检索结果-内蒙古大学图书馆

Self-supervised extracted contrast network for facial expression recognition

Multimedia Tools and Applications 2025年第15期84卷 14977-14996页

作者： Yan, Lingyu Yang, Jinquan Xia, Jinyao Gao, Rong Zhang, Li Wan, Jun Tang, Yuanyan School of Computer Science Hubei University of Technology Wuhan430068 China Department of Computer Science Royal Holloway University of London SurreyTW20 0EX United Kingdom School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan430073 China Zhuhai UM Science and Technology Research Institute Zhuhai519085 China

Self-supervised Contrastive learning has recently demonstrated significant performance in Facial Expression Recognition (FER). However, existing methods fail to address inherent challenges such as similar and blurred facial expressions, and low-quality semantic pairs from image cropping. To tackle these challenges, this paper proposes a Lightweight Self-supervised Distilled Contrastive network for FER (LSDC-FER), which consists of a center suppressed cropping module and a multi-scale feature joint distillation module. The former improves the quality of face expression semantic pairs by face image localization and center suppressed cropping. The latter learns fine-grained features using knowledge distillation and explores multi-scale contextual information to improve feature learning. Experimental results show that LSDC-FER achieves 75.65% and 61.16% recognition accuracy on RAF-DB and FER-2013 public facial expression datasets, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

A Novel Dynamic Hill Cipher and Its Applications on Medical IoT

引用

IEEE Internet of Things Journal 2025年第10期12卷 14297-14308页

作者： Jin, Jie Wu, Mengfan Ouyang, Aijia Li, Keqin Chen, Chaoyang Sanya Institute of Hunan University of Science and Technology Hainan Sanya572024 China Jishou University College of Computer Science and Engineering Jishou China Changsha Medical University School of Information Engineering Hunan Changsha410219 China Zunyi Normal University School of Information Engineering Guizhou Zunyi563002 China State University of New York Department of Mathematics and Computer science New PaltzNY United States

Cryptography is one of the most important areas in information security. Cryptography ensures secure communication and data privacy, and it is increasingly being applied in healthcare and related fields. As an important classical cryptographic method, the Hill cipher has always been closely studied by experts and scholars. In order to enhance the security of the conventional Hill cipher (CHC), a novel dynamic Hill cipher (NDHC) is proposed in this work. The proposed NDHC not only replaces the static key matrix of the CHC with a time-varying dynamic key matrix (TVDKM) to change the image pixel values over time t, but also uses the Logistic chaos sequence scrambling the image pixel positions, which greatly enhances the security of the CHC. However, how to effectively obtain the dynamic inversion key matrix (DIKM) of the TVDKM becomes an urgent issue in the NDHC decryption. In order to quickly find the DIKM, a fixed-time convergence fuzzy Zeroing neural network (FTCF-ZNN) model is constructed, and the convergence and robustness of the FTCF-ZNN model for solving the DIKM are verified through theoretical analysis and comparative experimental results. Moreover, the effectiveness and security of the proposed NDHC for medical images encryption and decryption are also validated by experiments. © 2025 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Multimodal Learning in Image Processing

引用

computers, Materials & Continua 2025年第2期82卷 3615-3618页

作者： Zhixin Chen Gautam Srivastava Shuai Liu School of Educational Science Hunan Normal UniversityChangsha410081China Institute of Interdisciplinary Studies Hunan Normal UniversityChangsha410081China Department of Math and Computer Science Brandon UniversityBrandonMB R7A 6A9Canada Research Centre for Interneural Computing China Medical UniversityTaichung406040Taiwan Institute of Engineering and Technology Chitkara UniversityChandigarh140401India

1 Introduction onMultimodal Learning in Image Processing IP(Image processing),as a classical research domain in computer application technology,has been researched for *** is one of the most important research directions in computer vision,which is the basis for many current hotspots such as intelligent transportation/education/industry,*** image processing is the strongest link for AI(artificial intelligence)applying to real world application,it has been a challenging research field with the development of AI,from DNN(deep convolutional network),Attention/LSTM(long-short term memory),to Transformer/Diffusion/Mamba based GAI(generated AI)models,e.g.,GPT and Sora[1].Today,the description ability of single-model feature limits the performance of image *** comprehensive description of the image is required to match the computational performance of current large scale models.

关键词： Image computer LSTM

来源：评论

学校读者我要写书评

暂无评论

Dr_ OrangeApp: Revolutionizing Real-Time Pest Detection in Citrus Orchards 24

Dr_ OrangeApp: Revolutionizing Real-Time Pest Detection in C...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Moshayedi, Ata Jahangir Jawadi, Mohammad Jalil Roy, Atanu Shuvam Rostami, Elahe Wang, Zhonghua Yang, Liqin Xu, Qun School of Information Engineering Jiangxi University of Science and Technology Jiangxi Ganzhou China Department of Computer Science and Engineering Indian Institute of Technology Uttar Pradesh Kanpur India Institute of Quality Standards & Testing Technology for Agro-products Fujian Provincial Key Laboratory of Quality and Safety of Agricultural Products Fujian Academy of Agricultural Sciences Fujian Fuzhou China Jiangxi Environmental Engineering Vocational College Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

Orange pests pose a significant threat to citrus crops, leading to reduced yield and quality, making effective control essential for healthy orchards and agricultural productivity. In this paper the novel idea of The development of the Dr_ Orange application which is facilitates real-time monitoring of pest infestations, enabling timely farmer interventions that improve crop health, reduce pesticide usage, and enhance productivity. To make the Application the Personal image classifier along the interface used to make the model. the have some features like Chart, report and QR generating which can help the farmers to detect the pests faster and also follow up the process of curiness. To test the app two type of test investigated and the The app has been rigorously tested on 313 images, over the five repeatable pests yielding strong overall performance with an average accuracy and recall of 0.75, perfect precision of 1.00, and an F1 score of 0.856. As the final test the application was evaluated in an orange orchard, successfully identifying and reporting the occurrence of Citrus Leafminer pests in 10 trees. Although the app demonstrates high precision, challenges such as variations in lighting conditions, the angle of the photographs, and data quality can affect result accuracy. Repeatedly taking pictures can help mitigate these effects and improve the interface’s impact on detection accuracy. based on obtained results, the proposed App enhances pest management efficiency for orange crops while also promoting improved agricultural productivity. © 2024 Copyright held by the owner/author(s).

关键词： Citrus fruits

来源：评论

学校读者我要写书评

暂无评论

MCDS: An Effective Multi-UAV Collaborative Decision-Making System in Mobile Edge Computing Networks

引用

IEEE Internet of Things Journal 2025年

作者： Xiong, Naixue Zhong, Weiyu Chen, Yuxiang He, Dacheng Li, Yuhui Chen, Linshu Liang, Wei Sanya Research Institute of Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology China Sanya Research Institute of Hunan University of Science and Technology Hunan University School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Information Science and Engineering China The Hong Kong Polytechnic University Department of Computing Hong Kong

Mobile Edge Computing (MEC) pushes computing resources from the network center to the network edge to provide efficient and reliable computing services. However, due to the mobility and diversity of mobile users (MUs), edge servers (ESs) are likely to be overloaded, which leads to a rapid decline in the quality of service provided by the MEC system. This paper introduces unmanned aerial vehicles (UAVs) to solve the problem of ES overload. This paper presents an effective Multi-UAV Collaborative Decision-Making System (MCDS) tailored to optimize task offloading and resource allocation in MEC networks. The proposed system seeks to reduce task computing delays and energy consumption while guaranteeing timely task completion and compliance with resource constraints. We design a distributed two-stage optimization algorithm to jointly optimize the task offloading decision and resource allocation of the collaborative computing system (UAVs, ESs, and MUs). To address the flight cooperation problem of multi-UAVs, we also proposed a task-aware scheduling algorithm for multi-UAVs. In addition, we conducted a large number of simulation experiments. Experimental results show that our two-stage optimization scheme is lower than other benchmark algorithms in terms of task completion delay, energy consumption and total cost of objective function. Specifically, compared with seven baseline algorithms under three different system setting scenarios, our algorithm reduces the total cost by an average of 38.79%, the energy consumption by an average of 40.70%, and the delay by an average of 15.67%. © 2014 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

AMSFuse:Adaptive Multi-Scale Feature Fusion Network for Diabetic Retinopathy Classification

引用

computers, Materials & Continua 2025年第3期82卷 5153-5167页

作者： Chengzhang Zhu Ahmed Alasri Tao Xu Yalong Xiao Abdulrahman Noman Raeed Alsabri Xuanchu Duan Monir Abdullah School of Computer Science and Engineering Central South UniversityChangsha410083China School of Humanities Central South UniversityChangsha410083China Department of Human Anatomy and Histology & Embryology Basic Medical SciencesChangsha Health Vocational CollegeChangsha410100China Glaucoma Institute Changsha Aier Eye HospitalChangsha410000China Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha67714Saudi Arabia

Globally,diabetic retinopathy(DR)is the primary cause of blindness,affecting millions of people *** widespread impact underscores the critical need for reliable and precise diagnostic techniques to ensure prompt diagnosis and effective *** learning-based automated diagnosis for diabetic retinopathy can facilitate early detection and ***,traditional deep learning models that focus on local views often learn feature representations that are less discriminative at the semantic *** the other hand,models that focus on global semantic-level information might overlook critical,subtle local pathological *** address this issue,we propose an adaptive multi-scale feature fusion network called(AMSFuse),which can adaptively combine multi-scale global and local features without compromising their individual ***,our model incorporates global features for extracting high-level contextual information from retinal ***,local features capture fine-grained details,such as microaneurysms,hemorrhages,and exudates,which are critical for DR *** global and local features are adaptively fused using a fusion block,followed by an Integrated Attention Mechanism(IAM)that refines the fused features by emphasizing relevant regions,thereby enhancing classification accuracy for DR *** model achieves 86.3%accuracy on the APTOS dataset and 96.6%RFMiD,both of which are comparable to state-of-the-art methods.

关键词： Diabetic retinopathy multi-scale feature fusion global features local features integrated attention mechanism retinal images

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing: Innovations and Impacts on Global Data Infrastructure

Cloud Computing: Innovations and Impacts on Global Data Infr...

引用

2025 IEEE International Conference on Computational, Communication and Information technology, ICCCIT 2025

作者： Banumathi, S. Sivajothi, E. Indumathi, G.S. Kefyalew, Enku Yosef Sivakumar, J. Priya, V. Banu Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science India Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai India St Joseph's College of Engineering OMR Department of MBA Chennai India Technical and Vocational Training Institute Department of Electrical and Electronics Technology Addis Ababa Ethiopia St.Joseph's College of Engineering Department of Electronics and Communication Engineering Chennai India R.M.K. College of Engineering and Technology Department of Mathematics Thiruvallur District India

ISBN: (纸本)9798331512965

Cloud computing has transformed global data infrastructure with unparalleled scale, flexibility, and accessibility. This study examines how cloud computing innovations have changed data storage, processing, and management worldwide. By examining the progression of cloud services from simple storage and computing to sophisticated platforms and SaaS, we examine how they have transformed corporate operations, economic growth, and societal development. Virtualization, containerization, serverless architectures, and edge computing are the main cloud computing advancements, which we investigate through a literature study and case studies. Data security, privacy, and regulatory frameworks are also considered while adopting the cloud. Cloud computing promotes digital transformation in banking, healthcare, education, and government, according to study. The industry's sustainability and green computing efforts and data centers' environmental impacts are also covered. We found that cloud computing continues to spur innovation by enabling new business models, global connectivity, and data-driven application growth. Cloud technologies' integration with AI, IoT, and 5G networks is likely to change the global data infrastructure, opening new research and development options. This report covers the cloud computing landscape, its advancements, and its potential to shape global data management and digital ecosystems. © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Improving Maritime Data: A Machine Learning-based Model for Missing Vessel Trajectories Reconstruction

引用

IEEE Transactions on Vehicular technology 2025年

作者： Chen, Jin Liang, Maohan Peng, Chang Zhang, Jixin Huo, Shengxu Sanya Institute Hunan University of Science and Technology China Department of Civil and Environmental Engineering National University of Singapore Singapore Singapore College of Computer Science and Electronic Engineering Hunan University China School of Computer Science Hubei University of Technology China

Advancements in maritime satellite technology have significantly impacted the maritime industry, enhancing both communication and safety at sea. These technological improvements have enabled Automatic Identification Systems (AIS) to transmit data through robust maritime communication networks. However, despite these advancements, AIS data often contain significant missing data due to limitations in both devices and network coverage. To overcome these limitations, this research presents an innovative approach for reconstructing missing points. In this paper, we first extracted the geometric shape and motion characteristics of vessels and constructed a decision tree using an adaptive sparse constraint mechanism to classify four types of vessel trajectories. Then, the vessel classification findings serve as input and the vessel acceleration features are constructed using the heading and velocity features of the trajectories at both ends. Finally, We employ a bidirectional Gate Recurrent Unit (GRU) network to simultaneously train on historical trajectory data. The method progressively shortens the reconstructed trajectory, thereby enhancing the accuracy of the reconstruction. In this paper, comparative experiments are conducted with several algorithms across various dimensions, including algorithm performance, trajectory types, and navigation scenarios. It is indicated by the experimental results that the algorithm discussed in this study outperforms baselines. Significant methodological advancements in vessel trajectory reconstruction are represented by this study, which also shows promising potential for application in intelligent maritime transportation systems. © 1967-2012 IEEE All rights reserved.

关键词： Waterway transportation

来源：评论

学校读者我要写书评

暂无评论

Decentralized Unlearning for Trustworthy AI-Generated Content (AIGC) Services

引用

IEEE Network 2025年第3期39卷 285-292页

作者： Lin, Yijing Du, Hongyang Gao, Zhipeng Yao, Jing Jiang, Bingting Niyato, Dusit Li, Ruidong Zhang, Ping Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China The University of Hong Kong Department of Electrical and Electronic Engineering Pokfulam Hong Kong Central South University School of Computer Science and Engineering Changsha410083 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore Kanazawa University Institute of Science and Engineering Kanazawa920-1192 Japan

The widespread adoption of AI-Generated Content (AIGC) has captured remarkable interests from academia and industry. However, this advancement brings forth challenges in data ownership, as emphasized by the General Data Protection Regulation’s right to be forgotten. The right to be forgotten allows participants to erase their data contributions from well-trained AIGC models. Training AIGC models demands an extensive amount of data and computations, often surpassing the capabilities of individual participants. As a solution, Federated Learning (FL) is employed to collaboratively train an AIGC model without sharing raw data directly. To protect the right to be forgotten in FL, "federated unlearning" has been introduced to eradicate the data contributions of unlearning participants from fully trained AIGC models, achieved by deleting historical model updates. However, given that historical updates are distributed among various participants, they may still hold contributions from the unlearning participants. This presents a challenge to the trustworthiness of federated unlearning. In this paper, we first provide an overview of both centralized and federated learning and unlearning methods. We survey relevant works and classify four main categories for federated unlearning. Subsequently, we introduce a comprehensive decentralized unlearning architecture designed for trustworthy AIGC services. To address the challenge of participants retaining historical contributions from unlearning participants, we integrate a coded computing-based interaction mechanism, ensuring both scalability and security. We further present a case study using NanoGPT to demonstrate the effectiveness of the proposed framework for decentralized unlearning. We conclude by identifying potential future research directions. © 1986-2012 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Smart Grid Optimization: Integrating Swarm Intelligence with Domain-Specific Heuristics for Superior Energy Efficiency 3rd

A Multi-objective Smart Grid Optimization: Integrating Swarm...

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Ammasai, Viswanathan Katbar, Nek Muhammad Kothalanka, Amarendra Vandadi, Venkata Ramana Udhaya Shankar Latha, Sindhu Sharma, Dilip Kumar Sengan, Sudhakar School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632 014 India School of Mathematics and Statistics Central South University Hunan Changsha410083 China Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522502 India Department of Computer Science and Engineering KSRM College of Engineering Andhra Pradesh Kadapa516003 India Department of Information Technology V.S.B. College of Engineering Technical Campus Tamil Nadu Coimbatore642109 India Department of Mathematics Jaypee University of Engineering and Technology Madhya Pradesh Guna473226 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli62745 India

ISBN: (纸本)9789819783540

The realm of Smart Grid Systems (SGS) has witnessed unprecedented progress, driven by increasing energy demands and the integration of Renewable Energy Sources (RES). While these grids promise enhanced efficiency and sustainability, their involved and dynamic nature poses significant optimization challenges. Existing solutions, although innovative, often overlook the intricate interplay between diverse factors, leaving room for potential improvements in optimization approaches. Recognizing this gap, the current study delves into developing a novel method that integrates Ant Colony Optimization (ACO) with domain-specific heuristics. By focusing on analytical sections like Load Forecasting, Renewable Energy Integration, Peak Shaving, and Grid Resilience, this method attempts to bridge the divide that existing approaches miss. The proposed method not only ensures optimal energy distribution but also tailors the solution to address the unique features and requirements of modern SGS. A more reliable, effective, and Renewable Energy (RE) future is within reach according to the outcomes of this investigation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Clean energy

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：