检索结果-内蒙古大学图书馆

IEEE Visual Communications and Image Processing (VCIP)

作者： Qiuming Liu Shen Wang Yulan Dai Jintao Zhang Yichen Wang Ruoxuan Zhou School of Software Engineering Jiangxi Univ. of Sci. and Tech. Jiangxi China School of Computer Science and Engineering Central South University Changsha China School of Computer Info. Engineering Jiangxi Normal University Jiangxi China Factory and Cultural Communications Nanchang Key lab. of Virtual Digital Jiangxi China

ISBN: (纸本)9781665475938

Proliferative Diabetic Retinopathy (PDR) is a seri-ous retinal disease threatening diabetic patients. Intense retinal neovascularization in the retinal image is the most important clinical symptom of PDR, leading to visual distortion if not controlled. Accurate and timely detection of neovascularization from retinal images allows patients to receive adequate treatment to avoid further vision loss. In this work, we propose a retinal neovascularization automatic segmentation model based on im-proved Pyramid Scene Parsing Network (PSP-Net). To improve the accuracy of the model, we introduce the proposed channel attention module into the model. The network is evaluated with color fundus images from practice. Evaluation results show the network is superior to FCN, SegNet, U-Net and PSP-Net in accuracy and sensitivity. The model could achieve accuracy, sensitivity, specificity, precision and Jaccard similarity score of 0.9832,0.9265,0.9897,0.9116 and 0.8501, respectively. This paper proves through plenty of experimental results that the network model is able to improve the accuracy of segmentation, relieve the workload of doctors, and is worthy of further clinical promotion.

关键词： Visualization Sensitivity Image color analysis Visual communication Retinopathy Semantic segmentation Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Prediction Method of Consumer Buying Behavior Based on Attention Mechanism and CNN-BiLSTM

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第2期7卷 375-385页

作者： Wang, Jian-Nan Cui, Jian-Feng Chen, Chin-Ling College of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China College of Software Engineering Xiamen University of Technology Xiamen361024 China School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China School of Information Engineering Changchun Sci-Tech University Changchun130600 China Department of Computer Science and Information Engineering Chaoyang University of Technology Taichung41349 Taiwan

A prediction method of consumer buying behavior based on attention mechanism and CNN-BiLSTM is proposed, to fully extract the effective features of the behavior and make its prediction more accurate and stable. In this paper, the CNN model is used to automatically extract local features of the consumer buying behavior to select and optimize important information. The BiLSTM model is used to collect sequence patterns of buying behavior to find the correlation among features. The attention mechanism is used to assign different weights to the state values of the hidden layers of each neural network so that the hidden layers can better express important information to obtain more accurate and stable predictions. The experiment results demonstrate that the proposed prediction method has advantages in not only accuracy but stability over other models. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Android based Emotion Detection Using Convolutions Neural Networks 2

Android based Emotion Detection Using Convolutions Neural Ne...

引用

2nd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2021

作者： Qayyum, Rabia Akre, Vishwesh Hafeez, Talha Ali Khattak, Hasan Nawaz, Asif Ahmed, Sheeraz Mohindru, Pankaj Khan, Doulat Ur Rahman, Khalil Mcs National University of Sciences Technology Department of Software Engineering Islamabad Pakistan Dubai Women's College Higher Colleges of Technology Dubai United Arab Emirates Comsats University Department of Computer Science Islamabad Pakistan Seecs National University of Sciences Technology Department of Computing Islamabad Pakistan Higher College of Technology Department of Electrical Engineering Dubai United Arab Emirates Iqra National University Department of Computer Science Peshawar Pakistan Punjabi University Electronics Communications Engineering Patiala India Capital University of Science Technology Department of Computer Science Islamabad Pakistan Northwest Normal University Deptt. of Comp. Sci. and Tech. Lanzhou China

ISBN: (纸本)9781665429214

With the advent of improved mobile processing capabilities we have seen many novel and useful applications. Among other usecases is the utilization of graphics capabilities of on-board computing capabilities. The study evaluates a new trend of functionality that has been considered in the emotion detection field. The proposed study uses Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) to conduct a comparison of which deep learning technique works best for emotion recognition. Both neural network are trained using FER2013 dataset of Kaggle with seven emotion classes. The trained models are evaluated where CNN attains the accuracy of 65% and RNN lack behind with the accuracy of 41%. The trained models are then applied using music player based on one's facial *** user gets the music according to the mood in two forms. Thus with the application user is provided with new and interactive way of getting the music that provides new and latest music and gets an entertaining music app. The Final Product has great scope as the end product can be modified and expanded where music recommendation can be exchanged with other recommendation systems like news, content etc. according to the emotion fetched. © 2021 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Study on machine learning based energy efficiency in developed countries 4

Study on machine learning based energy efficiency in develop...

引用

4th International Conference on IoT in Social, Mobile, Analytics and Cloud, ISMAC 2020

作者： Verma, Aditya Kumar, Yogesh PJC Infotech Department of Development Mohali India Chandigarh Group of Colleges Department of Computer Sci. and Engineering Landran Mohali India

ISBN: (纸本)9781728154640

The increase in energy consumption has seen a huge bump in the past few decades. The credit goes to extensive urbanization and globalization. Forecasting the amount of energy consumption helps in sustainable development and making cost-efficient decisions. The recent studies have revealed that uncontrollable energy demand can be faced in upcoming decades. This produces an alarming situation and various researchers have been working towards energy consumption by adopting various methods. This article presents a comprehensive review of the various researchers' contribution to forecasting the energy demand for various resources. This article apprises the multiple machine learning techniques adopted to study the real data using time series models. An in-depth review of efficient resource allocation and consumption in cloud computing has also been included. Various statistics have been presented as the ground of comparing the performance of various proposed models with the state-of-the-art. © 2020 IEEE.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

An Optimized Partitioning Around Medoids Algorithm for Analyzing Agricultural Data Utilizing Deep Neural Network for Feature Selection

An Optimized Partitioning Around Medoids Algorithm for Analy...

引用

International Symposium on Advanced Electrical and Communication Technologies (ISAECT)

作者： S. Gayathri Devi Samir El-Nakla A.P. Roger Rozario Hiren Mewada M. Arthi K. Rajasri School of Computer Sci. & Engg Vellore Institute of Technology Chennai India Electrical Engineering Department Prince Mohammad Bin Fahd University Al Khobar Kingdom of Saudi Arabia Electrical & Electronics Engg. Department Sri Ramakrishna Institute of Technology Coimbatore India Saveetha School of Engineering Saveetha Inst. of Medical & Tech. Sci Chennai India Electrical & Electronics Engg. Department MLR Institute of Technology Hyderabad Telangana India

ISBN: (数字)9798331529987

ISBN: (纸本)9798331529994

In India’s Agriculture, countless decisions are taken by personnel every day. The major challenge is an accurate estimation of crop yield. In the proposed work, the Partition Around Medoids (PAM) algorithm is employed. The algorithm challenges include 1) predicting the k value and 2) comparing cluster quality is time-consuming. This work evaluates agricultural data by 1) selecting optimal parameters and 2) applying optimized PAM (OPAM) to boost crop production. Initially, feature selection is carried out using a deep neural network (DNN). Additionally, massive amounts of crop, soil, and climatic data are mined for processing. Then, analyzing new, non-experimental data is performed which helps in optimizing the production and increases the resilience of agriculture to changes in climatic conditions. Later, the PAM algorithm is used on the dataset. In this case, the user enters a number of clusters (k). The Anarchic Society Optimization (ASO) algorithm selects k automatically. The model is then assessed using performance metrics.

关键词： Clustering algorithms Artificial neural networks Production Voltage Soil Prediction algorithms Feature extraction Agriculture Partitioning algorithms Solar panels

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Multi-Verse Optimizer for Multi-Product Partial U-Shaped Disassembly Line Balancing Problem 18

Multi-Objective Multi-Verse Optimizer for Multi-Product Part...

引用

18th IEEE International Conference on Networking, Sensing and Control, ICNSC 2021

作者： Zhang, Shancheng Guo, Laide Guo, Xiwang Liu, Shixin Qi, Liang Qin, Shujin Tang, Ying Zhao, Ziyan Liaoning Petrochemical University College of Computer and Communication Engineering Fushun113001 China Northeastern University College of Information Science and Engineering Shenyang110819 China Shandong University of Science and Technology Department of Computer Intelligent Sci. Tech Qingdao266590 China Shangqiu Normal University College of Economics and Management Shangqiu476000 China Rowan University Electrical and Computer Engineering GlassboroNJ United States

ISBN: (纸本)9781665440486

The development of industry and technology promotes the acceleration of product replacement, and generate a large number of end-of-life products. Meanwhile, robots also play a significant role in disassembly. This paper proposes a scheme to solve a U-shaped disassembly line balancing problem with robots. A mathematical model for maximizing profits and minimizing carbon emissions is established. Then, the paper proposes an improved Multi-Objective Multi-Verse Optimizer (MOMVO) to solve the problem. Taking the disassembly of ballpoint pen and hammer drill as examples, our method is compared with Non-dominated Sorting Genetic Algorithm II (NSGA-II), Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D), and Multi-Objective Cellular Genetic Algorithm (MOCGA). Comparison indexes include Inverted Generational Distance+ (IGD+) and hypervolume epsilon metric. The experimental results show that the MOMVO algorithm performs better than others on the U-shaped and robotic disassembly line. © 2021 IEEE.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Multi-objective discrete salp swarm optimizer for solving multiple-product U-shaped disassembly line balancing problem 2

Multi-objective discrete salp swarm optimizer for solving mu...

引用

2nd International Conference on computer Vision and Data Mining, ICVDM 2021

作者： Li, Jiawei Guo, Xiwang Peng, Fangjie Qi, Liang Qin, Shujin College of Computer and Communication Engineering Liaoning Petrochemical University Liaoning Fushun113001 China Department of Biochemistry Engineering Chaoyang Teachers College Liaoning Chaoyang122000 China Department of Computer Intelligent Sci. and Tech. Shandong University of Science and Technology Shandong Qingdao266590 China College of Economics and Management Shangqiu Normal University Henan Shangqiu476000 China

The disassembly line balancing problem is one of the most significant methods in handling large quantities of waste electrical and electronic equipment efficiently problems. In this paper, we propose a U-shaped layout disassembly line and set up a mathematical model to maximize the disassembly profit and minimize the disassembly time of hazardous parts. Therefore, an improved Multi-objective Salp swarm algorithm based on Pareto which combines with a stochastic simulation method is proposed to solve such a U-shaped disassembly line balancing problem. Some cases are used to verify the effectiveness of the proposed method. The results show the proposed method can solve the U-shaped disassembly line balancing problem and outdo the other two optimization algorithms: Nondominated Sorting Genetic Algorithm-II (NSGA-II) and Multi-objective Evolutionary Algorithm based on Decomposition (MOEA/D) in the quality of solutions. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Multi-objective ant lion optimizer for stochastic robotic disassembly line balancing problem subject to resource constraints 2

Multi-objective ant lion optimizer for stochastic robotic di...

引用

2nd International Conference on computer Vision and Data Mining, ICVDM 2021

作者： Dong, ChengShun Liu, Peisheng Guo, Xi Wang Qi, Liang Qin, Shujin Xu, Gongdan College of Computer and Communication Engineering Liaoning Petrochemical University Fushun113001 China Department of Computer Intelligent Sci. and Tech. Shandong University of Science and Technology Qingdao266590 China College of Economics and Management Shangqiu Normal University Shangqiu476000 China Institute of System Engineering Macao University of Science and Technology 999078 China

With the development of manufacturing and society, a large amount of end-of-life products are generated but with reuse value. Therefore, it is of great significance to dismantle and reuse them. A robotic linear disassembly line plays an important role and promotes the disassembly efficiency in a disassembly process. In this work, we establish a mathematical model of a linear robotic disassembly line balancing problem, which requires the maximization of profit and minimization of energy consumption. Then, an improved ant lion optimizer is proposed to optimize the objectives of the multi-objective robotic disassembly line balancing problem. The experimental results show that the multi-objective ant lion optimizer has good performance, and the diversity and convergence are better than its peers. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review Analysis of Supervised Machine Learning Techniques

A Comprehensive Review Analysis of Supervised Machine Learni...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： Shivangi Ghildiyal Raghav Garg Saurabh Dhanik Argya Sarkar Gayatry Sharma Pushpendra Singh Kharayat Deptt. of Computer Application Invertis University Bareilly Uttar Pradesh India Deptt. of Computer Sci. & Engg Tula’s Institute Dehradun U.K. India School of Computing Graphic Era Hill University Bhimtal India Graduate School of Business Tula’s Institute Dehradun U.K. India Department of Computer Science MIET Kumaun Haldwani Uttarakhand India Department of Electrical Engineering Graphic Era Deemed to be university Dehradun India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

This study presents an exhaustive review analysis of the supervised machine learning techniques. The different types of supervised machine learning methods which are discussed in this study are linear Regression, Logistic Regression, Decision Trees, Random Forest, Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), Naive Bayes, Gradient Boosting Machines (GBM) and Neural Networks. All these methods are showing its relevance and utility in the various domain of engineering and bio medical engineering. Using supervised machine learning methods, review evaluation involves assessing and deriving insight from evaluations, frequently in order to categorize them, identify themes, or forecast scores.

关键词： Support vector machines Logistic regression Machine learning algorithms Reviews Neural networks Nearest neighbor methods Boosting Bayes methods Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Securing Vehicle-to-Everything (V2X) Communication in AI-Empowered Electric Vehicles

Securing Vehicle-to-Everything (V2X) Communication in AI-Emp...

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Edward Naveen. V Dhivya. S M.Joe Marshell K Arul Jeyaraj Ebenezer. V Jenefa. A Dept. of CSE Sri Shakthi Inst. of Engg. and Tech. Coimbatore India Dept of Elect. and Instrumentation Engg. SRM Valliammai Engineering College Chengalpattu India Department of ECE PSNA College of Engineering and Technology Dindigul India School of computer science and tech. Karunya Institute of Tech. and Sci. Coimbatore India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

Data in AI-Empowered Electric Vehicles is protected by using blockchain technology for immutable and verifiable transactions, in addition to high-strength encryption methods and digital signatures. This research paper compares and evaluates the security mechanisms for V2X communication in AI-enabled EVs. The purpose of the study is to ensure the reliability of security measures by evaluating performance metrics including false positive rate, false negative rate, detection accuracy, processing time, communication latency, computational resources, key generation time, and throughput. A comprehensive experimental approach is implemented using a diverse dataset gathered from actual V2X communication condition. The evaluation reveals that the security mechanisms perform inconsistently. Message integrity verification obtains the highest detection accuracy with a low false positive rate of 2% and a 0% false negative rate. Traffic encryption has a low processing time, requiring only 10 milliseconds for encryption and decryption, and adds only 5 bytes of communication latency to V2X messages. The detection accuracy of intrusion detection systems is adequate at 95%, but they require more computational resources, consuming 80% of the CPU and 150 MB of memory. In particular attack scenarios, certificate-based authentication and secure key exchange show promise. Certificate-based authentication mitigates MitM attacks with a false positive rate of 3% and a false negative rate of 1%. Secure key exchange thwarts replication attacks with a false positive rate of 0 and a false negative rate of 2. Nevertheless, their efficacy varies based on the attack scenario, highlighting the need for adaptive security mechanisms. The evaluated security mechanisms exhibit varying rates of throughput. Message integrity verification and traffic encryption accomplish high throughput, enabling 1 Mbps and 800 Kbps, respectively, of secure data transfer rates. Overall, the results contribute to the compr

关键词： Accuracy Authentication Intrusion detection Electric vehicles Throughput Time measurement Encryption Safety Security Vehicle-to-everything

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：