检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Li Chen, Mohan Arnab, Anurag Xue, Xiangyang Torr, Philip H.S. The School of Data Science Fudan University China Google Research School of Computer Science Fudan University China The Department of Engineering Science University of Oxford United Kingdom

Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they are still limited in capturing long-range structured relationships as they typically consist of layers of local kernels. A fully-connected graph, such as the self-attention operation in Transformers, is beneficial for such modelling, however, its computational overhead is prohibitive. In this paper, we propose a dynamic graph message passing network, that significantly reduces the computational complexity compared to related works modelling a fully-connected graph. This is achieved by adaptively sampling nodes in the graph, conditioned on the input, for message passing. Based on the sampled nodes, we dynamically predict node-dependent filter weights and the affinity matrix for propagating information between them. This formulation allows us to design a self-attention module, and more importantly a new Transformer-based backbone network, that we use for both image classification pretraining, and for addressing various downstream tasks (e.g. object detection, instance and semantic segmentation). Using this model, we show significant improvements with respect to strong, state-of-the-art baselines on four different tasks. Our approach also outperforms fully-connected graphs while using substantially fewer floating-point operations and parameters. Code and models will be made publicly available at https://***/fudan-zvg/DGMN2. © 2022, CC BY.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Monarch Butterfly Optimization based Multi-Convolution Neural Network for Lung Cancer Classification 2

Monarch Butterfly Optimization based Multi-Convolution Neura...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Uma Maheswari, S. Adnan, Myasar Mundher Lathakumari, K.R. Pradeep, V. Praveena, Hirald Dwaraka Karunya Institute of Technology and Sciences Data Science and Cyber Security Coimbatore India The Islamic University Department of Computer Science Najaf Iraq Nitte Meenakshi Institute of Technology Dept of Ece Bengaluru India Alva's Institute of Engineering and Technology Department of Information Science and Engineering Mangalore India School of Engineering Mohan Babu University Erstwhile Sree Vidya Nikethan Engineering College Department of Ece Andhra Pradesh India

ISBN: (纸本)9798350382952

The lung cancer generally presented a pulmonary nodule on images of diagnostic and correct estimation in malignant pulmonary nodules is difficult for diagnosis and protecting of lung cancer. However, the existing methods has less classification accuracy because of irrelevant features on classification of lung cancer. In this research, proposed a Monarch Butterfly Optimization based Multi-Convolution Neural Network (MBO based M-CNN) method for lung cancer classification. dataset used for lung cancer classification is LIDC-IDRI dataset and it is pre-processed by Histogram Equalization (HE). Then, the features are extracted by Gray Level Co-occurrence Matrix (GLCM) and extracted features are selected by Monarch Butterfly Optimization (MBO) algorithm. Then, the lung cancer classification is performed by Multi-Convolution Neural Network (M-CNN). The performance of proposed algorithm is tested in terms of accuracy, precision, sensitivity and specificity. Developed technique obtained accuracy 99.71%, precision 95.39%, sensitivity 99.46%, f1-score 97.45% that is better than previous method like Adaptive Boosting Self-Normalized Multiview Convolution Neural Network (AdaBoost-SNMV-CNN). © 2024 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Fig fruit recognition method based on YOLO v4 deep learning 18

Fig fruit recognition method based on YOLO v4 deep learning

引用

18th International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON 2021

作者： Yijing, Wu Yi, Yang Xue-Fen, Wang Jian, Cui Xinyun, Li Donghua University College of Information Science and Technology Shanghai China North China Institute of Science and Technology Hebei Engineering Technology Research Center for IoT Data Acquisition Processing/College of Computer Langfang China Beijing University of Aeronautics and Astronautics School of Cyber Science and Technology Beijing China

ISBN: (纸本)9780738111278

Image-based fig fruit recognition is a key technology to achieve smart fig planting management. However, compared with apples and mangoes, fig fruits are less different in color from the background and have more dense branches and leaves. This makes the detection of fig fruits more challenging. In this paper, we propose a fig recognition method based on YOLO v4 deep learning technique to achieve fast and accurate recognition and localization of fig fruits in complex environment images. This paper also compares the detection effect of YOLO v4 with Faster R-CNN and YOLO v3 algorithms, which were widely used in the field of fruit recognition in the past, on the same fig dataset. The experimental results show that the detection effect of the fig fruit recognition model constructed based on the YOLO v4 algorithm has improved to a certain extent in terms of average precision and other core metrics. It proves that YOLO v4 deep learning method has good detection effect on figs in complex environment and can provide technical support for intelligent fig planting management. © 2021 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Random Forest and Sobol Method Based data Center PUE Prediction 12

Random Forest and Sobol Method Based Data Center PUE Predict...

引用

12th IEEE International Conference on Information and Communication Networks, ICICN 2024

作者： Yan, Longchuan Luan, Zhaofang He, Ling Jiang, Congfeng Liu, Junming Xu, Chuanqi Zhang, Liangbin State Grid Corporation of China Information & Telecommunication Branch Beijing China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Information Technology Center Hangzhou Dianzi University Hangzhou China College of Big Data and Software Engineering Zhejiang Wanli University Ningbo China

ISBN: (纸本)9798350355802

data centers are critical infrastructures that support a multitude of business loads such as big data, artificial intelligence, and cloud computing. While providing the necessary computing power, the problem of high energy consumption in data centers has become a major obstacle limiting their scale-up, reliability and quality of service. Improving the power usage effectiveness (PUE) of data centers is an important way to improve the energy efficiency of data centers. With the development of theories and methods of machine learning, modeling, analysis and prediction of data center energy consumption using machine learning techniques has become a feasible option. In this study, several accurate PUE prediction models are constructed using neural networks and machine learning techniques for the PUE of a small air-cooled data center in actual operation, among which the mean absolute error of the optimal model reaches 0.29%. In addition, this paper also uses Random Forest and Sobol methods to model and conduct sensitivity analyses of key factors affecting data center PUE, revealing the relationship between data center operating parameters and PUE, and finding that the cooling system exhibits different energy consumption patterns under different IT equipment power conditions, which has a decisive impact on PUE. Based on these sensitivity analyses, we argue that for small air-cooled data centers, improving internal insulation and humidity is an important strategy for optimizing PUE. © 2024 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Audio-Visual Active Speaker Extraction for Sparsely Overlapped Multi-Talker Speech

Audio-Visual Active Speaker Extraction for Sparsely Overlapp...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Junjie Li Ruijie Tao Zexu Pan Meng Ge Shuai Wang Haizhou Li Shenzhen Research Institute of Big Data Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore School of Data Science The Chinese University of Hong Kong Shenzhen China

Target speaker extraction aims to extract the speech of a specific speaker from a multi-talker mixture as specified by an auxiliary reference. Most studies focus on the scenario where the target speech is highly overlapped with the interfering speech. However, this scenario only accounts for a small percentage of real-world conversations. In this paper, we aim at the sparsely overlapped scenarios in which the auxiliary reference needs to perform two tasks simultaneously: detect the activity of the target speaker and disentangle the active speech from any interfering speech. We propose an audio-visual speaker extraction model named ActiveExtract, which leverages speaking activity from audio-visual active speaker detection (ASD). The ASD directly provides the frame-level activity of the target speaker, while its intermediate feature representation is trained to discriminate speech-lip synchronization that could be used for speaker disentanglement. Experimental results show our model outperforms baselines across various overlapping ratios, achieving an average improvement of more than 4 dB in terms of SI-SNR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Probe Population Based Initialization and Genetic Pool Based Reproduction for Evolutionary Bi-Objective Feature Selection

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Xu, Hang Xue, Bing Zhang, Mengjie School of Mechanical Electrical and Information Engineering Putian University Putian Fujian Province China Bing Xue and Mengjie Zhang with the Center for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

Feature selection can be treated as a bi-objective optimization problem, if aimed at minimizing both classification error and number of selected features, suitable for multi-objective evolutionary algorithms (MOEAs) to solve. However, traditional MOEAs would encounter setbacks when the number of features explodes to high dimensionality, causing difficulties for searching optimal solutions in large-scale decision space. In this paper, we propose two general methods applicable to integrate with existing MOEA frameworks in addressing bi-objective feature selection, especially for high-dimensional datasets. One based on probe populations for improving initialization is called PPI, and the other based on genetic pools for improving reproduction is called GPR, both aimed at boosting the search ability of MOEAs. Tested on 20 datasets, in terms of four performance metrics (including the computational time), the experimental section can be divided into three parts. First, five state-of-the-art MOEAs are used as baseline algorithms to integrate with PPI and GPR, while the integrated versions are then compared with their own baselines. Second, the PPI method is additionally compared with three representative feature selection initialization methods to further identify its advantages. Third, a complete PPI and GPR based MOEA (termed PGMOEA) is proposed to compare with three cutting-edge evolutionary feature selection algorithms to further position its search ability. In general, it is suggested from the empirical results that either PPI or GPR can significantly improve the overall performance of each integrated MOEA, while adopting both of them takes the most complementary effect. IEEE

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Max-Min Ant System Algorithm for Electric Capacitated Vehicle Routing Problem

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2024年第3期51卷 195-203页

作者： Hou, Yan-e Wang, Congran Zhang, Chunyang Dang, Lanxue Xiao, Chunjing Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China School of Computer and Information Engineering Henan University Kaifeng475004 China

Electric vehicles have become the first choice for products delivery in logistics, due to their environmental friendliness and low cost compared to the traditional fuel vehicles. This paper deals with an electric capacitated vehicle routing problem with variable energy consumption rate (E-CVRP), which aims to minimize the total cost including vehicle fixed cost, traveled distance cost and energy cost. First, a mixed integer linear programming model is constructed based on the fact that the energy consumption is affected by the vehicle load. Second, a hybrid Max-Min Ant System (HMMAS) algorithm is proposed to solve this problem. Three neighborhood structures are introduced and executed in a Variable Neighborhood Descent (VND) algorithm to improve the current solution. In addition, an effective charging station adjustment strategy is adopted to further improve the solution obtained by the local search process. Finally, some experiments have been conducted on public instances, and the results demonstrate the effectiveness and stability of the algorithm. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

BREAKING THE BARRIER: SELECTIVE UNCERTAINTY-BASED ACTIVE LEARNING FOR MEDICAL IMAGE SEGMENTATION

arXiv

引用

arXiv 2024年

作者： Ma, Siteng Wu, Haochang Lawlor, Aonghus Dong, Ruihai The Insight Centre for Data Analytics School of Computer Science University College Dublin Dublin Ireland School of Electrical and Electronic Engineering University College Dublin Dublin Ireland

Active learning (AL) has found wide applications in medical image segmentation, aiming to alleviate the annotation workload and enhance performance. Conventional uncertainty-based AL methods, such as entropy and Bayesian, often rely on an aggregate of all pixel-level metrics. However, in imbalanced settings, these methods tend to neglect the significance of target regions, eg., lesions, and tumors. Moreover, uncertainty-based selection introduces redundancy. These factors lead to unsatisfactory performance, and in many cases, even underperform random sampling. To solve this problem, we introduce a novel approach called the Selective Uncertainty-based AL, avoiding the conventional practice of summing up the metrics of all pixels. Through a filtering process, our strategy prioritizes pixels within target areas and those near decision boundaries. This resolves the aforementioned disregard for target areas and redundancy. Our method showed substantial improvements across five different uncertainty-based methods and two distinct datasets, utilizing fewer labeled data to reach the supervised baseline and consistently achieving the highest overall performance. Our code is available at https://***/HelenMa9998/Selective Uncertainty AL. Copyright © 2024, The Authors. All rights reserved.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Evaluating decisions: Characteristics, evaluation of outcome and serious games

Evaluating decisions: Characteristics, evaluation of outcome...

引用

14th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2012

作者： Inthorn, Julia Haun, Stefan Hoppe, Anett Nürnberger, Andreas Dick, Michael Data and Knowledge Engineering Group Faculty of Computer Science Otto-von-Guericke-University Germany Department for Ethics and History of Medicine University Medical Center Goettingen Germany Institute for Research and Development of Collaborative Processes School of Applied Psychology University of Applied Sciences and Arts Northwestern Switzerland Switzerland

ISBN: (纸本)9783642317149

The characteristics of decisions and the evaluation of their outcome are highly complex. In this paper, we first give a short analysis of different types of decisions such as long-term and short-term decisions or dilemmas by discussing different scenarios and examples. We identify characteristics of decisions and give a short account of the usually quite complex decision scenarios involved and the high uncertainty of long-term predictions. We introduce serious games as a tool for evaluation of decisions through simulation. By using serious games long-term effects of decisions can be evaluated and known measurement criteria for short-term decision can be transformed to support long-term decisions. © 2012 Springer-Verlag Berlin Heidelberg.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Green Energy AI Cloud: Intelligent Community-Based Electricity Management System 8

Green Energy AI Cloud: Intelligent Community-Based Electrici...

引用

8th IEEE International Conference on Energy Internet, ICEI 2024

作者： Mehta, Yukta Lo, Vincent Mehta, Vijen Agarwal, Kunal Madabathula, Charan Teja Gao, Jerry San Jose State University Department of Applied Data Science San JoseCA United States Evergreen Valley High School Department of Analysis San JoseCA United States San Jose State University Department of Computer Engineering San JoseCA United States

ISBN: (纸本)9798331523558

According to the U.S. Energy Information Administration, 60 percent of the world's electricity is generated from fossil fuels, 18 percent from nuclear power, and only 21 percent from green energy resources. These statistics highlight the pressing need to transition to renewable energy for a sustainable future. However, a major challenge that arises from this increased demand for green energy is the risk of electricity shortage. Overcoming this challenge requires a shift from conventional energy management to an AI-based electricity management system that can more efficiently balance supply and demand. In this paper, we have developed a comprehensive cloud-based Green AI service Management System to accommodate three important aspects of green energy services: electricity consumption, electricity generation, and shortage analysis. In this system, we propose using a community-based model that manages and analyzes multiple buildings' energy usage, allowing the model to be trained further via distributed and aggregated training. The models developed for these components use three approaches: deep learning, machine learning, and reinforcement algorithms, and achieved a shortage analysis accuracy of 98.2 percent. The model is deployed on the cloud and results are accessible from the user interface. Overall, we provide a unique Green AI solution to the market using a system that can handle various aspects of green energy and gives better accuracy than existing systems. © 2024 IEEE.

关键词： Consumption prediction Electricity Management System Electricity shortage forecasting Green AI Usage prediction

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：