检索结果-内蒙古大学图书馆

DDSS: Driver decision support system based on the driver behaviour prediction to avoid accidents in intelligent transport system

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 1-13页

作者： S, Balasubramani D, John Aravindhar Renjith, P.N. Ramesh, K. Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India

Accidents caused by drivers who exhibit unusual behavior are putting road safety at ever-greater risk. When one or more vehicle nodes behave in this way, it can put other nodes in danger and result in potentially catastrophic accidents. In order to anticipate and handle unusual driving behavior in Intelligent Transportation Systems (ITS), this research presents a unique Driver Decision Support System (DDSS). A reliable driving behavior prediction system is used by the suggested DDSS to categorize drivers as displaying normal or abnormal behavior. In order to prevent accidents in ITS scenarios, the system reliably detects anomalous driving patterns and advises nearby vehicles to change lanes or alter speed. The driver behavior prediction algorithm efficiently groups drivers into behavior categories using the K-Means clustering method. In order to evaluate the algorithm's efficacy, a comparative analysis is conducted by comparing its outcomes against those of Support Vector Machines (SVMs), Decision Trees, K-Nearest Neighbours (KNN), Logistic Regression, and Naïve Bayes. The integration of the Driver Decision Support System into the Intelligent Transportation System infrastructure serves to augment endeavours in accident prevention. Monitoring and analysis of driver behavior enable timely interventions, promoting safer driving practices and reducing accident risks. This research helps to create a more effective transportation system by reducing the number of accidents brought on by reckless driving. Because of its novel method to anticipating and controlling driver behavior, the proposed DDSS has promise for improving road safety and preventing accidents. The efficacy and the dependability of the driver behavior prediction algorithm are confirmed by the experimental assessment. © 2023

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Biometric Authentication Using Fragment Jaya Optimizer-Based Deep CNN with Multi-kernel SVM

引用

SN computer science 2024年第4期5卷 337页

作者： Umasankari, N. Muthukumar, B. Shanmuganathan, C. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India School of Computing Department of CSE Sathyabama Institute of Science and Technology Chennai India Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India

The earlier research clearly indicated that the bimodal authentication system has more efficiency than unimodal and multimodal. This is due to the reason for the best intact biometric traits of fingerprint and retina. There is a chance to additionally improve further performance of the proposed biometric trait combination by additional or alternate algorithms or methodologies. Therefore, in this research work, the multi-kernel support vector machine (MK-SVM), a machine learning classification approach, is proposed and is used for the implementation. In addition, a hybrid algorithm of fragment Jaya optimizer-based deep convolutional neural network (FJO-DCNN) approach is also used to improve the performance value for bimodal biometric authentication and classification. The recognition systems analyze both biometrics independently, and their conclusions are combined to determine whether to give or refuse access to the user in the end. According to the findings of the implementation, this work demonstrates more dependability than the cascaded biometric system. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Bimodal biometric authentication Deep convolutional neural network Fragment Jaya optimizer convolutional neural network Multi-kernel support vector machine

来源：评论

学校读者我要写书评

暂无评论

Optimal Hybrid Modeling Scheme for Electricity Price Prediction Using Ensemble Learning 4

Optimal Hybrid Modeling Scheme for Electricity Price Predict...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Minu, M.S. Yeshwanth, M. Venkataratnam, K. Deepak Reddy, N. Sai Srm Institute of Science and Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350300888

One of the most crucial aspects of decision-making for electricity market participants to develop rational competitive strategies is accurate energy price forecast. An important task in energy conservation is the prediction of energy prices and use. Support vector regression performs well when dealing with non-linear data issue with data regression It has been employed frequently in recent years to forecast building energy costs and usage. We draw the conclusion that the relationship between the cost of lighting energy, its consumption, and its influencing factors is non-linear based on historical data. For energy trading organizations, predicting energy prices and usage is a crucial task. As the accuracy of the prediction directly affects the company's profit, it should be as precise as possible. One of the most crucial tasks in the management and planning of power systems is the forecasting of electrical loads, energy prices, and consumption. Yet occasionally, we have to find a solution to this issue without access to enough and trustworthy historical data. The support vector regression with radial basis function was used to construct an accurate prediction model of lighting energy price and usage. The forecast findings show that support vector regression has greater prediction accuracy than neural networks. The prediction model can project building energy costs and consumption on an hourly basis and evaluate the effects of energy management strategies for office buildings. Once the base models have been selected, the next step is to construct the ensemble. The most common approach is to use a weighted average of the predictions of the base models. The weights can be determined using various techniques, such as cross-validation or gradient-based optimization. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Predictive Capabilities for Cyber Physical Systems Through Supervised Learning

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第16期49卷 77-86页

作者： Dhanalakshmi, B. Tamije Selvy, P. Department of Computer Science and Engineering Dr.N.G. P Institute of technology India Department of Computer Science and Engineering Hindusthan College of Engineering and Technology India

The rapid advancement and proliferation of Cyber-Physical Systems (CPS) have led to an exponential increase in the volume of data generated continuously. Efficient classification of this streaming data is crucial for predicting system behaviors and enabling proactive decision-making. This research aims to extract actionable knowledge from the continuous data streams of CPS and predict their behavior using advanced supervised learning algorithms. The predictions facilitate timely interventions and necessary actions within the interconnected physical network. The background of this work lies in the intersection of CPS, machine learning, and data stream mining. Traditional batch processing methods are inadequate for real-time analysis of CPS data due to their inherent latency and computational inefficiency. This research employs state-of-the-art techniques for real-time data processing, including incremental learning, sliding window models, and ensemble methods tailored for streaming data. Our approach differs from existing works by focusing on a comprehensive framework that integrates real-time data ingestion, preprocessing, feature extraction, and model updating in a seamless pipeline. Unlike previous studies that often rely on static datasets and offline analysis, our method ensures continuous learning and adaptation to evolving data patterns. Comparative analysis with existing techniques demonstrates superior performance in terms of accuracy, latency, and scalability. Specifically, our models achieved an average classification accuracy of 92%, with a precision of 90%, recall of 89%, and an F1 score of 89.5%. These metrics indicate significant improvements over traditional batch processing methods, which typically lag in responsiveness and adaptability. This research provides a robust and efficient solution for the real-time classification of streaming data from CPS, enhancing the system's ability to predict behaviors and take necessary actions promptly. © 2025 Slov

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Underwater video transmission with video enhancement using reduce hazing algorithm

引用

Journal of Optical Communications 2024年第2期45卷 379-388页

作者： Mathiazhagan, Janarthanan Gauni, Sabitha Mohan, Rajesvari Department of Electronic and Communication Engineering SRM Institute of Science and Technology Tamil Nadu Chennai India

Underwater video regulation is an insightful research field that can help engineers with bettering investigation on the lowered condition. Submerged video preparing has been utilized in a many fields, such as submerged infinitesimal location, landscape examining, mine identification, media transmission connections, and self-proficient lowered vehicles. Be that as it may, submerged video experiences solid assimilation, dissipating, shading contortion, and clamor from the manufactured light sources, causing video obscure, cloudiness, and a somewhat blue or greenish tone. In this way, the improvement can be separated into two techniques, submerged video de-preliminaries and underexposed video concealing remaking. Relentless in remote correspondence structures, for instance 3G, 4G, and so on, a coming crisis is endless deftly of the nonattendance of consistently Radio Frequency (RF) resources;this deterrent in moving speed cannot strengthen the improvement notable for high information speed. So the new innovation of Light-Fidelity (Li-Fi) came into picture. This innovation can be contrasted to that of Wi-Fi and offers points of interest like expanded available spectrum efficiency, effectiveness, security, low idleness and a lot higher speed. Communication is accomplished by exchanging light-emitting diode (LED) lights on and off at a speed higher than what is detectable to the human eye. This paper presents the explanation behind underexposed picture corruption and surveys the cutting-edge knowledge calculations like video reduce hazing algorithm. In this calculation, it uses two different de-hazing methods, simple Dark Channel Prior (DCP) and Approximate Dark Channel Prior (ADCP), to reduce haze in a video. © 2024 Walter de Gruyter GmbH. All rights reserved.

关键词： Light

来源：评论

学校读者我要写书评

暂无评论

Credit Card Fraud Detection and Prevention Using a Formula-Based HMM Model Authentication System for Secure Transaction 8th

Credit Card Fraud Detection and Prevention Using a Formula-B...

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Madhav Kathireven, Nishok Ramkumar, K. Department of Computer Science SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9789819748914

Credit card fraud is a persistent problem in the financial sector, despite the implementation of various cyber security measures. In this study, we propose a novel Hidden Markov Model-based approach (HMM) for analyzing user behavior and a formula-based authentication system for verification for identifying credit card fraud. The HMM is trained on recent transaction data to identify patterns in user behavior, and any deviation from the expected behavior pattern triggers the formula-based authentication system. Our proposed model aims to provide an effective solution to mitigate credit card fraud while providing a seamless user experience. We assess the effectiveness of the suggested solution using a number of criteria, such as accuracy, false-positive rate, false-negative rate, and processing time, and our evaluations demonstrate potential reductions in credit card fraud. Our proposed solution provides a strong defense against credit card fraud. The HMM model utilizes sophisticated machine learning algorithms to detect abnormalities in user behavior patterns, making it an effective tool for detecting fraudulent activity. Furthermore, our formula- based authentication system requires users to answer simple mathematical questions;this helps ensure that only legitimate users are able to access the system. In addition, the processing time of our proposed solution is relatively low, thereby providing a seamless user experience without compromising security. Finally, our solution can accurately detect credit card fraud while producing minimal false positives and false negatives. Our results demonstrate that our solution can be an effective and efficient tool for mitigating credit card fraud. © The Author(s).

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

NeurDB: an AI-powered autonomous data system

引用

science China(Information sciences) 2024年第10期67卷 129-150页

作者： Beng Chin OOI Shaofeng CAI Gang CHEN Yanyan SHEN Kian-Lee TAN Yuncheng WU Xiaokui XIAO Naili XING Cong YUE Lingze ZENG Meihui ZHANG Zhanhao ZHAO School of Computing National University of Singapore College of Computer Science and Technology Zhejiang University Department of Computer Science and Engineering Shanghai Jiao Tong University School of Information Renmin University of China School of Computer Science and Technology Beijing Institute of Technology

In the wake of rapid advancements in artificial intelligence(AI), we stand on the brink of a transformative leap in data systems. The imminent fusion of AI and DB(AI×DB) promises a new generation of data systems, which will relieve the burden on end-users across all industry sectors by featuring AI-enhanced functionalities, such as personalized and automated in-database AI-powered analytics, and selfdriving capabilities for improved system performance. In this paper, we explore the evolution of data systems with a focus on deepening the fusion of AI and DB. We present NeurDB, an AI-powered autonomous data system designed to fully embrace AI design in each major system component and provide in-database AI-powered analytics. We outline the conceptual and architectural overview of NeurDB, discuss its design choices and key components, and report its current development and future plan.

关键词： AI$\times$DB in-database AI intelligent data system

来源：评论

学校读者我要写书评

暂无评论

Performance Investigation of HFR Full-bridge Inverter in Resonant Inductive Coupled Power Transfer System for an Electric Vehicle

EAI Endorsed Transactions on Energy Web

引用

EAI Endorsed Transactions on Energy Web 2024年 11卷 1-9页

作者： Geetha, P. Usha, S. Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Kattankulathur Chennai603203 India

Inductive WPT of the resonant category is generally employed for medium and high-power transmission applications like electric vehicle charging due to it contributes excellent efficiency. The high-frequency resonant full-bridge inverter using series-series resonant topology is proposed. The design of the high-frequency resonant inverter is simulated and verified by MATLAB/SIMULINK software. The charging scheme which is available in the AC-DC as well as in the DC-DC converter should operate with the two steps to achieve a duty cycle-based voltage control and hysteresis current control. The resonant frequency of the proposed system has a frequency range of 65 kHz with a DC voltage of 12V. The simulation has been carried out successfully and transmitted a 5KW power load of constant current and voltage control. The Performance chart of with the existing method is carried out in terms of parameters and the efficiency can be achieved by 95%. © (2024), (European Alliance for Innovation). All Rights Reserved.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Efficient spectrum allocation for secondary users in cognitive radio network using round robin priority algorithm along with reservation channels

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第12期14卷 16715-16728页

作者： Suganthi, N. Meenakshi, S. Department of Computer Science and Engineering SRM Institute of Science and Technology Faculty of Engineering and Technology Ramapuram Tamil Nadu Chennai600119 India Tamil Nadu Chennai India

Cognitive Radio Network provides opportunistic spectrum access to unlicensed users in the absence of licensed users using dynamic spectrum access technology. The key challenge here is to impartially share the existing spectrum to all the secondary users in the network. A Round Robin Priority (RRP) algorithm along with reservation spectrum is proposed in this paper to impartially schedule available spectrum band and to provide continuous uninterrupted service to all secondary users. The QoS of secondary users are evaluated and compared with traditional spectrum allocation methods. The QoS parameters considered are blocking probability, the forced termination probability, spectrum utilization, average waiting time and the average delay of secondary users. The proposed Round Robin Priority Algorithm with Reservation scheme results reveals 22.82% reduction in Blocking Probability, 15.28% reduction in Forced Termination Probability, 12.54% reduction in average waiting time and 24.58% increase in Spectrum utilization when compared with traditional Constant Channel Aggregation Scheme. On comparing RRP with reservation with Variable Channel Aggregation schemes shows 19.32% reduction in Blocking Probability, 12.74% reduction in Forced Termination Probability and 10.57% increase in Spectrum Utilization. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Blocking probability

来源：评论

学校读者我要写书评

暂无评论

Lightweight and privacy-preserving device-to-device authentication to enable secure transitive communication in IoT-based smart healthcare systems

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第9期15卷 3331-3345页

作者： Das, Sangjukta Singh, Maheshwari Prasad Namasudra, Suyel Department of Computer Science and Engineering National Institute of Technology Patna Bihar India Department of Computer Science and Engineering National Institute of Technology Agartala Tripura India

Internet of Things (IoT) devices are often directly authenticated by the gateways within the network. In complex and large systems, IoT devices may be connected to the gateway through another device in the network. In such a scenario, new device should be authenticated with the gateway through the intermediate device. To address this issue, an authentication process is proposed in this paper for IoT-enabled healthcare systems. This approach performs a privacy-preserving mutual authentication between the gateway and an IoT device through intermediate devices, which are already authenticated by the gateway. The proposed approach relies on the session key established during gateway-intermediate device authentication. To emphasizes lightweight and efficient system, the proposed approach employs lightweight cryptographic operations, such as XOR, concatenation, and hash functions within IoT networks. This approach goes beyond the traditional device-to-device authentication, allowing authentication to propagate across multiple devices or nodes in the network. The proposed work establishes a secure session between an authorized device and a gateway, preventing unauthorized devices from accessing healthcare systems. The security of the protocol is validated through a thorough analysis using the AVISPA tool, and its performance is evaluated against existing schemes, demonstrating significantly lower communication and computation costs. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Internet of things

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：