检索结果-内蒙古大学图书馆

Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization Design

IEEE Journal on Selected Topics in Signal Processing 2023年第1期17卷 248-263页

作者： Huang, Ning Dai, Minghui Wu, Yuan Quek, Tony Q. S. Shen, Xuemin State Key Lab of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Taiwan University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Wireless federated learning (FL) is a collaborative machine learning (ML) framework in which wireless client-devices independently train their ML models and send the locally trained models to the FL server for aggregation. In this paper, we consider the coexistence of privacy-sensitive client-devices and privacy-insensitive yet computing-resource constrained client-devices, and propose an FL framework with a hybrid centralized training and local training. Specifically, the privacy-sensitive client-devices perform local ML model training and send their local models to the FL server. Each privacy-insensitive client-device can have two options, i.e., (i) conducting a local training and then sending its local model to the FL server, and (ii) directly sending its local data to the FL server for the centralized training. The FL server, after collecting the data from the privacy-insensitive client-devices (which choose to upload the local data), conducts a centralized training with the received datasets. The global model is then generated by aggregating (i) the local models uploaded by the client-devices and (ii) the model trained by the FL server centrally. Focusing on this hybrid FL framework, we firstly analyze its convergence feature with respect to the client-devices' selections of local training or centralized training. We then formulate a joint optimization of client-devices' selections of the local training or centralized training, the FL training configuration (i.e., the number of the local iterations and the number of the global iterations), and the bandwidth allocations to the client-devices, with the objective of minimizing the overall latency for reaching the FL convergence. Despite the non-convexity of the joint optimization problem, we identify its layered structure and propose an efficient algorithm to solve it. Numerical results demonstrate the advantage of our proposed FL framework with the hybrid local and centralized training as well as our proposed alg

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Fault Detection On Heat Pump Operational Data Using Machine Learning Algorithms 11

Fault Detection On Heat Pump Operational Data Using Machine ...

引用

11th International Conference on internet of things: Systems, Management and Security, IOTSMS 2024

作者： Rahman, Md Mahbubur Malekian, Reza Akerstroem, Vilhelm Malmö University Department of Computer Science and Media Technology Malmö20506 Sweden Malmö University Internet of Things and People Research Centre Malmö20506 Sweden Engineering Software Robert Bosch GmbH Lund Sweden

ISBN: (纸本)9798350366501

Heat pumps, being complex systems, are susceptible to various malfunctions. By harnessing contemporary IoT technologies, these devices continuously transmit data which enables monitoring, maintenance, and efficiency. This study focuses on identifying compressor short duration cycles as faults through supervised machine learning algorithms such as XGBoost, Random Forest, SVM, and k-NN. Data preprocessing and labeling were conducted using extensive logged data from heat pump systems, addressing issues like high dimensionality, data sparsity, and temporal dependencies. The methodology included feature engineering, interpolation of missing data, and downsampling for compressor short duration cycles. Supervised machine learning models were applied to classify these short duration cycles. Among the models, XGBoost achieved the highest accuracy and F1-scores, effectively distinguishing between normal and fault conditions. The findings highlight the potential of machine learning to enhance predictive maintenance and operational efficiency in heat pumps. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Wireless Federated Learning: A Secrecy Oriented Design via Sequential Artificial Jamming

引用

IEEE Transactions on Vehicular Technology 2023年第5期72卷 6412-6427页

作者： Wang, Tianshun Huang, Ning Wu, Yuan Quek, Tony Q. S. University of Macau State Key Laboratory of Internet of Things for Smart City 999078 China University of Macau Department of Computer and Information Science 999078 China University of Macau State Key Lab of Internet of Things for Smart City The Department of Computer and Information Science 999078 China Zhuhai UM Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Tainan701 Taiwan

Wireless federated learning (FL) is envisioned as a promising paradigm of distributed learning in wireless networks without disclosing users' data privacy. However, radio channel leads to a potential risk of eavesdropping attack when sending the trained model data in wireless networks. To address this eavesdropping attack, in this work, we propose an energy-efficient wireless FL by using artificial jamming. Specifically, the group of wireless devices (WDs) adopt the time division multiple access (TDMA) approach to send their locally trained models to the FL server for model aggregation subject to the eavesdropping attack of a malicious node. When one of the WDs sends its local model, all the other WDs send the artificial jamming signals to interfere with the eavesdropper, which helps increase the secrecy throughput of the targeted WD for uploading its local model. Different from many existing studies using stochastic gradient descent (SGD), we adopt the stochastic average gradient (SAG) method in the local training to improve the convergence of FL and derive the corresponding lower bound of the FL convergence rate via SAG. Furthermore, we formulate an optimization problem that aims at minimizing the energy consumption of the WDs by jointly optimizing different WDs' local training time, their uploading transmission time in TDMA and the transmit-powers for providing artificial jamming, as well as the FL configurations of the local/global iterations. We also propose an efficient algorithm for solving this non-convex optimization problem. Numerical results are illustrated to validate the advantages of our design of wireless FL and the corresponding algorithms. In particular, the results demonstrate that our secrecy oriented energy-efficient FL can significantly outperform the other heuristic FL schemes. © 1967-2012 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Segment Anything Model (SAM) Meets Object Detected Box Prompts 25

Segment Anything Model (SAM) Meets Object Detected Box Promp...

引用

25th IEEE International Conference on Industrial Technology, ICIT 2024

作者： Akin, Erdal Caltenco, Héctor Adewole, Kayode S. Malekian, Reza Persson, Jan A. Malmö University Department Of Computer Science And Media Technology Malmö205 06 Sweden Malmö University Internet Of Things And People Centre Malmö205 06 Sweden Bitlis Eren University Computer Engineering Department Bitlis13100 Turkey Ericsson Ab Ericsson Research Lund Sweden

ISBN: (纸本)9798350340266

Segmenting images is an intricate and exceptionally demanding field within computer vision. Instance Segmentation is one of the subfields of image segmentation that segments objects on a given image or video. It categorizes the class labels according to individual instances, ensuring that distinct instance markers are assigned to each occurrence of the same object class, even if multiple instances exist. With the development of computer systems, segmentation studies have increased very rapidly. One of the state-of-the-art algorithms recently published by Meta AI, which segments everything on a given image, is called the Segment Anything Model (SAM). Its impressive zero-shot performance encourages us to use it for diverse tasks. Therefore, we would like to leverage the SAM for an effective instance segmentation model. Accordingly, in this paper, we propose a hybrid instance segmentation method in which Object Detection algorithms extract bounding boxes of detected objects and load SAM to produce segmentation, called Box Prompted SAM (BP-SAM). Experimental evaluation of the COCO2017 Validation dataset provided us with promising performance. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Privacy-aware Hydra (PA-Hydra) for 3D Scene Graph Construction 10

Privacy-aware Hydra (PA-Hydra) for 3D Scene Graph Constructi...

引用

10th IEEE World Forum on internet of things, WF-IoT 2024

作者： Akin, Erdal Adewole, Kayode S. Caltenco, Hector Malekian, Reza Persson, Jan A. Malmö University Department of Computer Science and Media Technology Malmö205 06 Sweden Malmö University Internet of Things and People Centre Malmö205 06 Sweden Bitlis Eren University Computer Engineering Department Bitlis13100 Turkey Ericsson Research Ericsson AB Lund Sweden

ISBN: (纸本)9798350373011

A 3D Scene Graph (3DSG) is a hierarchical 3D representation of a physical environment. Hydra is a promising real-time spatial perception framework for 3DSG developed by MIT Spark lab. It uses sensor and camera data from an agent to construct a graph of the environment with five layers and continuously updates it. Albeit its utility and efficiency in generating and updating real-time 3DSG using visual-inertial sensors, Hydra and many other 3DSG frameworks ignore violating to identify private sensitive objects by segmenting, identifying, and reconstructing everything in data. Therefore, in this paper, we enhance Hydra to preserve sensitive data and increase the privacy-awareness of the framework. Accordingly, we propose a Privacy-aware Hydra (Pa-Hydra) framework, which integrates a state-of-the-art Object Detection (OD) algorithm that utilizes a proposed Filter Algorithm to cover sensitive objects with black boxes and prevent them from being constructed by Hydra. We implemented the framework with two popular OD algorithms with two different pre-trained models: You Only Look Once version 9 (YOLOv9) and Real-time Detection Transformer (RTDETR). We evaluated the algorithms using the COCO2017 validation dataset and observed the efficiency of the proposed framework on the uHuman2 (uH2) dataset. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Fast target-aware learning for few-shot video object segmentation

引用

science China(Information sciences) 2022年第8期65卷 71-86页

作者： Yadang CHEN Chuanyan HAO Zhi-Xin YANG Enhua WU Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and Technology School of Education Science and Technology Nanjing University of Posts and Telecommunications State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of Macau State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of Sciences Faculty of Science and Technology University of Macau

Few-shot video object segmentation(FSVOS) aims to segment a specific object throughout a video sequence when only the first-frame annotation is given. In this study, we develop a fast target-aware learning approach for FSVOS, where the proposed approach adapts to new video sequences from its firstframe annotation through a lightweight procedure. The proposed network comprises two models. First, the meta knowledge model learns the general semantic features for the input video image and up-samples the coarse predicted mask to the original image size. Second, the target model adapts quickly from the limited support set. Concretely, during the online inference for testing the video, we first employ fast optimization techniques to train a powerful target model by minimizing the segmentation error in the first frame and then use it to predict the subsequent frames. During the offline training, we use a bilevel-optimization strategy to mimic the full testing procedure to train the meta knowledge model across multiple video *** proposed method is trained only on an individual public video object segmentation(VOS) benchmark without additional training sets and compared favorably with state-of-the-art methods on DAVIS-2017, with a J &F overall score of 71.6%, and on YouT ubeVOS-2018, with a J &F overall score of 75.4%. Meanwhile,a high inference speed of approximately 0.13 s per frame is maintained.

关键词： video object segmentation few-shot target-aware meta knowledge bilevel-optimization

来源：评论

学校读者我要写书评

暂无评论

Parallel fault diagnosis using hierarchical fuzzy Petri net by reversible and dynamic decomposition mechanism

引用

Frontiers of Information Technology & Electronic engineering 2025年第1期26卷 93-108页

作者： Yinhong XIANG Kaiqing ZHOU Arezoo SARKHEYLI-HÄGELE Yusliza YUSOFF Diwen KANG Azlan Mohd ZAIN School of Communication and Electronics Engineering Jishou UniversityJishou 416000China Internet of Things and People Research Center Department of Computer Science and Media TechnologyMalmöUniversityMalmö20506Sweden Faculty of Computing Universiti Teknologi MalaysiaSkudai 81310Malaysia

The state space explosion,a challenge analogous to that encountered in a Petri net(PN),has constrained the extensivestudy of fuzzy Petri nets(FPNs).Current reasoning algorithms employing FPNs,which operate through forward,backward,andbidirectional mechanisms,are *** algorithms streamline the inference process by eliminating irrelevant componentsof the ***,as the scale of the FPN grows,the complexity of these algorithms escalates sharply,posing a significantchallenge for practical *** address the state explosion issue,this work introduces a parallel bidirectional reasoningalgorithm for an FPN that utilizes reverse and decomposition strategies to optimize the implementation *** algorithminvolves hierarchically dividing a large-scale FPN into two sub-FPNs,followed by a converse operation to generate the reversalsub-FPN for the *** detailed mapping between the original and reversed FPNs is thoroughly *** operations are then conducted on the left-sub-FPN and the resulting reversal right-sub-FPN,with the final resultderived by computing the Euclidean distance between the outcomes from the output places of the two sub-FPNs.A case study ispresented to illustrate the implementation process,demonstrating the algorithm’s significant enhancement of inference efficiencyand substantial reduction in execution time.

关键词： Fuzzy Petri net(FPN) State explosion Decomposition Parallel Bidirectional reasoning

来源：评论

学校读者我要写书评

暂无评论

Expeditious Diagnosis of Breast Cancer from Magnetic Resonance Images Using Grey Wolf Optimization based Improved K-means Algorithm

Expeditious Diagnosis of Breast Cancer from Magnetic Resonan...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Krishna Narayanan, S. Ganesh C S, Sundar Petchinathan, G. Ramaraj, Kottaimalai Murugan, Pallikonda Rajasekaran Thilagaraj, M. Mvj College of Engineering Department of Computer Science and Engineering Bengaluru India Karpagam College of Engineering Department of Electrical and Electronics Engineering Tamilnadu Coimbatore India Sri Shanmugha College of Engineering and Technology Department of Biomedical Engineering Tamilnadu Tiruchengode India Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamilnadu Krishnankoil India Mvj College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798350309140

Considering early recognition can improve patient survival rates, it is one of the most crucial concerns that ought to be addressed globally. Promptly identifying any malignant cell or cells has the potential to prevent millions of deaths. Early detection of breast cancer has been achieved by the use of MRIs and mammograms;if the disease is found early, the cost of therapy can be significantly lowered. Methods for segmentation are necessary for the identification of breast cancers. In analyzing images, segmentation - which comprises identification, extraction of features, categorization, and treatment - plays a crucial role. In order to plan treatments, segmentation assists doctors in measuring the amount of tissue in the breast. Utilizing image classification techniques, one may determine the degree of cancer by analyzing the form of the malignant cells. The application of unsupervised K-Means clustering is employed to distinguish the region of interest from the background. By utilizing K-centroids, the data is segmented into K-clusters. To enhance segmentation outcomes, the Grey Wolf Optimization (GWO) is integrated with K-means. GWO is a contemporary metaheuristic swarm intelligence technique known for its notable advantages over traditional methods. Notably, it excels in the absence of derivative information during the initial search and involves minimal parameters. As a result, GWO is widely utilized for optimizing various ***, it is straightforward, user-friendly, adaptable, scalable, and has the unique ability to manage exploration and exploitation throughout the search in a way that promotes optimal convergence. When tested on the MIAS breast cancer dataset, the hybrid GWO based enhanced K-means (GWO_iK-means) algorithm scored 93% dice score value on segmenting the infected region. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Rethinking Guidance Information to Utilize Unlabeled Samples: A label Encoding Perspective 41

Rethinking Guidance Information to Utilize Unlabeled Samples...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yulong Yao, Yuan Chen, Shuhao Jin, Pengrong Zhang, Yu Jin, Jian Lu, Jiangang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China College of Control Science and Engineering Zhejiang University Hangzhou China Beijing Teleinfo Technology Company Ltd. China Academy of Information and Communications Technology Beijing China Research Institute of Industrial Internet of Things China Academy of Information and Communications Technology Beijing China

Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples.A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their ***, EntMin emphasizes prediction discriminability while neglecting prediction *** alleviate this issue, in this paper, we rethink the guidance information to utilize unlabeled *** analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding label *** by this finding, we propose a label-Encoding Risk Minimization (LERM).It first estimates the label encodings through prediction means of unlabeled samples and then aligns them with their corresponding ground-truth label *** a result, the LERM ensures both prediction discriminability and diversity, and it can be integrated into existing methods as a ***, we analyze the relationships between LERM and ERM as well as ***, we verify the superiority of the LERM under several label insufficient *** codes are available at https://***/zhangyl660/LERM. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Artificial Bee Colony and Adaptive Fuzzy K-Means for Detecting Abnormalities in Brain MR Images 5

Hybrid Artificial Bee Colony and Adaptive Fuzzy K-Means for ...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Ts, Kiran Babu Arun Francis, G. Sathya, R. Vijayalakshmi, A. Ramaraj, Kottaimalai Thilagaraj, M. MVJ College of Engineering Department of Computer Science and Engineering Bengaluru India Karpagam College of Engineering Department of Electronics and Communication Engineering Coimbatore India Rajalakshmi Engineering College Department of Electronics and Communication Engineering Tamilnadu Chennai India Hindusthan College of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamilnadu Krishnankoil India MVJ College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798331530013

A brain tumor is an abnormal mass of cells in the brain and can cause issues by pressing on the brain or infiltrating brain tissue. Not all brain tumors are cancerous;grades 1 and 2 are benign but may recur and become malignant. Symptoms vary depending on the affected area of the brain, as different regions control different functions. Medical image processing is the need for the investigation of 3D images of the humans' internal organs, typically collected from a Magnetic Resonance Imaging or Computed Tomography, to identify disorders, assist therapeutic procedures like incision preparation and in academic research. The multiparametric MR images of individuals with low- and high-grade gliomas that were manually segregated by skilled assessors constitute up the BraTS data set. Human separation of tumors is a laborious, time-consuming process that necessitates the delineation of sections by a human expert. Segmenting gliomas using autonomous algorithms for learning has been explored as a solution to these inadequacies. For glioma segmentation, the suggested method combines artificial bee colony (ABC) optimization and adaptive fuzzy k-means clustering (AFKM) that may be readily integrated into the medical procedure. ABC optimization efficiently finds optimal initial cluster centroids, overcoming Fuzzy K-Means' limitation of poor initialization and suboptimal results. ABC optimization balances global search and local refinement for efficient clustering, while Adaptive Fuzzy K-Means dynamically adjusts clusters, with ABC fine-tuning for optimal fit. The efficacy of the suggested method was validated with the help of metric parameters. © 2024 IEEE.

关键词： Magnetic resonance imaging

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：