检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ghosh, Sabyasachi Rajwade, Ajit Dept. of Computer Science and Engineering Indian Institute of Technology Bombay Mumbai India

Recovery of signals with elements defined on the nodes of a graph, from compressive measurements is an important problem, which can arise in various domains such as sensor networks, image reconstruction and group testing. In some scenarios, the graph may not be accurately known, and there may exist a few edge additions or deletions relative to a ground truth graph. Such perturbations, even if small in number, significantly affect the Graph Fourier Transform (GFT). This impedes recovery of signals which may have sparse representations in the GFT bases of the ground truth graph. We present an algorithm which simultaneously recovers the signal from the compressive measurements and also corrects the graph perturbations. We analyze some important theoretical properties of the algorithm. Our approach to correction for graph perturbations is based on model selection techniques such as cross-validation in compressed sensing. We validate our algorithm on signals which have a sparse representation in the GFT bases of many commonly used graphs in the network science literature. An application to compressive image reconstruction is also presented, where graph perturbations are modeled as undesirable graph edges linking pixels with significant intensity difference. In all experiments, our algorithm clearly outperforms baseline techniques which either ignore the perturbations or use first order approximations to the perturbations in the GFT bases. Copyright © 2024, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing

arXiv

引用

arXiv 2024年

作者： Li, Muzhi Hu, Minda King, Irwin Leung, Ho-Fung Dept. of Computer Science & Engineering The Chinese University of Hong Kong Hong Kong

The Knowledge Graph Entity Typing (KGET) task aims to predict missing type annotations for entities in knowledge graphs. Recent works only utilize the structural knowledge in the local neighborhood of entities, disregarding semantic knowledge in the textual representations of entities, relations, and types that are also crucial for type inference. Additionally, we observe that the interaction between semantic and structural knowledge can be utilized to address the false-negative problem. In this paper, we propose a novel Semantic and Structureaware KG Entity Typing (SSET) framework, which is composed of three modules. First, the Semantic Knowledge Encoding module encodes factual knowledge in the KG with a Masked Entity Typing task. Then, the Structural Knowledge Aggregation module aggregates knowledge from the multi-hop neighborhood of entities to infer missing types. Finally, the Unsupervised Type Re-ranking module utilizes the inference results from the two models above to generate type predictions that are robust to false-negative samples. Extensive experiments show that SSET significantly outperforms existing state-of-the-art methods. 1 © 2024, CC BY-NC-SA.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Secure and Decentralized Smart Licensing of Charging Vehicles for Rajshahi City Corporation

Blockchain Based Secure and Decentralized Smart Licensing of...

引用

Information and Communication Technology for Sustainable Development (ICICT4SD), International Conference on

作者： Momenul Haque Subrata Kumer Paul Kamrul Islam Mursheda Nusrat Della Rakhi Rani Paul Sultan Fahim Dept. of Computer Science and Engineering Bangladesh Army University of Engineering & Technology Bangladesh Dept. of Computer Science and Engineering University of Rajshahi Rajshahi Bangladesh Dept. of Computer Science and Engineering Rabindra Maitree University Kusbtia Bangladesh Dept. of Information and Communication Engineering Bangladesh Army University of Engineering & Technology Bangladesh

The adoption of charging vehicles in Rajshahi has emerged as a significant step towards reducing air pollution and promoting a healthy, green city. However, the current centralized licensing system poses challenges such as time-consuming processes and the potential for fraudulent activities. To address these issues, this paper proposes the implementation of a secure and decentralized smart licensing system for charging vehicles in Rajshahi City Corporation, leveraging the smart capabilities of blockchain technology. By utilizing Hyperledger Fabric, the implementation generates blockchain based smart contracts that automate and streamline the licensing process smartly and efficiently. This approach ensures the immutability, transparency, and integrity of license records, minimizing the risk of fraud and enhancing overall efficiency. Additionally, the system incorporates the use of QR codes and an inquiry system to enhance the credibility of paper-based licenses. Compared to other digital licenses, this blockchain-based method significantly reduces risks and contributes to the development of a greener and more sustainable Rajshahi city environment. Furthermore, the introduction of a sustainable business policy, utilizing the G2C model, facilitates revenue generation and distribution fairly and equitably for all stakeholders involved in the charging vehicle ecosystem. This implementation not only offers cost benefits and efficiency improvements for drivers but also promotes a sustainable and environmentally friendly city.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Advanced Data Mining and computer Vision Techniques in License Plate Recognition

Application of Advanced Data Mining and Computer Vision Tech...

引用

Smart Technologies, Communication and Robotics (STCR)

作者： Ayorinde Alase Danish Multani Sai Rithwik Amajala Udhaya S K Kamal Upreti Electrical and Computer Engineering University of Arkansas at Little Rock Little Rock Arkansas US UST Global Solutions Gurgaon Haryana India Computer Science and Engineering India Computer Science and Engineering Easwari Engineering College Chennai India Dept. of Computer Science Christ University Delhi NCR India

ISBN: (数字)9798350357530

ISBN: (纸本)9798350357547

As urbanization is expanding rapidly and vehicular traffic is on the rise, efficient and automated vehicle identification is a must. Smart transportation, safety monitoring, & police work all heavily rely on Automatic License Plate Detection (ALPD). Traditional heuristic-based image processing techniques are incapable of handling environmental variations; Artificial intelligence (AI) & machine vision solutions are therefore used. YOLO, Faster R-CNN, and SSD are some of the most effective CNN-based and object identification algorithms that demonstrate cutting-edge accuracy in license plate recognition. The paper studies the usage of deep learning algorithms with prepossessing and advanced localization methods for ALPDs' optical character recognition (OCR) and character segmentation. The research also studies integrating ALPD with edge computing and IoTs to develop real-time smart traffic solutions. It also examines machine learning techniques, deep learning innovations, and conventional methods, emphasizing how well various models perform in comparison in terms of accuracy, computational efficiency, and real-time processing power. By employing cutting-edge designs, this study seeks to increase the scalability and resilience of license plate recognition systems, which will support future urban development, security applications, as intelligent transportation management.

关键词： YOLO Deep learning Computational modeling Lighting Real-time systems Computational efficiency Smart transportation Internet of Things License plate recognition Edge computing

来源：评论

学校读者我要写书评

暂无评论

Instance-Level Safety-Aware Fidelity of Synthetic Data and its Calibration 27

Instance-Level Safety-Aware Fidelity of Synthetic Data and i...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Cheng, Chih-Hong Stockel, Paul Zhao, Xingyu Chalmers & Univ. of Gothenburg Dept. of Computer Science & Engineering Sweden University of Hildesheim Department of Informatics Germany University of Warwick WMG CV4 7AL United Kingdom

ISBN: (纸本)9798331505929

Modeling and calibrating the fidelity of synthetic data is paramount in shaping the future of safe and reliable self-driving technology by offering a cost-effective and scalable alternative to real-world data collection. We focus on its role in safety-critical applications, introducing four types of instance-level fidelity that go beyond mere visual input characteristics. The aim is to ensure that applying testing on synthetic data can reveal real-world safety issues, and the absence of safety-critical issues when testing under synthetic data can provide a strong safety guarantee in real-world behavior. We suggest an optimization method to refine the synthetic data generator, reducing fidelity gaps identified by deep learning components. Experiments show this tuning enhances the correlation between safety-critical errors in synthetic and real data. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Routing Protocols in Vehicular Ad Hoc Networks (VANETs): Challenges, Solutions and Future Directions

A Comprehensive Review of Routing Protocols in Vehicular Ad ...

引用

IEEE UP Section Conference on Electrical computer and Electronics (UPCON)

作者： Sonika Bhardwaj Ramesh Saha Dept. of Computer Science & Engineering Indian Institute of Information Technology Sonepat India

ISBN: (数字)9798350378726

ISBN: (纸本)9798350378733

VANETs play a pivotal role in the growth/development of the intelligent transportation systems (ITS) by allowing seamless communication between vehicles and infrastructure. This paper presents a comprehensive review of various routing protocols used in VANETs, focusing on topology-based, position-based, hybrid, and machine learning (ML) enhanced protocols. The analysis evaluates these protocols across key performance metrics such as scalability, latency, packet delivery ratio (PDR), overhead, and security. Hybrid and context-aware protocols provide greater adaptability but come with more complexity than standard protocols, which struggle with scalability and security in dynamic contexts. The growing combination of ML, blockchain, and federated learning into VANET routing establishes potential for enhanced performance and security. Furthermore, the paper also highlights the current limitations of an existing protocols and recognizes the directions for the research, the more emphasizing on the need for scalable, secure, and real-time adaptable solutions for next-generation VANETs.

关键词： Federated learning Reviews Scalability Vehicular ad hoc networks Routing Routing protocols Real-time systems Blockchains Security Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Tomato Shelf Life Prediction using IoT and Machine Learning

Tomato Shelf Life Prediction using IoT and Machine Learning

引用

2024 International Conference on Innovations in science, engineering and Technology, ICISET 2024

作者： Naim, Nazmul Arafin Islam, Raisul Saifuddin, Mohammed Hoque, Md. Jiabul Hasan, Mohammad Nadib Khandaker, Mohammad Moneruzzaman International Islamic University Chittagong Dept. of Computer and Communication Engineering Kumira Chittagong4318 Bangladesh School of Agriculture Science & Biotechnology Sultan Zainal Abidin Besut Campus Besut Terengganu22200 Malaysia

ISBN: (纸本)9798350355499

Predicting tomato shelf life is crucial for optimizing supply chains and reducing waste. This study utilizes IoT and machine learning to analyze postharvest characteristics of tomatoes in four ripening stages under controlled conditions until the rotten phase. Key findings include significant reductions in weight and dimensions, increased red and decreased green color components indicating ripening, and longer shelf life for unripe tomatoes. Green 1 tomatoes had the most extended shelf life of 18 days. p H trends showed higher levels during ripening (pH 3.5) compared to the green stage (p H 4.5). To predict the shelf life, various machine learning models were applied and the Random Forest Regression was the most accurate model, exhibiting the lowest errors and highest predictive reliability. © 2024 IEEE.

关键词： Shelf life

来源：评论

学校读者我要写书评

暂无评论

Real-Time Face Mask Detector 3

Real-Time Face Mask Detector

引用

3rd IEEE International Conference on Technology, engineering, Management for Societal Impact using Marketing, Entrepreneurship and Talent, TEMSMET 2023

作者： Patel, Vishwajeet Guru Prasad, M.S. Aditya Pai, H. Kumar, A Suresh Praveen Gujjar, J. Naveen Kumar, H.N. Dept. of Computer Science and Engg. Dehradun India JAIN [Deemed-to-be University Faculty of Management Studies Bengaluru India Vidyavardhaka College of Engineering Dept. of Electronics and Communication Engg. Karnataka Mysuru India

ISBN: (纸本)9798350397819

When the COVID-19 pandemic was present we all have faced various challenges in our everyday lives. Pandemic created worldwide emergency which led to the lockdown in most of the countries resulting into disruption in world trade and movement. To reduce the covid cases WHO recommended to wear mask and maintain social distancing and then these steps became mandatory for some places, such as restaurants, hospitals, grocery stores etc., The purpose of limiting interaction with individuals as much as possible in such situations is simply defeated by having a staff personally check each person to make sure their mask is on. To avoid this dilemma, it became necessary to build a project named 'Real-time face mask detector', This reveals whether a mask-wearing individual is there. This project needed the use of some python libraries like TensorFlow, Keras, OpenCV. Using this project, we will be able to Detect mask-on faces in live video clip with accuracy of 97-98 %. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Prediction of Crop Yield Using Machine Learning Approaches for Agricultural Data

TechRxiv

引用

TechRxiv 2023年

作者： Hazra, Simanta Karforma, Sunil Bandyopadhyay, Abhishek Chakraborty, Sayantani Chakraborty, Debasis Dept. of Computer Science and Engineering Asansol Engineering College West Bengal 713305 India Dept. of Computer Science University of Burdwan West Bengal 713104 India The Dept. of Computer Application Asansol Engineering College West Bengal 713305 India The Dept. of Computer Science and Engineering Asansol Engineering College Asansol713305 India

For many developing nations, agriculture is the fundamental source of economic engine. Without a significant increase in food production, the rise in global population during the 21st century would not have been conceivable. Thus, a key issue in agricultural expansion is the accurate forecast of healthy crop output / crop type utilizing machine learning (ML) algorithms. In this paper, the aim is to identify the most effective model that can help farmers in predicting the crop yield / crop type for the benefit of farmers. Seven popular algorithms such as K-Nearest Neighbor (KNN), Random Forest (RF) Classifier, Extreme Gradient Boosting(XGBoost), Light Gradient Boosting Machine (LightGBM), Artificial Neural Network (ANN), Support Vector Machine(SVM) and Multi-layer Perceptron (MLP) are investigated on the numerical crop dataset and performances are studied. Experimental results reveal that XGBoost gives the highest accuracy among the seven. Subsequently, Another crop image dataset is explored to identify crop type using transfer learning in convolutional neural networks (CNN). Different models for crop image classification with weights trained on ImageNet such as VGG-19 (Visual Geometry Group-19), VGG-16, Inception v3, ResNet-50 and EfficientNet-B0 are studied. Results based on the accuracy and kappa coefficient show that VGG-19 outperforms other techniques. © 2023, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Soil Monitoring Using Machine Learning Algorithms

Soil Monitoring Using Machine Learning Algorithms

引用

Smart Devices (ICSD), International Conference on

作者： Jyoti Agarwal Ishita Bhatt Sahaj Goyal Prabhdeep Singh Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798350394412

ISBN: (纸本)9798350394429

Soil monitoring is important aspect of agriculture to grow good quality food. It is crucial aspect for famers and the environmental scientists as well. If soil is monitored properly then chances of good quality crop increased which reduces farmer’s tension and increase their income. This research paper is a step towards applying machine learning algorithms for soil monitoring. Decision Tree Regression, Random Forest Regression, Gradient Boosting Regressor and Stacking Regressor are such algorithms. Comparison analysis of these techniques are also done in this paper. This work will be helpful for farmers and land managers to accurately predict about the soil fertility which will further help them to take decision which crop should be grow as per the soil condition.

关键词： Machine learning algorithms Stacking Crops Soil Prediction algorithms Vectors Smart devices Regression tree analysis Monitoring Random forests

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：