检索结果-内蒙古大学图书馆

UAV Path Planning Based on Enhanced PSO-GA 1

3rd CAAI international conference on Artificial intelligence (CICAI)

作者： Xiang, Hongbo Liu, Xiaobo Song, Xinsheng Zhou, Wen China Univ Geosci Key Lab Geol Survey & Evaluat Minist Educ Wuhan 430074 Peoples R China China Univ Geosci Sch Automat Wuhan 430074 Peoples R China

ISBN: (数字)9789819991198

ISBN: (纸本)9789819991181;9789819991198

Path planning for unmanned aerial vehicles (UAV) is a key technology for UAV intelligent system in the aspect of model construction. In order to improve the rapidity and optimality of UAV path planning, we propose a hybrid approach for UAV path planning in 2D environment. First, an enhanced particle swarm optimization algorithm (EPSO) combine with genetic algorithm (GA) which named as EPSO-GA is utilized to obtain the initial paths of UAV. In EPSO-GA, a hybrid initialization of Q-learning and random initial solutions is adopted to find the better initial paths for the UAV, which improves the quality of initial paths and accelerates the convergence of the EPSO-GA. The acceleration coefficients of EPSO-GA are designed as adaptive ones by the fitness value to make full use of all particles and strengthen the global search ability of the algorithm. Finally, the effectiveness of the proposed algorithm is proved by the experiments of UAV path planning.

关键词： UAV path planning PSO-GA Hybrid initialization Q-learning

来源：评论

学校读者我要写书评

暂无评论

Implementation of campus supervision system based on Yolov5 and SlowFast optimization model 3

Implementation of campus supervision system based on Yolov5 ...

引用

3rd international conference on Green Communication, Network, and Internet of Things, CNIoT 2023

作者： Zhang, Ninghai Wang, Yanchao College of Electronics and Information Engineering Liaoning Institute of Science and Technology Liaoning Province Benxi China

ISBN: (纸本)9781510668867

With the end of the COVID-19 epidemic in China, colleges and universities across the country have restored the original order and implemented offline teaching. However, the turnover rate of campus personnel is also gradually increasing, and the traditional campus supervision system has pain points such as old and complex system and low efficiency. In order to solve the above problems and better assist the monitoring and management of the campus, we propose and make a campus monitoring system based on computer vision technology. We use the Yolov5 model for object detection, the optimized deepsort algorithm for object tracking, and the SlowFast network model open sourced by the Facebook team for behavior prediction. Through verification and actual test, the model has a range accuracy of 0.5 meters to 30 meters, and has strong anti-physical interference. Therefore, we conclude that this model has better efficiency and a wide range of application scenarios. © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Single-stage face detection method based on feature fusion and data enhancement 3

Single-stage face detection method based on feature fusion a...

引用

3rd international conference on Artificial intelligence and Computer Engineering, ICAICE 2022

作者： Li, Hua Chen, Yujie Yang, Yang Zhao, Lingdi College of Computer Science and Technology Changchun University of Science and Technology No.7186 Weixing Road Chaoyang District Changchun China

ISBN: (纸本)9781510663473

The depth face detector based on an anchor frame has demonstrated good performance with the advancement of science and technology, but tiny faces and partially occluded faces are still difficult to identify under the effect of posture, lighting, occlusion, and other factors. We present the ESSFD, an enhanced single-stage face detector, to increase the robustness of face detection in complex environments. The following are the important points: (1) Enhancing feature extraction by using an optimized ResNet-D network in the backbone network and adding Atrous Convolution Layer supplementary feature pyramids. (2) For data augmentation, use a combination of Gaussian blur and color jitter to lessen the impact of image environmental elements and increase the model's robustness;(3) Fine-tune the training parameters for the model. in the presence of unusual postures, complicated lighting, and partial occlusion, ESSFD can increase the detection accuracy of tiny faces when compared to *** reveal that in the easy and medium stages of the WIDER FACE dataset, the average accuracy (AP) of the ESSFD detector is around 1% higher than that of the advanced RetinaFace face detector (AP=95.373%). In the hard tiny face detection stage, it is around 2% higher than RetinaFace. © 2023 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Analysis of Panoramic Images using Deep Learning For Dental Disease Identification 3

Analysis of Panoramic Images using Deep Learning For Dental ...

引用

3rd international conference on Artificial intelligence and Smart Energy, ICAIS 2023

作者： Mallick, Mohamed Midhun Kumar, A. Govindaraju, Sakthi Kumar, A. Suresh Kandasamy, Manivel Anitha, P. Rathinam Group of Institutions Coimbaotore India Indian Biological Data Center Center for Biotechnology Database Engineer Faridabab India Galogotias University School of Computing Science and Engineering Delhi NCR India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Karnavati University Unitedworld School of Computational Intelligence Gujarat India Oasys Institute of Technology Trichy India

ISBN: (纸本)9781665462167

Dental caries is a distinct disease strategy caused by the metabolic action of dental biofilm, which continually demineralizes lacquer and dentine. Its commonly known as tooth rot, is one of the most prevalent and long- lasting dental illnesses, affecting people at all stages of their lives. There are a few different sorts of dental x-rays, each of which records a different perspective on dental living systems for caries detection and has the highest symptomatic accuracy, whereas panoramic radiography has the lowest Despite this, Bitewing has a few downsides, such as patient unease. Because of the lack of knowledge among administrators, Bitewing imaging frequently results in increased patient radiation exposure as a result of the need for image retakes. On the other hand, panoramic x-ray scans, also known as Orthopantomogram (OPG), are commonly utilized to capture the whole mouth with a small amount of radiation. OPG has a low radiation content, is simple to use, takes less time, and provides exceptional patient comfort. In this way, when compared to intraoral frameworks, pediatric, impaired, and senior people would profit greatly from panoramic imaging frameworks. This research work explores panoramic photos to detect accurate dental disease using deep learning. As a result, most patients can benefit from panoramic imaging, which covers a large portion of the maxillofacial region, including all of the teeth. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Exploratory Data Analysis Techniques for Power Theft detection in Residential Distribution Grids 3

Comparative Evaluation of Exploratory Data Analysis Techniqu...

引用

3rd IEEE international conference on Smart Technologies for Power, Energy and Control, STPEC 2023

作者： Agarwal, Swati Srivastava, Ayush Sodhi, Ranjana Soni, Tukesh Indian Institute of Technology Ropar Department of Electrical Engineering Rupnagar India Uiet Punjab University Dept. of Mechanical Engineering Chandigarh India

ISBN: (纸本)9798350304732

This paper presents a comparative evaluation of the performance of various Exploratory Data Analysis (EDA) techniques for detecting power theft in residential distribution networks. The techniques include Pearson Correlation Coefficient (PCC), Fuzzy C-Means Clustering (FCM) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). They are assessed using well-known classification assessment measures such as Accuracy, Geometric Truth Rate, Youden's Index and Area under Receiver operating characteristics curve. In the present work, power theft scenarios are divided into four different categories. Suspicious consumers are then identified using the concepts of feature extraction, correlation, and clustering. The information needed to detect the corrupt customers comes from a monitoring system at the distribution transformer for a block and electricity load data from smart meters installed at customer homes in the same block. The analysis is tested on actual dataset from UK power networks and it is found that FCM outperforms the other techniques. Sensitivity analysis is further performed to determine how the technique performs significantly w.r.t. various parameters. © 2023 IEEE.

关键词： Classification Assessment Metrics Exploratory Data Anal-ysis Techniques Feature Extraction Power theft detection

来源：评论

学校读者我要写书评

暂无评论

The Role of Machine Learning Algorithms in Developing Android App and to do Malware detection 3

The Role of Machine Learning Algorithms in Developing Androi...

引用

3rd international conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2023

作者： Sudhamsu, Gadug Bhatt, Rahul Jakka, Geethamanikanta Jweeg, Muhsin J. Alfurhood, Badria Sulaiman Tripathi, Vikas Department of Computer Science and Engineering Bangalore India Dev Bhoomi Uttarakhand University Department of CSE Uttarakhand Dehradun India University of the Cumberlands Data Analytics Information Technology United States Al-Farahidi University College of Technical Engineering Baghdad Iraq Princess Νourah Hint Ahdulrahman University College of Computer and Information Sciences Department of Computer Sciences Saudi Arabia Graphic Era Deemed to Be University Department CSE India

ISBN: (纸本)9798350399264

Because there are so many issues that have had suitable solutions, cybersecurity is now the subject that worries computer scientists and system administrators the most. The rapid development of information technology and its inherent integration into every aspect of our lives have made it possible to analyze and identify a broad variety of harmful software packages and the targets of these programmes. Malware ***, Android malware has gotten some notice. It seems to attract a lot of attention on the internet. Android is one of the most well-liked operating systems that dominates the operating system market. In 2020, 85% of smartphones will run on the Android operating system, according to statistics from the system. Mobile virus attacks have increased in frequency over time. Known to infect a phone system with applications that seem harmless but really contain malware is one of the most popular approaches. Malware on cellphones has already been detected using machine learning. Deep learning and supervised learning techniques have been used to achieve this. Drawing on consumer rights, this study evaluates the effectiveness of multiple categorization approaches to find virus in Android apps. © 2023 IEEE.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

Multi-task transient stability assessment of power system based on graph neural network with interpretable attribution analysis

引用

ENERGY REPORTS 2023年 9卷 930-942页

作者： Gu, Sili Qiao, Ji Shi, Wenlong Yang, Fan Zhou, Xiang Zhao, Zixuan China Elect Power Res Inst Dept Artificial Intelligence Applicat Beijing Peoples R China

Transient power angle stability analysis and voltage stability analysis are the key basis of power system security and stability control. The diversified operation modes of power system put forward higher requirements for real-time and topology generalization of transient stability assessment. Based on Convolution Neural Network (CNN) and Graph Attention Networks (GAT), this paper uses the wide-area transient response features to evaluate the transient angle stability and voltage stability of power system. Firstly, CNN is used to encode the temporal variation characteristics of transient features of electrical components in hidden layer space. Secondly, the encoded hidden layer features are mapped into graph data samples according to the spatial topological correlation of electrical components, so as to train and build a multi-task transient stability assessment model based on GAT. The model can adaptively capture the interaction relationship between encoded hidden layer features of topologically correlated components, and realizes real-time evaluation of transient angle stability and transient voltage stability by perceiving the temporal-spatial correlation of transient features. Finally, Shapley additive explanation (SHAP) method is used to explain the decision-making mechanism of the model and extract the key features that affect the transient stability, so as to enhance the ability of power grid operators to perceive the transient stability situation. The results of IEEE-39 system show that the transient stability assessment model has good accuracy and topology generalization, and the results of interpretable analysis are in line with the conclusions of traditional mechanism cognition, which helps to improve the credibility of the model results. & COPY;2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Transient stability assessment Graph neural network Shapley additive explanation Deep learning interpretable method

来源：评论

学校读者我要写书评

暂无评论

Research on the application of YOLOv5 in station interlocking test 3

Research on the application of YOLOv5 in station interlockin...

引用

3rd international conference on Image Processing and Intelligent Control, IPIC 2023

作者： Cheng, Hao He, Tao Tian, Rui Key Laboratory of Optoelectronic Technology and Intelligent Control Ministry of Education Lanzhou Jiaotong University Gansu Lanzhou China Institute of Automatic Control Lanzhou Jiaotong University Gansu Lanzhou China

ISBN: (纸本)9781510668140

With the rapid development of high-speed railway, it is necessary to ensure the safety of railway running, and the computer interlock system is the key equipment to ensure the safety of railway running in the station. It is a real-time system with high safety and reliability, which needs comprehensive and strict testing before it is put into use. In order to ensure that the interlocking system can strictly complete the function of each part, the computer interlocking test is very important. In recent years, with the rapid development of deep learning and image processing technology, in order to further improve the test efficiency of computer interlocking system, this paper studies the result decision module of automatic interlocking test. Target detection algorithm YOLOv5 is adopted to realize the location and recognition of signal, switch and section icon on the interlocking interface. © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Research on Accounting Data Encryption Processing system based on Artificial intelligence 3

Research on Accounting Data Encryption Processing System bas...

引用

3rd international conference on Machine Learning and Big Data Analytics for IoT Security and Privacy, SPIoT2023

作者： Yao, Li Jin, Minyan College of Accounting Zhanjiang Science and Technology College Guangdong Zhanjiang524009 China

To address the issues of low confidentiality and poor real-time performance in the encryption process of accounting system data, a proposed solution based on artificial intelligence is presented. Firstly, by studying the knowledge and reasoning abilities utilized by artificial intelligence technology to simulate human experts in solving complex problems, the fundamental structure of the accounting system is obtained. Then, the data prior to encryption is processed using the wavelet denoising method to eliminate noise points from the data. Additionally, a chaotic parameter modulation encryption method is introduced, utilizing a logistic chaotic mapping model to modulate the data parameters. Simultaneously, during encryption and decryption analysis, iterative criteria for data parameters are established to reduce the number of iterations and achieve real-time data encryption. Finally, experimental results demonstrate that this method possesses higher efficiency in terms of real-time performance, integrity, and confidentiality, providing superior real-time data encryption capabilities. © 2023 The Authors. Published by Elsevier B.V.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A Classification of Attacks in an IDS Using Sparse Convolutional Autoencoder and DNN 1

引用

3rd international conference on Smart Computing and Cyber Security—Strategic Foresight, Security Challenges and Innovation, SMARTCYBER 2023

作者： Kandula, Pradeep Roy, Monideepa Ghosh, Kuntal Rao, Budipi Nageswara Datta, Sujoy School of Computer Engineering KIIT Bhubaneswar India Machine Intelligence Unit Indian Statistical Institute Kolkata India School of Electronics Engineering KIIT Bhubaneswar India

ISBN: (数字)9789819705733

ISBN: (纸本)9789819705726

The network security plays an important role in this modern world. After emerging modern technologies like cloud computing, big data, Internet of Things (IOT), Blockchain and so forth, network security set more complex task to firewalls and cyber security department. Network intrusion detection is a software system or a device which helps in monitoring unauthorized access and vulnerabilities in the complex networks. We propose a hybrid model using Sparse Convolution Autoencoder (SCA) along with Deep Neural Network for intrusion detection in the communication network. We applied our model on KDDCup’99 dataset and achieved an accuracy of 99.7%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Intrusion detection

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：