检索结果-内蒙古大学图书馆

Secure Computation Efficiency Resource Allocation for Massive MIMO-Enabled Mobile Edge computing Networks

China Communications 2024年第11期21卷 150-162页

作者： Sun Gangcan Sun Jiwei Hao Wanming Zhu Zhengyu Ji Xiang Zhou Yiqing School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou 450001China Beijing Key Laboratory of Mobile Computing and Pervasive Device and the Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

In this article,the secure computation efficiency(SCE)problem is studied in a massive multipleinput multiple-output(mMIMO)-assisted mobile edge computing(MEC)*** first derive the secure transmission rate based on the mMIMO under imperfect channel state *** on this,the SCE maximization problem is formulated by jointly optimizing the local computation frequency,the offloading time,the downloading time,the users and the base station transmit *** to its difficulty to directly solve the formulated problem,we first transform the fractional objective function into the subtractive form one via the dinkelbach ***,the original problem is transformed into a convex one by applying the successive convex approximation technique,and an iteration algorithm is proposed to obtain the ***,the stimulations are conducted to show that the performance of the proposed schemes is superior to that of the other schemes.

关键词： eavesdropping massive multiple input multiple output mobile edge computing partial offloading secure computation efficiency

来源：评论

学校读者我要写书评

暂无评论

A Weighted Ensemble Causal Discovery Method for Effective Connectivity Estimation 9

A Weighted Ensemble Causal Discovery Method for Effective Co...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Zhang, Qiqi Zhang, Yingwei Ding, Yanhui Chen, Yiqiang Song, Shuchao Wu, Shuang Shandong Normal University School of Information Science and Engineering Jinan China Shandong Academy of Intelligent Computing Technology Jinan China Chinese Academy of Sciences Institute of Computing Technology Beijing China Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing China

ISBN: (纸本)9798350319804

Exploring and explaining the effective connectivity (EC) between brain regions can help us understand the mechanisms behind neurodegenerative diseases such as Alzheimer's disease, thus helping us to diagnose patients better. Causal discovery techniques have been widely used in this domain recently, but diverse methods may produce conflicting outcomes because of the differences in underlying principles and search methods. To solve this problem, we integrate the causal relationships generated by different algorithms to obtain high-confidence inferences, resulting in a more reliable weighted ensemble causal discovery (WECD) method with higher accuracy. First of all, WECD defines a distribution metric function to measure the weights of different individual methods. Then, WECD adaptively chooses the critical threshold to obtain the confident edges set based on the generated directed edge confident metric curve. Finally, the directed acyclic graph condition is used to refine the confident edges set and acquire the final causal graph. We validate the effectiveness of WECD with both the simulated dataset and real functional near-infrared spectroscopy (fNIRS) dataset collected on AD patients, MCI patients and healthy controls. By comparing with other existing methods, experimental results demonstrate the potential of WECD as an effective tool for estimating brain EC. © 2023 IEEE.

关键词： Alzheimer's disease causal discovery effective connectivity ensemble learning functional near-infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Sub-femtonewton force sensing in solution by super-resolved photonic force microscopy (Jun, 10.1038/s41566-024-01462-7, 2024)

引用

NATURE PHOTONICS 2024年第9期18卷 998-998页

作者： Shan, Xuchen Ding, Lei Wang, Dajing Wen, Shihui Shi, Jinlong Chen, Chaohao Wang, Yang Zhu, Hongyan Huang, Zhaocun Wang, Shen S. J. Zhong, Xiaolan Liu, Baolei Reece, Peter John Ren, Wei Hao, Weichang Lu, Xunyu Lu, Jie Su, Qian Peter Chang, Lingqian Sun, Lingdong Jin, Dayong Jiang, Lei Wang, Fan Beihang University School of Physics Beijing People’s Republic of China (GRID:grid.64939.31) (ISNI:0000 0000 9999 1211) University of Technology Sydney School of Biomedical Engineering Faculty of Engineering and Information Technology Sydney Australia (GRID:grid.117476.2) (ISNI:0000 0004 1936 7611) RMIT University Centre for Atomaterials and Nanomanufacturing School of Science Melbourne Australia (GRID:grid.1017.7) (ISNI:0000 0001 2163 3550) University of Technology Sydney Institute for Biomedical Materials and Devices (IBMD) School of Mathematical and Physical Sciences Faculty of Science Sydney Australia (GRID:grid.117476.2) (ISNI:0000 0004 1936 7611) The Australian National University Australian Research Council Centre of Excellence for Transformative Meta-Optical Systems Department of Electronic Materials Engineering Research School of Physics Canberra Australia (GRID:grid.1001.0) (ISNI:0000 0001 2180 7477) Beihang University Key Laboratory of Biomechanics and Mechanobiology (Ministry of Education) Beijing Advanced Innovation Center for Biomedical Engineering School of Biological Science and Medical Engineering Beijing People’s Republic of China (GRID:grid.64939.31) (ISNI:0000 0000 9999 1211) University of Melbourne Computing and Information Systems Department Melbourne School of Engineering Melbourne Australia (GRID:grid.1008.9) (ISNI:0000 0001 2179 088X) The University of New South Wales School of Physics Sydney Australia (GRID:grid.1005.4) (ISNI:0000 0004 4902 0432) Shaanxi Normal University School of Chemistry & Chemical Engineering Xi’an People’s Republic of China (GRID:grid.412498.2) (ISNI:0000 0004 1759 8395) The University of New South Wales Particles and Catalysis Research Laboratory School of Chemical Engineering Sydney Australia (GRID:grid.1005.4) (ISNI:0000 0004 4902 0432) University of Technology Sydney Australian Artificial Intelligence Institute Faculty of Engineering and IT Sydney Australia (GRID:grid.117476.2) (ISNI:0000 0004 1936 7611) University of

Precise force measurement is critical to probe biological events and physics processes, spanning from molecular motor’s motion to the Casimir effect, as well as the detection of gravitational waves. Yet, despite extensive technological developments, the three-dimensional nanoscale measurement of weak forces in aqueous solutions still faces major challenges. Techniques that rely on optically trapped nanoprobes are of significant potential but are beset with limitations, including probe heating induced by high trapping power, undetectable scattering signals and localization errors. Here we report the measurement of the long-distance interaction force in aqueous solutions with a minimum detected force value of 108.2 ± 510.0 attonewton. To achieve this, we develop a super-resolved photonic force microscope based on optically trapped lanthanide-doped nanoparticles coupled with nanoscale three-dimensional tracking-based force sensing. The tracking method leverages neural-network-empowered super-resolution localization, where the position of the force probe is extracted from the optical-astigmatism-modified point spread function. We achieve a force sensitivity down to 1.8 fN Hz–1/2, which approaches the nanoscale thermal limit. We experimentally measure electrophoresis forces acting on single nanoparticles as well as the surface-induced interaction force on a single nanoparticle. This work opens the avenue of nanoscale thermally limited force sensing and offers new opportunities for detecting sub-femtonewton forces over long distances and biomechanical forces at the single-molecule ***-resolved photonic force microscopy employs the fluorescence of lanthanide-doped nanoparticles as a force probe, enabling the measurement of sub-femtonewton forces with a sensitivity of 1.8 fN Hz–1/2, approaching the thermal limit.

关键词： Electrophoresis

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning for Cross-User sEMG Gesture Recognition: Overcoming User Forgetting 9

Incremental Learning for Cross-User sEMG Gesture Recognition...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Yang, Weiwen Zhang, Yingwei Chen, Yiqiang Guo, Changru Ma, Shuo Cheng, Shiyu Chinese Academy of Sciences Institute of Computing Technology Beijing China Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing China University of Chinese Academy of Sciences Beijing China Lanzhou University School of Information Science and Engineering Lanzhou China

ISBN: (纸本)9798350319804

Surface Electromyography (sEMG) based gesture recognition has gained significant attention in the fields of medical rehabilitation and entertainment. However, sEMG exhibits strong user-dependent properties among users with different physiological states, limiting the generalization and personalization of existing models. Although incremental learning methods can help the model balance the knowledge learned from old and new users, the existing incremental learning literature lacks attempts at sEMG gesture recognition. This paper fills these gaps and proposes the incremental learning-based cross-user sEMG gesture recognition framework (IncreEGR), to explore the catastrophic forgetting challenges in cross-user sEMG data. IncreEGR consists of two parts: a sampling method based on the center of features (CoF) and discrepancy-based distillation learning (DDL). CoF samples and saves representative user data and replays them during subsequent training processes to ensure that the model can review previous knowledge. DDL aligns the features extracted from the old and new models using a Gaussian kernel-based distance constraint to help the model overcome catastrophic forgetting. We conduct experiments on the benchmark sEMG gesture recognition dataset (i.e., the Ninapro dataset) to verify the effectiveness of IncreEGR. The experimental results demonstrate that our proposed IncreEGR method successfully balances the knowledge between new and old users and achieves the best recognition performance. © 2023 IEEE.

关键词： Cross-user Gesture Recognition Incremental learning Surface Electromyography

来源：评论

学校读者我要写书评

暂无评论

Time-Frequency Fusion-Augmentation based Contrastive Learning for Self-Supervised Human Activity Recognition 9

Time-Frequency Fusion-Augmentation based Contrastive Learnin...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Guo, Changru Zhang, Yingwei Chen, Yiqiang Yang, Weiwen Wu, Qingyu Wang, Zhong Lanzhou University School of Information Science and Engineering Lanzhou China Chinese Academy of Sciences Institute of Computing Technology Beijing China Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350319804

Human activity recognition (HAR) using sensor data from wearable devices has significant applications in health assessment and accident monitoring. However, building a generalized recognition model requires large amounts of annotated time series data, which can be both costly and time-consuming. Contrastive learning has emerged as a promising approach for learning activity representations from raw sensor data without the need for human annotations. Therefore, we combine contrastive learning and HAR and propose a Time-Frequency Fusion-Augmentation based Contrastive Learning (FusionCL) method to realize self-supervised human activity recognition. FusionCL combines the time-domain augmentation method (named TNet) with the frequency-domain augmentation method (named FNet) to generate diverse augmentation samples. TNet aims to capture different temporal aspects of original sensor data with time-domain variations, such as jittering, scaling, and permutation. FNet aims to augment the original time-domain data with frequency-domain information, which is particularly useful for HAR tasks where different activities can have distinct frequency components. By augmenting the original data from both the time and frequency domains, the proposed FusionCL method can construct a more informative pre-train model, consequently enhancing the generalizability and robustness of the final HAR model. Extensive experiments on four benchmark HAR datasets show that the FusionCL method achieves state-of-the-art performance, demonstrating the effectiveness of our proposed method and the potential for constructing the unified HAR model with contrastive learning strategies. © 2023 IEEE.

关键词： contrastive learning frequency-domain augmentation human activity recognition self-supervised time-domain augmentation

来源：评论

学校读者我要写书评

暂无评论

Discharge image reconstruction and frequency domain analysis based on event data

引用

High Voltage 2024年第6期9卷 1195-1201页

作者： Quan Yuan Lei Deng Hao Guo Qishen Lyu Xin Zhang Jibin Wu Yu Deng Hongyang Zhou Xilin Wang Zhidong Jia Engineering Laboratory of Power Equipment Reliability in Complicated Coastal Environments Tsinghua Shenzhen International Graduate SchoolTsinghua UniversityShenzhenGuangdongChina Department of Precision Instrument Center for Brain Inspired Computing ResearchTsinghua UniversityBeijingChina College of Information and Computer Taiyuan University of TechnologyTaiyuanChina Shenzhen Power Supply Corporation China Southern Power Grid CorporationShenzhenChina Department of Computing The Hong Kong Polytechnic UniversityHong KongChina China Electric Power Research Institute BeijingChina School of Electrical Engineering and Automation Xiamen University of TechnologyXiamenChina

Optical image method has been the earliest and most used direct method for observing gas ***,research on gas discharge monitoring based on visible light mainly relies on high-speed cameras,but the large size,significant data storage requirements,and susceptibility to interference from complex backgrounds and lighting conditions limit their further *** vision sensing(DVS)technology is a neuromorphic sensing technology that asynchronously measures the luminance changes at each *** offers advantages such as a large dynamic range(>120 dB),high temporal resolution(up to 1µs),and small data volume(MB level).In this study,dynamic vision sensing technology was employed to monitor both 30 mm short-gaps and 1080 mm long-gaps discharge processes *** study developed the CountImage encoding method for event data and conducted image reconstruction,time-domain analysis,and frequency-domain charac-teristic analysis based on the event *** results show that the event-reconstructed images are highly consistent with the high-speed camera images,and the arc develop-ment process and its path can also be clearly ***,this study discovered a correlation between the electrical characteristics and event information during the discharge *** the time domain,the duration of the maximum DVS event count closely matches the duration during which the voltage drops to zero during *** the frequency domain,the Pearson correlation coefficient between the event stream spectrum and the voltage signal spectrum is greater than *** the maximum number of brightening events(ONmax)and the maximum number of darkening events(OFFmax)are positively correlated with the voltage applied between the *** study demonstrates that,compared to the GB/s data rate of high-speed cameras,this approach can record the discharge process and accurately reconstruct the discharge process,arc morphology,and discharge path at M

关键词： image analysis holds

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: Fooling Segment Anything Model to Segment Nothing 38

DarkSAM: Fooling Segment Anything Model to Segment Nothing

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Zhou, Ziqi Song, Yufei Li, Minghui Hu, Shengshan Wang, Xianlong Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integration of Artificial Intelligence and Wearable Internet of Things for Mental Health Detection

引用

International Journal of Cognitive computing in engineering 2024年第1期5卷 307-315页

作者： Wang, Wei Chen, Jian Hu, Yuzhu Liu, Han Chen, Junxin Gadekallu, Thippa Reddy Garg, Lalit Guizani, Mohsen Hu, Xiping Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University Guangdong Shenzhen518172 China School of Medical Technology Beijing Institute of Technology Beijing100081 China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong Shenzhen518000 China School of Software Dalian University of Technology Dalian116621 China Division of Research and Development Lovely Professional University Phagwara India Center of Research Impact and Outcome Chitkara University Punjab India Faculty of Information and Communication Technology University of Malta Msida Malta United Arab Emirates

The integration of Artificial Intelligence (AI) and Wearable Internet of Things (WIoT) for mental health detection is a promising area of research with the potential to revolutionize mental health monitoring and diagnosis. Since early detection of mental diseases, i.e., depression, is of great importance for diagnosis and treatment, a fast and convenient way is urgently needed. Traditional diagnostic methods are time-consuming, laborious, over-subjective, and easily lead to misdiagnosis. The advance in information techniques and wearable devices brings innovation to mental disease detection. Therefore, this article first compares intelligent depression detection methods and traditional methods to illustrate the significance and then analyzes the opportunities of the wearable device. Then we provide specific psychophysiological data measured by wearable devices and introduce relevant datasets for depression detection. An illustrative example of depression detection with sleep data is presented and discussed and our proposed ensemble method has improved nearly 10% to baselines. Analytical results demonstrate the great potential of using wearable device-measured psychophysiological data to detect depression intelligently. © 2024 The Authors

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Efficient Spatial-Temporal Representation Method for EEG Emotion Recognition 19

An Efficient Spatial-Temporal Representation Method for EEG ...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Weng, Weining Gu, Yang Chen, Yiqiang Wang, Guoqiang Shi, Nianfeng Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China The Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing China School of Computer and Information Engineering Luoyang Institute of Science and Technology Luoyang China

ISBN: (纸本)9798350346558

Affective computing based on electroencephalogram (EEG) has been widely studied due to the high correlation between the brain and emotions. Neurological research shows that emotions are generated by the interaction of neural circuits separated in different brain regions. Recently, many deep learning methods have been demonstrated to recognize different emotions. However, these methods extract features at the data level, ignoring the brain's neural mechanisms of emotion generation, which may result in the features' weak ability to express emotion. To solve this problem and extract more discriminant features according to the neural mechanism of emotion generation, this article proposes an attention based spatial-temporal representation method (ASTR) for emotion recognition. The ASTR method constructs spatial-temporal representations of emotion from neural circuits' activity in different brain regions. In the model, the cascade attention quantifies the multi-granularity correlation and information exchange pattern between brain regions as the spatial features, which measure neural circuits' activation and information interaction in different brain regions. The one-way transformer introduces temporal order in spatial features, calculates temporal variation features from the long-term activity of neural circuits and generates the emotion representation. The representation incorporates spatial-temporal features of neural circuits' activity during emotion generation, which is highly related to emotion. We conducted experiments on SEED and DEAP datasets. The experimental results show that the emotion recognition accuracy of our model is about 3.0% higher than that of the SOTA algorithms, reaching more than 98%. The results also visualize the emotion generation process, revealing how the brain works under different emotions. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Semantic Segmentation on Lidar Point Clouds 19th

A Novel Method for Semantic Segmentation on Lidar Point Clou...

引用

19th EAI International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness, QShine 2023

作者： Wang, Fei Wan, Liangtian Zhu, Yan Sun, Lu Zhao, Xiaowei Zheng, Jianbo Wang, Xianpeng Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian116620 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Guangdong Shenzhen518172 China Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Shenzhen MSU-BIT University Guangdong Shenzhen518172 China Department of Communication Engineering Institute of Information Science Technology Dalian Maritime University Dalian116026 China School of Information and Communication Engineering Hainan University Haikou570228 China

ISBN: (纸本)9783031651250

Autonomous driving relies on multiple sensors, such as lidar and cameras, to perceive the surrounding environment and the vehicle’s own position. Among them, lidar point cloud segmentation is a crucial and challenging task for 3D scene understanding. In this paper, we propose a novel deep learning method RPNet for lidar point cloud segmentation that combines range image-based segmentation and point based segmentation. Our method extracts point cloud features from range images and predicts 3D point cloud labels from point clouds. The segmentation results of both branches are fused to improve accuracy. We evaluate our method on the Semantic KITTI dataset and show that it outperforms other fusion algorithms in terms of effectiveness and robustness. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Semantic Segmentation

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

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

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：