检索结果-内蒙古大学图书馆

CBIR: a novel identification approach for college students in need based on consumer behavior psychology theory

Neural Computing and Applications 2025年第6期37卷 4663-4677页

作者： Liu, Xinze Liu, Shixi Hu, Xiaojing Zhang, Yudong Fang, Xianwen School of Computer and Information Engineering Chuzhou University Chuzhou239000 China School of Computer Science and Engineering Southeast University Nanjing210096 China School of Mathematics and Big Data Anhui University of Science and Technology Huainan232001 China

The accurate identification of students in need is crucial for governments and colleges to allocate resources more effectively and enhance social equity and educational fairness. Existing approaches to identifying students in need rely on manual operations that include manually extracting consumption behavior information, statistical consumption characteristics and principal component analysis. However, this issue may lead to low prediction accuracy and inefficiency in identifying students in need. We design a three-stage framework to accurately identify college students in need from the perspective of consumer behavior psychology. The consumption behavior information is first obtained from the student consumption records using the consumption behavior clustering approach. The consumption behavior matrix is then built by extracting consumption and spatiotemporal information in different periods. Finally, a novel consumption behavior identification ResNeSt (CBIR) model is proposed to identify college students in need accurately. The experimental results on real datasets show that the CBIR model has higher prediction accuracy than the baseline models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Social psychology

来源：评论

学校读者我要写书评

暂无评论

Secured Provisioning of Multimedia Contents in Cloud Platform Using Cryptographic Approaches 1

Secured Provisioning of Multimedia Contents in Cloud Platfor...

引用

1st International Conference on computer science and Emerging Technologies, CSET 2023

作者： Arul Mary, S.A. Sahaaya Nevgi, Akshaj Nair, Rhea Ranjith Sharukh Bhathena, Jehan Chaudhry, Angad Jessika, S. Sharon School of Computer Science and Engineering Vit India Computer Science and Engineering India Computer Science with Specialization in Data Science India

ISBN: (纸本)9798350341737

Cloud computing is a technology that allows the utilisation of a vast network of computers that are distributed and run in parallel with one another. The management of the multimedia files presents challenges and the significant of which is the prevalence of attackers and users with malicious intent. This article presents the conceptual foundation for a four-tiered data security paradigm that can be implemented in cloud computing. The proposed framework employs a DNA-computing-based password or secret key with a length of 1024 bits for the purpose of encrypting the user private multimedia file or correspondence. The DNABMS algorithm is applied in the cryptographic generation of digital identities as well as pseudorandom number generators. The results of the testing that was done on the model have validated both its reliability and its efficacy, demonstrating that the model that was developed is both reliable and effective. Experiments have demonstrated that the developed method is superior to other well-known existing strategies in terms of both effectiveness and efficiency. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Effi-CNN: real-time vision-based system for interpretation of sign language using CNN and transfer learning

引用

Multimedia Tools and Applications 2025年第6期84卷 3137-3159页

作者： Pranav Katarya, Rahul Big Data Analytics and Web Intelligence Laboratory Computer Science & Engineering Department Delhi Technological University New Delhi India

The deaf and mute population has difficulty conveying their thoughts and ideas to others. Sign language is their most expressive mode of communication, but the general public is callow of sign language;therefore, the mute and deaf have difficulty communicating with others. A system that can correctly translate sign language motions to speech and vice versa in real time is required to overcome this communication barrier. Effi-CNN, a vision-based Sign Language Recognition (SLR) system employing transfer learning with EfficientNetB2, is proposed in this paper. We have also developed a system covering sign gestures to text in real time. Our approach was evaluated on eight publicly available datasets, including the Massey University gesture dataset, the ArSL2018 dataset, the MNIST-ASL dataset, and others. When comparing our results to state-of-the-art algorithms, the experimental findings showed that our proposed work is more successful than existing models. Our proposed model delivered an accuracy of 99.90 on MNIST dataset. The results show that our Effi-CNN surpasses most currently existing solutions and can categorize many gestures with a low error rate. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Dimensional Training Optimization for Efficient Federated Synergy Learning

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 6243-6258页

作者： Fu, Shucun Dong, Fang Chen, Runze Shen, Dian Zhang, Jinghui He, Qiang Southeast University School of Computer Science and Engineering Nanjing China Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan China

Edge learning (EL) is an end-to-edge collaborative learning paradigm enabling devices to participate in model training and data analysis, opening countless opportunities for edge intelligence. As a promising EL framework, federated synergy learning (FSyL) mitigates the computation and communication overhead on resource-constrained devices by offloading partial model layers to the edge server for synergistic training. Nevertheless, due to the system and statistical heterogeneity, naively using existing FSyL methods is significantly time-consuming and causes accuracy degradation. Motivated by this issue, this paper introduces a novel FSyL framework that integrates multi-dimensional training optimization and formulates the edge learning cost minimization (ELCM) problem. To tackle the ELCM efficiently, we design OL-MG, an OnLine Model Splitting and Resource Provisioning Game. Specifically, we first reformulate and decompose the original ELCM based on data quality evaluation. Then, given a model splitting decision, we determine the optimal resource provisioning in Sub-problem1, based on which optimal model splitting in Sub-problem2 is modeled as a potential game. Subsequently, we introduce a decentralized algorithm to find a Nash equilibrium (NE) solution. Furthermore, we further extend OL-MG to support a budget-aware multi-edge scenario. Extensive experiments demonstrate that the proposed mechanism significantly outperforms state-of-the-art methods in cost-saving and accuracy improvement. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Distributed Model Compression for Efficient Decentralized Federated Learning and Incentive Provisioning in Edge Computing Networks

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 6293-6314页

作者： Asheralieva, Alia Niyato, Dusit Wei, Xuetao Southern University of Science and Technology Department of Computer Science and Engineering 1088 Xueyuan Avenue Shenzhen China Nanyang Technological University College of Computing and Data Science 50 Nanyang Avenue Singapore639798 Singapore

We study decentralized federated learning (DFL) in edge computing networks where edge nodes (ENs) collaboratively train their artificial intelligence (AI) models in a serverless manner without sharing local data. We consider the following critical DFL challenges: i) scarce bandwidth resources of ENs;ii) dynamic, heterogeneous edge environment;iii) incentive provisioning and complex tradeoffs between the DFL performance and training costs. To resolve these challenges, we develop a new model compression method where ENs utilize dynamic, non-identical compression rates to improve the communication efficiency of DFL under time-varying, heterogeneous resource constraints. We show that our method can be formulated as a graphical Markov potential game where ENs act as players deciding on their compression factors and the number of data samples used for model updates. Each EN is incentivized to participate in DFL through rewards based on the EN's contribution to training. We prove that our game has a dominant pure-strategy Nash equilibrium (NE) maximizing its potential function and propose a dynamic distributed compression algorithm in which each EN can find its dominant strategy independently. We show that this algorithm converges to the Pareto-optimal NE, representing the most efficient solution of our game enhancing the DFL performance with minimal costs. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

MD-HIT:Machine learning for material property prediction with dataset redundancy control

引用

npj Computational Materials 2024年第1期10卷 638-648页

作者： Qin Li Nihang Fu Sadman Sadeed Omee Jianjun Hu College of Big Data and Statistics Guizhou University of Finance and EconomicsGuiyangChina Department of Computer SCience and Engineering University of South CarolinaColumbiaSCUSA

Materials datasets usually contain many redundant(highly similar)materials due to the tinkering approach historically used in material *** redundancy skews the performance evaluation of machine learning(ML)models when using random splitting,leading to overestimated predictive performance and poor performance on out-of-distribution *** issue is well-known in bioinformatics for protein function prediction,where tools like CD-HIT are used to reduce redundancy by ensuring sequence similarity among samples greater than a given *** this paper,we survey the overestimated ML performance in materials science for material property prediction and propose MD-HIT,a redundancy reduction algorithm for material *** MD-HIT to composition-and structure-based formation energy and band gap prediction problems,we demonstrate that with redundancy control,the prediction performances of the ML models on test sets tend to have relatively lower performance compared to the model with high redundancy,but better reflect models’true prediction capability.

关键词： prediction property performance

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Dynamic Flexible Job Shop Scheduling With Biased Objectives via Multitask Genetic Programming

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 169-183页

作者： Zhang, Fangfang Shi, Gaofeng Mei, Yi Zhang, Mengjie Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Emerson New Plymouth4310 New Zealand

Dynamic flexible job shop scheduling is an important combinatorial optimization problem that has rich real-world applications such as product processing in manufacturing. Genetic programming has been successfully used to learn scheduling heuristics for dynamic flexible job shop scheduling. Intuitively, users prefer small and effective scheduling heuristics that can not only generate promising schedules but also are computationally efficient and easy to be understood. However, a scheduling heuristic with better effectiveness tends to have a larger size, and the effectiveness of rules and rule size are potentially conflicting objectives. With the traditional dominance relation-based multiobjective algorithms, there is a search bias toward rule size, since rule size is much easier to optimized than effectiveness, and larger rules are easily abandoned, resulting in the loss of effectiveness. To address this issue, this article develops a novel multiobjective genetic programming algorithm that takes size and effectiveness of scheduling heuristics for optimization via multitask learning mechanism. Specifically, we construct two tasks for the multiobjective optimization with biased objectives using different search mechanisms for each task. The focus of the proposed algorithm is to improve the effectiveness of learned small rules by knowledge sharing between constructed tasks which is implemented with the crossover operator. The results show that our proposed algorithm performs significantly better, i.e., with smaller and more effective scheduling heuristics, than the state-of-the-art algorithms in the examined scenarios. By analyzing the population diversity, we find that the proposed algorithm has a good balance between exploration and exploitation during the evolutionary process. © 2024 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Patterns of Widespread Structural Abnormalities in Autism Spectrum Disorder using Diffusion Tensor Imaging

Patterns of Widespread Structural Abnormalities in Autism Sp...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Bharti, Dilip Kumar Singh, Sanjay Kumar Kumar, Mukesh Kanaujia, Vishal Kumar Aeri, Manisha Abes Engineering College Computer Science And Engineering-Data Science Ghaziabad India Kashi Institute Of Technology Department Of Computer Science & Applications Mirzamurad U.P Varanasi India Graphic Era Hill University Computer Science And Engineering Uttarakhand Dehradun248002 India Abes Engineering College Computer Science And Engineering Data Science Department Ghaziabad India

ISBN: (纸本)9798350366846

Diffusion tensor imaging (DTI) is a neuroimaging approach that lets in for the visualization and quantification of the structural integrity of white depend fibers in the brain. In latest years, DTI has come to be an essential tool for investigating the underlying neurobiological mechanisms of autism spectrum sickness (ASD), a neurodevelopmental disorder characterized via problems in social communication and repetitive behaviors. Through the usage of DTI, researchers have identified good sized styles of structural abnormalities in the brains of individuals with ASD. these abnormalities encompass changes in the microstructure of white remember fibers, along with decreased fiber density, changes in fiber directionality, and decreased connectivity between mind areas. Additionally, there may be evidence of bizarre mind development in early formative years, with a few research finding that these structural variations are present even in very younger children with ASD. One constant finding in DTI studies of ASD is reduced white rely integrity inside the corpus callosum, a large fiber package deal that connects the two hemispheres of the mind. This abnormality has been connected to deficits in social communiqué and language in people with ASD, as well as difficulties in integrating records from distinctive brain areas. The results showed extensive structural abnormalities in people with ASD in comparison to TD individuals. © 2024 IEEE.

关键词： Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

An efficient Quasi-Affine Transformation Evolutionary algorithm with fixed dimension updating and its application in UAV 3D path planning

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 9755-9781页

作者： Sung, Tien-Wen Zhao, Baohua Zhang, Xin Lee, Chao-Yang Fang, Qingjun Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Computer Science and Mathematics Fujian University of Technology Fuzhou China Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Taiwan

Quasi-Affine Transformation Evolutionary (QUATRE) algorithm is a kind of swarm-based collaborative optimization algorithm that solves the problem of a position deviation in a DE search by using the co-evolution matrix M instead of the cross-control parameter CR in the differential evolution algorithm (DE). However, QUATRE shares some of the same weaknesses as DE, such as premature convergence and search stagnation. Inspired by the artificial bee colony algorithm (ABC), we propose a new QUATRE algorithm to improve these problems that ranks all the individuals and evolves only the poorer half of the population. In an evolving population, individuals of different levels intersect with dimensions of different sizes to improve search efficiency and accuracy. In addition, we establish a better selection framework for the parent generation individuals and select more excellent parent individuals to complete the evolution for the individuals trapped in search stagnation. To verify the performance of the new QUATRE algorithm, we divide the comparison algorithm into three groups, including ABC variant group, DE variant group, and QUATRE variant group, and the CEC2014 test suite is used for the comparison. The experimental results show the new QUATRE algorithm performance is competitive. We also successfully apply the new QUATRE algorithm on the 3D path planning of UAV, and compared with the other famous algorithm performance it is still outstanding, which verifies the algorithm's practicability. © 2024 - IOS Press. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Support for the Prompt Identification and Understanding of the Broader Spectrum of Autism in Children 5

Artificial Intelligence Support for the Prompt Identificatio...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Julaiha, A.G. Noorul Hemamalini, S. Preiya, V. Sathya Sathyamoorthy, K. Priyanka, V. Rajalakshmi Institute of Technology Centre for Data Science Department of Computer Science & Engineering Chennai India Panimalar Engineering College Department of Artificial Intelligence & Data Science Chennai India Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331518097

This research work presents a novel language intervention system for Tamil-speaking children with autism spectrum disorder (ASD). The system satisfies the considerable requirement for tools aimed at one more section of population that has actually been forgotten by mainstream economics. Traditional language learning applications often lack specificity for diverse linguistic contexts, focusing on general learning rather than the unique challenges faced by ASD children. The proposed solution leverages Deep Learning (DL) modules to transform partial spoken Tamil words into complete, child-friendly vocabulary. This system goes beyond simple word completion;it incorporates interactive features to engage children with ASD and promote active learning. Preliminary evaluations yielded promising results, suggesting the system's potential in enhancing communication skills among Tamil-speaking children with ASD. This paper research study reviews the limitations of existing language learning tools and the rationale behind employing a DL-based approach. We discuss the specific DL architecture (e.g., Recurrent Neural Networks) envisioned for the system and how it will be trained on a corpus of Tamil speech data. This study also investigate the potential advantages beyond vocabulary learning, such as improved sentence formulation and the development of practical language abilities. Future ambitions include broadening the system's scope to include more languages, refining the DL model through ongoing training with enriched datasets, and conducting extensive user research with varied ASD populations. Validation across demographics is critical to ensuring the system's efficiency and generality. This research has the potential to bridge the language acquisition gap for Tamil-speaking children with ASD, empowering them to develop crucial communication skills and fostering their social inclusion. © 2024 IEEE.

关键词： Recurrent neural networks

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

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

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：