检索结果-内蒙古大学图书馆

2024 International Workshop on Artificial Intelligence for Signal, Image Processing and Multimedia, AI-SIPM 2024

作者： Trinh, Quoc-Huy Thi, Phuoc-Thao Vo Tran, Minh-Triet Nguyen, Hai-Dang Faculty of Information Technology University of Science VNU-HCM Ho Chi Minh Viet Nam University of Science VNU-HCM Ho Chi Minh Viet Nam Software Engineering Laboratory University of Science VNU-HCM Ho Chi Minh Viet Nam

ISBN: (纸本)9798400705489

The robust human representation embedding is the key challenge of the person-identification task. Although the previous methods achieve competitive results, they still depend on the appearance feature which can be failed in the pedestrian surveillance camera due to the changing of the human's appearance. To overcome this limitation, we introduce Pose Knowledge distill guidance, an effective pose guide learning for the Person Re-Identification framework that leverages pose knowledge guidance through Knowledge distillation to yield more generalized feature embeddings. Because of the significance of human pose in distinguishing individuals, apart from the appearance knowledge, our framework also guides the model to learn the pose information, consequently reducing the overreliance on the appearance of the human and thereby enhancing the model's robustness. Furthermore, the pose knowledge guides transfer the pose knowledge to the Re-Identification model without no increasing the computation cost for the backbone. Through our framework, the re-identification model demonstrates competitive performance, as evidenced by its state-of-the-art results on two datasets: Market-1501 and CuHK03. These results attest to the effectiveness of our approach. © 2024 ACM.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

An Experimental Evaluation of Flagging Sensitive Contents Over Social Networking Environment Using Elevated Classification Logic

An Experimental Evaluation of Flagging Sensitive Contents Ov...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Devadas, Mercy Sharon Sabitha, R. Shankar, K. Edlabadkar, A.P. Aljawawdeh, H.J. Pramitha, K. Jeppiaar Institute of Technology Department of Ece Chennai India Rajalakshmi Engineering College Department of Cse Thandalam Chennai India Easwari Engineering College Department of Cse Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Zarqa University Faculty of information technology Department of Software Engineering Zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia R.M.K. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Kavaraipettai India

ISBN: (纸本)9798331543617

The amount of sensitive content blankets on social networking platforms is rising quickly, necessitating the necessity for swift identification and removal measures. In this paper, our focus is on the capacity of social network flagging systems to recognize and block offensive content. In the rapidly evolving landscape of social networking, the ability to effectively flag sensitive content is crucial for maintaining platform integrity and user safety. This paper introduces an advanced methodology for identifying and managing sensitive content through the Elevated Learning based Classification Logic (ELCL) framework, in which the work is cross-validated with the conventional learning algorithm called Recurrent Neural Network (RNN) to evaluate the efficiency of the proposed scheme. The proposed approach ELCL integrates sophisticated classification algorithms with contextual analysis to enhance the accuracy and efficiency of content moderation in social networking environments. By employing a multi-tiered approach that includes deep learning models and semantic analysis, ELCL can detect nuanced and context-dependent sensitive content that traditional systems often overlook. The framework utilizes a combination of supervised learning for training on labeled datasets and unsupervised learning to adapt to emerging content trends. Empirical evaluations demonstrate that ELCL significantly improves the precision of content flagging, reducing false positives and missed detections. This research highlights ELCL's potential to advance content moderation practices, offering a robust solution for safeguarding user experiences and ensuring compliance with community standards. The impact of user behavior, site affordances, and content type on flagging are also taken into account. This knowledge will help to design better content moderation systems which are both efficient and ethical, in order to make real benefits for the safety and well-being of users on online platforms. © 2024

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis of Plant Disease Identification Methodology Based on Improved Classification and Deep Learning Principle

Experimental Analysis of Plant Disease Identification Method...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Shibu, S. Priyadharshini, S. Madhini, M. Radha, K. Giri, Pallavi Samhan, Ahmad A. Ali Panimalar Engineering College Department of Ece Chennai India Karpaga Vinayaga College of Engineering and Technology Department of Robotics and Automation Tamil Nadu Chengalpattu India S.A. Engineering College Department of Ece Chennai India Dr. Mahalingam College of Engineering and Technology Department of Cse Pollachi Coimbatore India Laxminarayan Innovation Technological University Department of Civil engineering Nagpur India Zarqa University Faculty of Information Technology Deoartment of Software Engineering Zarqa Jordan Universityof Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

The agriculture industry is essential for providing excellent food and significantly contributes to the growth of economies and people. Plant diseases can result in substantial reductions in food output and diminish species diversity. The prompt identification of plant diseases by precise or automated detection methods can improve food production quality and save economic losses. In recent years, deep learning has significantly enhanced the identification accuracy of image categorization and object detection systems. In this paper, a novel method termed Learning Enabled Disease Detection Logic (LDDL) is introduced for the efficient identification of plant diseases, which is cross-validated against the traditional Convolutional Neural Network (CNN) to assess the efficacy of the proposed scheme. The report delineates the specific crop illnesses addressed, the models utilized, the data sources referenced, and the overall efficacy as measured by the performance criteria applied in each study for plant disease diagnosis. The findings demonstrate that the proposed model, LDDL, achieves superior accuracy compared to prevalent illness detection methods and identifies the primary parameters influencing the efficacy of deep learning-based tools. The research offers significant insights for researchers, practitioners, and industry professionals in plant disease detection by addressing challenges and limitations, presenting a thorough understanding of the current research landscape, elucidating the advantages and drawbacks of various methods, and suggesting potential solutions to facilitate their implementation. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analyzing Data Format Interoperability in API Ecosystems Using Big Data Architecture

Analyzing Data Format Interoperability in API Ecosystems Usi...

引用

International Conference on information technology (ICIT)

作者： Wael Alzyadat Suleyman Al-Showarah Department of Software Engineering Faculty of Science and IT Alzaytoonah University of Jordan Amman Jordan dept of Software Engineering Faculity of Information Technology Mutah University

The API is a key player in cut edge technology for interact and exchange information across platforms whatever internally or external where the transfer information needs to be adjusted by several issues during request/response *** traditional concept of API was handle it by data mapping functions for this point uncapitalizable with big data architecture especially of variety of data which data able to presents in different kinds of structured data that aimed to fnd out approach to solve it, for this point the XML play an important role for variety data by dynamic behavior with effective

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adapting Pedagogical Frameworks to Online Learning: Simulating the Tutor Role with LLMs and the QUILT Model

Adapting Pedagogical Frameworks to Online Learning: Simulati...

引用

Advancements in Computing (ICAC), International Conference on

作者： Sandaru Madhubhashana Vibhashana Ranhinda Dineth Jayakody Lakmuthu Shavinda Malithi Nawarathne Prasanna Haddela Dept. of Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331517878

ISBN: (纸本)9798331517885

This paper presents SoloScholar, a novel asynchronous online learning platform designed to deliver personalized education to large undergraduate student groups by integrating established pedagogical frameworks with Large Language Models (LLMs). Leveraging Bloom's Revised Taxonomy, learners are categorized into beginner, intermediate, and advanced levels to personalize the educational content. The platform employs the Questioning and Understanding to Improve Learning and Thinking (QUILT) model to structure tutorial sessions and simulate the teaching role of a tutor at a Higher Education Institute (HEI). To generate contextually relevant and cognitively appropriate questions, carefully crafted prompts are fed into LLMs, synthesizing information from reliable knowledge sources. The efficacy of SoloScholar was evaluated through a dual assessment approach: a technical evaluation using the Retrieval Augmented Generation Assessment (RAGAS) framework and a human evaluation involving academic experts. The technical evaluation demonstrated high scores in answer relevancy and context utilization across all learning levels. Similarly, quantitative responses from academic experts indicated strong satisfaction with the quality and appropriateness of the generated content. The findings underscore the potential of integrating LLMs with pedagogical models to enhance personalization in online education. SoloScholar effectively addresses challenges associated with large-group teaching by providing adaptive learning experiences that cater to diverse cognitive needs.

关键词： Adaptation models Adaptive learning Computational modeling Large language models Education Taxonomy Retrieval augmented generation Tutorials Reliability

来源：评论

学校读者我要写书评

暂无评论

Design and Simulation of a Network Infrastructure for a Multi-Branch Organization Using Cisco Packet Tracer 25

Design and Simulation of a Network Infrastructure for a Mult...

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Aljamal, Osama S. Aljamal, Mahmoud Alsarhan, Ayoub Aljaidi, Mohammad Okour, Saif Al-Aiash, Issa Al-Qerem, Ahmad Daoud, Essam Al Elrashidi, Ali Al Hussein Technical University Department of Computer Science Amman Jordan Irbid National University Faculty of Science and Information Technology Department of Cybersecurity Irbid21110 Jordan The Hashemite University Department of Information Technology Zarqa Jordan Zarqa University Department of Computer Science Zarqa Jordan Irbid National University Department of Software Engineering Irbid Jordan Zarqa University Department of Cybersecurity Zarqa Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

Designing and simulating a network infrastructure for multi-branch organizations is essential for ensuring seamless connectivity and efficient operations. This paper addresses the challenges faced by organizations in maintaining consistent and reliable network connectivity across multiple locations, including managing network traffic, ensuring security, and optimizing resource allocation while keeping costs under control. The study presents a comprehensive methodology involving the conceptualization of network ideas, designing the network architecture, adding necessary devices and tools, configuring these devices according to the network topology, and troubleshooting to ensure optimal performance. Key elements such as VLANs, routers, switches, and routing protocols like RIP, OSPF, and EIGRP are incorporated, with the entire design and simulation conducted using Cisco Packet Tracer. The findings demonstrate that full connectivity between headquarters and branch sites can be achieved within a budget of $40,000. This paper provides a practical guide for implementing similar network projects, emphasizing the importance of detailed configurations and troubleshooting steps, and recommends adopting this methodology to enhance network infrastructure efficiently and cost-effectively. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

ThyroidNet:A Deep Learning Network for Localization and Classification of Thyroid Nodules

引用

Computer Modeling in engineering & Sciences 2024年第4期139卷 361-382页

作者： Lu Chen Huaqiang Chen Zhikai Pan Sheng Xu Guangsheng Lai Shuwen Chen Shuihua Wang Xiaodong Gu Yudong Zhang Ultrasonic Department Zhongda Hospital Affiliated to Southeast UniversityNanjing210009China School of Physics and Information Engineering Jiangsu Second Normal UniversityNanjing211200China School of Computing and Mathematical Sciences University of LeicesterLeicesterLE17RHUK Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia State Key Laboratory of MillimeterWaves Southeast UniversityNanjing210096China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Jiangsu Second Normal UniversityNanjing211200China School of Software Engineering Quanzhou Normal UniversityQuanzhou362000China Department of Biological Sciences Xi’an Jiaotong-Liverpool UniversitySuzhou215123China

Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques ***:A novel method,ThyroidNet,is introduced and evaluated based on deep learning for the localization and classification of thyroid ***,we propose the multitask TransUnet,which combines the TransUnet encoder and decoder with multitask ***,we propose the DualLoss function,tailored to the thyroid nodule localization and classification *** balances the learning of the localization and classification tasks to help improve the model’s generalization ***,we introduce strategies for augmenting the ***,we submit a novel deep learning model,ThyroidNet,to accurately detect thyroid ***:ThyroidNet was evaluated on private datasets and was comparable to other existing methods,including U-Net and *** results show that ThyroidNet outperformed these methods in localizing and classifying thyroid *** achieved improved accuracy of 3.9%and 1.5%,***:ThyroidNet significantly improves the clinical diagnosis of thyroid nodules and supports medical image analysis *** research directions include optimization of the model structure,expansion of the dataset size,reduction of computational complexity and memory requirements,and exploration of additional applications of ThyroidNet in medical image analysis.

关键词： ThyroidNet deep learning TransUnet multitask learning medical image analysis

来源：评论

学校读者我要写书评

暂无评论

FGRL-Net: Fine-Grained Personalized Patient Representation Learning for Clinical Risk Prediction Based on EHRs

FGRL-Net: Fine-Grained Personalized Patient Representation L...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Chio, KaKit Zhu, Wenhao He, Lihua Zhang, Dian Yang, Xu Luo, Wuman Macao Polytechnic University Faculty of Applied Sciences S.A.R Macao China School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Province China Shenzhen University Department of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350337020

Personalized patient representation learning (PPRL) is a critical element in clinical risk prediction. It aims to obtain a complete portrait of each patient based on Electronic Health Records (EHR). Although existing works have achieved remarkable progress in healthcare prediction, there are still three major issues. First, feature correlation is crucial for risk prediction, but it has not yet been fully exploited by existing works. Second, variation pattern of dynamic feature contains useful information about patient's physical status, but adaptive pattern recognition is still a challenge. Third, existing works usually adopt a two-stage embedding process to process each dimension of the EHR data. However, some useful low-level information for PPRL will be lost. To address these issues, in this paper, we propose a fine-grained PPRL architecture named FG RL- N et for clinical risk prediction based on EHR. Specifically, we propose a Medical Feature Correlation Detection Module (FCM) to effectively learn the feature correlations for each patient and a Temporal Variation Pattern Recognition Module (TVM) to effectively detect the variation patterns of each dynamic feature. Moreover, we design a Fine-Grained Representation Mechanism (FGRM) to preserve the low-level information (from both feature and visit dimensions) useful for risk prediction. In addition, in the stage of data preprocessing, We utilize generic medical classification knowledge to classify numerical dynamic data. We conduct the in-hospital mortality experiment and the decompensation experiment on a real-world dataset. The experiment results show that the FGRL-Net outperforms state-of-the-art approaches. The source code is provided in github https://***/JackyChio/FGRL-Net. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Low-Cost IoT Mornitoring the Quality of River: A Case Study of Wang River in Lampang Municipality 27

The Low-Cost IoT Mornitoring the Quality of River: A Case St...

引用

27th International Computer Science and engineering Conference, ICSEC 2023

作者： Krueganta, Narong Chieochan, Oran Saokaew, Anukit Yana, Ekkachai Singkaew, Chaowoot Sawangtook, Weerachai Boonchieng, Ekkarat Wongchai, Warakhom Srimakorn, Sakchai School of Industrial Technology Lampang Rajabhat University Faculty of Industrial Technology Lampang52000 Thailand School of Information Technology Lampang Rajabhat University Faculty of Sciences Lampang52100 Thailand School of Environmental Innovation Lampang Rajabhat University Faculty of Science Lampang52100 Thailand School of Computer Engineering Lampang Rajabhat University Faculty of Industrial Technology Lampang52100 Thailand Chiang Mai University Faculty of Sciences Department of Computer Sciences Chiang Mai50200 Thailand School of Industrial Electrical Engineering Lampang Rajabhat University Faculty of Industrial Technology Lampang52000 Thailand School of Software Engineering Lampang Rajabhat University Faculty of Industrial Technology Lampang52000 Thailand

ISBN: (纸本)9798350342109

The research project focuses on prototyping an IoT (Internet of Things) system for measuring and monitoring the quality of the Wang River in Lampang Municipality. The system utilizes EC (Electrical Conductivity), pH, and temperature sensors connected to an ESP32 microcontroller with a custom-developed board. Additionally, the IoT system is supported by a solar cell system to provide power. The software programming is implemented using Arduino C++ on the PlatformIO platform, which is integrated with Visual Studio code. The IoT platform chosen for this project is ThingsBoard, specifically the community version. The research findings indicate that the utilization of IoT technology combined with the sensors has improved the prototype of a low-cost IoT monitoring system for assessing the quality of the Wang River in Lampang Municipality. © 2023 IEEE.

关键词： Rivers

来源：评论

学校读者我要写书评

暂无评论

Autonomous Warning System To Detect Road Blockers And Collisions While Notifying Users About Potential Risks

Autonomous Warning System To Detect Road Blockers And Collis...

引用

International Research Conference on Smart Computing and Systems engineering (SCSE)

作者： P. Mahinsa Athree Dharshana Kasthurirathna Faculty of Graduate Studies and Research Sri Lanka Institute of Information Technology Malabe Sri Lanka Dept. of Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798350375688

ISBN: (纸本)9798350375695

Usually, only time and distance are considered when choosing a route, not the risk involved. Due to not taking the danger into account before the trip, we might have to experience numerous problems and risks. As a result, there may be dangerous situations for the driver and passengers and time and fuel wastage. Thus, the issue is how to evaluate the road while choosing the route before using it and What elements are crucial to take into account while evaluating a route’s issues. This project aims to develop a system to evaluate risk before a vehicle enters a dangerous area and predict the best path by evaluating aspects of roads including accidents, road repairs, and road blockers. Image Classification is used to detect road repairs and blockers. Federated Learning will be used to improve the accuracy of the Road blocker detector. Here, Clients will train locally using private data, send their optimized parameters to the central server, and then aggregate those trained parameters to produce a global model. This process will be continued until the system has a trained model that is ideal for predicting roadblocks. YOLOV7 object detector will be used to detect vehicle collisions and accidents in real-time. Finally, Federated Learning will be used to notify users about detected incidents and event details will be marked in a Google map which is running on a Flask application. Using the Blocker map, drivers can decide which route is more suitable based on the proposed system’s detections and blocker details.

关键词： Federated learning Roads Detectors Maintenance engineering Data models Real-time systems Servers

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：