检索结果-内蒙古大学图书馆

Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Rikos, Apostolos I. Jiang, Wei Charalambous, Themistoklis Johansson, Karl H. Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Department of Electrical and Computer Engineering School of Engineering University of Cyprus Nicosia1678 Cyprus Division of Decision and Control Systems KTH Royal Institute of Technology StockholmSE-100 44 Sweden

In realistic distributed optimization scenarios, individual nodes possess only partial information and communicate over bandwidth constrained channels. For this reason, the development of efficient distributed algorithms is essential. In our paper we addresses the challenge of unconstrained distributed optimization. In our scenario each node’s local function exhibits strong convexity with Lipschitz continuous gradients. The exchange of information between nodes occurs through 3-bit bandwidth-limited channels (i.e., nodes exchange messages represented by a only 3-bits). Our proposed algorithm respects the network’s bandwidth constraints by leveraging zoom-in and zoom-out operations to adjust quantizer parameters dynamically. We show that during our algorithm’s operation nodes are able to converge to the exact optimal solution. Furthermore, we show that our algorithm achieves a linear convergence rate to the optimal solution. We conclude the paper with simulations that highlight our algorithm’s unique characteristics. © 2024, CC BY.

关键词： Optimization algorithms

Large-scale hyperspectral image clustering using contrastive learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cai, Yaoming Zhang, Zijia Liu, Yan Ghamisi, Pedram Li, Kun Liu, Xiaobo Cai, Zhihua School of Computer Science China University of Geosciences Wuhan430074 China Helmholtz Institute Freiberg for Resource Technology Freiberg09599 Germany Vienna1030 Austria College of Electronic Science and Technology National University of Defense Technology Changsha410073 China School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China University of Geosciences Wuhan430074 China

Clustering of hyperspectral images is a fundamental but challenging task. The recent development of hyperspectral image clustering has evolved from shallow models to deep and achieved promising results in many benchmark datasets. However, their poor scalability, robustness, and generalization ability, mainly resulting from their offline clustering scenarios, greatly limit their application to large-scale hyperspectral data. To circumvent these problems, we present a scalable deep online clustering model, named Spectral-Spatial Contrastive Clustering (SSCC), based on self-supervised learning. Specifically, we exploit a symmetric twin neural network comprised of a projection head with a dimensionality of the cluster number to conduct dual contrastive learning from a spectral-spatial augmentation pool. We define the objective function by implicitly encouraging withincluster similarity and reducing between-cluster redundancy. The resulting approach is trained in an end-to-end fashion by batch-wise optimization, making it robust in large-scale data and resulting in good generalization ability for unseen data. Extensive experiments on three hyperspectral image benchmarks demonstrate the effectiveness of our approach and show that we advance the state-of-the-art approaches by large margins. Copyright © 2021, The Authors. All rights reserved.

关键词： Spectroscopy

A hierarchical conditional random field-based attention mechanism approach for gastric histopathology image classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Yixin Wu, Xinran Li, Chen Sun, Changhao Rahaman, Md Chen, Haoyuan Yao, Yudong Li, Xiaoyan Zhang, Yong Jiang, Tao Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Department of Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ07030 United States China Medical University Liaoning Cancer Hospital and Institute Shenyang China Control Engineering College Chengdu University of Information Technology Chengdu China

In the Gastric Histopathology Image Classification (GHIC) tasks, which are usually weakly supervised learning missions, there is inevitably redundant information in the images. Therefore, designing networks that can focus on distinguishing features has become a popular research topic. In this paper, to accomplish the tasks of GHIC superiorly and assist pathologists in clinical diagnosis, an intelligent Hierarchical Conditional Random Field based Attention Mechanism (HCRF-AM) model is proposed. The HCRF-AM model consists of an Attention Mechanism (AM) module and an Image Classification (IC) module. In the AM module, an HCRF model is built to extract attention regions. In the IC module, a Convolutional Neural Network (CNN) model is trained with the attention regions selected, and then an algorithm called Classification Probability-based Ensemble Learning is applied to obtain the image-level results from the patch-level output of the CNN. In the experiment, a classification specificity of 96:67% is achieved on a gastric histopathology dataset with 700 images. Our HCRF-AM model demonstrates high classification performance and shows its effectiveness and future potential in the GHIC field. Copyright © 2021, The Authors. All rights reserved.

关键词： Image classification

Distributed Optimization via Gradient Descent with Event-Triggered Zooming over Quantized Communication

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Rikos, Apostolos I. Jiang, Wei Charalambous, Themistoklis Johansson, Karl H. The Department of Electrical and Computer Engineering Division of Systems Engineering Boston University BostonMA02215 United States Hong Kong The Department of Electrical and Computer Engineering School of Engineering University of Cyprus Nicosia1678 Cyprus The Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland The Division of Decision and Control Systems KTH Royal Institute of Technology StockholmSE-100 44 Sweden

In this paper, we study unconstrained distributed optimization strongly convex problems, in which the exchange of information in the network is captured by a directed graph topology over digital channels that have limited capacity (and hence information should be quantized). Distributed methods in which nodes use quantized communication yield a solution at the proximity of the optimal solution, hence reaching an error floor that depends on the quantization level used;the finer the quantization the lower the error floor. However, it is not possible to determine in advance the optimal quantization level that ensures specific performance guarantees (such as achieving an error floor below a predefined threshold). Choosing a very small quantization level that would guarantee the desired performance, requires information packets of very large size, which is not desirable (could increase the probability of packet losses, increase delays, etc) and often not feasible due to the limited capacity of the channels available. In order to obtain a communication-efficient distributed solution and a sufficiently close proximity to the optimal solution, we propose a quantized distributed optimization algorithm that converges in a finite number of steps and is able to adjust the quantization level accordingly. The proposed solution uses a finite-time distributed optimization protocol to find a solution to the problem for a given quantization level in a finite number of steps and keeps refining the quantization level until the difference in the solution between two successive solutions with different quantization levels is below a certain pre-specified threshold. Therefore, the proposed algorithm progressively refines the quantization level, thus eventually achieving low error floor with a reduced communication burden. The performance gains of the proposed algorithm are demonstrated via illustrative examples. © 2023, CC BY.

关键词： Directed graphs

Toward parallel intelligence: an interdisciplinary solution for complex systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Yong Zhu, Zhengqiu Chen, Bin Qiu, Sihang Huang, Jincai Lu, Xin Yang, Weiyi Ai, Chuan Huang, Kuihua He, Cheng Jin, Yucheng Liu, Zhong Wang, Fei-Yue College of Systems Engineering National University of Defense Technology Changsha410073 China Hunan Institute of Advanced Technology Changsha410073 China Shanghai Institute of Infectious Disease and Biosecurity Shanghai200032 China Neuherberg Germany Department of Computer Science Hong Kong Baptist University 999077 Hong Kong State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

The growing complexity of real-world systems necessitates interdisciplinary solutions to confront myriad challenges in modeling, analysis, management, and control. To meet these demands, the parallel systems method rooted in Artificial systems, Computational experiments, and Parallel execution (ACP) approach has been developed. The method cultivates a cycle, termed parallel intelligence, which iteratively creates data, acquires knowledge, and refines the actual system. Over the past two decades, the parallel systems method has continuously woven advanced knowledge and technologies from various disciplines, offering versatile interdisciplinary solutions for complex systems across diverse fields. This review explores the origins and fundamental concepts of the parallel systems method, showcasing its accomplishments as a diverse array of parallel technologies and applications, while also prognosticating potential challenges. We posit that this method will considerably augment sustainable development while enhancing interdisciplinary communication and cooperation. © 2023, CC BY-NC-ND.

关键词： Iterative methods

A Wavelet Guided Attention Module for Skin Cancer Classification with Gradient-Based Feature Fusion

学校读者我要写书评

暂无评论

A Wavelet Guided Attention Module for Skin Cancer Classifica...

IEEE International Symposium on Biomedical Imaging

作者： Ayush Roy Sujan Sarkar Sohom Ghosal Dmitrii Kaplun Asya Lyanova Ram Sarkar Department of Electrical Engineering Jadavpur University Kolkata India Department of Computer Science and Engineering Jadavpur University Kolkata India Department of Electronics and Communication Engineering International Institute of Information Technology Naya Raipur Chhattisgarh India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Skin cancer is a highly dangerous type of cancer that requires an accurate diagnosis from experienced physicians. To help physicians diagnose skin cancer more efficiently, a computer-aided diagnosis (CAD) system can be very helpful. In this paper, we propose a novel model, which uses a novel attention mechanism to pinpoint the differences in features across the spatial dimensions and symmetry of the lesion, thereby focusing on the dissimilarities of various classes based on symmetry, uniformity in texture and color, etc. Additionally, to take into account the variations in the boundaries of the lesions for different classes, we employ a gradient-based fusion of wavelet and soft attention-aided features to extract boundary information of skin lesions. We have tested our model on the multi-class and highly class-imbalanced dataset, called HAM10000, and achieved promising results, with a 91.17% F1-score and 90.75% accuracy. The code is made available at: https://***/AyushRoy2001/WAGF-Fusion.

关键词： Solid modeling Image color analysis Biological system modeling Melanoma Medical services Feature extraction Skin

Towards better surgical instrument segmentation in endoscopic vision: multi-angle feature aggregation and contour supervision

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qin, Fangbo Lin, Shan Li, Yangming Bly, Randall A. Moe, Kris S. Hannaford, Blake Research Center of Precision Sensing and Control Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing101408 China SeattleWA98195-2500 United States Department of Otolaryngology-Head & Neck Surgery UW Seattle United States Department of Electrical Computer and Telecommunications Engineering Technology Rochester Institute of Technology United States

—Accurate and real-time surgical instrument segmentation is important in the endoscopic vision of robot-assisted surgery, and significant challenges are posed by frequent instrument-tissue contacts and continuous change of observation perspective. For these challenging tasks more and more deep neural networks (DNN) models are designed in recent years. We are motivated to propose a general embeddable approach to improve these current DNN segmentation models without increasing the model parameter number. Firstly, observing the limited rotation-invariance performance of DNN, we proposed the Multi-Angle Feature Aggregation (MAFA) method, leveraging active image rotation to gain richer visual cues and make the prediction more robust to instrument orientation changes. Secondly, in the end-to-end training stage, the auxiliary contour supervision is utilized to guide the model to learn the boundary awareness, so that the contour shape of segmentation mask is more precise. The effectiveness of the proposed methods is validated with ablation experiments conducted on novel Sinus-Surgery datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

A Hybrid Deep Learning Forecasting Model Using GPU Disaggregated Function Evaluations Applied for Household Electricity Demand Forecasting

学校读者我要写书评

暂无评论

Energy Procedia 2016年 103卷 280-285页

作者： Vitor N. Coelho Igor M. Coelho Eyder Rios Alexandre S.T. Filho Agnaldo J.R. Reis Bruno N. Coelho Alysson Alves Guilherme G. Netto Marcone J.F. Souza Frederico G. Guimarães Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais Belo Horizonte Brazil Instituto de Pesquisa e Desenvolvimento de Tecnologias Ouro Preto Brazil Department of Computer Science State University of Rio de Janeiro Rio de Janeiro Brazil Institute of Computer Science Fluminense Federal University Niteroi Brazil Department of Control Engineering and Automation Universidade Federal de Ouro Preto Ouro Preto Brazil Department of Computer Science Universidade Federal de Ouro Preto Ouro Preto Brazil Department of Electrical Engineering Universidade Federal de Minas Gerais BeloHorizonte Brazil

As the new generation of smart sensors is evolving towards high sampling acquisitions systems, the amount of information to be handled by learning algorithms has been increasing. The Graphics Processing Unit (GPU) architectures provide a greener alternative with low energy consumption for mining big-data, harnessing the power of thousands of processing cores in a single chip, opening a widely range of possible applications. Here, we design a novel evolutionary computing GPU parallel function evaluation mechanism, in which different parts of time series are evaluated by different processing threads. By applying a metaheuristics fuzzy model in a low-frequency data for household electricity demand forecasting, results suggested that the proposed GPU learning strategy is scalable as the number of training rounds increases.

关键词： Microgrid Household Electricity Demand Deep Learning Graphics Processing Unit Parallel forecasting model Big Time-series Data

Overhead Power Line Detection from UAV Video Images

学校读者我要写书评

暂无评论

Overhead Power Line Detection from UAV Video Images

International Conference on Mechatronics and Machine Vision in Practice

作者： Tang Wen YANG Hang YIN Qiu Qi RUAN Jian Da HAN Jun Tong QI Qing YONG Zi Tong WANG Zeng Qi SUN Beijing Key Laboratory of Advanced Information Science and Network Technology Institute of Information Science Beijing Jiaotong University Beijing 100044 China Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing 100044 China State Key Laboratory of Robotics Shenyang Institute of Automation CAS Shenyang 110016 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)9781467316439

Currently, unmanned aerial vehicles (UAVs) are applied to routine inspection tasks of electric distribution networks. As an important information source, machine vision attracts much attention in the area of the UAV's autonomous control. To this end, real-time algorithms are studied-in this paper to detect the power lines in the UAV video images. First, video images are converted into binary images through an adaptive thresholding approach. Then, Hough Transform is used to detect line candidates in the binary images. Finally, a fuzzy C- means (FCM) clustering algorithm is used to discriminate the power lines from the detected line candidates. The properties of power lines are used to remove the spurious lines, and the length and slope of the detected lines are used as features to establish the clustering data set. Experimental results show that the algorithms proposed are effective and able to tolerate noises from complicated terrain background and various illuminations.

关键词： Hough transforms autonomous aerial vehicles computer vision fuzzy set theory pattern clustering power overhead lines power system control video signal processing