检索结果-内蒙古大学图书馆

Enhancing EEG-Based Cross-Subject Emotion Recognition via Adaptive Source Joint Domain Adaptation

IEEE Transactions on Affective computing 2024年

作者： Liu, Ke Luo, Xin Zhu, Wenrui Yu, Zhuliang Yu, Hong Xiao, Bin Wu, Wei Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Chongqing University of Posts and Telecommunications Key Laboratory of Big Data Intelligent Computing China South China University of Technology College of Automation Science and Engineering Guangzhou510641 China Shanghai Jiao Tong University School of Medicine Department of Neurology Songjjiang Hospital and Songjiang Research Institute Shanghai Key Laboratory of Emotions and Affective Disorders Shanghai201600 China

EEG emotion recognition is crucial in both human-machine interaction and healthcare. However, recognizing emotions across different subjects remains challenging due to individual variability. While existing multi-source domain adaptation methods have been utilized for cross-subject EEG emotion decoding, they often struggle with irrelevant or weakly relevant source domains, leading to negative transfer. Additionally, variations within subdomains are often neglected in these studies. We propose a joint domain adaptation method, Adaptive Source Joint Domain Adaptation (ASJDA) to address these issues. ASJDA utilizes an unsupervised adaptive source selection strategy to select a subset of source domains by evaluating the Jensen-Shannon divergence between the source and target domains, choosing those most relevant to the target. Subsequently, it implements joint domain adaptation with these chosen sources at both the domain and category subdomain levels. Our proposed method outperforms existing state-of-the-art methods, achieving cross-subject accuracies of 96.81% in SEED, 89.69% in SEED-IV, and 69.31% in DEAP. This work significantly advances the state of the art in EEG emotion recognition by effectively addressing the challenges of cross-subject variability. The source code for ASJDA is available at https://***/Pam098/ASJDA. © 2010-2012 IEEE.

关键词： adaptive source selection cross-subject domain adaptation EEG emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Free-space Continuous-variable Quantum Secret Sharing

arXiv

引用

arXiv 2025年

作者： Yang, Fangli Chang, Liang Qiu, Daowen Pan, Minghua Xiong, Wanjun Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin541004 China

Free-space quantum cryptography has the potential to enable global quantum communication. However, most existing continuous-variable quantum secret sharing (CV-QSS) schemes rely on fiber channels. In this paper, we present a CV-QSS protocol designed for free-space transmission and construct models of crucial parameters, including channel transmittance, excess noise, and interruption probability, thus deriving the bound of the secret key rate. In particular, we provide a multi-source excess noise model for free-space CV-QSS based on the local local oscillator (LLO) scheme and a straightforward optimization of the noise. Furthermore, our research considers the impact of atmospheric turbulence on the protocol. Simulation results demonstrate that the intensification of atmospheric turbulence adversely affects the aforementioned crucial parameters, leading to a significant reduction in the key rate. However, our protocol shows its capability to securely share secrets over a distance of exceeding 60 km among five participants in the presence of turbulence with Cn2 = 1 × 10−15m−2/3, while maintaining a high key rate of approximately 0.55 bit/pulse over a distance of 10 km across twenty participants. These findings suggest that efficient CV-QSS in free space is indeed achievable. This research may serve as a reference for the design and optimization of the practical CV-QSS system. Copyright © 2025, The Authors. All rights reserved.

关键词： Atmospheric turbulence

来源：评论

学校读者我要写书评

暂无评论

Nano-wire bridge waveguide-assisted silicon polarizing beam splitter 13

Nano-wire bridge waveguide-assisted silicon polarizing beam ...

引用

Holography, Diffractive Optics, and Applications XIII 2023

作者： Liu, H.P. Feng, J.J. Chen, J. Zhou, W.J. Bi, Q.Y. Zeng, H.P. School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Key Lab of Advanced Optical Manufacturing Technologies of Jiangsu Province Soochow University Suzhou215006 China Chongqing Key Laboratory of Precision Optics Chongqing Institute of East China Normal University Chongqing401120 China State Key Laboratory of Precision Spectroscopy East China Normal University Shanghai200241 China

ISBN: (纸本)9781510667853

A low-loss and wideband silicon polarizing beam splitter is demonstrated with the assistance of a nano-bridge waveguide. Transverse magnetic light can be coupled to the cross port through the nano-bridge waveguide, while the transverse electric light comes out mainly from the through port. The designed device has a coupling length of 19.6 µm, which can realize an extinction ratio of 32.43 dB for TM mode or 34.23 dB for TE mode at a 1565-nm wavelength. Compared with the conventional three-waveguide coupler structure, the proposed device is based on a resonant tunneling principle, which can help to effectively improve the fabrication tolerance. The device is fabricated with a commercial CMOS processing facility, which can achieve an extinction ratio of 23.07 dB for TM or 23.46 dB for TE mode with a low excess loss, and the extinction ratio of more than 10 dB can be realized in the wavelength range from 1525 to 1610 nm for both modes. The device performance can be further improved, which would facilitate its practical applications in commercial integrated optical circuits. © 2023 SPIE.

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

CNN-based Deep Learning Approach for MRI-based Brain Tumor Detection

CNN-based Deep Learning Approach for MRI-based Brain Tumor D...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： Kanagaraj Narayanasamy Elangovan Sathish Kumar L M Maragatharajan D. Deepa Department of Computer Science Karpagam Academy of Higher Education Coimbatore TamilNadu India Department of DSBS SRM Institute of Science and Technology Kattankulathur TamilNadu India School of Computing Science and Engineering VIT Bhopal University Kotrikalan MP India Department of CSE Kongu Engineering College Perundurai Tamil Nadu India

Conventional brain tumor prediction method is a time-consuming and inaccurate process that involves manually evaluating a large number of MRI (magnetic resonance imaging) scan pictures in search of signs of brain cancer. This might have an effect on the patient's medical care. It may take a long time to analyse a large volume of scan data sets comprising brain pictures. Normal brain tissue and brain cancer tissue seem quite similar under the microscope, making it difficult to distinguish between the two during segmentation. A very accurate automated method for detecting cancer is crucial. This research study has developed a novel method that uses an algorithm to analyse 2D MRI human brain scans and detect brain Tumors. Combining conventional classification algorithms with deep learning methods, the approach makes use of a convolutional neural network (CNN). The model was successfully trained using a dataset of magnetic resonance imaging (MRI) scan images, including Tumors of varied sizes, locations, and intensities. Here, a SVM classifier (Support Vector Machine) and several activation methods are also used to check the results, including Softmax, RMSProp, and sigmoid. Our research showed that a CNN could attain an accuracy of 99.87%, which is higher than the present state-of-the-art findings. The CNN -based approach is meant to aid doctors in the precise identification of brain cancers in MRI scans. This innovation might greatly accelerate the pace at which patients are helped.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis of Intrinsic High-Frequency Characteristic Fluctuation of Emerging Silicon Gate-All-Around Nanosheet (NS) MOSFETs at Sub-3-nm Nodes

Statistical Analysis of Intrinsic High-Frequency Characteris...

引用

IEEE Electron Devices technology and Manufacturing Conference (EDTM)

作者： Sekhar Reddy Kola Yiming Li Min-Hui Chuang Kazuhiko Endo Seiji Samukawa Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Institute of Communications Engineering Department of Electronics and Electrical Engineering Institute of Biomedical Engineering Center for mm Wave Smart Radar System and Technologies National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Fluid Science Tohoku University 2-1-1 Katahira Aoba-ku Sendai Japan National Institute of Advanced Industrial Science and Technology Tsukuba Japan

In recent years, the GAA NS Si MOSFET has been explored as a leading technology. However, the intrinsic parameters of GAA NS Si MOSFETs are affected to varying degrees by various fluctuation sources, Statistically independent and identically distributed $(iid)$ assumptions on the aforementioned random variables overestimate the variability of high-frequency characteristics, compared with considering all fluctuation factors simultaneously. Notably, the random nanosized metal grains dominates the variations of voltage gain, cut-off frequency, and 3dB frequency because the random work functions strongly alter the channel surface potential.

关键词： MOSFET Fluctuations Statistical analysis Gallium arsenide Cutoff frequency Metals Logic gates

来源：评论

学校读者我要写书评

暂无评论

An Integrated Web Solution for Planetary Data Visualization and Exploration

An Integrated Web Solution for Planetary Data Visualization ...

引用

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Ananya Maheshwari Love Lakhwani Pariav Naik Abhishek Kumar Jai G. Singla Amitabh Nitant Dube VijayPal Singh Dhaka School of Computing and Intelligent Systems Manipal University Jaipur Dehmi Kalan Jaipur Rajasthan India Department of Computer Engineering Charotar University of Science and Technology Anand Gujarat India Department of Electrical Engineering Indian Institute of Technology Bhubaneshwar Bhubaneshwar Odisha India Signal and Image Processing Area Space Applications Centre ISRO Ahmedabad Gujarat India

ISBN: (数字)9798350390346

ISBN: (纸本)9798350390353

The exploration and study of planetary bodies have produced vast amounts of geospatial data, creating a need for effective visualization and analysis tools. Many existing solutions are constrained by platform limitations and are resource-intensive, reducing their accessibility for broader use. To overcome these challenges, we developed a lightweight, web-based platform that visualizes interplanetary data and supports multiple geospatial data formats, including shapefiles, KML, and CZML. Our solution includes unique features such as 2D and 2.5D terrain visualization, 3D tiles, and tools for navigating to specific coordinates and measuring distances. These enhancements allow users to explore and interact with geospatial data from various planetary bodies across multiple devices without requiring specialized hardware or software. By modifying the underlying system, we extended its application to planetary data while preserving accessibility and performance across different platforms. This paper discusses the methodology behind these customizations, the challenges we encountered, and the potential applications of our platform in scientific research and education.

关键词： Performance evaluation Three-dimensional displays Coordinate measuring machines Navigation Data visualization Geoscience and remote sensing Extraterrestrial measurements Software Hardware Geospatial analysis

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning-based Traffic Classification with Small-Scale Datasets for Wireless Networks

Ensemble Learning-based Traffic Classification with Small-Sc...

引用

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Xiaorong Wang Wenting Wei Xiaoshan Yu Danyang Zheng Neeraj Kuma Lei Liu State Key Laboratory of Integrated Service Networks Xidian University Xi'an China School of Computing and Artificial Intelligence Southwest Jiaotong University China Department of Computer Science and Engineering Thapar Institute of Engineering and Technology India Guangzhou Institute of Technology Xidian University Xi'an China Shaanxi Key Laboratory of Information Communication Network and Security Xi'an University of Posts & Telecommunications Xi'an China

ISBN: (数字)9798350384475

ISBN: (纸本)9798350384482

Traffic classification is an essential part of intelligent network management in Fifth generation (5G) networks, from quality of service guarantees to security monitoring. With the evolution of diverse services and applications over 5G networks, traffic patterns and their implications also becoming more complicated, especially in wireless networks. How to dynamically manage the growing traffic demand and satisfy the quality of service (QoS) needs of new applications is particularly critical. The biggest challenge is how to identify traffic types accurately without application information and manual features. However, the existing deep learning (DL)-based classifiers heavily rely on extensive and high-quality samples, which proves impractical to obtain in wireless networks. To overcome this limitation, we propose an ensemble Learning based traffic classification model to provide accurate identification with small-scale datasets, where Attention-based Long Short-Term Memory Networks are bagged to train this classifier. The ensemble learning approach employs a combinatorial design involving five base models to construct more accurate and robust learning models. This enables effective feature absorption, making it feasible to train classifiers on limited sample sets. Comprehensive experiments are conducted using a real-world dataset covering 16 applications. Results demonstrate that, even with a mere 10% of training samples, our proposed model achieves a classification accuracy of 95.57% and a precision of 95.83%, surpassing multiple cutting-edge methods.

关键词： Training Accuracy 5G mobile communication Wireless networks Computational modeling Quality of service Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Deep Learning Models for Water Quality Index Prediction: A Comparative Study of LSTM, TCN, ANN, and MLP

arXiv

引用

arXiv 2024年

作者： Ismail, Muhammad Abbas, Farkhanda Shah, Shahid Munir Aljawarneh, Mahmoud Dhomeja, Lachhman Das Abbas, Fazila Shoaib, Muhammad Alrefaei, Abdulwahed Fahad Albeshr, Mohammed Fahad Department of Computer Science Karakoram International University Gilgit15100 Pakistan School of Computer Science China University of Geosciences Wuhan430074 China Department of Computing Faculty of Engineering Science and Technology Hamdard University Karachi74600 Pakistan Faculty of Information Technology Applied Science Private University Amman11937 Jordan Department of Information Technology Faculty of Engineering and Technology University of Sindh Jamshoro76080 Pakistan Institute of Soil and Environmental Sciences University of Agriculture Faisalabad Faisalabad38000 Pakistan State Key Laboratory of Hydraulic Engineering Simulation and Safety School of Civil Engineering Tianjin University Tianjin300072 China Department of Zoology College of Science King Saud University Riyadh11451 Saudi Arabia

Environmental monitoring and predictive modeling of Water Quality Index (WQI) through the assessment of the water quality is an important area of research. In order to predict WQI this study utilizes four popular Deep Learning models i.e. Artificial Neural Network (ANN), Temporal Convolutional Network (TCN), Long Short-Term Memory (LSTM), and Multi-Layer Perceptron (MLP). Based on the Area Under the Operating Characteristic Curve (AUC), the per- formance of the employed models is evaluated and the results are compared. Comparative analysis showed that TCN achieved the highest AUC score i.e. 0.94 as compared to the other employed models i.e. MLP: 0.94,’LSTM’: 0.77, and’ANN’: 0.93. This comparative study provides insights into the suitability of various Deep Learning models for predicting WQI, contributing to advancements in environmental monitoring and management practices. © 2024, CC BY.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

arXiv

引用

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Distributed Pricing Mechanism and Optimal Schedulingin Smart Grid using Improved Grey Wolf Optimization

A Distributed Pricing Mechanism and Optimal Schedulingin Sma...

引用

Intelligent Algorithms for Computational Intelligence Systems (IACIS), International Conference on

作者： Y. Nagendar Haider Alabdeli Prashanth V Aarthy G C. Thangavel School of Computer Science and Engineering SR University Warangal India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Electrical & Electronics Engineering Nitte Meenakshi Institute of Technology Bengaluru India School of Computing and Information Technology REVA University Bengaluru India Department of Mechanical Engineering Vinayaka Mission's Kirupananda Variyar Engineering College Vinayaka Mission's Research Foundation (Deemed to be University) Salem India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360677

In recent days, energy is most important resource new techniques and methods which introduced to fulfill energy demand for price-based demand response (DR). The preface to this study has shown that load management strategies implemented based on Costlier scheduling for low or consistent energy users results from price-based demand response strategies. Suggested work has taken into account and broadened the same concept to include numerous EV charging regions and corresponding loads from an analytical and implementation point of view. This research provides an innovative approach called Improved Grey Wolf Optimization (IGWO) that uses the distinct energy consumption patterns of EVs in each location to calculate EV charging costs. Dynamic price signal that is non-discriminatory is sent to all EV regions and stations. First, a brand-new mathematical model based on market dynamics and real-time load demand is provided to determine charging prices. The global optimum solution produced by the optimization algorithm successfully converges, confirming the efficacy of the suggested mechanism. Lastly, analysis and simulation outcomes are performed to demonstrate the accomplishments of our suggested task in standings of reasonable cost high user satisfaction distribution. IGWO demonstrated usefulness's revenue is modest by either mechanism or cost saving is 0.69-6.89%.

关键词： Energy consumption Costs Simulation Optimal scheduling Pricing Electric vehicle charging Real-time systems Demand response Scheduling Smart grids

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：