检索结果-内蒙古大学图书馆

A systematic literature review of visual feature learning: deep learning techniques, applications, challenges and future directions

引用

Multimedia Tools and Applications 2024年 1-58页

作者： Abdullahi, Mohammed Oyelade, Olaide Nathaniel Kana, Armand Florentin Donfack Bagiwa, Mustapha Aminu Abdullahi, Fatimah Binta Junaidu, Sahalu Balarabe Iliyasu, Ibrahim Ore-ofe, Ajayi Chiroma, Haruna Department of Computer Science Ahmadu Bello University Zaria Zaria Nigeria Department of Mechanical Engineering Ahmadu Bello University Zaria Nigeria Department of Computer Engineering Ahmadu Bello University Zaria Nigeria College of Computer Science and Engineering University of Hafr Al Batin Hafar Al-Batin31991 Saudi Arabia School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Belfast United Kingdom

Visual Feature Learning (VFL) is a critical area of research in computer vision that involves the automatic extraction of features and patterns from images and videos. The applications of VFL are vast, including object detection and recognition, facial recognition, scene understanding, medical image analysis, and autonomous vehicles. In this paper, we propose to conduct extensive systematic literature review (SLR) on VFL based on deep learning algorithms. The paper conducted an SLR covering deep learning algorithms such as Convolutional Neural Networks (CNNs), Autoencoders, and Generative Adversarial Networks (GANs) including their variants. The review highlights the importance of VFL in computer vision and the limitations of traditional feature extraction techniques. Furthermore, it provides an in-depth analysis of the strengths and weaknesses of various deep learning algorithms for solving problems in VFL. The discussion of the applications of VFL provides an insight into the impact of VFL on various industries and domains. The review also analyzed the challenges faced by VFL, such as data scarcity and quality, overfitting, generalization, interpretability, and explainability. The discussion of future directions for VFL includes hybrid techniques, unsupervised feature learning, continual learning, attention-based models, and explainable AI. These techniques aim to address the challenges faced by VFL and improve the performance of the models. The systematic literature review concludes that VFL is a rapidly evolving field with the potential to transform many industries and domains. The review highlights the need for further research in VFL and emphasizes the importance of responsible use of VFL models in various applications. The review provides valuable insights for researchers and practitioners in the field of computer vision, who can use these insights to enhance their work and ensure the responsible use of VFL models. © The Author(s), under exclusive licence to

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking

Leveraging Estimated Transferability Over Human Intuition fo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Bai, Jun Chen, Zhuofan Li, Zhenzi Hong, Hanhua Zhang, Jianfei Li, Chen Lin, Chenghua Rong, Wenge School of Computer Science and Engineering Beihang University China Department of Computer Science University of Manchester United Kingdom

ISBN: (纸本)9798891761643

Text ranking has witnessed significant advancements, attributed to the utilization of dual-encoder enhanced by Pre-trained Language Models (PLMs). Given the proliferation of available PLMs, selecting the most effective one for a given dataset has become a non-trivial challenge. As a promising alternative to human intuition and brute-force fine-tuning, Transferability Estimation (TE) has emerged as an effective approach to model selection. However, current TE methods are primarily designed for classification tasks, and their estimated transferability may not align well with the objectives of text ranking. To address this challenge, we propose to compute the expected rank as transferability, explicitly reflecting the model's ranking capability. Furthermore, to mitigate anisotropy and incorporate training dynamics, we adaptively scale isotropic sentence embeddings to yield an accurate expected rank score. Our resulting method, Adaptive Ranking Transferability (AiRTran), can effectively capture subtle differences between models. On challenging model selection scenarios across various text ranking datasets, it demonstrates significant improvements over previous classification-oriented TE methods, human intuition, and ChatGPT with minor time consumption. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Model for Human Detection-Enhanced YOLO Comparative Analysis 4

Deep Learning Model for Human Detection-Enhanced YOLO Compar...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Suresh, P. Aswathy, R.H. Soms, Nisha Niranjani, V. Saveetha School of Engineering Simats Department of Computer Science and Engineering Thandalam Chennai India Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Sri eshwar college of engineering Department of Computer science and engineering Coimbatore India

ISBN: (纸本)9798331540364

Video surveillance systems employing closed-circuit television (CCTV) are crucial for public safety. Accurately detecting humans within video frames is a core component of this technology. This knowledge is crucial for numerous uses, including detecting possible dangers, observing crowd dynamics, and examining patterns of human behavior. This research introduces a new method called YOLOv8, designed to enhance human detection capabilities within CCTV footage. The proposed algorithm, YOLOv8, is built upon the popular object recognition framework, YOLO, but with significant enhancements to improve its accuracy and efficiency in detecting humans. YOLOv8 utilizes deep convolutional neural networks (CNNs) and advanced object recognition techniques to achieve high accuracy in human detection, even in challenging environments such as low light conditions, occlusions, and varying scales of human poses. To assess the effectiveness of YOLOv8, various tests were performed using standard datasets and real-world CCTV surveillance footage. The results demonstrate that YOLOv8 outperforms existing human detection algorithms regarding accuracy, robustness, and real-time processing capability. YOLOv8 achieved an average precision of over 95% in human detection, making it highly suitable for everyday CCTV surveillance. The proposed YOLOv8 algorithm has the potential to significantly improve human detection in security camera footage and enhance public safety. This research contributes to advancing human detection technology and can benefit various domains, including law enforcement, public safety, and video analytics. © 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

Microgrids with day-ahead energy forecasting for efficient energy management in smart grids: hybrid CS-RERNN

引用

Australian Journal of Electrical and Electronics engineering 2024年第3期21卷 213-227页

作者： Shirley, C.P. Pattar, Jagannath Kavitha Rani, P. Saini, Sumit Ranga, Jarabala Elangovan, D. Venkatakrishna Reddy, Ch. Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Mechanical Engineering Madanapalle Institute of Technology & Science Madanapalle India Department of M.Tech Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India Department of Electrical Engineering School of Engineering & Technology Central University of Haryana Mahendergarh India Detartment of Electrical and Electronics Engineering Ramachandra College of Engineering Eluru India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Electrical and Electronics Engineering Chaitanya Bharathi institute of technology Hyderabad India

By integrating smart grid technology with home energy management systems, households can monitor and optimise their energy consumption. This allows for more efficient use of energy resources, reducing waste and lowering energy bills. In this manuscript, a hybrid approach is proposed for smart grid home energy management with microgrids and day-ahead energy forecasts. The proposed control approach combines the Circle Search (CS) algorithm and Recalling-Enhanced Recurrent Neural Network (RERNN). Commonly it is named as CS-RERNN technique. The novelty of this paper is to optimise energy consumption and production within microgrids, thereby contributing to the overall efficiency of the smart grid system. The proposed method is used to reduce the electricity cost, peak-to-average ratio (PAR), and maximising consumer comfort. Energy management is performed based on the CS algorithm. A smart home connected to the external power grid (PG) is managed by the proposed method. Here, load demand is predicted by using RERNN. By then, the performance of the proposed method is implemented in MATLAB platform. The proposed method shows a high efficiency of 96%, and 22 $ of low electricity bill cost compared with other existing methods such as Particle swarm optimisation (PSO), Cuckoo search algorithm (CSA, and Border collie Optimisation (BCO). ©, Engineers Australia.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

BMWP: the first Bengali math word problems dataset for operation prediction and solving

引用

Discover Artificial Intelligence 2025年第1期5卷 1-15页

作者： Mondal, Sanchita Khatua, Debnarayan Mandal, Sourav Prasad, Dilip K. Sekh, Arif Ahmed School of Medical Science and Technology IIT Kharagpur West Bengal Kharagpur721302 India Department of Mathematics and Statistics Vignan’s Foundation for Science Technology and Research Andhra Pradesh Guntur512213 India School of Computer Science and Engineering XIM University Odisha Puri752050 India Department of Computer Science Uit the Arctic University of Norway Tromsø9017 Norway

Solving math word problems of varying complexities is one of the most challenging and exciting research questions in artificial intelligence (AI), particularly in natural language processing (NLP) and machine learning (ML). Foundational language models such as GPT must be evaluated for intelligence, and solving word problems is a key method for this assessment. These problems become especially difficult when presented in low-resource regional languages such as Bengali. Word problem solving integrates the cognitive domains of language processing, comprehension, and transformation into real-world solutions. During the past decade, advances in AI and machine learning have significantly progressed in addressing this complex issue. Although researchers worldwide have primarily utilized datasets in English and some in Chinese, there has been a lack of standard datasets for low-resource languages such as Bengali. In this pioneering study, we introduce the first Bengali Math Word Problem Benchmark Data Set (BMWP), comprising 8653 word problems. We detail the creation of this dataset and the benchmarking methods employed. Furthermore, we investigate operation prediction from Bengali word problems using state-of-the-art deep learning (DL) techniques. We implemented and compared various standard DL-based neural network architectures, achieving an accuracy of 92±2%. The data set and the code will be available at https://***/SanchitaMondal/BMWP. © The Author(s) 2025.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

TRS Scheduling for Improved QoS Performance in Cloud System

引用

computers, Materials & Continua 2023年第4期75卷 1547-1559页

作者： G.John Samuel Babu M.Baskar Department of Computer Science and Engineering School of ComputingCollege of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathurChengalpattuTamilnadu603203India Department of Computing Technologies School of ComputingCollege of Engineering andTechnologySRM Institute of Science and TechnologyKattankulathurChengalpattuTamilnadu603203India

Numerous methods are analysed in detail to improve task schedulingand data security performance in the cloud environment. The methodsinvolve scheduling according to the factors like makespan, waiting time,cost, deadline, and popularity. However, the methods are inappropriate forachieving higher scheduling performance. Regarding data security, existingmethods use various encryption schemes but introduce significant serviceinterruption. This article sketches a practical Real-time Application CentricTRS (Throughput-Resource utilization–Success) Scheduling with Data Security(RATRSDS) model by considering all these issues in task scheduling anddata security. The method identifies the required resource and their claim timeby receiving the service requests. Further, for the list of resources as services,the method computes throughput support (Thrs) according to the number ofstatements executed and the complete statements of the service. Similarly, themethod computes Resource utilization support (Ruts) according to the idletime on any duty cycle and total servicing time. Also, the method computesthe value of Success support (Sus) according to the number of completions forthe number of allocations. The method estimates the TRS score (ThroughputResource utilization Success) for different resources using all these supportmeasures. According to the value of the TRS score, the services are rankedand scheduled. On the other side, based on the requirement of service requests,the method computes Requirement Support (RS). The selection of service isperformed and allocated. Similarly, choosing the route according to the RouteSupport Measure (RSM) enforced route security. Finally, data security hasgets implemented with a service-based encryption technique. The RATRSDSscheme has claimed higher performance in data security and scheduling.

关键词： Cloud task scheduling TRS quality of service RSM route security data security SDE RATRSDS

来源：评论

学校读者我要写书评

暂无评论

Adaptive Particle Swarm Optimization of U-net Parameters for Marine Aquaculture Image Segmentation 13

Adaptive Particle Swarm Optimization of U-net Parameters for...

引用

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Zhao, Jin Wang, Jun Han, Min Fan, Jianchao School of Computer Science and Engineering Chongqing Three Gorges University Chongqing China Department of Computer Science Department of Data Science City University of HongKong Hong Kong School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9798331516147

Marine aquaculture image segmentation plays a crucial role in managing aquatic resources and environmental protection. Traditional deep learning models rely on manual parameter tuning for image segmentation, which limits their efficiency and accuracy. This paper proposes an adaptive Particle Swarm Optimization (PSO) algorithm to optimize the parameters of the U-net model automatically. The algorithm dynamically adjusts the PSO parameters based on the population’s entropy and clustering metrics and employs a hill-climbing algorithm to address the issue of the PSO easily falling into local optima, enhancing the algorithm’s adaptability. The proposed algorithm updates and iterates particles to automatically find suitable model parameters. The remote sensing data used in this experiment were from the Yellow Sea aquaculture area near Dalian, China, with a segmentation accuracy of 91.8%. This method improves segmentation accuracy, reduces the burden of manual parameter tuning, and provides an effective solution for optimizing deep learning models. © 2025 IEEE.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Adaptive Hypergraph Network for Trust Prediction 40

Adaptive Hypergraph Network for Trust Prediction

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Xu, Rongwei Liu, Guanfeng Wang, Yan Zhang, Xuyun Zheng, Kai Zhou, Xiaofang School of Computing Macquarie University Australia School of Computer Science and Engineering University of Electronic Science and Technology of China China Hong Kong University of Science and Technology Department of Computer Science and Engineering China

ISBN: (纸本)9798350317152

Trust plays an essential role in an individual's decision-making. Traditional trust prediction models rely on pairwise correlations to infer potential relationships between users. However, in the real world, interactions between users are usually complicated rather than pairwise only. Hypergraphs offer a flexible approach to modeling these complex high-order correlations (not just pairwise connections), since hypergraphs can leverage hyperedeges to link more than two nodes. However, most hypergraph-based methods are generic and cannot be well applied to the trust prediction task. In this paper, we propose an Adaptive Hypergraph Network for Trust Prediction (AHNTP), a novel approach that improves trust prediction accuracy by using higher-order correlations. AHNTP utilizes Motif-based PageRank to capture high-order social influence information. In addition, it constructs hypergroups from both node-level and structure-level attributes to incorporate complex correlation information. Furthermore, AHNTP leverages adaptive hypergraph Graph Convolutional Network (GCN) layers and multilayer perceptrons (MLPs) to generate comprehensive user embeddings, facilitating trust relationship prediction. To enhance model generalization and robustness, we introduce a novel supervised contrastive learning loss for optimization. Extensive experiments demonstrate the superiority of our model over the state-of-the-art approaches in terms of trust prediction accuracy. © 2024 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

QCVNET - Leveraging Quantum Technology in Convolutional Neural Networks for Improved Cardiovascular Disease Prediction 5

QCVNET - Leveraging Quantum Technology in Convolutional Neur...

引用

5th International Conference on Circuits, Control, Communication and Computing, I4C 2024

作者： Karthigeyan, S. Diviya, M. Bhuvaneswari, R. Sabhanayagam, T. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India School of Computer Science and Engineering Galgotias University UP Greater Noida India

ISBN: (纸本)9798331528539

The primary issue of global health today is Cardio-vascular diseases (CVDs) and thus requires accurate predictive models for detecting it early. Quantum technology combined with regular deep learning techniques are used by researchers here to improve the accuracy of forecast on heart diseases. While using an expanded dataset with clinical and demographic records, an innovative approach was found to use Quantum Convolutional Neural Network (QCVNET) structure that merged quantum layers into classical CNN framework with Principal Component Analysis (PCA) that allowed for consistency of features with respect to the quantum bits' number. The performance of the QCVNET was evaluated by comparing it to Quantum LSTM, Quantum DNN, Quantum GRU, and Quantum RNN, which are other quantum models enhanced with conventional neural networks, and other traditional non-quantum models like SVM, RF, RNN and DNN, using different indicators of quality like f1-score or recall. In early CVD prediction, the QCVNET model produced an impressive accuracy of 91.73%, beating all other models, showcasing the potential impact of quantum-enhanced deep learning for timely diagnosis and personalized treatment strategies while providing means to reduce the global burden of cardiovascular diseases. © 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

Space/Air Covert Communications:Potentials,Scenarios,and Key Technologies

引用

China Communications 2024年第3期21卷 1-18页

作者： Mao Haobin Liu Yanming Zhu Lipeng Mao Tianqi Xiao Zhenyu Zhang Rui Han Zhu Xia Xianggen School of Electronic and Information Engineering Beihang UniversityBeijing 100191China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore School of Science and Engineering Shenzhen Research Institute of Big Datathe Chinese University of Hong KongShenzhenGuangdong 518172China Department of Electrical and Computer Engineering University of HoustonHoustonTX 77004USA Department of Computer Science and Engineering Kyung Hee UniversitySeoulSouth Korea446-701 Department of Electrical and Computer Engineering University of DelawareNewarkDE 19716USA

Space/air communications have been envisioned as an essential part of the next-generation mobile communication networks for providing highquality global connectivity. However, the inherent broadcasting nature of wireless propagation environment and the broad coverage pose severe threats to the protection of private data. Emerging covert communications provides a promising solution to achieve robust communication security. Aiming at facilitating the practical implementation of covert communications in space/air networks, we present a tutorial overview of its potentials, scenarios, and key technologies. Specifically, first, the commonly used covertness constraint model, covert performance metrics, and potential application scenarios are briefly introduced. Then, several efficient methods that introduce uncertainty into the covert system are thoroughly summarized, followed by several critical enabling technologies, including joint resource allocation and deployment/trajectory design, multi-antenna and beamforming techniques, reconfigurable intelligent surface(RIS), and artificial intelligence algorithms. Finally, we highlight some open issues for future investigation.

关键词： artificial intelligence(AI) sixth generation(6G) space-air-ground integrated networks(SAGINs) space/air covert communications

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：