检索结果-内蒙古大学图书馆

An efficient Quasi-Affine Transformation Evolutionary algorithm with fixed dimension updating and its application in UAV 3D path planning

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 9755-9781页

作者： Sung, Tien-Wen Zhao, Baohua Zhang, Xin Lee, Chao-Yang Fang, Qingjun Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Computer Science and Mathematics Fujian University of Technology Fuzhou China Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Taiwan

Quasi-Affine Transformation Evolutionary (QUATRE) algorithm is a kind of swarm-based collaborative optimization algorithm that solves the problem of a position deviation in a DE search by using the co-evolution matrix M instead of the cross-control parameter CR in the differential evolution algorithm (DE). However, QUATRE shares some of the same weaknesses as DE, such as premature convergence and search stagnation. Inspired by the artificial bee colony algorithm (ABC), we propose a new QUATRE algorithm to improve these problems that ranks all the individuals and evolves only the poorer half of the population. In an evolving population, individuals of different levels intersect with dimensions of different sizes to improve search efficiency and accuracy. In addition, we establish a better selection framework for the parent generation individuals and select more excellent parent individuals to complete the evolution for the individuals trapped in search stagnation. To verify the performance of the new QUATRE algorithm, we divide the comparison algorithm into three groups, including ABC variant group, DE variant group, and QUATRE variant group, and the CEC2014 test suite is used for the comparison. The experimental results show the new QUATRE algorithm performance is competitive. We also successfully apply the new QUATRE algorithm on the 3D path planning of UAV, and compared with the other famous algorithm performance it is still outstanding, which verifies the algorithm's practicability. © 2024 - IOS Press. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Smart Security Camera System using YOLO Algorithm in Security Setting 2

Deep Learning based Smart Security Camera System using YOLO ...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Vijayakumar, P. Praveen Santhoshkumar, G. Pyingkodi, M. Shwetha, C. Sibitha, S. Vedha Shruthi, K. Kongu Engineering College Master of Computer Applications Perundurai Erode India Nandha Engineering College Electronics and Communication Engineerig Erode India

ISBN: (纸本)9798350368413

The proposed Deep Learning based Smart Security Camera System using Yolo Algorithm in Security Setting is designed to detect unusual behavior, like someone covering their face entirely, and responding to that by generating a beep sound to alert. Unlike older systems, it doesn't just record incidents for later review it can recognize problems as it happens and take action right away. Even if someone wears a full face mask, this system notes them and raise an alarm immediately. It works by using an efficient algorithm called YOLO (You Only Look Once) to quickly know what's happening in the live camera footage. That is, it can spot multiple objects in real time without slowing down. Overall, this security system is a step ahead in keeping areas safer. It is faster, as it can react to potential threats without needing as many human interventions. © 2024 IEEE.

关键词： Object detection Security camera YOLO

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction using Modified BPSO for Feature Selection with RNN Variants on Top Tech Companies

Stock Price Prediction using Modified BPSO for Feature Selec...

引用

2023 IEEE World Conference on Communication and Computing, WCONF 2023

作者： Gupta, Priyank Paharia, Nitin Gupta, Sanjay Kumar Jadon, Rakesh Singh Jiwaji University SOS Computer Science and Applications Gwalior India Prestige Institute of Management and Research Department of Computer Applications Gwalior India MITS Department of Computer Science and Engineering Gwalior India

ISBN: (纸本)9798350311204

The most often utilized data in recent years is time series data, used for things like stock market price prediction and others. Recent research has focused chiefly on stock market prediction using neural networks, and new techniques are being developed to improve these models' accuracy. One such method uses optimization algorithms like PSO, GWO, or GA. Other variants, such as Binary-PSO and Binary-GWO, are developed by further enhancing the original algorithms. The paper suggested a variant of BPSO called MBPSO / TBPSO that assigned binary values to the features during optimization using the 'tanh' activation function. The TBPSO is then applied individually for two, five, and ten years to the datasets of five leading Tech firms. The dataset, which comprises a variety of historical and technical indicators, is applied to different variants of RNN and finds the best results with the GRU model to forecast the closing stock price. What transpired proves that, when used for prediction on the GRU model and when choosing more features than BPSO, TBPSO provides us with features that will provide more accuracy. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Flood Detection from Satellite Images Using Self-Attention Empowered EfficientNetV2 Mechanism 7

Flood Detection from Satellite Images Using Self-Attention E...

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Selva Jeba, G. Chitra, P. Thiagarajar College of Engineering Dept. of Computer Science and Engineering Madurai India Thiagarajar College of Engineering Dept. of Computer Applications Madurai India

ISBN: (纸本)9798350304268

Floods occur when water overflows onto normally dry land and are a destructive natural disaster. In recent times, deep learning models have demonstrated their remarkable capabilities in identifying objects and classifying images. As a result, the utilization of deep learning in remote sensing, especially for the crucial task of flood detection, has become an increasingly prominent and promising area of research and application. This study proposes a lightweight yet powerful feature extraction framework by leveraging a self-attention(SA) based EfficientNetV2. The EfficientNetV2 architecture serves as the backbone of the model and has exhibited effectiveness in image classification tasks. By incorporating self-attention mechanisms, the model can capture spatial relationships within remote sensing images, enhancing its accuracy and efficiency in flood detection. The model was trained and assessed using the SEN12-FLOOD dataset, and the outcomes demonstrate that the suggested framework exhibits enhanced flood detection performance, achieving an accuracy of 95.9%. © 2023 IEEE.

关键词： attention mechanism deep learning EfficientNetV2 flood detection remote sensing

来源：评论

学校读者我要写书评

暂无评论

Image Forgery Detection Using Deep Learning 7th

Image Forgery Detection Using Deep Learning

引用

7th International Conference on Smart Trends in Computing and Communications, SmartCom 2023

作者： Koshy, Litty Chithu, K. Department of Computer Science and Engineering SCMS School of Engineering & Technology Ernakulam India Master of Computer Applications SCMS School of Engineering & Technology Ernakulam India

ISBN: (纸本)9789819908370

Since cameras are so widely available, taking pictures has become more and more common. In order to gain more information, it is frequently necessary to enhance photographs, which are crucial in our daily lives as memories or sources of wealth of information. There are many tools accessible to enhance the quality of photos;however, some of them are also widely used to alter images, leading to the dissemination of false information. This makes picture forgeries more severe and frequent, which is now a major cause of concern. To identify fake images, many conventional methods have been developed over time. Convolutional neural networks (CNNs) have drawn a lot of interest recently, and they have had an impact on the area of picture fraud detection as well. However, the majority of CNN-based picture forgery detection methods currently used in the literature are restricted to identifying a certain kind of fraud (either image splicing or copymove). As a result, a method that can quickly and precisely identify any hidden forgeries in a picture is needed. We present a powerful deep learning-based approach for detecting picture forgeries in this study. The RGB format images converted to error level analysis (ELA) are used to train our model. The suggested model is compact, and its effectiveness shows that it outperforms cutting-edge methods in terms of speed. The experiment's findings are promising, with a 91.37% total validation accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Predictive Model for Edge Computing Resource Scheduling Based on Deep Neural Network

引用

computer Modeling in engineering & Sciences 2024年第4期139卷 259-277页

作者： Ming Gao Weiwei Cai Yizhang Jiang Wenjun Hu Jian Yao Pengjiang Qian School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi214122China The Center for Intelligent Systems and Applications Research School of Artificial Intelligence and Computer ScienceJiangnan UniversityWuxi214122China School of Information Engineering Huzhou UniversityHuzhou313000China

Currently,applications accessing remote computing resources through cloud data centers is the main mode of operation,but this mode of operation greatly increases communication latency and reduces overall quality of service(QoS)and quality of experience(QoE).Edge computing technology extends cloud service functionality to the edge of the mobile network,closer to the task execution end,and can effectivelymitigate the communication latency ***,the massive and heterogeneous nature of servers in edge computing systems brings new challenges to task scheduling and resource management,and the booming development of artificial neural networks provides us withmore powerfulmethods to alleviate this ***,in this paper,we proposed a time series forecasting model incorporating Conv1D,LSTM and GRU for edge computing device resource scheduling,trained and tested the forecasting model using a small self-built dataset,and achieved competitive experimental results.

关键词： Edge computing resource scheduling predictive models

来源：评论

学校读者我要写书评

暂无评论

A differential approach and deep neural network based data privacy-preserving model in cloud environment

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第5期14卷 4659-4674页

作者： Gupta, Rishabh Gupta, Ishu Saxena, Deepika Singh, Ashutosh Kumar Department of Computer Applications National Institute of Technology Haryana Kurukshetra India Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung Taiwan

Data outsourcing has become indispensable to allow information sharing among multiple parties. The users do not fully trust the cloud platform since it is operated by a third party. Preserving privacy while sharing the data among different parties is a challenging task;therefore, users apply the differential privacy mechanism to protect their data. However, such protection mechanisms suffer from the problem of degradation of learning results. In this paper, the authors address the degradation of the learning results due to noise injection into user’s data through ϵ-differential privacy. A differential approach and deep neural network based data privacy-preserving model is proposed, which injects noise at an appropriate position by exploiting the properties of the Laplace transform to maintain the accuracy level. The experiments are conducted over Steel Plates Fault, Spambase, Banknote Authentication, and Monk Problem datasets for deep neural network classifier to evaluate the model’s efficiency in accuracy, precision, recall, and F1-score terms. The achieved results show that the proposed model ensures high accuracy, precision, recall, and F1-score up to 99.75%, 99.72%, 99.72%, and 99.72%, and improvement up to 19.34%, 30.67%, 29.39%, and 32.11%, respectively, as compared to existing approaches. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Image Segmentation with Recurrent Neural Network Architectures 2

Enhancing Medical Image Segmentation with Recurrent Neural N...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Masson, Palak Sharma, Deepak Yadav, Kanchan Sethi, Tarun Raj Kumar Goel Institute of Technology Department of Computer Science & Engineering UP Ghaziabad India Srm Institute of Science and Technology Department of Computer Applications UP Modinagar India Gla University Department of Mechanical Engineering UP Mathura India Iamr Department of Computer Applications UP Ghaziabad India

ISBN: (纸本)9798350371055

Scientific imaging is a swiftly evolving and developing vicinity of healthcare. Greater accurate segmentation of clinical images is paramount for correct diagnosis. Recent breakthroughs in profound mastering studies have allowed researchers to faucet into a powerful but unstructured information form - images. With the usage of recurrent neural network architectures (RNNs), researchers are exploring the capacity of this shape of facts to acquire better consequences from scientific photograph segmentation. RNNs are regarded for their flexibility in encoding temporal relationships and processing established statistics. In medical image segmentation, this flexibility aids in recognizing complicated styles in photographs and helps the model to localize features inside the image better. Furthermore, the networks can run on images of various sizes, ensuring that models can handle photos created using unique imaging modalities. Additionally, RNNs can examine large annotated datasets and, consequently, help supply meaningful segmentation outcomes. Recent advances in using RNNs for medical photo segmentation have shown promising effects. RNNs have been used to phase colon anatomy, mind tumors, and lymph nodes. U-internet-primarily based segmentation fashions that include RNNs and feature-achieved high segmentation accuracy for medical photograph segmentation responsibilities have also evolved. Within destiny, RNN-based total models will remain superior and could be implemented in various medical imaging segmentation tasks. As such, RNNs will make scientific imaging segmentation extra green and accurate, allowing faster and more accurate analysis and treatment. © 2024 IEEE.

关键词： Achieved Recognizing Relationships Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Review on Deep Learning Techniques for skin disease Detection 1

A Review on Deep Learning Techniques for skin disease Detect...

引用

1st International Conference on Advanced Computing and Emerging Technologies, ACET 2024

作者： Verma, Sarvachan Kumar, Ajitesh Kumar, Manoj Gla University Computer Engineering and Applications Mathura India Guru Ghasidas Vishwavidyalaya Information Technology Bilaspur India

ISBN: (纸本)9798350367720

Skin cancer ranks among the most concerning global health threats. Correct skin cancer diagnosis is difficult to achieve. Timely recognition of skin cancer symptoms is crucial due to the increasing incidence rates, notable mortality rates, and substantial financial burden linked with medical interventions. Assumed the severity of complications, experts have made several primary recognition methods for skin disease. Deep learning algorithms have been engineered to excel across diverse tasks and are increasingly leveraged for diagnosing skin diseases. We presents a review of deep-learning techniques for diagnosing skin disease. We initial provide a brief description of skin disease and describe some readily accessible skin datasets. Then examine well-liked deep learning architectures and well-liked frameworks aiding deep learning algorithm implementation. This article's main goal is to offer a conceptual and comprehensive evaluation of recent efforts on deep learning-based skin disease diagnosis. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Data Mining Classification Techniques to Analyze the TV Market Data 2

Data Mining Classification Techniques to Analyze the TV Mark...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Pethe, Yoginee Surendra Uparkar, Satyajit Das, Himansu Computer Applications Shri Ramdeobaba College of Engineering and Management Nagpur India School of Computer Engineering Kiit Deemed to Be University Bhubaneswar India

ISBN: (纸本)9798350308846

WEKA has expansive capabilities, which include Data Mining Algorithms similar to Random Forest, J48, Multilayer Perceptron, and Naive Bayes. In this paper, trouble has been made to compare the analysis of several categorization systems. A dataset of television request analysis was used as the base for this analysis, which was carried out with the aid of WEKA. Several data mining approaches are applied to the dataset, including J48, naive Bayes, and arbitrary timber. Applying four classifiers while taking the operating system into consideration for the analysis of the television request. Grounded on the accuracy percentage a conclusion is shown in this paper. © 2023 IEEE.

关键词： Classification Algorithms TV market analysis WEKA

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：