检索结果-内蒙古大学图书馆

2023 3rd international conference on Big Data, Artificial intelligence and Risk Management, ICBAR 2023

作者： Lin, Guoyang Xu, Huarong School of Computer and Information Engineering Xiamen University of Technology Fujian Xiamen361024 China

ISBN: (纸本)9798400716478

Missed detection is usually caused by variations in target scales, dense occlusion, and uneven illumination. To tackle the challenge of missed detection in road target detection during complex environments, an enhanced approach called YOLOv5n-SBF based on YOLOv5n has been proposed. Specifically, YOLOv5n-SBF replaces the backbone network of YOLOv5n with Swin Transformer structure and fuses features extracted from Swin Transformer Block and neck network, effectively solving the problem of missing detection and improving the ability to extract features from small targets. Furthermore, we add the BiFormer attention mechanism to the neck of YOLOv5n to capture global and local features, improving the model's performance in visual tasks. Extensive experiments have been conducted on two real-world datasets. The experimental results demonstrate that YOLOv5n-SBF exhibits superior detection efficiency compared to baseline models, and achieves 5.7 percentage points and 18.2 percentage points in mAP@0.5 scores on the public datasets of KITTI and UA-DETRAC, respectively. © 2023 ACM.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Apple Leaves Disease detection Using Multilayer Convolutional Neural Network 3

Apple Leaves Disease Detection Using Multilayer Convolutiona...

引用

3rd IEEE international conference on Intelligent Technologies, CONIT 2023

作者： Das, Saradindu Sharma, Abhilasha Delhi Technological University Department of Software Engineering Delhi India

ISBN: (纸本)9798350338607

Agriculture is the process of growing crops and raising livestock and cultivating other forms of food. It has been a fundamental activity for human societies throughout history, providing food and other resources necessary for survival. Hence plant diseases can have a significant impact on the economy, particularly in agricultural-dependent countries. Crop yield loss, trade restrictions, increased production costs and reduced agricultural productivity are some of the ways plant diseases can affect the economy. Farmers visually inspect their crops for symptoms of diseases, such as discoloration, spots, wilting, and deformities. Farmers can also use their sense of touch and smell to detect diseases, such as the sticky or slimy feel of plant leaves infected with fungal diseases and the foul smell of rotting or decaying plant material. However, traditional methods of plant disease detection do have limitations. Visual inspection and other traditional methods may not always detect diseases at an early stage, and there is a risk of misdiagnosis. Furthermore, conventional techniques may fail to identify illnesses that are not perceptible to the unaided observation. The other alternatives are the use of Artificial intelligence(AI) which includes training computers to detect plant diseases using image recognition technology. These AI methods are increasingly being used for plant disease detection because they offer a fast, accurate, and cost-effective way to diagnose plant diseases, which can help prevent crop losses and increase yields. In this article, a Multilayer CNN model, inspired by InceptionNet, is put forward. This model is trained on the "Plant Pathology 2021: FGVC8 dataset". This proposed model is compared with three existing CNN models using RMSprop with Nesterov Momentum Optimizer. The suggested model outperforms other models that are already trained and achieves an accuracy of 92.56% in diagnosing the disease. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Research on insulation state evaluation and detection technology for 40.5 kV switchgear wall bushing

引用

ENERGY REPORTS 2023年 9卷 295-302页

作者： Niu, Bo Xiang, Zhonghua Liu, Weifeng Ma, Feiyue Xu, Zhi Power Res Inst State Grid Ningxia Power Co Yinchuan 750001 Peoples R China State Grid Ningxia Power Co Yinchuan 750011 Peoples R China State Grid Shanxi Power Co Power Res Inst Xian 710054 Peoples R China Ningxia Licheng Elect Grp Co Ltd Yinchuan 750011 Peoples R China

Wall bushing is the core insulator of 40.5 kV air insulation switchgear, and its insulation performance determines the insulation level and service life of the switchgear. Wall bushing often appears partial discharge, insulation aging, grounded breakdown, and other problems after a period of operation. The main reason is the partial discharge of the equipotential line for the wall bushing. In this paper, the influence of the wall bushing equipotential line on the electric field distribution is systematically analyzed to improve the operating reliability and service life of the 40.5 kV wall bushing. Based on the electric field simulation of the equipotential line, the feasibility of the traditional live detection method is given. The characteristic gas detection method is proposed through air electrolysis, thermal decomposition, early warning of the development trend of the internal suspension defect state. Finally, it proposes corresponding preventive measures to avoid the development of internal suspension defect of wall bushing into a sudden grounding, and ensure the reliability of the system operation.(c) 2022 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： Air switchgear Wall bushing Equipotential line Electric field simulation Partial discharge

来源：评论

学校读者我要写书评

暂无评论

Movement Pattern Recognition in Boxing Using Raw Inertial Measurements 3rd

Movement Pattern Recognition in Boxing Using Raw Inertial Me...

引用

3rd international conference on Optimization, Learning Algorithms and Applications (OL2A)

作者： Puchalski, Radoslaw Giernacki, Wojciech Poznan Univ Tech Poznan Poland

ISBN: (纸本)9783031530357;9783031530364

In the paper, a new machine-learning technique is proposed to recognize movement patterns. The efficient system designed for this purpose uses an artificial neural network (ANN) model implemented on a microcontroller to classify boxing punches. Artificial intelligence (AI) enables the processing of sophisticated and complex patterns, and the X-CUBE-AI package allows the use of these possibilities in portable microprocessor systems. The input data to the network are linear accelerations and angular velocities read from the sensor mounted on the boxer's wrist. By using simple time-domain measurements without extracting signal features, the classification is performed in real-time. An extensive experiment was carried out for two groups with different levels of boxing skills. The developed model demonstrated high efficiency in the identification of individual types of blows.

关键词： activity recognition artificial intelligence artificial neural networks edge computing microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Binary Optimization Using Hybrid Owl Optimization for Biomarker Selection from Cancer Datasets 3

Binary Optimization Using Hybrid Owl Optimization for Biomar...

引用

3rd IEEE international conference on technology, Engineering, Management for Societal Impact using Marketing, Entrepreneurship and Talent, TEMSMET 2023

作者： Sahu, Bibhuprasad Madhavi, Chakradharamahanthi Pani, Sasmita Ravindra, Jvr Department of Artificial Intelligence and Data Science Hyderabad India Balasore College of Engineering and Technology Department of Computer Science and Engineering Odisha Balasore India Department of Electronics & Communication Engineering Hyderabad India

ISBN: (纸本)9798350397819

The enhancement of medical technology generates a massive amount of disease data. For accurate disease detection, feature subset selection plays an important role in solving different classification problems. The selection of a good feature subset enhances the accuracy of the machine learning model and reduces the training time. However, it becomes tricky and challenging to identify the optimal feature subset from the high-dimensional datasets. Different hybrid models are proposed by various researchers to deal with these types of issues. The Owl optimization algorithm proves its efficiency in selecting the optimal features. Keeping an eye on the performance of this stochastic optimization, a binary version of the hybrid Owl optimization algorithm with simulating annealing is proposed to detect the biomarker features from the cancer datasets. K nearest neighbors (KNN) are used as a wrapper to find the best biomarkers. Eight benchmark datasets were employed for the proposed model's performance evaluation. The results show that the proposed model is significantly better than binary Owl optimization, and other counterparts using various performance matrices such as accuracy, selection of best biomarkers, and computational time. The proposed model Owl-SA performs with an accuracy of 100% in the case of CNS and lymphoma datasets. And it retains the accuracy of 99.14%, 97.16%, 98.41%, 97.94%, 98.93%,98.32% for breast, colon, ALL-AML, ovarian, SRBCT, and MLL respectively. © 2023 IEEE.

关键词： Biomarkers

来源：评论

学校读者我要写书评

暂无评论

Document Image Text Extraction Using Emperor Penguin Optimization with Convolutional Neural Network 3

Document Image Text Extraction Using Emperor Penguin Optimiz...

引用

3rd IEEE international conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Ramadan, Ghazi Mohamad Kumar, Bura Vijay Pareek, Piyush Kumar Adnan, Myasar Mundher Jabar, Muhammed Basim College of MLT Ahl Al Bayt University Karbala Iraq School of Computer Science and Artificial Intelligence SR University Telangana Warangal India Nitte Meenakshi Institute of Technology Department of AI and ML Bengaluru India The Islamic University Najaf Iraq National University of Science and Technology Dhi Qar Iraq

ISBN: (纸本)9798350317022

Text attained from natural scenes different information: accordingly, it is greatly utilized in different applications to understand the scenarios of image and also to retrieve the visual information. Human beings greatly benefit from the scene image's semantic content, which helps to understand their surroundings. The process of text identification and character recognition is more difficult in these natural images since the text presents a flexible appearance in an unrestricted environment. Therefore, implemented an Emperor Penguin Optimization (EPO) with Convolutional Neural Network (CNN)-based deep learning process is employed in this framework to effectually detect the text and to recognize the character from the scene images. To eliminate noise natural scene images, a grayscale conversion and image noise removal is typically applied during the preprocessing step. The DWT, LBP, and ResNet 50 techniques are used in feature techniques process, which are assists for the classification process. Following that, extracted features are selected by EPO technique. At last, with these selected features, the character recognition and text detection are achieved successfully by CNN techniques. © 2023 IEEE.

关键词： Convolutional Neural Network (CNN) Emperor Penguin Optimization (EPO) Feature extraction Text, and OCR

来源：评论

学校读者我要写书评

暂无评论

Implementation of Artificial Neural Networks for Grasping Activity detection 3

Implementation of Artificial Neural Networks for Grasping Ac...

引用

3rd IEEE international Biomedical Instrumentation and technology conference, IBITeC 2023

作者： Zaeni, Ilham Ari Elbaith Mahfudz, Mohamad Sulthon Hakim Lestari, Dyah Universitas Negeri Malang Dept. of Electrical Engineering and Informatics Malang Indonesia

ISBN: (纸本)9798350302424

A grasping detection system is essential to develop a prosthesis for helping people with disabilities. This study aims to detect grasping activity using an Artificial Neural Network using an Electromyograph sensor. The tool consists of three components: an Electromyograph sensor, an Arduino Nano, and an LED. The Electromyograph sensor detects muscle activity on the lower left arm. There are 5 healthy subject is involved in this study. Data from the subject is acquired and processed on a computer, and the best architecture with the slightest error was selected to be implemented on the Arduino Nano. The weights and biases for the best architecture were entered in the Arduino Nano and then calculated using the new data from the Electromyograph sensor. The average success rate was 88% for the real-time test. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Communication with Gesture Recognition for People with Disabilities 3

Enhancing Communication with Gesture Recognition for People ...

引用

3rd IEEE international conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Kumar, Akshay Joshi, Kapil Chattopadhyay, Saumitra Kaushik, Yogita Anandaram, Harishchander Taneja, Vansh Uttaranchal Institute of Technology Uttaranchal University Department of CSE Dehradun India Graphic Era Hill University Department of CSE Dehradun India Sunder Deep Group of Institutions Department of MCA/BCA UP Ghaziabad India Amrita School of Artificial Intelligence Coimbatore Department of CSE Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798350317022

Gesture recognition plays a vital role in the era of smart city and visual perception. This work introduces an innovative smart application designed to enhance inclusive communication for individuals with disabilities. By leveraging real-time sign language detection and interpretation, the application harnesses advanced technologies such as artificial intelligence, computer vision, and gesture recognition. Its main goal is to overcome communication barriers, facilitating smooth conversations between sign language users and non-sign language users. This article provides a comprehensive analysis of the application's design, features, and functionality, emphasizing its potential to bridge the communication gap. Through an evaluation of effectiveness, usability, and user satisfaction, the research showcases the transformative impact of the application on sign language communication. The findings highlight the significant role of this technology in promoting inclusivity, empowerment, and equal participation across various domains for individuals with disabilities. Additionally, the article discusses implications, limitations, and identifies future research directions for the further development and implementation of the application. The model is trained on a large corpus downloaded from Kaggle and can be used to interpret sign language. The user simply needs to perform their sign gesture and the model will automatically read and convert it to text in real time. It achieved 97.3% final accuracy hence can be used by sign language users to communicate with non sign language users effectively. © 2023 IEEE.

关键词： Computer vision Convolutional neural network Gesture recognition Sign language

来源：评论

学校读者我要写书评

暂无评论

UAV Path Planning Based on Enhanced PSO-GA 1

引用

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

Machine Learning Approaches for Analysing Static features in Android Malware detection 3

Machine Learning Approaches for Analysing Static features in...

引用

3rd international conference on Secure Cyber Computing and Communications, ICSCCC 2023

作者： Sharma, Nitin Sangal, A.L. Dr B.R Ambedkar National Institute of Technology Department of Computer Science and Engineering Jalandhar India

ISBN: (纸本)9798350300710

As the number of people who own and use smart-phones grows, attackers are always looking for ways to steal sensitive information from mobile phones. Researchers are always working on making it easier to find android malware so that information can be hidden and kept safe. Since the number of new malware is going up, techniques based on machine learning are the best way to find them on a large ***2019 included in this paper uses android permissions and intent as a dataset and a set of features to look for malware. As a way to choose features, Principal Component Analysis (PCA) was used. Different machine learning (ML) models like Naive bias, Decision tree (DT), and Random Forest(RF), k-NN are used to train and test the dataset. The dataset is modeled and evaluated on well-known ML models, and RF was the best classifier in binary classification with a 99.7% success rate and in case of category classification RF was the best classifier with 97.30% success rate for ransomware category. © 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

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：