检索结果-内蒙古大学图书馆

Guest Editorial Special Issue on Neuromorphic Devices and Circuits for Next-Generation Flexible electronics in IEEE Journal on Flexible electronics

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible electronics 2024年第1期3卷 2-3页

作者： Liu, Fengyuan Goswami, Sreetosh Pan, Lijia Wang, Yanzhi Fondazione Bruno Kessler Microsystems Technology Unit Center for Sensors and Devices Trento38123 Italy Northeastern University Bendable Electronics and Sustainable Technologies Group Electrical and Computer Engineering Department BostonMA02120 United States Indian Institute of Science Centre for Nano Science and Engineering Bengaluru560012 India Nanjing University School of Electronic Engineering Nanjing210023 China Northeastern University Electrical and Computer Engineering Department BostonMA02120 United States

It is fascinating how our body receives an immense amount of sensory information through numerous receptors distributed throughout the body and efficiently integrates it to make decisions for daily activities, while maintaining extremely low energy consumption and cognitive load. This bioinspired sensory information processing paradigm offers unparalleled advantages over traditional von Neumann architectures due to its exceptional energy efficiency, fault tolerance, and adaptability. While previous efforts in this area have mainly focused on the development of biomimetic sensors, it is equally important to create a computing architecture that can process sensory data locally before transmitting it to a higher level. The strategy of offloading computation at the edge can significantly reduce data latency, saving transmission bandwidth and relieving the burden of computation at a higher level, just like the way our peripheral nervous system complements the central nervous system.

关键词： Special issues and sections Neuromorphic engineering Receptor (biochemistry) Flexible electronics

来源：评论

学校读者我要写书评

暂无评论

End-to-End Transformer Architecture with Novel Ensemble Learning Method Integrating CT Scans and Clinical Narratives for Brain Stroke Diagnosis 1

引用

41st computer Graphics International Conference, CGI 2024

作者： Abdul Wahid, Junaid Ayoub, Muhammad Xu, Mingliang Jiang, Xiaoheng Lei, Shi Li, Lifeng Hussain, Shabir Khawaja, Ashfaque Gao, Yufei School of Computer Science and Artificial Intelligence Zhengzhou University Zhengzhou450001 China School of Electronic Information and Electrical Engineering Shanghai Jiaotong University Shanghai200240 China School of Computer Science and Engineering Central South University Hunan Changsha336017 China School of Cyber Space and Security Zhengzhou University Zhengzhou450002 China Institute of Biopharmaceutical and Health Engineering Tsinghua Shenzhen International Graduate School Shenzhen100084 China

ISBN: (数字)9783031820243

ISBN: (纸本)9783031820236

This study is an extension of our previously published manuscript [2]. Building upon the foundations laid in our earlier work, this research further refines and extends the transformer-based approach to enhance its diagnostic capabilities. The focus remains on the integration of multi-modal information, combining both textual clinical narratives and imaging data from multi slice CT scans, to provide a more comprehensive and accurate diagnosis of brain strokes. In addition, we introduce a new ensemble learning approach based on logic gates. This innovative method combines information from clinical narratives and CT scans to enhance the diagnostic capabilities of our framework, marking a significant evolution in our approach to advancing precision in brain stroke detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules

Parm: Efficient Training of Large Sparsely-Activated Models ...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Xinglin Pan Wenxiang Lin Shaohuai Shi Xiaowen Chu Weinong Sun Bo Li Data Science and Analytics Thrust The Hong Kong University of Science and Technology (Guangzhou) Department of Computer Science Hong Kong Baptist University School of Computer Science and Technology Harbin Institute of Technology Shenzhen Department of Computer Science and Engineering The Hong Kong University of Science and Technology

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Sparsely-activated Mixture-of-Expert (MoE) layers have found practical applications in enlarging the model size of large-scale foundation models, with only a sub-linear increase in computation demands. Despite the wide adoption of hybrid parallel paradigms like model parallelism, expert parallelism, and expert-sharding parallelism (i.e., MP+EP+ESP) to support MoE model training on GPU clusters, the training efficiency is hindered by communication costs introduced by these parallel paradigms. To address this limitation, we propose Parm, a system that accelerates MP+EP+ESP training by designing two dedicated schedules for placing communication tasks. The proposed schedules eliminate redundant computations and communications and enable overlaps between intra-node and inter-node communications, ultimately reducing the overall training time. As the two schedules are not mutually exclusive, we provide comprehensive theoretical analyses and derive an automatic and accurate solution to determine which schedule should be applied in different scenarios. Experimental results on an 8-GPU server and a 32-GPU cluster demonstrate that Parm outperforms the state-of-the-art MoE training system, DeepSpeed-MoE, achieving 1.13× to 5.77× speedup on 1296 manually configured MoE layers and approximately 3× improvement on two real-world MoE models based on BERT and GPT-2.

关键词： Training Schedules Costs Processor scheduling Computational modeling Prototypes Graphics processing units

来源：评论

学校读者我要写书评

暂无评论

Progressive edge-sensing dynamic scene deblurring

引用

Computational Visual Media 2022年第3期8卷 495-508页

作者： Tianlin Zhang Jinjiang Li Hui Fan School of Information and Electronic Engineering Shandong Technology and Business UniversityYantai 264005China School of Computer Science and Technology Shandong Technology and Business UniversityYantai 264005China Institute of ZhongKe Network Technology Yantai 264005China

Deblurring images of dynamic scenes is a challenging task because blurring occurs due to a combination of many *** recent years,the use of multi-scale pyramid methods to recover high-resolution sharp images has been extensively *** have made improvements to the lack of detail recovery in the cascade structure through a network using progressive integration of data *** new multi-scale structure and edge feature perception design deals with changes in blurring at different spatial scales and enhances the sensitivity of the network to blurred *** coarse-to-fine architecture restores the image structure,first performing global adjustments,and then performing local *** this way,not only is global correlation considered,but also residual information is used to significantly improve image restoration and enhance texture *** results show quantitative and qualitative improvements over existing methods.

关键词： image deblurring dynamic scenes multiscale edge features

来源：评论

学校读者我要写书评

暂无评论

Enhancing Alzheimer Disease Diagnosis: Integrating Gabor Convolutional Neural Network with Conventional CNNs 2

Enhancing Alzheimer Disease Diagnosis: Integrating Gabor Con...

引用

2nd International Conference on Intelligent Perception and computer Vision, CIPCV 2024

作者： Addo, Daniel Al-Antari, Mugahed A. Zhou, Shijie Ashalley, Eric Muoka, Gladys Wavinya Nartey, Obed T. University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Sejong University Seoul AISSLab Department of Artificial Intelligence and Data Science Korea Republic of University of Electronic Science and Technology of China Institute of Fundamental and Frontier Science Chengdu610054 China ChengduUniversity of Technology of China Sino-British Collaborations Erxianqiao Campus Chengdu610059 China

ISBN: (纸本)9798350360097

Alzheimer's disease (AD) presents a formidable challenge in healthcare, characterized by its progressive nature and the absence of definitive diagnostic markers. This study introduces an innovative method to enhance AD detection by integrating advanced technology with established techniques. We have developed a hybrid model that combines Gabor Convolutional Neural Networks (GCNN) with traditional Convolutional Neural Networks (CNNs) to improve feature extraction from MRI images, thereby achieving a more precise diagnosis of AD. The efficacy of our model is evidenced by its high-performance metrics: an accuracy of 98.58%, a sensitivity of 98.17%, a precision of 97.11%, and robust empirical support. This approach benefits from the use of augmented data and the unique capabilities of GCNN. Comprehensive evaluations, including confusion matrix analysis and ROC curve assessments, confirm the model's proficiency in accurately classifying various stages of dementia. By enhancing diagnostic accuracy, this innovative approach holds the potential to improve patient outcomes, facilitate better care, and enable more timely interventions in the treatment of Alzheimer's disease. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Interpretive Clinical Measurements Prediction and Diagnosis in ICU with Multi-Task Attention-Guided Sequential Feature Learning 7

Interpretive Clinical Measurements Prediction and Diagnosis ...

引用

7th Asian Conference on Artificial Intelligence Technology, ACAIT 2023

作者： Zhao, Peng Xiao, Yan Lei, Yuqing Ren, Yazhou Xu, Zenglin Chongqing Medical University School of Basic Medical Sciences Chongqing China University of Electronic Science And Technology of China School of Computer Science And Engineering Chengdu China University of Electronic Science And Technology of China Shenzhen Institute For Advanced Study Shenzhen China Harbin Institute of Technology Shenzhen School of Computer Science And Technology Shenzhen China Peng Cheng National Lab Center of Artificial Intelligence Shenzhen China

ISBN: (纸本)9798350359145

During the outbreak of COVID-19, it is particularly important to improve clinical decision making for critically ill patients in intensive care units (ICU). Machine learning has become increasingly important in healthcare analysis with the wide adoption of electronic Health Records (EHR). Many deep learning algorithms, such as Recurrent Neural Networks (RNNs), have been developed to deal with clinical time series data to predict the health status of patients, such as mortality, ventilation, and phenotype, etc. Despite RNN being successful in medical tasks, the special traits of data, such as long temporality, high dimensionality, existence of missing values, and multi-labels, have brought challenges to either shallow or deep learning algorithms. Motivated by the fact that the progress of diseases may vary over time, to address these challenges, we proposed a multi-task attention-guided recurrent neural network for learning sequential features (MASFL) model, which employs recurrent units and an attention mechanism. The recurrent units can memorize the past progressive information of patients after entering ICU, while the attention mechanism can selectively utilize this information for different prediction tasks. Meanwhile, the attention also helps to interpret the relationship between the clinical time series data and the prediction result. Furthermore, in order to solve undesirable local solutions for the patient's length-of-stay task, we develop an ordinal regression loss to address the issue. According to the experiments on MIMIC-III, we demonstrate that the proposed model can improve the prediction performance over state-of-the-art prediction approaches. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Domain-Adaptive Clustered Federated Transfer Learning for EV Charging Demand Forecasting

引用

IEEE Transactions on Power Systems 2025年第2期40卷 1241-1254页

作者： Wang, Tianjing Ren, Chao Dong, Zhao Yang Yip, Christine Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore KTH Royal Institute of Technology Wallenberg-NTU Presidential Researcher School of Electrical Engineering and Computer Science StockholmSE-100 44 Sweden City University of Hong Kong Department of Electrical Engineering Hong Kong999077 Hong Kong The University of Sydney CAFEA Smart City Limited Hong Kong and School of Civil Engineering SydneyNSW2006 Australia

To address the privacy concerns for state-of-the-art cutting-edge centralized machine learning in electric vehicle (EV) charging demand forecasting applications, federated learning (FL) has been employed to transfer training processes from the cloud server to edge devices. Nevertheless, traditional FL still grapples with several challenges in terms of personalization, transferability, feature extraction, and data security. This study proposes a domain-adaptive clustered federated transfer learning (FTL) scheme for EV charging demand forecasting. This scheme combines the principles of transfer learning (TL) with FL by utilizing maximum mean discrepancy to measure the differences between local features and cluster them, weight local model parameters in the global model aggregation, and realize domain adaptation for projecting local data and new data to the trained FL model. A multi-head attention-based transformer is leveraged to construct a forecasting model to focus on the most relevant spatio-temporal features. Under multi-stage differential privacy protections, Laplace noise is injected into the local feature, model update and local model during the clustering, FL and TL processes, respectively. The case study demonstrates that the proposed domain-adaptive clustered FTL outperforms the conventional FTL and FL, local training, and other domain shift handling techniques in predictive accuracy and operational risk. © 1969-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Resource Scheduling for Deterministic Communication and Computation Integration

Two-Stage Resource Scheduling for Deterministic Communicatio...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Zhang, Weiting Tang, Nian Zhang, Chuan Guo, Ruibin Li, Mingyan Ying, Chenhao Jin, Jian Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Chongqing University College of Computer Science Chongqing400044 China Shanghai Jiao Tong University Department of Computer Science Shanghai200030 China Caict Research Institute of Industrial Internet of Things Beijing100095 China

ISBN: (纸本)9798350351255

In this paper, we investigate a resource orchestration and transmission scheduling problem for data-intensive services with diversified service requirements. A three-layer collaborative architecture is presented to support dynamic networking and computing resource allocation. To obtain optimal orchestration and scheduling policies, we formulate a constrained resource scheduling problem with the objective to maximizing resource utilization and scheduling success ratio. Since the complicated coupled constraints among decisions, we decouple the problem into a two-stage sub-problems of resource orchestration and transmission scheduling. To realize cross-domain resource orchestration and deterministic transmission of large-scale computing tasks, a two-stage resource scheduling scheme is proposed. Specifically, the first stage makes the resource orchestration decision by a greedy algorithm, and the second stage makes the transmission scheduling decision based on a deep reinforcement learning algorithm. Simulation results show that the proposed solution can effectively improve resource utilization and scheduling success ratio while satisfying diversified service requirements, as compared with benchmarks. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MV-MOS: Multi-View Feature Fusion for 3D Moving Object Segmentation

MV-MOS: Multi-View Feature Fusion for 3D Moving Object Segme...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Cheng, Jintao Chen, Xingming Liang, Jinxin Tang, Xiaoyu Chen, Xieyuanli Li, Dachuan Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China School of Electronic and Information Engineering South China Normal University Foshan528225 China College of Intelligence Science and Technology National University of Defense Technology Changsha China

ISBN: (纸本)9781665481090

Effectively summarizing dense 3D point cloud data and extracting motion information of moving objects (moving object segmentation, MOS) is crucial to autonomous driving and robotics applications. How to effectively utilize motion and semantic features and avoid information loss during 3D-to-2D projection is still a key challenge. In this paper, we propose a novel multi-view MOS model (MV-MOS) by fusing motion-semantic features from different 2D representations of point clouds. To effectively exploit complementary information, the motion branches of the proposed model combines motion features from both bird's eye view (BEV) and range view (RV) representations. In addition, a semantic branch is introduced to provide supplementary semantic features of moving objects. Finally, a Mamba module is utilized to fuse the semantic features with motion features and provide effective guidance for the motion branches. We validated the effectiveness of the proposed multi-branch fusion MOS framework via comprehensive experiments, and our proposed model outperforms existing state-of-the-art models on the SemanticKITTI benchmark. The implementation codes are available at https://***/Chengjt1999/MV-MOS. © 2024 IEEE.

关键词： Robot applications

来源：评论

学校读者我要写书评

暂无评论

Extending RIS Life Span for Reliable Communication Under Hardware Ageing Effects

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2024年 5卷 3395-3409页

作者： Mondal, Atiquzzaman Ghosh, Shyamal Singh, Keshav Biswas, Sudip Duong, Trung Q. Indian Institute of Information Technology Guwahati Department of Electrical Communication Engineering Guwahati781015 India Indian Institute of Science Education and Research Thiruvananthapuram Department of Data Science Thiruvananthapuram695551 India National Sun Yat-sen University Institute of Communications Engineering Kaohsiung80424 Taiwan Memorial University Faculty of Engineering and Applied Science St. John'sNLA1C 5S7 Canada Queen's University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom

In this paper, we address the critical aspect of hardware ageing effects in reconfigurable intelligent surfaces (RISs), whereby the problem of extending the RIS's life cycle under the impact of non-residual stochastic hardware impairment is considered. Through the replication of the RIS hardware and diverse wireless environments within a statistical simulation environment, we formulate an electronic maintenance framework (EMF) for RIS, where we incorporate non-residual impairments through stochastic modeling and determine the electronic reliability of the system. Accordingly, we derive optimal analytical solutions within the EMF to determine whether systematic maintenance of the RIS hardware should be done immediately or postponed in order to extend the expected life cycle of the RIS system. Furthermore, for the scenario with imperfect maintenance of the RIS-aided system, a reliable communication framework (RCF) is also introduced with residual impairments to assess the error probability of the RIS-aided communication. The RCF is established by deriving the distribution of the received signal-to-interference-plus-noise ratio in the presence of residual hardware impairment arising due to imperfect maintenance of the RIS system. Extensive numerical examples are provided to elucidate the derived solutions and illustrate the reliability performance of the proposed framework under hardware impairments. © 2020 IEEE.

关键词： Wireless sensor networks

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：