检索结果-内蒙古大学图书馆

6th International Symposium on computer, Consumer and Control, IS3C 2023

作者： Tseng, Kuo-Hao Chu, Shao-Wei Huang, Chieh-Ling Wang, Chuin-Mu Jain, Atishay National Chin-Yi University of Technology Dept. of Computer Science and Information Engineering Taichung Taiwan National Chin-Yi University of Technology Dept. of Artificial Intelligence and Computer Engineering Taichung Taiwan VIT Bhopal University School of Computing Science and Engineering Madhya Pradesh India

ISBN: (纸本)9798350301953

Nondestructive testing is the most economical method for material inspection used in science and technology industries to evaluate the properties of a material component or system without causing damage. Aside from straightforward sensory inspections, the most popular nondestructive testing methods for welds include liquid penetrant, radiography, magnetic particle, eddy current, and ultrasonic testing. Contaminants and metallurgical flaws can be introduced into the weld via the welding process and technique. A weak weld causes a welding fault, which weakens the joint. It is described as the location in the welding process that is outside the allowable tolerance. In our research, we have applied data augmentation technique to our dataset. Further, we have used Detectron2 which offers various detection and segmentation algorithms to perform instance segmentation to segment out various defects in the images of welds. We used Slicing Aided Hyper Inference to slice and overlap the images and performed large-scale instance segmentation using Mask R-CNN X101-FPN on 44,339 images. The approach results in 0.98 training accuracy of MASK- RCNN and a total training loss of 0.2. The Average Precision is calculated as 0.826. © 2023 IEEE.

关键词： Welds

来源：评论

学校读者我要写书评

暂无评论

Arabic Sentiment Analysis of Food Delivery Services Reviews

Arabic Sentiment Analysis of Food Delivery Services Reviews

引用

2023 International Symposium on Networks, computers and Communications, ISNCC 2023

作者： Mustafa, Dheya Khabour, Safaa M. Shatnawi, Ahmed S. Taqieddin, Eyad The Hashemite University Faculty of Engineering Dept. of Computer Engineering Zarqa13133 Jordan Yarmouk University Faculty of Information Technology and Computer Sciences Dept. of Information Systems Irbid21163 Jordan Jordan University of Science & Technology Dept. of Software Engineering Irbid21110 Jordan School of Computing and Informatics Dept. of Cyber Security Al-Hussein Technical University Amman Jordan

ISBN: (纸本)9798350335590

Customer reviews on online platforms have grown to become an important source of insight into a company's performance. Food delivery services (FDS) companies aim to effectively use customers' feedback to identify areas for improvement of customer satisfaction. Although Arabic is becoming one of the most widely used languages on the Internet, only a few studies have focused on Arabic sentiment analysis to date. The present study conducts an extensive emotion mining and sentiment analysis on FDS-related reviews in Arabic, exploiting natural language processing, and machine learning techniques to extract information that reflects customers' subjective viewpoints, recognize their feelings, and determine polarity in the FDS domain. This work begins with collecting the FDS dataset (Talabat), and then extracting and creating a dialects lexicon for Arabic dialects, followed by walking the reader through detailed steps of cleaning and pre-processing a manually annotated dataset. Finally, we examined classification algorithms including Decision Tree (DT), and Support Vector Machine (SVM). We achieved a maximum accuracy of about 82% using the SVM classifier. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Flexibility and Privacy: A Multi-Head Federated Continual Learning Framework for Dynamic Edge Environments 11

Flexibility and Privacy: A Multi-Head Federated Continual Le...

引用

11th International Symposium on Computing and Networking, CANDAR 2023

作者： Chen, Chunlu Wang, Kevin I-Kai Li, Peng Sakurai, Kouichi Kyushu University Graduate School of Information Science and Electrical Engineering Fukuoka Japan The University of Auckland Dept. of Electrical Computer and Software Engineering Auckland New Zealand The University of Aizu School of Computer Science and Engineering Aizuwakamatsu Japan Kyushu University Faculty of Information Science and Electrical Engineering Fukuoka Japan

ISBN: (纸本)9798350306705

Federated Learning (FL) and the Internet of Things (IoT) have revolutionized data processing and analysis, overcoming the traditional limitations of cloud computing. However, traditional machine learning strategies lead to increased costs and catastrophic forgetting due to model retraining with new datasets. Continual learning has been proposed to counter this, enabling models to adapt to new data while preserving previous knowledge, which is beneficial for dynamic edge environments. Despite these advantages, the retention of previous knowledge during the continual learning process may lead to the information leakage. To address the inherent challenges of multitask scenarios, we present a Federated Continual Learning (FCL) framework that integrates the privacy-preserving benefits of Federated Learning (FL) into a continual learning system, ensuring both continual learning and privacy preservation in edge computing data processing and analysis. Specifically, our architecture introduces dedicated fully-connected layers for each task. This architecture ensures that distinctive features pertinent to each task are not only captured but also preserved throughout the model's lifespan. Within our framework, data is processed via task-specific layers. Subsequently, the final label is determined by associating it with the paramount prediction value, thus capitalizing on the model's comprehensive knowledge reservoir to bolster prediction accuracy. We subjected our FCL framework to rigorous validation using two benchmark datasets: MNIST and CFAR-10. Experimental outcomes unequivocally substantiate the efficacy of our proposed methodology. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing–Based UAV Imaging in Heat Pattern Analysis Impact on Climate Change Detection Using Fuzzy Stacked Lasso Elastic-Net Model

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 699-708页

作者： Sailaja, M. Kumar, M. Prema Jyothi, B. Swarna Vanguri, G. L. Narasamba Manjula, S. Priya, D. Divya Department of Computer Science and Engineering Ravindra College of Engineering for Women Andhra Pradesh Kurnool India Dept. of ECE Shri Vishnu Engineering College for Women (A) Andhra Pradesh Bhimavaram 534202 India Department of Computer Science & amp Engineering Madanapalle Institute of Technology & amp Science Andhra Pradesh Madanapalle India Information Technology Aditya College of Engineering & amp Technology(A) Andhra Pradesh Surampalem 533437 India Department of Computer Science and Business Systems Nehru Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Urban heat islands raise surface temperatures, which has an effect on city dwellers’ health and welfare. Urbanisation-related changes to the land surface, which are especially notable right after sunset, have an impact on radiative forcing. Recently, there has been a surge in the usage of unmanned aerial vehicle (UAV) technology, particularly for precision agriculture and plant phenotyping. This is due to the declining cost and increased accessibility of both UAVs and thermal imaging sensors. This interruption affects subsequent operations like target item categorisation and water quality parameter inversion. The goal of this study was to evaluate the potential for combining machine learning (ML) with unmanned aerial vehicle (UAV)–based imaging technology. In this research, the novel technique in UAV image–based temperature pattern detection of various regions of earth and their sea level rise analysis using image classification by machine learning model. Here, the input is collected as UAV images which have been processed for noise removal and normalisation. These image features have been extracted using convolutional active contour–based kernel component analysis and classified using region-based fuzzy stacked lasso elastic-net model. The classified output shows temperature analysis with sea level rise based on image analysis. The experimental analysis has been carried out for various UAV image dataset in terms of detection accuracy, RMSE, F-measure, mean average precision (MAP), and recall. Proposed technique F-measure of 89%, detection accuracy of 96%, MAP of 94%, recall of 92%, and RMSE of 60%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Convolutional active contour Heat pattern detection Kernel component analysis Lasso elastic-net model Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Design of a High-Resolution Video Reconstruction and Transcoding System based on Super-Resolution GAN

Design of a High-Resolution Video Reconstruction and Transco...

引用

2022 IET International Conference on engineering Technologies and Applications, IET-ICETA 2022

作者： Hsu, Tz-Heng Wu, Po-Hui Horng, Gwo-Jiun Southern Taiwan University of Science and Technology Dept. of Computer Science and Information Engineering Tainan Taiwan

ISBN: (数字)9781665491389

ISBN: (纸本)9781665491389

With the popularization of high-definition video devices, more and more users and video streaming service providers desire to restore early classic videos and deliver classic video contents with improved resolution. However, existing video transcoding systems do not support super-resolution video reconstruction. A high-resolution video reconstruction and transcoding system design based on super-resolution image generative adversarial network (GAN) is proposed to perform super-resolution video reconstruction for low resolution videos and then transcode videos with different resolutions to meet the playback requirements of heterogeneous mobile devices in order to provide users with good video viewing quality. Users can have good video viewing quality with the proposed system even in the absence of the original high-resolution videos. © 2022 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Building Wireless Observation Network to Track Biological Clustering

Building Wireless Observation Network to Track Biological Cl...

引用

2022 IET International Conference on engineering Technologies and Applications, IET-ICETA 2022

作者： Guo, Yun-Ru Huang, Yu-Chin Horng, Gwo-Jiun Southern Taiwan University of Science and Technology Dept. Computer Science and Information Engineering Tainan Taiwan

ISBN: (数字)9781665491389

ISBN: (纸本)9781665491389

In recent years, wireless sensor network has been widely used to automatically collect the field ecological environment and observation data, so that researchers can analyze the natural changes of the field ecological environment through the huge amount of data. In this study, biological observation data are transmitted back to the cloud server through wireless communication network, and new wireless communication technologies are developed to improve the data transmission mechanism and overcome the difficulties of remote wireless communication in field areas. In addition, the data transmission efficiency is improved to ensure that the data is successfully transmitted back to the server in real time and quickly, so that the observers do not need to go to the tracking target trap location to read the observation related data. © 2022 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

FACE UNLOCK SYSTEM FOR VEHICLES 2

FACE UNLOCK SYSTEM FOR VEHICLES

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Navya, Soleti Suresh, Juttu Sangeetha, A. Praveen, G. Nabi, Shaik Abdul Kumar, Dilip Mlr Institute of Technology Department of Computer Science and Information Technology India Malla Reddy Engineering College and Management Sciences Department of Information Technology Hyderabad India Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India Cse Dept Avniet Jntuh India Mlr Institute of Technology Dept. of Electrical and Electronics Engineering Hyderabad India

ISBN: (纸本)9798350370188

Currently, all vehicles are key operated. Our intention is therefore to develop an intelligent unlocking system based on facial recognition technology. In Today's era of automation and smart devices, privacy and security are important issues in information technology so to information system, so it is urgent to change system security measures. In previous systems, many vehicle doors had mechanical locks with a limited number of keys. To enhance security, we propose an intelligent vehicle door unlocking system based on facial recognition the system uses camera sensor to recognize faces and image matching algorithms to recognize authenticated faces. Only people with matching faces can open the door this system not only provides additional security but also useful for systems without physical keys. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Modified EfficientNetB3 Deep Learning Model to Classify Colour Fundus Images of Eye Diseases 5

Modified EfficientNetB3 Deep Learning Model to Classify Colo...

引用

5th IEEE International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2023

作者： Sharma, Riya Gangrade, Jayesh Gangrade, Shweta Mishra, Ashish Kumar, Gautam Kumar Gunjan, Vinit Manipal University Jaipur Dept of Computer Science & Engineering Jaipur India Learning Manipal University Jaipur Dept. of Artificial Intelligence & Machine Jaipur India Manipal University Jaipur Dept of Information Technology Jaipur India Jaypee Institute of Information Technology Dept of Computer Science & Engineering Noida India CMR Institute of Technology Department of Computer Science & Engineering Hyderabad India

ISBN: (纸本)9798350338287

The only way to prevent blindness from eye problems is by early detection and prompt treatment. Although colour fundus photography (CFP) is useful for fundus inspection, there is a need for computer-assisted automated diagnosis tools due to the similarities between the early symptoms of many eye disorders. The suggested approach uses cutting-edge deep learning model to categorize images into several disease categories by learning distinguishing features from the input images. The high-resolution fundus photos from individuals with diabetic retinopathy (DR), glaucoma, cataract, and healthy eyes make up most of the dataset used for this research. The experimental findings show that the suggested system achieve 97% accuracy with modified efficientNetB3 model and surpasses current approaches for categorizing eye diseases. This approach may help doctors diagnose and treat eye conditions earlier, leading to better patient outcomes. © 2023 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Toward Project Success Forecasting in Reward-based Crowdfunding through Wide-and-Deep Computational Learning 15

Toward Project Success Forecasting in Reward-based Crowdfund...

引用

15th IEEE International Conference on Industry Applications, INDUSCON 2023

作者： Petchhan, Jirayu Phanichraksaphong, Varinya Doungtap, Surasachai Tridet, Natthanicha Dept. of Electrical Engineering National Taiwan University of Science & Technology Taiwan Dept. of Electronic National Taipei University of Technology Taiwan Dept. of Computer Science and Information Engineering National Taipei University of Technology Taiwan Dept. of Business Management National Taipei University of Technology Taiwan

ISBN: (纸本)9798350314182

While reward-based crowdfunding platforms centered like Kickstarter in the United States, allow entrepreneurs or well-off investors like industrial owners to gather assets and seek patron support, they have evolved into an option for generating funds via an internet platform. Conversely, these crowdfunding initiatives pose innovation challenges due to the uncertainty of receiving support and success. Both project developers and supporters may benefit from it for better knowledge and more accurate forecasting of project success. Analyzing a completed project information, this study aims to identify critical success characteristics of crowdfunding. It investigates the effectiveness of wide-and-deep learning in predicting models. These findings can help fundraisers understand the likelihood of successful fundraising initiatives. © 2023 IEEE.

关键词： Kickstarter Project Success Prediction Reward-based Crowdfunding Wide-and-Deep Learning

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-based Technique to Prevent Grade Tampering: A University Perspective 3

A Blockchain-based Technique to Prevent Grade Tampering: A U...

引用

3rd International Conference on Electrical, computer and Communication engineering, ECCE 2023

作者： Habib, Md. Ahsan Hossen Manik, Md. Motaleb Zaman, Saklain Khulna University of Engineering & Technology Dept. of Computer Science and Engineering Khulna Bangladesh School of Information Studies Syracuse University New York United States

ISBN: (纸本)9798350345360

Education plays a significant role in the advancement of a country. The quality of education that a university provides is crucial to this progress. Almost every university stores the assessed grades on the local server, making them vulnerable to different security attacks e.g. DDoS, SQL injections, cross-site scripting, etc. Any alteration to the assessed grades highly affects the students' personal, academic, and professional lives. This study proposes a blockchain-based secure approach for storing, managing and recovering students' grades by employing both a local server and a blockchain server. The immutability feature of blockchain ensures grade integrity and facilitates the implementation of a grade recovery system. Grades are encrypted before storing on the local and blockchain server to protect privacy. The blockchain server returns the index number of the corresponding block to the user for further use. Finally, the experimental analyses demonstrate the system's effectiveness over state-of-the-art works. © 2023 IEEE.

关键词： Cryptography

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：