检索结果-内蒙古大学图书馆

Next Generation Intelligent Traffic Signal Control: Empowering Electronics Consumers with Edge-AIoT Capabilities

IEEE Transactions on Consumer Electronics 2025年第1期71卷 1926-1934页

作者： Chavhan, Suresh Doswada, Rohit Gupta, Deepak Gunjal, Saymam Rodrigues, Joel J.P.C. School of Data Sciences Indian Institute of Science Education and Research Kerala Thiruvananthapuram India C-DoT Karnataka Bangalore India Dept. of Computer Science and Engineering Maharaja Agrasen Institute of Technology Delhi India Centre for Research Impact and Outcome Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering University of Visvesvaraya College of Engineering Karnataka Bangalore India Federal University of Piaui PI Teresina Brazil

Traffic congestion has become a major issue that is being faced by the majority of road users. The increasing vehicle usage, and the lack of space and funds to construct new transport infrastructure, further complicates the issue. In this scenario, it is important to come up with an intelligent and economical solution that improves the quality of road users' service. The problem with the traffic handling framework is signal timings are fixed which is not adaptive to the density of vehicles. To address this issue we propose an Edge-Augument Artificial Intelligence of Things (AIoT) road user cooperation for traffic management. The proposed system efficiently utilizes electronic devices to learn and adapt to changing traffic conditions in real-time. By optimizing the traffic signal timings based on the actual traffic conditions, adaptive systems reduce delay, improve traffic flow, reduce fuel consumption and pollution, and improve the electronics consumers' and road users' experiences. The proposed system has been tested with real-time experiments by integrating Electronic devices like cameras, smartphones, and AGX Xavier (edge device) with Cloud (ThingSpeak). The proposed system is verified by simulating the proposed system in the SUMO traffic simulator and its reliability is concluded by comparing the waiting time, depart delay, running, and halt time with the existing traditional method. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Dual-level Mixup for Graph Few-shot Learning with Fewer Tasks 25

Dual-level Mixup for Graph Few-shot Learning with Fewer Task...

引用

34th ACM Web Conference, WWW 2025

作者： Liu, Yonghao Li, Mengyu Giunchiglia, Fausto Huang, Lan Li, Ximing Feng, Xiaoyue Guan, Renchu College of Computer Science and Technology Jilin University Changchun China Department of Information Engineering and Computer Science University of Trento Trento Italy Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education China

ISBN: (纸本)9798400712746

Graph neural networks have been demonstrated as a powerful paradigm for effectively learning graph-structured data on the web and mining content from it. Current leading graph models require a large number of labeled samples for training, which unavoidably leads to overfitting in few-shot scenarios. Recent research has sought to alleviate this issue by simultaneously leveraging graph learning and meta-learning paradigms. However, these graph meta-learning models assume the availability of numerous meta-training tasks to learn transferable meta-knowledge. Such assumption may not be feasible in the real world due to the difficulty of constructing tasks and the substantial costs involved. Therefore, we propose a SiMple yet effectIve approach for graph few-shot Learning with fEwer tasks, named SMILE. We introduce a dual-level mixup strategy, encompassing both within-task and across-task mixup, to simultaneously enrich the available nodes and tasks in meta-learning. Moreover, we explicitly leverage the prior information provided by the node degrees in the graph to encode expressive node representations. Theoretically, we demonstrate that SMILE can enhance the model generalization ability. Empirically, SMILE consistently outperforms other competitive models by a large margin across all evaluated datasets with in-domain and cross-domain settings. Our anonymous code can be found here. © 2025 Copyright held by the owner/author(s).

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Artificial Bee Colony and Adaptive Fuzzy K-Means for Detecting Abnormalities in Brain MR Images 5

Hybrid Artificial Bee Colony and Adaptive Fuzzy K-Means for ...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Ts, Kiran Babu Arun Francis, G. Sathya, R. Vijayalakshmi, A. Ramaraj, Kottaimalai Thilagaraj, M. MVJ College of Engineering Department of Computer Science and Engineering Bengaluru India Karpagam College of Engineering Department of Electronics and Communication Engineering Coimbatore India Rajalakshmi Engineering College Department of Electronics and Communication Engineering Tamilnadu Chennai India Hindusthan College of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamilnadu Krishnankoil India MVJ College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798331530013

A brain tumor is an abnormal mass of cells in the brain and can cause issues by pressing on the brain or infiltrating brain tissue. Not all brain tumors are cancerous;grades 1 and 2 are benign but may recur and become malignant. Symptoms vary depending on the affected area of the brain, as different regions control different functions. Medical image processing is the need for the investigation of 3D images of the humans' internal organs, typically collected from a Magnetic Resonance Imaging or Computed Tomography, to identify disorders, assist therapeutic procedures like incision preparation and in academic research. The multiparametric MR images of individuals with low- and high-grade gliomas that were manually segregated by skilled assessors constitute up the BraTS data set. Human separation of tumors is a laborious, time-consuming process that necessitates the delineation of sections by a human expert. Segmenting gliomas using autonomous algorithms for learning has been explored as a solution to these inadequacies. For glioma segmentation, the suggested method combines artificial bee colony (ABC) optimization and adaptive fuzzy k-means clustering (AFKM) that may be readily integrated into the medical procedure. ABC optimization efficiently finds optimal initial cluster centroids, overcoming Fuzzy K-Means' limitation of poor initialization and suboptimal results. ABC optimization balances global search and local refinement for efficient clustering, while Adaptive Fuzzy K-Means dynamically adjusts clusters, with ABC fine-tuning for optimal fit. The efficacy of the suggested method was validated with the help of metric parameters. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Tasks Benefit Skeleton-based Action Recognition

Auxiliary Tasks Benefit Skeleton-based Action Recognition

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yang, Yuheng Chen, Haipeng College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China

ISBN: (纸本)9798350368741

Skeleton-based action recognition has long been a fundamental and intriguing problem in machine intelligence. This task is challenging due to pose occlusion and rapid motion, which typically results in incomplete or noisy skeleton data. State-of-the-art methods tend to learn human motion directly from these corrupted skeletons as if they were reliable. Unfortunately, this might lead to unsatisfactory results when key regions of the skeleton are occluded or disturbed. To tackle the problem, we propose a novel framework that integrates auxiliary tasks into a motion modeling network. These auxiliary tasks corrupt partial human skeletons with masking or noise and then force the network to recover the corrupted data, explicitly facilitating robust feature representation learning. We further propose supervising the auxiliary tasks with mutual information losses, mathematically ensuring feature consistency and spatial alignment between the recovered and original skeleton data. Empirically, our approach sets the new state-of-the-art performance on three benchmark datasets. © 2025 IEEE.

关键词： auxiliary task mutual information skeleton-based action recognition

来源：评论

学校读者我要写书评

暂无评论

Mini Prototype of the Futuristic Bin with an Automatic Waste Sortation System for Managing the Garbage Problems in Society 10

Mini Prototype of the Futuristic Bin with an Automatic Waste...

引用

10th International Conference on Wireless and Telematics, ICWT 2024

作者： Putra, Muhammad Taufik Dwi Adiwilaga, Anugrah Munggaran, Jezzy Putra Adhitama, Muhammad Azka As'ad, Raihan Anwar Alhafidz, Ahmad Ali Nurmalasari, Rin Rin Juhana, Agus Universitas Pendidikan Indonesia Computer Engineering Study Program Bandung Indonesia UIN Sunan Gunung Djati Department of Electrical Engineering Bandung Indonesia Universitas Pendidikan Indonesia Multimedia Education Study Program Bandung Indonesia

ISBN: (纸本)9798350377057

This article explores the development and implementation of futuristic bins with automated waste sortation systems to address improper and mixed waste disposal challenges. Despite the existence of categorized waste bins, individuals often dispose of waste improperly, hindering the sorting and decomposition processes. Integrating advanced technologies, such as Artificial Intelligence (AI), futuristic bins offer innovative solutions. Futuristic bins with automated sorting systems facilitate accurate waste sorting, reduce mixing, and optimize waste disposal. These bins increase efficiency, reduce costs, and optimize collection routes while promoting environmental cleanliness and awareness of waste management. The article describes the research methodology, including preliminary study, specification requirements analysis, prototype development, and testing. The results demonstrate the implemented system's accuracy and real-time object detection capabilities. The study also acknowledges limitations and suggests future research directions, including improving communication between object detection algorithms and microcontrollers. Overall, the development of futuristic bins with automated waste sortation systems represents a significant advancement in waste management, with the potential to revolutionize waste management systems and create sustainable cities and communities. © 2024 IEEE.

关键词： Waste disposal

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Optimization of Software Quality Model Using Improvised Genetic Algorithm and EEM 1

Hyperparameter Optimization of Software Quality Model Using ...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Singh, Rakhi Sharma, Vishnu Kaushik, Neeraj Malhotra, Ritu Rauthan, Hemlata Delhi Institute of Higher Education Department of Computer Application Greater Noida India ITS Engineering College Department Of Computer Science and Engineering Greater Noida India Galgotias College of Engineering and Tehnology Department of Computer Applications Greater Noida India GNIOT Institute of Professional Studies Department of Computer Applications Greater Noida India Delhi Institute of Higher Education Department of Computer Applications Greater Noida India

ISBN: (纸本)9798350356816

Software quality analysis has become one of the topmost concerns in the modern world and requires the massive attention of developers and testers during software development. Software quality analysis is a multidimensional notion and one attribute may not describe the software product's overall quality. Software developer's objective is to build a software product that attains the highest quality which depends on multifarious attributes namely functional suitability, maintainability, etc. However, analysis of software product quality is challenging in both the development and maintenance phases. This research is aimed at hyperparameter optimization of the software quality model using an improvised genetic algorithm and an enhanced ensemble model (EEM) approach. In this research, there has been shown the optimal possibility of software quality model hyperparameter optimization using the modified architecture of genetic algorithm along with EEM. To validate the performance of this suggested approach, PROMISE Repository datasets have been utilized. As a result, this proposed approach achieves all performance metrics very optimal. The evaluated values of accuracy, precision, recall, and F1- score are 99.45%, 98.83%, 97.28%, and 99.37%, respectively. In the future, this approach may be integrated with modified architectures of software quality models for automated software product quality analysis. © 2024 IEEE.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

Correntropy-Based Data Selective Adaptive Filtering

引用

IEEE Transactions on Circuits and Systems I: Regular Papers 2024年第2期71卷 754-766页

作者： Chien, Ying-Ren Wu, Sheng-Teng Tsao, Hen-Wai Diniz, Paulo S.R. Adaptive and Autonomous Communication Laboratory Department of Electrical Engineering National Ilan University Yilan City260007 Taiwan College of Electrical Engineering and Computer Science Graduate Institute of Communication Engineering National Taiwan University Taipei10617 Taiwan Program of Electrical Engineering Department of Electronics and Computer Engineering COPPE/Poli Universidade Federal do Rio de Janeiro Rio de Janeiro68504 Brazil

Data selection can be used in conjunction with adaptive filtering algorithms to avoid unnecessary weight updating and thereby reduce computational overhead. This paper presents a novel correntropy-based data selection method as an alternative to conventional data selection mechanisms based on squared error values. We developed a variable correntropy sensing algorithm to maximize the instantaneous correntropy function for the Gaussian kernel function to mitigate the impact of impulse noise and other forms of noise that can be disregarded in data selection. The proposed data selection mechanism can be implemented with any adaptive filtering algorithm. In simulations, the proposed method (implemented with the least mean squared algorithm) outperformed comparable error-based data selection schemes in terms of hit rate and miss rate, and the resulting weight updating ratio was close to the expected weight updating ratio. © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Privacy enhanced course recommendations through deep learning in Federated Learning environments

引用

International Journal of Information Technology (Singapore) 2025年第1期17卷 629-635页

作者： Kolli, Chandra Sekhar Seelamanthula, Sreenivasu Reddy V, Venkata Krishna Babu, Padamata Ramesh Reddy, Mule Rama Krishna Gumpina, Babu Rao Department of Information Technology Shri Vishnu Engineering College for Women Andhra Pradesh Bhimavaram India Department of Information Technology Lakireddy Bali Reddy College of Engineering Andhra Pradesh Mylavaram India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Department of Computer Science and Engineering Narasaraopeta Engineering College Narasaraopeta India Department of Compute Science GITAM School of Science GITAM (Deemed to be University) Andhra Pradesh Visakhapatnam India

The increasing concerns around data security and privacy among users have significantly pushed the interest of the research community towards developing privacy-preserving recommendation systems. Amidst this backdrop, our study introduces a novel course recommendation methodology leveraging Federated Learning (FL) coupled with advanced Deep Learning techniques. This method executes the recommendation process across local nodes through several stages, including agglomerative matrix formulation, course clustering, bi-level matching, identification of learner-preferred courses, and ultimately, course recommendation. Notably, course clustering is achieved through Deep Fuzzy Clustering (DFC), while Deep Convolutional Neural Networks (DCNN) are employed for the recommendation phase. The efficacy of our DFC-DCNN-FL approach is rigorously evaluated based on several metrics: accuracy, False Positive Rate (FPR), loss function, Mean Square Error (MSE), Root MSE (RMSE), and Mean Average Precision (MAP). The results demonstrate remarkable performance with scores of 0.909, 0.116, 0.126, 0.291, 0.539, and 0.925, respectively. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Course recommendation Deep fuzzy clustering Deep learning Federated learning Privacy preservation

来源：评论

学校读者我要写书评

暂无评论

Advanced Knee Osteoarthritis Detection and Severity Prediction 15

Advanced Knee Osteoarthritis Detection and Severity Predicti...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Santosh, B. Rama Sai Reddy, N. Vinay Kumar Krishna, B. Jathin Vadlamudi, Venkata Naveen Jeyaraj, Jane Rubel Angelina Subhashini, S.J. Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamilnadu Virudhnagar India Department of IT SRM Madurai College for Engineering and Technology Tamil Nadu India

ISBN: (纸本)9798331300579

Millions of individuals worldwide suffer from knee osteoarthritis (OA), a crippling joint ailment that is marked by joint stiffness, discomfort, and functional impairment. To make a decision severity, physical symptoms, medical history, and further joint screening exams including radiography, MRIs, and CT scans are frequently considered. Unfortunately, the old methods are quite subjective, which makes it difficult to identify early illness development. Worldwide, Osteoarthritis affects close to 240 million individuals. Arthritis's most widespread kind, particularly in older people, is knee OA. Doctors utilize the Kellgren and Lawrence (KL) measure in order to assess the level of severity of knee OA. visually using X-ray or MR imaging. For the intent of detecting and predicting the severity of Knee Osteoarthritis, we are putting forth a model that uses novel Deep Learning models, such as Inception and Exception. By utilizing the KL Grading Scale, we propose ahead a model that can determine the degree of knee osteoarthritis in people. © Grenze Scientific Society, 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Role of Non Fungible Tokens in Transforming Academic Credentials for Trust and Transparency 6

Role of Non Fungible Tokens in Transforming Academic Credent...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Naik, Girish R. Naik, Poornima G. KIT's College of Engineering Department of Mechanical Engineering Kolhapur India Chh Shahu Institute of Business Education & Research Department of Computer Studies Kolhapur India

ISBN: (纸本)9798350306613

Blockchain technology in education offers immutable records of academic achievements, ensuring secure storage and verification of credentials. It enables transparent, decentralized systems for certification, fostering trust, eliminating fraud, and providing individuals with greater control over their educational data and achievements. Additionally, blockchain facilitates efficient and instant verification of qualifications, streamlining processes for educational institutions, employers, and learners. The current research explores the transformation of non-fungible items into Non-Fungible Tokens (NFTs) and their significance in authentication and verification within the blockchain realm. Addressing the limitations of traditional certificates, NFT certificates leverage blockchain technology to ensure trust, ownership proof, and enhanced transferability. The study extensively discusses the ERC721 standard for NFT implementation, the OpenZeppelin library for smart contract security, and tools like Hardhat, Alchemy, Pinata Cloud, and *** in NFT creation and deployment. The research demonstrates the practical implementation of NFT token minting, ownership verification, and transfer operations through smart contracts on different networks, highlighting the significance of NFTs in ensuring secure and transparent ownership in the digital landscape. © 2024 IEEE.

关键词： Blockchain-based Certificates Decentralized education ERC721 Standard Immutable Credential Verification Non-Fungible Tokens (NFTs) OpenZeppelin Library

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：