statistics Faculty of Applied Science Bangkok Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798331543273

Accurate fall detection for orthopedic walker users is essential for timely medical intervention and enhancing safety for elderly and mobility-impaired individuals. This paper introduces a new method using a bidirectional gated recurrent unit (BiGRU) neural network to detect falls and classify motion patterns in walker usage. We use the Walker dataset, which includes inertial measurement unit sensor data for four motion classes: idle, motion, step, and fall. The dataset consists of 6-axis IMU readings (3-axis accelerometer and 3-axis gyroscope) from sensors mounted on orthopedic walkers, with around 620 samples per class. Our BiGRU model leverages temporal dependencies in both forward and backward directions to improve classification accuracy. We assess the model's performance in two scenarios: binary classification (fall vs. non-fall) and multi-class classification of all four motion types. The proposed architecture shows strong performance, achieving 99.79% accuracy and a 99.73% F1-score in binary classification, and 98.51% accuracy and a 98.50% F1-score in multi-class classification. It outperforms traditional deep learning models like CNN, LSTM, and GRU. The experimental results confirm the effectiveness of bidirectional processing in capturing temporal motion patterns, indicating significant potential for realtime fall detection in walker-assisted mobility. The high precision and recall values in both scenarios demonstrate the model's reliability for practical healthcare monitoring applications. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

引用

International Journal of computer Vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Validation Methods for Sensor-Based Human Activity Recognition Using Deep Learning Models 10

A Comparative Study of Validation Methods for Sensor-Based H...

引用

作者： Mekruksavanich, Sakorn Hnoohom, Narit Phaphan, Wikanda Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Research Group in Statistical Learning and Inference Department of Applied Statistics Faculty of Applied Science Bangkok Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798331543273

With the rise of wearable sensors and smart devices, human activity recognition (HAR) has become a vital research area in ubiquitous computing. Although many studies report high accuracy using k-fold cross-validation, these results often do not reflect actual generalization interpretation due to subject-dependent data leakage, where models test on activities from the subjects they were trained. This study compares traditional k-fold cross-validation with leave-one-subject-out (LOSO) validation using the WISDM dataset, highlighting the importance of proper validation techniques in HAR systems. We implemented and evaluated five advanced deep learning models - convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU) - on windowed raw sensor data. Our experiments showed significant differences between validation methods. The BiGRU model achieved 97.91% accuracy with k-fold cross-validation and 98.02% with LOSO validation, while the CNN model achieved only 92.55% and 93.44%, respectively. These results underscore the impact of both model architecture and validation approach on performance. Our findings stress the need for subject-independent validation strategies like LOSO to develop truly generalizable HAR systems. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CLCFE: complementary loss coupling for feature-enhanced few-shot fine-grained visual recognition

引用

Applied Intelligence 2025年第10期55卷 1-21页

作者： Wu, Heng Zheng, Zijun Lv, Laishui Zhang, Changchun Xu, Yifeng Bardou, Dalal Niu, Shanzhou Yu, Gaohang College of Information Engineering Hangzhou Vocational & Technical College Hangzhou China College of Education Ludong University Yantai China College of Sciences China Jiliang University Hangzhou China College of Information Engineering China Jiliang University Hangzhou China School of Technology Beijing Forestry University Beijing China State Key Laboratory of Efficient Production of Forest Resources Beijing China Research Center for Biodiversity Intelligent Monitoring Beijing Forestry University Beijing China ICOSI Laboratory Department of Computer Science and Mathematics University of Abbes Laghrour Khenchela Algeria School of Mathematics and Computer Science Gannan Normal University Ganzhou China School of Science Zhejiang University of Science and Technology Hangzhou China

Few-shot learning aims to generate a classifier capable of identifying novel concepts with limited instances. While most existing approaches in this field focus on general object recognition, the ability to quickly identify novel concepts with subtle differences using scarce annotation is crucial for perceptual understanding in real-world scenarios. To address this issue, the paper presents a Complementary Loss Coupling for Feature-Enhanced (CLCFE) few-shot fine-grained visual recognition. In this approach, a dual-stream attention module is utilized to enhance the embedded features extracted from the query and support images. This module builds global contextual relations by incorporating structural and semantic information. Additionally, a complementary loss coupling module is designed to obtain intensified discriminative prototypes, through mining fine-grained differences among inter-class features and exploring the correlation among intra-class features. To validate the effectiveness of the proposed modules, interpretable visualizations and detailed ablations are conducted. Comparative experiments demonstrate that the CLCFE approach outperforms the previous models by a large margin in 4 few-shot fine-grained benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Adaptation for Deep Learning-based Wireless Communications

arXiv

引用

arXiv 2024年

作者： Wang, Ouya He, Hengtao Zhou, Shenglong Ding, Zhi Jin, Shi Letaief, Khaled B. Li, Geoffrey Ye The ITP Lab Department of Electrical and Electronic Engineering Imperial College London United Kingdom The School of Mathematics and Statistics Beijing Jiaotong University Beijing China The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The Department of Electrical and Computer Engineering University of California Davis United States The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

The integration with artificial intelligence (AI) is recognized as one of the six usage scenarios in next-generation wireless communications. However, several critical challenges hinder the widespread application of deep learning (DL) techniques in wireless communications. In particular, existing DL-based wireless communications struggle to adapt to the rapidly changing wireless environments. In this paper, we discuss fast adaptation for DL-based wireless communications by using few-shot learning (FSL) techniques. We first identify the differences between fast adaptation in wireless communications and traditional AI tasks by highlighting two distinct FSL design requirements for wireless communications. To establish a wide perspective, we present a comprehensive review of the existing FSL techniques in wireless communications that satisfy these two design requirements. In particular, we emphasize the importance of applying domain knowledge in achieving fast adaptation. We specifically focus on multiuser multiple-input multiple-output (MU-MIMO) precoding as an examples to demonstrate the advantages of the FSL to achieve fast adaptation in wireless communications. Finally, we highlight several open research issues for achieving broadscope future deployment of fast adaptive DL in wireless communication applications. © 2024, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Using EEG Signals in Human Brain Waves and Deep Learning Approaches 10

Emotion Recognition Using EEG Signals in Human Brain Waves a...

引用

ISBN: (纸本)9798331543273

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Validation Methods for Sensor-Based Human Activity Recognition Using Deep Learning Models

A Comparative Study of Validation Methods for Sensor-Based H...

引用

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Sakorn Mekruksavanich Narit Hnoohom Wikanda Phaphan Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Computer Engineering Faculty of Engineering Image Information and Intelligence Laboratory Mahidol University Nakhon Pathom Thailand Department of Applied Statistics Faculty of Applied Science Research Group in Statistical Learning and Inference King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

With the rise of wearable sensors and smart devices, human activity recognition (HAR) has become a vital research area in ubiquitous computing. Although many studies report high accuracy using k-fold cross-validation, these results often do not reflect actual generalization interpretation due to subject-dependent data leakage, where models test on activities from the subjects they were trained. This study compares traditional k-fold cross-validation with leave-one-subject-out (LOSO) validation using the WISDM dataset, highlighting the importance of proper validation techniques in HAR systems. We implemented and evaluated five advanced deep learning models – convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU) – on windowed raw sensor data. Our experiments showed significant differences between validation methods. The BiGRU model achieved 97.91% accuracy with k-fold cross-validation and 98.02% with LOSO validation, while the CNN model achieved only 92.55% and 93.44%, respectively. These results underscore the impact of both model architecture and validation approach on performance. Our findings stress the need for subject-independent validation strategies like LOSO to develop truly generalizable HAR systems.

关键词： Deep learning Accuracy Bidirectional long short term memory Ubiquitous computing Data models Human activity recognition Convolutional neural networks Smart devices Wearable sensors Stress

来源：评论

学校读者我要写书评

暂无评论

SAFL: Structure-Aware Personalized Federated Learning via Client-Specific Clustering and SCSI-Guided Model Pruning

arXiv

引用

arXiv 2025年

作者： Li, Nan Wang, Xiaolu Du, Xiao Cai, Puyu Wang, Ting Engineering Research Center of Software/Hardware Co-Design Technology and Application Ministry of Education the Shangh ai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China Software Engineering Institute East China Normal University Shanghai200050 China Computer Science Department New York University New YorkNY10012 United States

Federated Learning (FL) enables clients to collaboratively train machine learning models without sharing local data, preserving privacy in diverse environments. While traditional FL approaches preserve privacy, they often struggle with high computational and communication overhead. To address these issues, model pruning is introduced as a strategy to streamline computations. However, existing pruning methods, when applied solely based on local data, often produce sub-models that inadequately reflect clients’ specific tasks due to data insufficiency. To overcome these challenges, this paper introduces SAFL (Structure-Aware Federated Learning), a novel framework that enhances personalized federated learning through client-specific clustering and Similar Client Structure Information (SCSI)-guided model pruning. SAFL employs a two-stage process: initially, it groups clients based on data similarities and uses aggregated pruning criteria to guide the pruning process, facilitating the identification of optimal sub-models. Subsequently, clients train these pruned models and engage in server-based aggregation, ensuring tailored and efficient models for each client. This method significantly reduces computational overhead while improving inference accuracy. Extensive experiments demonstrate that SAFL markedly diminishes model size and improves performance, making it highly effective in federated environments characterized by heterogeneous data. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Sleep Control in 5G and Beyond Radio Access Networks: An Overview

Deep Reinforcement Learning for Sleep Control in 5G and Beyo...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Nessrine Trabelsi Rihab Maaloul Lamia Chaari Fourati Wael Jaafar Laboratory of Signals systeMs aRtificial intelligence and neTworkS – Digital Research Center of Sfax Sfax Tunisia Higher Institute of Computer Science of Mahdia (ISIMa) University of Monastir Tunisia Higher Institute of Computer Science and Multimedia in Sfax (ISIMS) University of Sfax Tunisia Department of Software and IT Engineering École de technologies supérieure (ÉTS) Montreal Canada

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

The advent of 5G and beyond networks is envisioned to support lower latency, higher data rates, and wider connectivity than previous cellular network generations. However, given the denser deployment of base stations (BSs) to accommodate such improvements, this results inevitably in a significant and unsustainable increase in the network’s energy consumption. Sleep Control (SC), which allows switching off some BS hardware components during light-traffic time, is considered a viable solution for greener and more energy-efficient Radio Access Networks (RAN). However, the optimization of SC is a highly challenging large-scale network combinatorial problem that depends on dynamic wireless channel conditions and varying traffic demands with stringent Quality-of-Service (QoS) requirements. Driven by the benefits and efficiency of Deep Reinforcement Learning (DRL), which has been successfully applied to multiple wireless network optimization problems, this paper investigates DRL approaches addressing sleep control in 5G and beyond RAN. To this end, we propose a taxonomy to classify the related literature. Then, we provide an overview of the different components of the Markov Decision Process (MDP) modeling the sequential decision-making of sleep control and the applied DRL algorithms. Finally, we highlight the main challenges in existing works and suggest novel strategies to address them.

关键词： 5G mobile communication Wireless networks Taxonomy Decision making Quality of service Switches Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：