检索结果-内蒙古大学图书馆

Drone Detection and Tracking using Deep Convolutional Neural Networks from Real-time CCTV Footage

IEIE Transactions on Smart Processing and Computing 2024年第4期13卷 313-321页

作者： Allmamun, Md Akter, Fahima Talukdar, Muhammad Borhan Uddin Chakraborty, Sovon Uddin, Jia Department of Computer Science and Engineering European University of Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering University of Liberal Arts Bangladesh Dhaka Bangladesh AI and Big Data Department Woosong University Daejeon Korea Republic of

Drones are flying objects that may be controlled remotely or programmed to do a wide range of tasks, including aerial photography, videography, surveys, crop and animal monitoring, search and rescue missions, package delivery, and military operations. Unrestrained use, however, can pose a significant threat to safety, privacy, and security through eavesdropping, flying close to prohibited locations, interfering with public events, and delivering illicit items. Hence, real-time drone detection and tracking are indispensable and appropriate measures. This study developed real-time drone detection and tracking using the most efficient deep-learning approaches. The models were fine-tuned first to suit the required purpose and yield the desired outcome. The performance of the developed system was better than that of earlier endeavors in terms of accuracy and loss. Of the seven fined-tuned models, the Xception model constantly rendered the maximum accuracy with negligible loss. The model outperformed other state-of-the-art architectures, exhibiting an accuracy and loss of 99.18% and 3.83, respectively. Copyrights © 2024 The Institute of Electronics and Information Engineers.

关键词： Aerial photography

来源：评论

学校读者我要写书评

暂无评论

Utilization of Two Cross Two Switch for Bitonic Sorting Circuit

引用

Micro and Nanosystems 2025年第1期17卷 45-57页

作者： Bhattacharjee, Subhasree Sarkar, Soumyadip Das, Kunal Sadhu, Arindam Sarkar, Bikramjit Department of Computer Application Narula Institute of Technology Kolkata India Department of Computer Science Acharya Prafulla Chandra College Kolkata India Department of Electronics & Communication Engineering Greater Kolkata College of Engineering and Management West Bengal India Department of Computer Science & Engineering JIS College of Engineering West Bengal India

Background: The synthesis of reversible logic has gained prominence as a crucial research area, particularly in the context of post-CMOS computing devices, notably quantum computing. Objective: To implement the bitonic sorting circuit, 2x2 switch, is used. The overarching objective of implementing a reversible sorting circuit is to mitigate power consumption while promising secure communication. The successful implementation of the bitonic sorting circuit utilizing the proposed 2x2 switch is validated through simulations conducted in IBM Qiskit. Methods: This study begins by employing the control swap gate to implement a 2x2 switch, aimed at enabling concurrent computing operations within multiprocessor systems to enhance throughput. Subsequently, following the successful implementation of the 2x2 switch, the study proceeds to design a bitonic sorting circuit. Results: Bitonic sort using a 2x2 switch on the IBM Quantum Experience (IBMQ) platform via the QISKit SDK in Python 3.6. Specifically, Qiskit v0.29.0 is utilized, with OpenQASM. OpenQASM serves as the quantum assembly and instruction language. Conclusion: This work presents a methodology for constructing a 2x2 switch, utilizing a reversible control swap gate as its core component. Additionally, it demonstrates the intricate development and implementation of a bitonic sorting circuit, capitalizing on this innovative switch architecture. © 2025 Bentham science Publishers.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

IoT enabled plant leaf disease segmentation and multi-classification using mayfly bald eagle optimization-enabled machine learning

引用

Multimedia Tools and Applications 2024年第21期83卷 59747-59781页

作者： Mishra, Monalisa Choudhury, Prasenjit Pati, Bibudhendu Department of Computer Science and Engineering National Institute of Technology Durgapur India Department of Computer Science Rama Devi Women’s University Bhubaneswar India

Agricultural production is critical to the economy. This is one of the reasons why disease detection in plants is so important in agricultural settings, as plant disease is rather common. Farmers are not engaged in increasing their agricultural productivity daily since there are no technologies in the previous system to detect diseases in various crops in an agricultural environment. With the exponential population growth, food scarcity is a huge concern globally. In addition to this, the productivity of agricultural products has been highly impacted by the rapid increase in phytopathological adversities. The main challenges in leaf segmentation and plant disease identification are prior knowledge is required for segmentation, the implementation still lacks the accuracy of results, and more tweaking is required. To reduce the devastating impacts of illnesses on the economy, early detection of illnesses in plants is therefore essential. This paper describes an approach for segmenting and detecting plant leaf diseases based on images acquired via the Internet of Things (IoT) network. Here, a plant leaf area is segmented with a UNet, whose trainable parameters are optimized using the Mayfly Bald Eagle Optimization (MBEO) algorithm. Further, plant type classification is carried out by the Deep batch normalized AlexNet (DbneAlexNet), optimized by the Sine Cosine Algorithm-based Rider Neural Network (SCA-based RideNN). Finally, the DbneAlexNet, with weights adapted by the MBEO algorithm, is used to identify plant disease. The Plant Village dataset is used to evaluate the proposed DbneAlexNet-MBEO for plant-type classification and disease detection. The efficiency of the UNet-MBEO for segmentation is examined based on the Dice coefficient and Intersectin over Union (IOU) and has achieved superior values of 0.927 and 0.907. Moreover, the DbneAlexNet-MBEO is examined considering accuracy, Test Negative Rate (TNR), and Test Positive Rate (TPR) and offered superior values of 0

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based software engineering: progress,challenges, and opportunities

引用

science China(Information sciences) 2025年第1期68卷 57-144页

作者： Xiangping CHEN Xing HU Yuan HUANG He JIANG Weixing JI Yanjie JIANG Yanyan JIANG Bo LIU Hui LIU Xiaochen LI Xiaoli LIAN Guozhu MENG Xin PENG Hailong SUN Lin SHI Bo WANG Chong WANG Jiayi WANG Tiantian WANG Jifeng XUAN Xin XIA Yibiao YANG Yixin YANG Li ZHANG Yuming ZHOU Lu ZHANG School of Journalism and Communication Sun Yat-sen University School of Software Technology Zhejiang University School of Software Engineering Sun Yat-sen University School of Software Dalian University of Technology School of Computer Science and Technology Beijing Institute of Technology Key Laboratory of High Confidence Software Technologies (Peking University) Ministry of EducationSchool of Computer Science Peking University State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science and Engineering Beihang University Institute of Information Engineering Chinese Academy of Sciences School of Computer Science Fudan University State Key Laboratory of Complex & Critical Software Environment (CCSE) School of Software Beihang University School of Computer and Information Technology Beijing Jiaotong University School of Computer Science and Technology Harbin Institute of Technology School of Computer Science Wuhan University Huawei Technologies

Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many studies have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However,although several surveys have provided overall pictures of the application of deep learning techniques in software engineering,they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this study, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically. For each of the selected subareas,we highlight the major advances achieved by applying deep learning techniques with pointers to the available datasets i

关键词： deep learning software engineering software benchmark software artifact representation survey

来源：评论

学校读者我要写书评

暂无评论

An Improved Graph Partitioning Algorithm Based Approach for Workflow Offloading in a Fog Environment

引用

Journal of The Institution of Engineers (India): Series B 2025年第2期106卷 623-634页

作者： Mahajan, Neetu Narang Kaur, Parmeet Department of Computer Science and Engineering Jaypee Institute of Information Technology Noida India

The paper addresses the critical problem of application workflow offloading in a fog environment. Resource constrained mobile and Internet of Things devices may not possess specialized hardware to run complex workflows locally and hence, need to offload these tasks to fog nodes. As compared to cloud-based servers, fog nodes can provide responses in a more-timely manner and are preferred for latency-sensitive applications. Workflow applications are characterized by inter-task dependencies and hence, can be readily represented as directed acyclic graphs. Therefore, the proposed offloading solution approach utilizes an improved graph partitioning algorithm based on the Louvain community detection algorithm. The aim of the algorithm is to partition the workflow graph in such a manner that the workflow tasks having high communication costs between them are transferred or offloaded to the same fog node. The benefits of the proposed algorithm have been verified by simulation experiments where it was observed that it results in a lower makespan as compared to the related approaches. © The Institution of Engineers (India) 2024.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Dynamic Anomaly Detection Using Robust Random Cut Forests in Resource-Constrained IoT Environments

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第23期48卷 107-120页

作者： Vashisth, Sristi Goyal, Anjali Sharda University Department of Computer Science and Engineering Greater Noida India

This paper investigates dynamic anomaly detection in resource-constrained environments by leveraging Robust Random Cut Forests (RRCF). Anomaly detection is crucial for maintaining the integrity and security of data streams in Internet of Things (IoT) environments, where data is continuously generated and often subject to noise and fluctuations. We begin with a comprehensive exploration of resilient random cut data structures tailored for analyzing incoming data streams, highlighting their effectiveness in adapting to the dynamic nature of *** methodology encompasses extensive experimentation with diverse datasets, including real-time Arduino data and benchmark datasets such as IoT-23 and CIC-IoT. Through this approach, we assess the performance of the RRCF algorithm under various scenarios, focusing on its capability to accurately identify trends and anomalies over time. Notably, we achieve significant performance improvements, with an average Area Under the Curve (AUC) of 95.6 and an F1 score of 0.86, demonstrating RRCF’s effectiveness in real-time anomaly *** further enhance detection accuracy, we introduce dynamic thresholds that adapt to changing data characteristics, allowing our model to maintain robust performance even in the presence of noise. Detailed evaluations reveal that our approach consistently outperforms existing state-of-the-art methods, particularly in terms of handling noisy data and ensuring computational efficiency under resource *** findings underscore the potential of RRCF as a powerful tool for real-time applications within IoT systems, providing a solid theoretical foundation for future advancements in dynamic anomaly detection. By investigating non-parametric anomalies and analyzing the influence of external factors on data integrity, we uncover hidden patterns amidst dynamic fluctuations. This research emphasizes the need for adaptive strategies in evolving data landscapes, laying the groundwork for enhanced resil

关键词： Data streams

来源：评论

学校读者我要写书评

暂无评论

Predicting circRNA-Disease Associations by Using Multi-Biomolecular Networks Based on Variational Graph Auto-Encoder with Attention Mechanism

引用

Chinese Journal of Electronics 2024年第6期33卷 1526-1537页

作者： Jing YANG Xiujuan LEI Yi PAN School of Computer Science Shaanxi Normal University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology

CircRNA-disease association(CDA) can provide a new direction for the treatment of diseases. However,traditional biological experiment is time-consuming and expensive, this urges us to propose the reliable computational model to predict the associations between circRNAs and diseases. And there is existing more and more evidence indicates that the combination of multi-biomolecular information can improve the prediction accuracy. We propose a novel computational model for CDA prediction named MBCDA, we collect the multi-biomolecular information including circRNA, disease, miRNA and lncRNA based on 6 databases, and construct three heterogeneous network among them, then the multi-heads graph attention networks are applied to these three networks to extract the features of circRNAs and diseases from different views, the obtained features are put into variational graph auto-encoder(VGAE) network to learn the latent distributions of the nodes, a fully connected neural network is adopted to further process the output of VGAE and uses sigmoid function to obtain the predicted probabilities of circRNA-disease *** a result, MBCDA achieved the values of AUC and AUPR under 5-fold cross-validation of 0.893 and 0.887. MBCDA was applied to the analysis of the top-25 predicted associations between circRNAs and diseases, these experimental results show that our proposed MBCDA is a powerful computational model for CDA prediction.

关键词： Knowledge engineering Attention mechanisms Computational modeling Biological system modeling Predictive models Feature extraction Heterogeneous networks Topology Data mining Diseases

来源：评论

学校读者我要写书评

暂无评论

Limits of Depth: Over-Smoothing and Over-Squashing in GNNs

引用

Big Data Mining and Analytics 2024年第1期7卷 205-216页

作者： Aafaq Mohi ud din Shaima Qureshi Department of Computer Science and Engineering National Institute of Technology SrinagarSrinagar 190006India

Graph Neural Networks(GNNs)have become a widely used tool for learning and analyzing data on graph structures,largely due to their ability to preserve graph structure and properties via graph representation ***,the effect of depth on the performance of GNNs,particularly isotropic and anisotropic models,remains an active area of *** study presents a comprehensive exploration of the impact of depth on GNNs,with a focus on the phenomena of over-smoothing and the bottleneck effect in deep graph neural *** research investigates the tradeoff between depth and performance,revealing that increasing depth can lead to over-smoothing and a decrease in performance due to the bottleneck *** also examine the impact of node degrees on classification accuracy,finding that nodes with low degrees can pose challenges for accurate *** experiments use several benchmark datasets and a range of evaluation metrics to compare isotropic and anisotropic GNNs of varying depths,also explore the scalability of these *** findings provide valuable insights into the design of deep GNNs and offer potential avenues for future research to improve their performance.

关键词： Graph Neural Networks(GNNs) learning on graphs over-smoothing over-squashing isotropic-GNNs anisotropic-GNNs

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Functional Safety Design Methodology Using ASIL Decomposition for Automotive Cyber-Physical Systems

引用

IEEE Transactions on Reliability 2024年 1-23页

作者： Xie, Guoqi Peng, Hao Huang, Jing Li, Renfa Li, Keqin Department of Computer Engineering College of Computer Science and Electronic Engineering Hunan University Changsha 410082 China and also with the Key Laboratory for Embedded and Cyber-Physical Systems of Hunan Province Changsha 410082 China College of Computer Science and Electronic Engineering Hunan University Changsha 410082 China and also with the Department of Computer Science State University of New York New Paltz NY 12561 USA

Automotive cyber-physical systems (ACPS) are typical cyber-physical systems because of the joint interaction between the cyber part and physical part. Functional safety requirement (including response time and reliability requirements) for an ACPS function must be assured for safe driving. Auto industry is cost-sensitive, power-sensitive, and environment-friendly. Energy consumption affects the development efficiency of the ACPS and the living environment of people. This paper solves the problem of optimizing the energy consumption for an ACPS function while assuring its functional safety requirement (i.e., energy-efficient functional safety for ACPS). However, implementing minimum response time, maximum reliability, and minimum energy consumption is a conflicting problem. Consequently, solving the problem is a challenge. In this paper, we propose a three-stage design process toward energy-efficient functional safety for ACPS. The topic problem is divided into three sub-problems, namely, response time requirement verification (first stage), functional safety requirement verification (second stage), and functional safety-critical energy consumption optimization (third stage). The proposed energy-efficient functional safety design methodology is implemented by using automotive safety integrity level decomposition, which is defined in the ACPS functional safety standard ISO 26262. Experiments with real-life and synthetic ACPS functions reveal the advantages of the proposed design methodology toward energy-efficient functional safety for ACPS compared with state-of-the-art algorithms. IEEE

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Enhanced segmentation of optic disc and cup using attention-based U-Net with dense dilated series convolutions

引用

Neural Computing and Applications 2025年第9期37卷 6831-6847页

作者： Kumar, G. Bharadwaja Kumar, Soham Department of Computer Science and Engineering VIT Chennai TamilNadu Chennai600127 India

Delineating the boundaries of the optic disc and cup regions is a critical pre-requisite for glaucoma screening because it allows for precise measurement of key parameters, such as cup-to-disc ratio, which is a critical indicator of optic nerve head damage, a hallmark of glaucoma progression. Accurate segmentation enables early detection and monitoring of the disease, aiding in timely intervention to prevent vision loss. The main contribution of this research work is to develop an automated process to isolate and demarcate the optic disc and cup from retinal fundus images. To prevent the blood vessels from interfering with the segmentation process, a novel method is used for vessel mask generation and vessel inpainting. Most of the research works have used based encoder–decoder models like U-Net architecture or handcrafted feature extraction techniques such as hough transform, fuzzy clustering, etc. The proposed model has made significant modifications to the U-Net model. (1) Dual attention mechanism at every layer of decoder and (2) dense dilated series convolutions as skip connections to generate higher level feature map. The proposed model achieved benchmark accuracies - Dice score of 95.95% and IoU score of 92.22% for optic disc segmentation averaged over fivefold. For the task of outlining the optic cup region, it attained a Dice score of 88.7% and IoU of 79.72%. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Image segmentation

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：