检索结果-内蒙古大学图书馆

Dehazing using Generative Adversarial Network - A Review

SN computer Science 2025年第1期6卷 1-17页

作者： Khatun, Amina Mostafiz, Rafid Shorif, Sumaita Binte Uddin, Mohammad Shorif Hadi, Md. Abdul Department of Computer Science and Engineering Jahangirnagar University Dhaka Bangladesh Institute of Information Technology Noakhali Science and Technology University Noakhali Bangladesh Department of Computer Science: Information Technology University of Nebraska Omaha Omaha United States

Dehazing is a difficult process in computer vision that seeks to improve the clarity and excellence of pictures taken under cloudy, foggy, and rainy circumstances. The Generative Adversarial Network (GAN) has been a viable method for removing haze from photos in recent years. This is because GAN can understand intricate data patterns and provide high-quality outcomes. This paper provides a thorough examination of the most advanced strategies in dehazing utilizing GAN. The study examines the various elements utilized in GAN-based dehazing, including generator and discriminator architectures, loss functions, and training strategies. It also explores the evaluation metrics employed to assess the effectiveness of GAN-based dehazing methods. It also examines the datasets often used to train and evaluate these models. This research concludes by examining prospective avenues for future study in the domain of dehazing, employing GAN to tackle the obstacles of real-time dehazing, managing intricate scenarios with various atmospheric conditions, and enhancing the resilience of GAN-based dehazing models. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Atmospheric haze Dehazing Generative Adversarial Network (GAN) Performance evaluation metrics

来源：评论

学校读者我要写书评

暂无评论

Data-driven output regulation control for constrained linear systems

引用

Science China(information Sciences) 2025年第3期68卷 338-353页

作者： Chaoyu XIA Yi DONG Chaoli WANG Shengyuan XU Shanghai Research Institute for Intelligent Autonomous Systems Tongji University College of Electronic and Information Engineering Shanghai Research Institute for Intelligent Autonomous SystemsTongji University Department of Control Science and Engineering School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and Technology Department of Automation Nanjing University of Science and Technology

This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking performance while satisfying the state and input constraints, even when system matrices are not available. We first establish a sufficient condition necessary for the existence of a solution pair to the regulator equation and propose a data-based approach to obtain the feedforward and feedback control gains for state feedback control using linear programming. Furthermore, we design a refined Luenberger observer to accurately estimate the system state, while keeping the estimation error within a predefined set. By combining output regulation theory, we develop an output feedback control strategy. The stability of the closed-loop system is rigorously proved to be asymptotically stable by further leveraging the concept of λ-contractive sets.

关键词： output regulation constrained system data-driven.

来源：评论

学校读者我要写书评

暂无评论

SAMFNet: Scene-aware sampling and multi-stage fusion for multimodal 3D object detection

引用

Alexandria engineering Journal 2025年 126卷 90-104页

作者： Wang, Baotong Xia, Chenxing Gao, Xiuju Ge, Bin Li, Kuan-Ching Fang, Xianjin Zhang, Yan Yang, Yuan College of Computer Science and Engineering Anhui University of Science and Technology Huainan232001 China College of Electrical and Information Engineering Anhui University of Science and Technology Huainan232001 China Department of Computer Science and Information Engineering Providence University Taichung43301 China The School of Electronics and Information Engineering Anhui University Hefei230039 China School of Mathematics and Big Data Anhui University of Science and Technology Huainan232001 China

Recently, multimodal 3D object detection (M3OD) that fuses the complementary information from LiDAR data and RGB images has gained significant attention. However, the inherent structural differences between point clouds and images pose fusion challenges, significantly hindering the exploration of correlations within multimodal data. To address this issue, this paper introduces an enhanced multimodal 3D object detection framework (SAMFNet), which leverages virtual point clouds generated from depth completion. Specifically, we design a scene-aware sampling module (SASM) that employs tailored sampling strategies for different bins based on the density distribution of point clouds. This effectively alleviates the detection bias problem while ensuring the key information of virtual points, significantly reducing the computational cost. In addition, we introduce a multi-stage feature fusion module (MSFFM) that embeds point-level and regional-adaptive feature fusion strategies to generate more informative multimodal features by fusing features with different granularities. To further improve the accuracy of model detection, we also introduce a confidence prediction branch unit (CPBU), which improves the detection accuracy by predicting the confidence of feature classification in the intermediate stage. Extensive experiments on the challenging KITTI dataset demonstrate the validity of our model. © 2025 The Authors

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

EEMLCR: Energy-Efficient Machine Learning-Based Clustering and Routing for Wireless Sensor Networks

引用

IEEE Access 2025年 13卷 70849-70871页

作者： Akram, Muhammad Ullah Bazai, Sibghat Imran Ghafoor, Muhammad Akram, Saira Ilyas, Qazi Mudassar Mehmood, Abid Iqbal, Sajid Asim Rafique, Muhammad Department of Software Engineering Quetta87300 Pakistan Department of Computer Engineering Quetta87300 Pakistan Pakistan Television Corporation Department of Engineering Lahore44000 Pakistan King Faisal University College of Computer Sciences and Information Technology Department of Information Systems Al Hofuf31982 Saudi Arabia King Faisal University College of Business Administration Department of Management Information Systems Al Hofuf31982 Saudi Arabia

Wireless Sensor Networks (WSNs) offer a powerful technology for sensing and transmitting data across vast geographical regions. However, limitations inherent to WSNs, such as low-power sensor units, communication constraints, and limited processing capabilities, can significantly impact their lifespan. To address these limitations and enhance the energy efficiency of WSNs, it is often necessary to divide sensors into clusters and establish routing to conserve energy. Machine learning algorithms can potentially automate these processes, minimizing energy consumption and extending network lifetime. This research investigates the application of machine learning algorithms, specifically Q-learning and K-means clustering, to propose the Energy-Efficient Machine Learning-based Clustering and Routing (EEMLCR) method for WSNs. This method facilitates cluster formation and routing path selection. The proposed method is compared with the well-established LEACH algorithm and two multi-hop variants, DMHT LEACH and EDMHT LEACH to validate its effectiveness. Our experimental results demonstrate the effectiveness of EEMLCR compared to LEACH and its multi-hop variants (DMHT LEACH and EDMHT LEACH). After 600 rounds in networks comprising 400 nodes, EEMLCR showed significant improvements in key performance metrics. These include increased alive nodes, reduced average energy consumption, higher remaining energy levels, and improved packet reception. Additionally, we compared EEMLCR with recent state-of-the-art algorithms such as EECDA and CMML, where our method demonstrated comparable or superior performance in terms of network lifetime and energy efficiency. By optimizing clustering and routing strategies, WSNs can reduce energy consumption, leading to more efficient utilization of the limited energy resources available to sensor nodes. The primary objective of this research is to contribute to the development of energy-efficient WSNs by leveraging machine learning algorithms for dat

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Dynamic Indian Sign Language Sentence Captioning System Using Machine Learning 5th

Dynamic Indian Sign Language Sentence Captioning System Usin...

引用

5th International Conference on Electrical and Electronics engineering, ICEEE 2024

作者： Kulkarni, Vedant Dattatray Bajaj, Anushree Shrigopal Marathe, Himanshu Deshmukh, Mandar Sreemathy, R. Jagdale, Jayashree Department of Information Technology Pune Institute of Computer Technology Pune India Department of Electronics and Telecommunication Engineering Pune Institute of Computer Technology Pune India

ISBN: (纸本)9789819791118

Sign language serves as a vital mode of communication for the deaf and hard of hearing community, yet access to sign language content remains limited due to the lack of accurate and timely captioning. In this paper, a comprehensive comparison has been made between Long Short-Term Memory (LSTM)- and Support Vector Machine (SVM)-based neural networks for sign language recognition. Our approach uses LSTM networks to effectively recognize and translate sign language gestures into textual descriptions. We leverage a large dataset of sign language videos paired with English captions for training and evaluation. Through extensive experimentation, we demonstrate the effectiveness of our system in accurately captioning sign language videos, thereby enhancing accessibility for individuals with hearing impairments. Our self-curated dataset includes 28 unique sentences on which our LSTM-based model achieved an accuracy of 90% whereas it was 97% for SVM-based approach. Our research contributes to advancing the field of accessibility technology and holds promise for real-world applications in education, entertainment, and communication for the deaf and hard of hearing community. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Entropy-Bottleneck-Based Privacy Protection Mechanism for Semantic Communication

引用

computers, Materials & Continua 2025年第5期83卷 2971-2988页

作者： Kaiyang Han Xiaoqiang Jia Yangfei Lin Tsutomu Yoshinaga Yalong Li Jiale Wu School of Information Engineering Inner Mongolia University of TechnologyHohhot010051China Department of Computer and Network Engineering University of Electro-CommunicationsChofuTokyo1828585Japan

With the rapid development of artificial intelligence and the Internet of Things,along with the growing demand for privacy-preserving transmission,the need for efficient and secure communication systems has become increasingly *** communication methods transmit data at the bit level without considering its semantic significance,leading to redundant transmission overhead and reduced *** communication addresses this issue by extracting and transmitting only the mostmeaningful semantic information,thereby improving bandwidth ***,despite reducing the volume of data,it remains vulnerable to privacy risks,as semantic features may still expose sensitive *** address this,we propose an entropy-bottleneck-based privacy protection mechanism for semantic *** approach uses semantic segmentation to partition images into regions of interest(ROI)and regions of non-interest(RONI)based on the receiver’s needs,enabling differentiated semantic *** focusing transmission on ROIs,bandwidth usage is optimized,and non-essential data is *** entropy bottleneck model probabilistically encodes the semantic information into a compact bit stream,reducing correlation between the transmitted content and the original data,thus enhancing privacy *** proposed framework is systematically evaluated in terms of compression efficiency,semantic fidelity,and privacy *** comparative experiments with traditional and state-of-the-art methods,we demonstrate that the approach significantly reduces data transmission,maintains the quality of semantically important regions,and ensures robust privacy protection.

关键词： Semantic communication privacy protection semantic segmentation entropy-based compression

来源：评论

学校读者我要写书评

暂无评论

Drone-Based Public Surveillance Using 3D Point Clouds and Neuro-Fuzzy Classifier

引用

computers, Materials & Continua 2025年第3期82卷 4759-4776页

作者： Yawar Abbas Aisha Ahmed Alarfaj Ebtisam Abdullah Alabdulqader Asaad Algarni Ahmad Jalal Hui Liu Faculty of Computing and AI Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Information Technology College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Science and Engineering College of InformaticsKorea UniversitySeoul02841Republic of Korea Cognitive Systems Lab University of BremenBremen28359Germany

Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot ***,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera *** research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)*** first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale *** YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further *** joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are *** features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity ***-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing *** particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.

关键词： Activity recognition geodesic distance pattern recognition neuro fuzzy classifier

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Gauging information Extracted from Smartphones Using Neutrosophic Logic

引用

Neutrosophic Sets and Systems 2025年 76卷 154-171页

作者： Abou Alzahab, R.M. Ismail, Amr Abd Elkhalik, S.H. Shams, M.Y. El-Bakry, H.M. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Department. of Communication and Computer Engineering Air Defense University Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Department of Information Systems. Faculty of Computer and Information Science Mansoura University Egypt

Smartphones contain a vast amount of information about their users, which can be used as evidence in criminal cases. However, the sheer volume of data can make it challenging for forensic investigators to identify and use the most relevant information. Neutrosophic logic is a generalization of fuzzy logic that allows for uncertainty and vagueness, making it a more potent tool for dealing with the ambiguity of real-world data. The proposed framework aims to identify and utilize the most relevant information for forensic investigators, making it easier to solve criminal cases using Neutrosophic logic. This novel approach provides a more powerful tool for dealing with the ambiguity of smartphone data, ultimately improving the accuracy and effectiveness of forensic investigations. Our research has utilized Neutrosophic logic to evaluate the degree of truth, falsity, or Indeterminacy of this information. Additionally, this study analyzes conversations between individuals using Excel’s fuzzy lookup add-in to determine the percentage of truth and false in each conversation. The results were compiled into a dataset and utilized a Neutrosophic Python code to evaluate the information. The results indicate the percentage of truth, false, and Indeterminacy in each conversation and which can be used to determine its admissibility as evidence and which not. © 2025, University of New Mexico. All rights reserved.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Smart Farming: Enhancing Urban Agriculture Through Predictive Analytics and Resource Optimization

引用

IEEE Access 2025年 13卷 72375-72388页

作者： Aldhahri, Eman Ali Almazroi, Abdulwahab Ali Alkinani, Monagi Hassan Ayub, Nasir Alghamdi, Elham Abdullah Janbi, Nourah Fahad University of Jeddah Collage of Computer Science and Engineering Department of Computer Science and Artificial Intelligence Jeddah21959 Saudi Arabia University of Jeddah College of Computing and Information Technology at Khulais Department of Information Technology Jeddah21959 Saudi Arabia Air University Islamabad Department of Creative Technologies Islamabad44000 Pakistan

Optimal agricultural methods need precise crop health and ecological strain monitoring. This study proposes a novel data science strategy to improve crop health prediction and stress assessment. ResXceNet-HBA is a cutting-edge classification model that uses ResNet blocks, Xception modules with Adaptive Depthwise Separable Convolutions, and HBA-optimized parameters. This model uses HBA's Dynamic Exploration-Exploitation Balance-fine-tuned Dynamic Feature Recalibration and adaptive convolutions. Imputation Weight Crop Labels (WICL) to accurately fill in missing data, Localised Feature Scaling (LFS) and Adaptive Feature Discretization (AFD) to standardize and categorize features, and the Environmental Stress Factor (ESF) to evaluate crop stress address data problems ASRFS and Crop-Specific Environmental Impact Weighting increase model performance. Our system also employs Adaptive Synthetic Resampling with Environmental Context. Using novel measures including the Crop Type Generalisation Score (CTGS) and Environmental Sensitivity Index (ESI), the ResXceNet-HBA model achieved 98.5% accuracy, 98.2% precision, 98.7% recall, and 98.4% F1-Score. These results beat ResNet, CNN, and Inception V2. The model executed in 50.9 seconds, faster than the alternatives. The confusion matrix exhibits minimal false positives and negatives, suggesting good prediction accuracy. ResXceNet-HBA's statistics and resource optimization value increases. Precision farming and sustainable agriculture benefit from our strategy's significant environmental stress and crop health assessments. © 2013 IEEE.

关键词： Monitoring Crops Temperature measurement Adaptation models Temperature sensors Plants (biology) Accuracy Predictive models Urban agriculture Deep learning

来源：评论

学校读者我要写书评

暂无评论

DELTa: Dynamic Energy-and-Latency-aware Task scheduling for Fog-Cloud Paradigm

引用

IEEE Access 2025年 13卷 74617-74633页

作者： Mahapatra, Abhijeet Pradhan, Rosy Majhi, Santosh K. Mishra, Kaushik Department of Computer Science & Engineering Odisha Burla768018 India Sikkim Manipal University Sikkim Manipal Institute of Technology Department of Artificial Intelligence and Data Science Sikkim India Department of Electrical Engineering Odisha Burla768018 India Department of Computer Science and Information Technology Chhattisgarh Bilaspur495009 India Manipal Academy of Higher Education Manipal Institute of Technology Bengaluru Department of Computer Science and Engineering Manipal India

The rapid proliferation of IoT devices like smartphones, smartwatches, etc. has significantly elevated the quantity of data requiring execution. It poses challenges for centralized Cloud computing servers, such as latency overhead and increased consumption of energy. To address this, Fog computing has been incorporated in this research as a complementary paradigm to the Cloud-based computing model. It thereby reduces the huge distance between end-user IoT gadgets and the Cloud computing servers. In order to improve the latency and waiting time this research employs a Multi-Level Queue (MLQ) for classifying tasks based on their priority. For parallel processing, a Self-adaptive Fuzzy C-means++ (SaFCm++) approach has been applied to cluster the Fog computing nodes depending on the heterogeneity of the computational nodes. For efficient scheduling, a Dynamic Energy-and-Latency-aware Task scheduling (DELTa) approach has been proposed to optimize latency, makespan, and utilization of resources. Extensive simulations are carried out for different test cases considering task and machine heterogeneity, followed by a statistical analysis. The overall improvements of the proposed method over other baselines are 9.75% for makespan, 64.59% for service latency, 13.90% for resource utilization, and 12.75% for energy consumption. The proposed energy-efficient scheduling method effectively manages diverse tasks and resources, enhancing task processing efficiency while minimizing energy consumption and maximizing resource utilization. Furthermore, the value of the Friedman statistics FF for the proposed model is estimated at 5.44, which shows superiority over the crucial value for four methodologies and four evaluation matrices. © 2013 IEEE.

关键词： Fog computing

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：