检索结果-内蒙古大学图书馆

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： Nalla, Harshitha Lakshmi Durga Bhuchupalli, Anusha Addala, Tejasree Sabbineni, Yasasri Geetha, Koppisetti Sravya Aasha, Ghantasala Bonthu, Sridevi Department of Computer Science and Engineering Vishnu Institute of Technology Andhra Pradesh Bhimavaram India

ISBN: (纸本)9783031770746

In today’s era of rapid urbanization and environmental challenges, effective disaster and crisis management demand innovative solutions. This paper presents a novel approach focusing on community-level water-related issues through an intelligently designed application. The primary objective is to develop a user-friendly platform facilitating the reporting of water-related problems by both social media posts and the general public, subsequently enabling prompt action by relevant government authorities. Leveraging deep learning techniques and user-generated data, our solution introduces real-time detection and classification of six distinct water-related problems. A custom dataset is curated to train a ResNet-18 model, achieving an impressive accuracy of 73%. The application, developed with a React-based frontend and Flask-powered backend, acts as a centralized hub for reporting and managing water issues. Notably, it employs user-inputted data to accurately pinpoint problem locations, thereby enhancing the precision of reporting. By presenting a holistic approach, this research significantly contributes to the development of efficient crisis management and response strategies for water-related disasters. © ICST institute for computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Stationary wavelet transform and SpinalNet trained light spectrum Tasmanian devil optimization enabled DR detection using fundus images

引用

Multimedia Tools and Applications 2025年第4期84卷 1597-1626页

作者： Tamboli, Mubin Shoukat Dhumane, Amol Prasad, Rajesh Prasad, Jayashree Rajesh Ranjan, Nihar M. Computer Engineering Pimpri Chinchwad College of Engineering Pradhikaran Maharashtra Pune411044 India Computer Science and Engineering Symbiosis Institute of Technology Maharashtra Pune India Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Maharashtra Pune412201 India Information Technology JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India

Diabetes is a common disease that causes complications in the eyes known as Diabetic Retinopathy (DR). It aids in discovering the DR and tends to be the main cause behind people’s blindness amidst the previous decades. For prevent the complications of DR and to control the level of blood Glucose, the timely and crucial diagnosis is essential. A model is provided for detecting the DR. Here, Light Spectrum Tasmanian Devil Optimization (LSTDO) is utilized with SpinalNet for DR detection. The method undergoes an adaptive median filter and Region of interest mining process to generate a pre-processed image. The Sparse Fuzzy C-Means (FCM) is adapted for segmenting the optic disks followed by feature extraction. Then, the Hough line transformation with Tyler Coye algorithm (HLTCA) is used for blood vessel segmentation. Concurrently, the Stationary Wavelet Transform (SWT) is adapted to input image to overwhelm the deficiency of translation-invariance issue and then the feature mining is done. The feature vector is generated by unifying the outputs of the three-feature extraction phases and is employed to detect DR. The accuracy, sensitivity, and specificity obtained by the LSTDO-based SpinalNet are 91.6%, 89.9% and 92.1%, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

Blockchain Approach for Analyzing the Issues of IoT Systems 5th

Blockchain Approach for Analyzing the Issues of IoT Systems

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Rawat, Abhishek Verma, Rajat Suryavanshi, Raghuraj Singh Department of Computer Science and Engineering Pranveer Singh Institute of Technology UttarPradesh Kanpur India

ISBN: (纸本)9789819771776

The Internet of Things combined with blockchain technology has emerged as an innovative platform to better safeguard data, save costs, and pale, achieve strength. Combining blockchain and IoT means that the distributed ledger with sophisticated cryptographic mechanisms, consensus mechanisms, and some other processes may transmit data and information in a secure and open approach among devices across long distances. This paper begins with an introduction to the IoT and blockchain technology platforms before conducting a study of how their merger can help improve the platforms. The paper will additionally emphasize critical criteria before integrating the blockchain in IoT systems. Finally, the paper offers practical examples from blockchain-supported IoT project. Overall, combining blockchain technology into IoT might transform, how perceive and communicate technical advancements, paving the path for a more secure, connected, but decentralized future. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Distributed ledger

来源：评论

学校读者我要写书评

暂无评论

Maximizing Weighted Dominance in the Plane 21st

Maximizing Weighted Dominance in the Plane

引用

21st International Colloquium on Theoretical Aspects of Computing, ICTAC 2024

作者： Akram, Waseem Saxena, Sanjeev Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kanpur208016 India

ISBN: (纸本)9783031770180

Let P be a set of n weighted points, Q be a set of m unweighted points in the plane, and k a non-negative integer. We study the k-maxDominance problem, where the objective is to find a subset Q′⊆Q with size at most k such that the sum of the weights of the points in P dominated by at least one point in Q′ is maximized. A point q in the plane dominates another point p if and only if x(q)≥x(p) and y(q)≥y(p), and at least one inequality is strict. An algorithm for the k-maxDominance problem can be used to solve problems previously examined in scheduling, graph optimization, and database systems. We present a simple algorithm solving the problem in O(km2+nlogm) time and O(n+m) space. The algorithm is faster than the existing one when m=o(n). Additionally, we provide another solution to the problem with O(kmin{n+m,nk+m2}logm) time and O(n+m) space. These bounds are the same or better than those of the existing solution (the bounds are better when m=o(n)). The expected number of skyline points is θ(logn), a term much less than n. To obtain the second solution, we design a general technique that can be used to reduce the number of points n in P to min{n,m2} in any algorithm for the k-maxDominance problem. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Novel Anchor Generation Based Residual Network for Object Tracking in Video-Surveillance Applications

引用

SN computer Science 2025年第2期6卷 1-12页

作者： Mohanapriya, D. Rajalakshmi, K. Helen Josephine, V.L. Panneerselvam, Karthick Department of Computer Science (SF) Sourasthra College Tamil Nadu Madurai India Department of Computer Applications CMR Institute of Technology Karnataka Bangalore India Business Analytics School of Business and Management Christ University Karnataka Bangalore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Tamilnadu Uthupalayam 641407 India

The activity of the object in question is alerted directly upon completion of an effective object tracking. Dependent on hardware support or not, a strong object tracking protocol is required for a precise object tracking application. According to these methods, tracking an object accurately within a predetermined processing time window required a significant amount of computer complexity. In contrast, a variety of quality-degrading elements, including occlusion, shifting lighting, shadows, and so on, have an adverse effect on tracking. All of these tracking shortcomings will be fixed by a revolutionary residual network based on loss operator and anchor creation. Detection of object has concerns that rely on the process of feature extraction to afford efficient quality. For this purpose a model called ResNet has been used that comprises thirty layers and hence named as Resnet-thirty. These networks are a type of Convolutional Neural Network (CNN) that contain residual connections among various layers. The various merits of these connections is the network has the capability to learn the features of global, local and intermediate in parallel. As such, the system is robust against changes in lighting. These variations in light were understood in terms of tracking objects within a changing background. The proposed work uses MOT datasets. This dataset comprises of MOT 15, MOT16, MOT17 and MOT20. The results have been found by using these datasets. Hence, it evidently outperforms in terms of precision, recall, MOTA, IDF, MOTP, SAIDF and F1 measure to track the objects. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： computer vision Loss operator Object tracking Residual network

来源：评论

学校读者我要写书评

暂无评论

Adaptive Load Balancing for Distributed Multi-Controller SDNs through Switch Migration Strategy 17

Adaptive Load Balancing for Distributed Multi-Controller SDN...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Rao, Allu Sudharshan Khanal, Bipal Alam Ansari, Md. Sarfaraj National Institute of Technology Sikkim Department of Computer Science and Engineering Sikkim Ravangla India

ISBN: (纸本)9798331531195

Software-defined networking (SDN) is a transformative technology that systematically centralises and manages network resources. This paradigm shift allows for greater flexibility, agility, and efficiency in network management. In the ever-evolving landscape of distributed software-defined networks, the escalating demand for cloud services and data traffic underscores the critical need for a sophisticated load-balancing scheme. This paper addresses the pivotal challenge of optimising resource utilisation in SDN controllers to mitigate bottlenecks, enhance responsiveness, and ensure efficient network operations. This paper proposes a switch migration algorithm for efficient load balancing in distributed multi-controller topology. The proposed framework uses resource utilisation, load balancing rate, and re-association time for performance measurement. The proposed algorithm considers the switch to controller distance and remaining processing capacity to select an immigration controller. It also minimizes re-association time in the process of switch migration. The proposed algorithms are compared with benchmark algorithms like 'Closest Switch Migration' and 'Maximum Utilization Switch Migration' using various performance metrics. It has shown promising results and outperforms the benchmark algorithms. © 2025 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Single-Frame Image Based Multi-variant Bird Species Identification and Classification 5th

Single-Frame Image Based Multi-variant Bird Species Identifi...

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Adhikari, Nilanjana Bhattacharya, Suman Sultana, Mahamuda Department of Computer Science and Engineering Guru Nanak Institute of Technology Kolkata700114 India

ISBN: (纸本)9789819771776

The increasing demand for advanced ornithological tools and techniques aimed at accurately identifying and classifying multiple bird species within a single-frame image has led us to develop a framework for researchers, environmentalists, and bird enthusiasts. Traditional methods often struggle to handle the complexity of diverse avian variants present in each scene, particularly when capturing images in real-world, uncontrolled environments. Single-frame images, such as those obtained through wildlife monitoring cameras or handheld devices, offer a practical and common means of avian observation. Our work centered on the automated detection and classification of a group of multi-variant bird species using a Deep Learning (DL) framework. The You Only Look Once (YOLO) version 5 networks were deployed in this study. Each object within the image frame was detected, annotated, and captured in a bounded box. Subsequently, each bounded object underwent scrutiny and recognition. The manually collected dataset comprises five mutually exclusive local bird species native to India. The developed model demonstrated satisfactory performance in terms of Precision, Recall, mAP, and F1 values, achieving scores of 0.87, 0.81, 0.82, and 0.826, respectively. This system can work as an automated bird species detection, recognition and classification tool for numerous individuals encountering difficulty recognizing multiple birds within a single image frame. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Advanced IoT and Machine Learning System for Real-Time Crop and Fertilizer Recommendation 14

Advanced IoT and Machine Learning System for Real-Time Crop ...

引用

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： Khemnar, Vijaya R. Bendre, Mininath R. Kolekar, Vikas K. Department of Computer Engineering Pravara Rural Engineering College Loni India Department of Computer Engineering Vishwakarma Institute of Information Technology Pune India

ISBN: (纸本)9798331531935

The integration of Internet of Things (IoT) and Machine Learning (ML) technology has the capacity to transform agriculture via the improvement of precision agricultural methods. The proposed research work explores integration of IoT and ML in field of crop and fertilizer recommendation. Proposed system’s primary goal is to develop predictive models for determining the appropriate crop and fertilizer types based on various environmental and soil features. Using ML techniques, this research work aims to recommend the best crop and fertilizer combinations to optimize agricultural yield and sustainability. The collected data of IoT sensors give immediate soil health information, while ML algorithms analyze this data to recommends the most suitable crops and suggests the appropriate fertilizers. This integration promises to enhance agricultural productivity and sustainability through data-oriented decision taking and resource efficient utilization. The proposed system has used four ML models as Random Forest, Gradient Boosting, CatBoost, and XGBoost for predictions by using precision, recall, accuracy and F1 score. The obtained results shows that best accuracy value among the models for recommending crop is 0.9909 and for recommending fertilizer is 0.9886. © 2025 IEEE.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Enhancing Robustness of Smart Contracts Through Declarations 7th

Enhancing Robustness of Smart Contracts Through Declaration...

引用

7th International Conference on Blockchain, ICBC 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： Shyamasundar, R.K. Borse, Snehal Ummair, Mohammad Department of Computer Science and Engineering Indian Institute of Technology Bombay Mumbai400076 India

ISBN: (纸本)9783031770944

Run-time monitoring has been one of the widely used techniques to realize robust smart contracts. In this paper, we show how we can abstract aspects of run-time monitoring through declarations of programming languages so that a majority of run-time monitoring code required for preserving the intended semantics of Solidity and thereby overcome vulnerabilities can be instrumented automatically at compile time itself. For illustrative purposes, we use Solidity and call the augmented Solidity language SolidityD. SolidityDsyntactically is identical to Solidity except for declarations. The declarations preserve the intended semantics of various constructs and thus overcome a large number of vulnerabilities. We illustrate how a vast variety of vulnerabilities encountered in programming smart contracts in Solidity are overcome through declarations. Declarations envisaged in SolidityDare similar to that used in classic concurrent programming languages and are easily visualizable by the programmer. Declarations lead to automatic introduction of run-time code at compilation time needed to satisfy various executional constraints needed to satisfy the semantic requirements of declarations. Further, we demonstrate that SolidityD, can be automatically transformed to pure Solidity: thus, enabling an effective debugging at source level rather than at the byte or EVM level. Another important outcome of using SolidityD, is that it can be effectively used for asserting coarse-grained properties of declarations. Such a feature leads to gaining trust in the usage of smart contracts. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Program debugging

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：