检索结果-内蒙古大学图书馆

IEEE International Conference on systems, Man and Cybernetics

作者： Xiaoyong Bian Chunfang Chen Yang Chen Xiongjun Fei Jingshan Tang Intelligent Information Processing and Real-time Industrial Systems Hubei Province Key Laboratory School of Computer Science and Technology Wuhan University of Science and Technology and Institute of Big Data Science and Engineering Wuhan University of Science and Technology Wuhan China School of Information Science and Engineering and Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Wuhan University of Science and Technology Wuhan China School of Technology Michigan Technological University Michigan USA

Efficient and accurate classification of high-resolution scene remains a challenge of within-class diversity and between-class similarity due to rich image variations in viewpoint, object pose, spatial resolution and background. To address these issues, we propose a multi-branch convolutional neural network (MB-CNN), which focuses on tackling the problem of learning the appropriate representation of a high-resolution scene that is rich enough to discriminate between different semantic classes. First, pyramid scene parsing network (PSPNet) with minor modification is introduced to gather global object information. Then, an attention net is proposed to highlight transformation invariance and key regions for attention feature extraction. Finally, above two branches are fused with original input branch to learn consistently semantic class information and generate powerful predictions. Our approach achieves better performance favorably against state-of-the-arts on two publicly available scene datasets.

关键词： Conferences Cybernetics

来源：评论

学校读者我要写书评

暂无评论

SelectQ: Calibration Data Selection for Post-Training Quantization

TechRxiv

引用

TechRxiv 2022年

作者： Zhang, Zhao Gao, Yangcheng Fan, Jicong Zhao, Zhongqiu Yang, Yi Yan, Shuicheng School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei230009 China School of Data Science The Chinese University of Hong Kong Shenzhen China The College of Computer Science and Technology Zhejiang University Hangzhou China Singapore

Post-training quantization (PTQ) can reduce the memory footprint and latency of deep model inference while still preserving the accuracy of model, with only a small unlabeled calibration set and without the retraining on full training set. To calibrate a quantized model, current PTQ methods usually randomly select some unlabeled data from the training set as calibration data. However, we show the random data selection would result in performance instability and degradation due to the activation distribution mismatch. In this paper, we attempt to solve the crucial task on appropriate calibration data selection, and propose a novel one-shot calibration data selection method termed SelectQ, which selects specific data for calibration via dynamic clustering. The setting of our SelectQ uses the statistic information of activation and performs layer-wise clustering to learn an activation distribution on training set. For that purpose, a new metric called Knowledge Distance is proposed to calculate the distances of the activation statistics to centroids. Finally, after calibration with the selected data, quantization noise can be alleviated by mitigating the distribution mismatch within activations. Extensive experiments on ImageNet dataset show that our SelectQ increases the Top-1 accuracy of ResNet18 over 15% in 4-bit quantization, compared to randomly sampled calibration data. It’s noteworthy that SelectQ does not involve both the backward propagation and batch normalization parameters, which means that it has fewer limitations in practical applications. © 2022, CC BY.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Time-Threshold Based Receive Buffer for Vehicle-to-Cloud Multipath Transmission

Dynamic Time-Threshold Based Receive Buffer for Vehicle-to-C...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Yuyang Zhang Ping Dong Xiaojiang Du Hongbin Luo Hongke Zhang Mohsen Guizani State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University P. R. China School of Electronic and Information Engineering Beijing Jiaotong University P. R. China Dept. of Computer and Information Sciences Temple University USA School of Computer Science and Engineering Beihang University P. R. China Dept. of Computer Science and Engineering Qatar University Qatar

ISBN: (数字)9781728149059

ISBN: (纸本)9781728149066

Vehicle-to-cloud is a network access model that aims to share computing resources for vehicles. In vehicle-to-cloud communication, reliable links are critical. Through multipath transmission, comprehensive utilization of heterogeneous wireless networks between the vehicle and the cloud server can effectively improve the reliability and efficiency of transmission. A large number of studies have pointed out that a receive butter can greatly improve the performance of multipath transmission in vehicle-to-cloud communication. However, most of these studies, which use receive buffers to improve multipath transmission performance, do not explicitly specify the design details of the receive butter. A classic design idea is to use a fixed length receive butter. However, this idea makes it difficult to determine the appropriate butter length in a complex vehicle-to-cloud communication scenario. This paper proposes a Dynamic Time-Threshold (DTT) receive buffer. The DTT receive buffer takes into account the instability of vehicular wireless networks, and dynamically adjusts the time-threshold so that the packets in the receive butter do not affect the overall communication performance due to premature departure or excessive waiting. We verified the performance of the DTT receive butter through a large number of simulations and real tests. By comparison, the performance of DTT receive butter is significantly better than the fixed length receive butter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tongue image segmentation via color decomposition and thresholding

Tongue image segmentation via color decomposition and thresh...

引用

作者： Li, Zuoyong Yu, Zhaochai Liu, Weixia Xu, Yong Zhang, Daoqiang Cheng, Yong Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China The Fujian College's Research Base of Humanities and Social Science for Internet Innovation Research Center Minjiang University Fuzhou350121 China Straits Institute Minjiang University Fuzhou350121 China Bio-Computing Research Center Shenzhen Graduate School Harbin Institute of Technology Shenzhen518055 China Department of Computer Science and Engineering Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Communication Engineering Nanjing Institute of Technology Nanjing211167 China

Tongue image segmentation is a crucial step in developing an automatic tongue diagnosis system. After exploring characteristics of image thresholding in different color spaces, we propose a simple and effective tongue image segmentation method. Specifically, the proposed method first extracts an initial tongue body region by performing image thresholding on the transformed hue component in HSI (Hue, Saturation, and Intensity) color space. Then, one of two image thresholding results on the red component of an original tongue image is adaptively selected to find the gap region between the tongue body root and the upper lip. Finally, the initial tongue body region is refined by removing fake object regions such as the upper lip to obtain final tongue image segmentation result. Experimental results on a tongue image dataset containing 200 subjects demonstrate the effectiveness of the proposed method. © 2018 John Wiley & Sons, Ltd.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Dual Weighted Inverted Specific-Class Distance Measure for Nominal Attributes

SSRN

引用

SSRN 2023年

作者： Gong, Fang Lu, Tao Guo, Xingfeng Wang, Dianhong Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan430073 China School of Computer Science and Engineering Wuhan Institute of Technology Wuhan430205 China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan430205 China School of Mechanical and Electronic Information China University of Geosciences Wuhan430074 China

The inverted specific-class distance measure (ISCDM) continues to be one of the top distance metrics addressing only address nominal attributes when missing values and noises exist in the training set. However, its attribute independence assumption fails to hold true in applications with sophisticated attribute dependencies. To alleviate this assumption, several attribute weighting-based and instance weighting-based improved versions have been proposed. However, all of them are limited to focusing solely on either attribute weighting or instance weighting;they ignore the enhancement of the measuring performance by the combination of attribute weighting and instance weighting. Thus, in this study, we developed a novel dual-weighting scheme that considers attribute weighting and instance weighting simultaneously, denoted as dual weighted ISCDM (DWISCDM). We incorporate the attribute and instance weights into the difference formulas of two attribute values and instances, respectively. Extensive experimental results demonstrate the effectiveness of the proposed DWISCDM against ISCDM and some existing state-of-the-art baselines in terms of negative conditional log likelihood and root relative squared error. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Traffic Signal control for Large-Scale Urban Traffic Networks: Real-World Experiments using Vision-based Sensors

Traffic Signal Control for Large-Scale Urban Traffic Network...

引用

International Conference on control and Automation (ICCA)

作者： Jiho Park Tong Liu Chieh Wang Hong Wang Qichao Wang Zhong-Ping Jiang Department of Electrical and Computer Engineering Control and Networks Lab Tandon School of Engineering New York University Brooklyn NY USA Oak Ridge National Laboratory Oak Ridge TN USA National Renewable Energy Laboratory Computational Science Center Golden CO USA

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

Effective control of traffic signals plays a critical role in ensuring smooth vehicle flow in urban areas. Expertly engineered traffic signal controllers can considerably minimize travel delays and enhance sustainability. In this paper, the team proposes the Model Predictive control (MPC) traffic signal control strategy using real-time traffic flow data from a vision-based camera as feedback information. Also, a realistic signal timing plan that considers National electrical Manufacturers Association (NEMA) constraints has been developed to be applied to real-world scenarios. The primary aim is to reduce the number of vehicles across all links in the controlled area, thereby optimizing traffic flow and reducing energy consumption. To validate the proposed method, several real-life experiments were conducted at 24 intersections in Chattanooga, Tennessee, by collaborating with traffic field engineers. These experiments demonstrated significant performance improvements in comparison to the existing method.

关键词： Energy consumption Urban areas Decentralized control Data processing Real-time systems Sensors Delays

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Detection Using Boosted HOG Features

Pedestrian Detection Using Boosted HOG Features

引用

International Conference on Intelligent Transportation

作者： Zhen-Rui Wang Yu-Lan Jia Hua Huang Shu-Ming Tang School of Electronics and Information Xi'an Jiaotong University Xi'an China School of Electronics and Information Engineering Xi'an Jiaotong University Xi'an China Key Laboratory of Complex Systems and Intelligence Science of Institute of Automation of Chinese Academy and Sciences Beijing China Institute of Automation Chinese Academy of Sciences Jinan China College of Information and Electrical Engineering Shandong University of Science and Technology Beijing China

This paper presents a novel approach in pedestrian detection in static images. The state-of-art feature named histograms of oriented gradients (HOG) is adopted as the basic feature which we modify and create a new feature using boosting algorithm. The detection is achieved by training a linear SVM with the boosted HOG feature. We experimentally demonstrate that our solution achieve comparable performance as the HOG algorithm on the INRIA pedestrian dataset yet considerably reduce storage requirement and simplify the computation in terms of elementary operations.

关键词： Support vector machines Intelligent transportation systems Support vector machine classification Automation Humans computer vision Histograms Shape Infrared detectors Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Robust Reinforcement Learning for Risk-Sensitive Linear Quadratic Gaussian control

arXiv

引用

arXiv 2022年

作者： Cui, Leilei Başar, Tamer Jiang, Zhong-Ping The Control and Networks Lab Department of Electrical and Computer Engineering Tandon School of Engineering New York University BrooklynNY11201 United States The Coordinated Science Laboratory University of Illinois Urbana-Champaign UrbanaIL61801 United States

This paper proposes a novel robust reinforcement learning framework for discrete-time linear systems with model mismatch that may arise from the sim-to-real gap. A key strategy is to invoke advanced techniques from control theory. Using the formulation of the classical risk-sensitive linear quadratic Gaussian control, a dual-loop policy optimization algorithm is proposed to generate a robust optimal controller. The dual-loop policy optimization algorithm is shown to be globally and uniformly convergent, and robust against disturbances during the learning process. This robustness property is called small-disturbance input-to-state stability and guarantees that the proposed policy optimization algorithm converges to a small neighborhood of the optimal controller as long as the disturbance at each learning step is relatively small. In addition, when the system dynamics is unknown, a novel model-free off-policy policy optimization algorithm is proposed. Finally, numerical examples are provided to illustrate the proposed algorithm. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Quantum advantage for differential equation analysis

引用

Physical Review A 2022年第2期105卷 022415-022415页

作者： Bobak Toussi Kiani Giacomo De Palma Dirk Englund William Kaminsky Milad Marvian Seth Lloyd Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Giacomo De Palma Scuola Normale Superiore 56126 Pisa Italy QuEra Computing Boston Massachusetts 02143 USA Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Electrical and Computer Engineering Center for Quantum Information and Control University of New Mexico Albuquerque New Mexico 87131 USA

Quantum algorithms for differential equation solving, data processing, and machine learning potentially offer an exponential speedup over all known classical algorithms. However, there also exist obstacles to obtaining this potential speedup in useful problem instances. The essential obstacle for quantum differential equation solving is that outputting useful information may require difficult postprocessing, and the essential obstacle for quantum data processing and machine learning is that inputting the data is a difficult task just by itself. In this study, we demonstrate that, when combined, these difficulties solve one another. We show how the output of quantum differential equation solving can serve as the input for quantum data processing and machine learning, allowing dynamical analysis in terms of principal components, power spectra, and wavelet decompositions. To illustrate this, we consider continuous-time Markov processes on epidemiological and social networks. These quantum algorithms provide an exponential advantage over existing classical Monte Carlo methods.

关键词： Machine learning Quantum algorithms Quantum computation Markovian processes Numerical techniques

来源：评论

学校读者我要写书评

暂无评论

L/sup 1/ sensitivity minimization for plants with commensurate delays

L/sup 1/ sensitivity minimization for plants with commensura...

引用

IEEE Conference on Decision and control

作者： M.A. Dahleh Y. Olhta Laboratory of Information and Decision Systems Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Dept. of Electr. Eng. & Comput. Sci. MIT Cambridge MA USA

A solution is presented to the L/sup 1/ minimization problem for plants with commensurate delays. In the special case where the weight has one pole, the problem can be solved by a single linear programming problem. Other special cases are also presented. A method for computing the optimal performance and a characterization of minimizing solutions are given.< >

关键词： Polynomials Atomic measurements Optimized production technology Delay systems control systems Optimal control Algebra Laplace equations H infinity control

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：