检索结果-内蒙古大学图书馆

IEEE Recent Advances in Intelligent Computational Systems (RAICS)

作者： Senthil Kumar Seeni P. Maheswari Jothibabu Konidhala M. Raja Suguna M.V. Ishwarya S. Srinivasan Department of Mobile Application Development Cognizant Technology Solutions Buffalo Grove Illinois USA Faculty of Management Studies SRM Institute of Science and Technology Kattankulathur Chennai India Department of Electronics and Communication Engineering University of Technology and Applied Sciences- Al Musannah Musanna South Al Batina Oman Department of Computer Science and Engineering RMK College of Engineering and Technology Chennai Tamil Nadu India Artificial intelligence and Data science Department Agni College of Technology Chennai Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350381689

ISBN: (纸本)9798350381696

The research uses Internet of Things technology for predictive maintenance in the construction sector. The system addresses incorporating Internet of Things sensors into construction machinery to enable real-time monitoring of operating parameters. The study suggests a proactive maintenance strategy that may anticipate equipment breakdowns by examining the data obtained and using sophisticated prediction models. With this strategy, construction teams can arrange maintenance activities systematically, which cuts down on downtime and helps avoid expensive interruptions. The abstract emphasizes the advantages of this practice, which include reducing unexpected downtime as much as possible, extending the life of equipment, and making the most of available resources. The study proves the usefulness of the IoT-based predictive maintenance approach via empirical investigations and the analysis of case studies. This validates the strategy's efficacy, contributing to enhanced equipment performance and increased work efficiency in the construction industry.

关键词： Electric breakdown Predictive models Real-time systems Sensor systems Maintenance Sensors Trajectory Internet of Things Machinery Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Handling SQL Injection Attack Using Progressive Neural Network 5th

Handling SQL Injection Attack Using Progressive Neural Netwo...

引用

5th International Conference on Information, Communication and Computing Technology, ICICCT 2020

作者： Pathak, Rohit Kumar Mohit Yadav, Vrinda Department of Computer Science and Engineering Centre for Advanced Studies Dr. A.P.J. Abdul Kalam Technical University New Campus LucknowUttar Pradesh226031 India

ISBN: (纸本)9789811596704

Training in machine learning can solve complex problems like catastrophic forgetting. Catastrophic forgetting in machine learning is forgetting the previously known data while training a new model. In this paper, our main focus is to handle the SQL injection attack using Progressive Neural Network. This protects the data that is lost while training a new security model and defends against a new security attack. The proposed technique is a better approach for solving the problem of network security while transferring knowledge from one module to another module. It is found that Progressive neural Network with Naïve based classifier gives an accuracy of 97.897% which is comparatively higher than existing techniques. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

XiaoMu: an AI-driven assistant for MOOCs

引用

science China(Information sciences) 2021年第6期64卷 222-224页

作者： Zhengyang SONG Jie TANG Tracy Xiao LIU Wenjiang ZHENG Lili WU Wenzheng FENG Jing ZHANG Institute for Interdisciplinary Information Sciences Tsinghua University Department of Computer Science and Technology Tsinghua University School of Economics and Management Tsinghua University Center for Strategic Studies Chinese Academy of Engineering Information School Renmin University of China

Nowadays, massive open online courses(MOOCs), are attracting widespread interest as an alternative education model. Several MOOCs platforms, such as Coursera, edX,and Udacity have been built and they provide low-cost opportunities for anyone who needs to access a massive number of courses from the worldwide top universities. However, the learning completion rate of the learners via MOOCs is extremely low compared with that in real classroom ***, this study builds a system, called XiaoMu, to design intelligent intervention strategies for the learning process of learners and improve the learning efficiency through automatic analysis of courses and learners. We deployed our system on the website1), which is one of the largest MOOCs in China.

关键词： Information Systems and Communication Service

来源：评论

学校读者我要写书评

暂无评论

Optimization of Agent-Based Evacuation Models Using Behavioral Data from Vr-Based Experiments

SSRN

引用

SSRN 2022年

作者： Juřík, Vojtěch Uhlík, Ondřej Snopková, Dajana Kvarda, Ondřej Apeltauer, Tomáš Apeltauer, Jiří Department of Psychology Faculty of Arts Masaryk University Brno Czech Republic Institute of Computer Aided Engineering and Computer Science Faculty of Civil Engineering Brno University of Technology Brno Czech Republic Department of Geography Faculty of Science Masaryk University Brno Czech Republic Department of Library and Information Studies Faculty of Arts Masaryk University Brno Czech Republic Institute of Road Structures Faculty of Civil Engineering Brno University of Technology Czech Republic

Agent-based evacuation modeling represents an effective tool for making predictions about evacuation aspects of buildings such as egress times, congestions, and maximum safe building capacity. These models, however, have various computation algorithms with different input parameters and outcomes, which affects their validity and potential application. To refine these models, a comparison with evacuation behavior data from the real situations is necessary. However, collection of such data is time-consuming, costly, and completely impossible in the case of unbuilt buildings. In recent years evacuation experiments conducted in Virtual Reality (VR) have been frequently proposed in the literature as an effective tool for collecting data about human behavior. However, empirical studies which would assess validity of VR-based data for such purposes are still rare in the evacuation domain. This study explores opportunities that the VR-based behavioral data may bring for refining outputs of agent evacuation models. To this end, this study compared various input settings of agent-based evacuation models, including those based on data gathered in the REAL and VR evacuation experiment. Key model input variables (quantities) were selected based on empirical data gathered from an original evacuation exercise conducted in a real building and its virtual twin. Several approaches were applied to run agent simulations on human evacuation behavior in the building in the case of emergency. This study found that the resulting predictions of agent models using data collected in the VR environment after proposed corrections match real-world behavior and offer desirable variance in the data outputs necessary for practical applications. © 2022, The Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models

arXiv

引用

arXiv 2025年

作者： Wang, Chengming Jia, Dongyao Wang, Wei Ngoduy, Dong Peng, Bei Wang, Jianping School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou215123 China Institute of Transport Studies Monash University Clayton3800 Australia Department of Computer Science University of Liverpool LiverpoolL69 7ZX United Kingdom Department of Computer Science City University of Hong Kong China

Car-following models (CFMs) are fundamental to traffic flow analysis and autonomous driving. Although calibrated physics-based and trained data-driven CFMs can replicate human driving behavior, their reliance on specific datasets limits generalization across diverse scenarios and reduces reliability in real-world deployment. Moreover, these models typically focus on behavioral fidelity and do not support the explicit optimization of local and string stability, which are increasingly important for the safe and efficient operation of autonomous vehicles (AVs). To address these limitations, we propose a Knowledge-Informed Deep Learning (KIDL) paradigm that distills the generalization capabilities of pre-trained Large Language Models (LLMs) into a lightweight and stability-aware neural architecture. LLMs are used to extract fundamental car-following knowledge beyond dataset-specific patterns, and this knowledge is transferred to a reliable, tractable, and computationally efficient model through knowledge distillation. KIDL also incorporates stability constraints directly into its training objective, ensuring that the resulting model not only emulates human-like behavior but also satisfies the local and string stability requirements essential for real-world AV deployment. We evaluate KIDL on the real-world NGSIM and HighD datasets, comparing its performance with representative physics-based, data-driven, and hybrid CFMs. Both empirical and theoretical results consistently demonstrate KIDL’s superior behavioral generalization and traffic flow stability, offering a robust and scalable solution for next-generation traffic systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Missing Links in Bicycle Networks

arXiv

引用

arXiv 2022年

作者： Vybornova, Anastassia Cunha, Tiago Gühnemann, Astrid Szell, Michael Computer Science Department IT University of Copenhagen Copenhagen2300 Denmark Institute for Transport Studies University of Natural Resources and Life Sciences Vienna1180 Austria ISI Foundation Turin10126 Italy Complexity Science Hub Vienna Vienna1080 Austria

Cycling is an effective solution for making urban transport more sustainable. However, bicycle networks are typically developed in a slow, piecewise process that leaves open a large number of gaps, even in well developed cycling cities like Copenhagen. Here, we develop the IPDC procedure (Identify, Prioritize, Decluster, Classify) for finding the most important missing links in urban bicycle networks, using data from OpenStreetMap. In this procedure we first identify all possible gaps following a multiplex network approach, prioritize them according to a flow-based metric, decluster emerging gap clusters, and manually classify the types of gaps. We apply the IPDC procedure to Copenhagen and report the 105 top priority gaps. For evaluation, we compare these gaps with the city’s most recent Cycle Path Prioritization Plan and find considerable overlaps. Our results show how network analysis with minimal data requirements can serve as a cost-efficient support tool for bicycle network planning. By taking into account the whole city network for consolidating urban bicycle infrastructure, our data-driven framework can complement localized, manual planning processes for more effective, city-wide decision-making. Copyright © 2022, The Authors. All rights reserved.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

A miniaturized UWB monopole antenna for sub-6 GHz 5G wireless applications

A miniaturized UWB monopole antenna for sub-6 GHz 5G wireles...

引用

2023 IEEE Silchar Subsection Conference, SILCON 2023

作者： Panja, Aparna De, Arnab Bhattacharjee, Koyndrik Maity, Somnath Bhattacharya, Ankan Roy, Bappadittya Sarkar, Partha Pratim Bhattacharjee, Anup Kumar National Institute of Technology Deparment of Ece West Bengal Durgapur713209 India Vadlamudi Dept. of Advanced Computer Science and Engineering Vignan's Foundation for Science A.P Guntur India Dr. B C Roy Engineering College Department of Civil Engineering West Bengal Durgapur713206 India Government Women's Polytechnic Deparment of Ece Jharkhand Jamshedpur832108 India Hooghly Engineering & Technology College Dept. of Electronics and Communications Engineering West Bengal Hooghly India VIT-AP University School of Electronics Engneering Amaravati India University of Kalyani Deparment of Engineering and Technological Studeies Kalyani India

ISBN: (纸本)9798350314144

This article describes a miniaturized, ultra-wideband monopole antenna with dimensions of 23.00 x 20.00 x 1.60 mm3 (0.23λ0 x 0.23λ0 x 0.016λ0) designed for sub-6 GHz 5G wireless applications. The suggested layout is compatible with sub-6 GHz 5G, including satellite X-band (7.5-8.5 GHz), ITU n77 (3.3-4.2 GHz), and n79 (4.4-5 GHz) bands, 502.11a WLAN (5.15 - 5.85 GHz), and WiMAX bands (3.5/5.5 GHz). The suggested structure uses a fusion shape of rectangular, triangular, and trapezoidal slits on the ground plane and isosceles triangle, octagonal slot on the metal patch to improve the radiation characteristics and impedance bandwidth. The addition of rectangular slits which are incorporated into the bottom plane just below the microstrip line and trapezoidal-shaped slots shifts the lower cut-off frequency towards the left, while the octagon-shaped slot and the isosceles triangular slit on the radiating patch shift the higher cut-off frequency towards the right. The suggested structure operates over the range from 3.10 to 18.87GHz, having an equivalent fractional bandwidth of 143.56% and a peak gain of around 5.37 dBi. The antenna has a radiation efficiency of 80.00% and displays a decent S11 ≤-10 dB throughout the bandwidth. Results from measurement and simulation are good in agreement. © 2023 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

FedVQCS: Federated Learning via Vector Quantized Compressed Sensing

arXiv

引用

arXiv 2022年

作者： Oh, Yongjeong Jeon, Yo-Seb Chen, Mingzhe Saad, Walid The Department of Electrical Engineering POSTECH Gyeongbuk Pohang37673 Korea Republic of The Institute for Convergence Research and Education in Advanced Technology Yonsei University Incheon21983 Korea Republic of The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Wireless@VT Bradley Department of Electrical and Computer Engineering Virginia Tech ArlingtonVA22203 United States

In this paper, a new communication-efficient federated learning (FL) framework is proposed, inspired by vector quantized compressed sensing. The basic strategy of the proposed framework is to compress the local model update at each device by applying dimensionality reduction followed by vector quantization. Subsequently, the global model update is reconstructed at a parameter server by applying a sparse signal recovery algorithm to the aggregation of the compressed local model updates. By harnessing the benefits of both dimensionality reduction and vector quantization, the proposed framework effectively reduces the communication overhead of local update transmissions. Both the design of the vector quantizer and the key parameters for the compression are optimized so as to minimize the reconstruction error of the global model update under the constraint of wireless link capacity. By considering the reconstruction error, the convergence rate of the proposed framework is also analyzed for a non-convex loss function. Simulation results on the MNIST and FEMNIST datasets demonstrate that the proposed framework provides more than a 2.4% increase in classification accuracy compared to state-of-the-art FL frameworks when the communication overhead of the local model update transmission is 0.1 bit per local model entry. Copyright © 2022, The Authors. All rights reserved.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Compendious review on 3D-printed gels for effluent treatment

Hybrid Advances

引用

Hybrid Advances 2024年 6卷

作者： Panchapakesan, Apsara Dalave, Priyanka Anil Kandasubramanian, Balasubramanian Ismail, Sikiru O. Additive Manufacturing Laboratory Defence Institute of Advanced Technology (DU) Girinagar Maharashtra Pune 411025 India Department of Metallurgy and Material Science COEP Technological University Pune Pune 411005 India Centre for Engineering Research School of Physics Engineering and Computer Science University of Hertfordshire England Hatfield AL10 9AB United Kingdom

Direct ink writing (DIW) has emerged as an innovative and efficient method for gel synthesis, presenting numerous advantages over conventional techniques. Leveraging a diverse array of raw materials, DIW offers precise control over gel construction, facilitating the fabrication of materials with larger pore sizes. This capability contrasts with traditional methods like ionic gelation, which typically produce a maximum pore size of 130 μm. The increasing demand for materials with exceptional adsorption properties, especially for effluent treatment, has driven extensive research in this domain. While traditional gel preparation methods remain valuable, they exhibit inherent limitations. Thus, there is a pressing need for more efficient and scalable approaches to gel synthesis. DIW serves as a superior alternative, providing enhanced control over printing parameters and enabling the customization of materials to meet specific requirements. This paper not only addresses the limitations of traditional methods but also highlights the benefits of utilizing DIW for gel formulation. Additionally, it offers an overview of commonly employed adsorption isotherm and kinetic models and explores the applications of DIW-printed gels in effluent treatment. Given the expanding body of research in this area, this critical and comprehensive review underscores the potential of DIW in the adsorption of pollutants from wastewater. © 2024 The Authors

关键词： 3D printing Adsorption Direct ink writing Effluent treatment Gels

来源：评论

学校读者我要写书评

暂无评论

Healthcare Delivery through Telemedicine during the COVID-19 Pandemic: Case Study from a Tertiary Care Center in South India

引用

Hospital Topics 2021年第4期99卷 151-160页

作者： D’Souza, Brayal Suresh Rao, Shreyas Hisham, Sayed Shetty, Avinash Sekaran, Varalakshmi Chandra Pallagatte, Mamatha Channappa G, Somu Suresh Rao, Tejas Prasanna School of Public Health Manipal MAHE India Department of Computer Science & Engineering Sahyadri College of Engineering and Management Mangalore India Baby Memorial Hospital Kerala India Kasturba Medical College Manipal MAHE India Melaka Manipal Medical College Manipal MAHE India Department of Management Studies Indian Institute of Science Bangalore India Department of Hospital Administration KMC Manipal Manipal MAHE India Bangalore India

The Coronavirus disease 2019 (COVID-19) pandemic has necessitated medical centers across the world to deliver healthcare through telemedicine. We discuss the adoption, delivery of telemedicine services at a tertiary care center and patient satisfaction involving 456 patients in south India. Most respondents had sought telemedicine care at the department of Medicine (16.23%). The maximum satisfaction was reported by patients in OBG (100%). The responses were generally positive across all the age groups. The paper offers insights on best practices adopted at the center, lessons learnt, and provides recommendations for health care systems offering telemedicine during COVID-19 times. © 2021 Taylor & Francis Group, LLC.

关键词： COVID-19 pandemic patient satisfaction telehealth Telemedicine

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：