检索结果-内蒙古大学图书馆

2nd international conference on Artificial Intelligence: Towards Sustainable Intelligence, AI4S 2024

作者： Aylani, Amit Rao, Madhuri Thampi, G.T. Thadomal Shahani Engineering College Mumbai Bandra India

ISBN: (纸本)9783031813689

The need for inter-governmental protocols on climate change, world trade agreements, and increased awareness of human rights and sustainability issues has made it imperative for corporations globally to adopt environmental, social, and governance (ESG) practices at a faster rate. This paper highlights the key areas where digital and artificial intelligence can be successfully combined to address these demands. As the importance of ESG and sustainability issues grows, organization are actively seeking out advanced technological solutions to tackle intricate problems. The research methodology used in this paper incorporates a framework, highlighting how technology can address complex issues in data collection and contribute to sustainable practices. The results suggest that AI technology has the potential to greatly improve ESG practices in different areas. It can help organizations enhance their corporate governance by automating compliance monitoring, assessing risks, and providing decision support systems. This paper investigates artificial intelligence technology in creating and implementing an architectural solution for environmental, social, and governance practices, providing a strong foundation for further exploration and application. By using artificial intelligence and IoT, organizations can better align themselves with sustainable development goals and ESG reporting. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

YOLOv8: A Novel Vehicle Mirror Detection Algorithm with Enhanced Performance using Deep Learning

YOLOv8: A Novel Vehicle Mirror Detection Algorithm with Enha...

引用

Electronics and Renewable systems (ICEARS), international conference on

作者： Sundarakrishnan Narayanan Yashas Donthi Mohana Ramakanth Kumar P Sreelakshmi K Computer Science and Engineering Center for Computer Vision Research RV College of Engineering® Bengaluru India Electronics & Telecommunication Engineering Center for Computer Vision Research RV College of Engineering® Bengaluru India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

In recent times, Artificial intelligence (AI) and machine learning (ML) technologies have demonstrated remarkable capabilities in addressing real time needs and challenges across multiple domains and fields. In the world of deep learning, various Neural Network architectures like DNN, CNN, and RNN have been instrumental in advancing solutions to complex problems spanning multiple industries, business environments and law enforcement use cases. This paper implemented a special type of CNN, YOLOv8(You Only Look Once), a SOTA architecture to detect the presence of rear-view mirrors in two-wheelers for traffic surveillance and law enforcement applications. The proposed research introduces a novel idea in the realm of road safety by presenting the first ever paper on vehicle mirror detection. This approach sheds light on an often-overlooked aspect, contributing significantly to the enhancement of road safety measures. A custom dataset of 1246 training images, 155 test images and 157 validation images has been considered. This dataset has been used to train and test a binary classification model with the label "mirror". Images with the label "mirror" indicate the presence of one or both rear-view mirrors on two-wheelers. On the other hand, images with no mirrors are treated as "background" images. The model achieved a maximum precision of 93.8%, recall of 87.9%, mAP50 of 94.1% and F1-score of 90.9%. These results stand as evidence of the robustness and proficiency of the model, ensuring that it can be potentially used in real world use cases, specifically for law enforcement applications.

关键词： Deep learning YOLO Training Law enforcement Traffic control Video surveillance Road safety Robustness Mirrors Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CCTV Surveillance-Based Vehicle Identification: Query-Driven Search Using Colour, Manufacturer & License Plate

CCTV Surveillance-Based Vehicle Identification: Query-Driven...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), international conference

作者： Ramakanth Kumar P Pranav V Jambur Diptanshu Kumar Computer Science & Engineering R. V. College of Engineering Bengaluru India Artificial Intelligence & Machine Learning Engineering R. V. College of Engineering Bengaluru India

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

The paper addresses the challenges of vehicle detection and identification in road safety and surveillance, especially in hit-and-run incidents and vehicle theft cases. The solution combines computer vision with YOLO models for real-time vehicle detection, colour classification, and a custom CNN for accurate vehicle type classification. YOLO is also used for license plate recognition, paired with Tesseract OCR to extract alphanumeric details for precise identification. The colour identification process is two-fold: YOLO detects vehicles in video frames and isolates their bounding boxes, which are then processed through a YOLO-based classifier trained on the VCoR dataset with 15 vehicle colour labels. Trained over 25 epochs, the model achieved 85.6% top-1 accuracy and 99.5%top-5 accuracy, proving reliable across diverse lighting, weather, and traffic conditions. This system automates vehicle detection and identification, reducing the time and manual effort needed to review large video datasets. Integrating vehicle type classification, colour recognition, and license plate identification, it provides a scalable and efficient tool for law enforcement and surveil- lance, enabling rapid suspect vehicle identification in complex traffic environments. The solution enhances traffic monitoring and security, delivering high accuracy in real-world scenarios. Scalable across urban areas, highways, toll booths, and smart city infrastructure, it offers a versatile approach to modern traffic surveillance.

关键词： YOLO Accuracy Smart cities Law enforcement Surveillance Computational modeling Color Traffic control Real-time systems License plate recognition

来源：评论

学校读者我要写书评

暂无评论

Application and Research of Intelligent Algorithms in Scheduling Optimization of Civil Engineering Projects

引用

international Journal of High Speed Electronics and systems 2025年

作者： Jin, Yang Tingting, Gao Shengnan, Song College of Intelligent Science and Engineering Xi'an Peihua University Shaanxi Xi'an710125 China College of Electronic and Control Engineering Chang'an University Shaanxi Xi'an710061 China

Efficient scheduling optimization is a critical component of resource management in civil engineering projects, which often involve dynamic and complex environments. Traditional scheduling approaches face challenges in addressing large-scale constraints, real-time adaptability, and the combinatorial nature of tasks, leading to resource underutilization and delays. To address these issues, this study proposes a novel Adaptive Scheduling Framework (ASF) integrated with a Dynamic Task Allocation Strategy (DTAS) tailored specifically for civil engineering applications. The ASF employs graph-based task-resource modeling and multi-objective optimization to manage the scalability and flexibility required in construction projects. By representing scheduling problems as bipartite graphs, the framework captures temporal dynamics, task dependencies, and resource constraints to achieve a balance between priority and feasibility. The DTAS enhances scheduling efficiency by introducing dynamic task prioritization, iterative conflict resolution, and real-time feedback-driven refinement. Experimental results, focused on civil engineering scenarios, demonstrate that the proposed methods significantly reduce project completion time, improve resource utilization, and adapt effectively to changes in construction requirements and resource availability. This study underscores the transformative potential of intelligent algorithms in optimizing scheduling for civil engineering project management and other resource-intensive domains. © The Author(s).

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Multiple Time Parameter Superposition Based on Separation of Measure Theory Study on Similar Design problems

引用

international Journal of High Speed Electronics and systems 2025年

作者： He, Shengya Li, Hengyi Ye, Liang Huang, He Peng, Wei Wang, Zhijia Zhang, Jianjing Zhang, Youliang Xie, Peng Guangzhou Metro Design & Research Institute Co. Ltd. Guangzhou510010 China College of Civil Engineering and Architecture Hainan University Haikou570228 China

The self-contradiction of time similarity ratios in geomechanical model tests under superimposed multiple time parameters hinders experimental accuracy. This study investigates the root causes of such variability: (1) divergent derivation outcomes from distinct control parameters, (2) empirical formulas exhibiting dimensional nonhomogeneity, and (3) the superiority of a unit time similarity ratio in liquefaction and creep modeling. A novel similarity ratio calculation scheme is proposed by integrating the separation of magnitudes theory and aberration-compensated design theory. The centrifugal shaking table model test for earthquake–rainfall coupling is employed to demonstrate the method. By decomposing the system into subsystems (soil, seismic, and rainfall) and applying distortion compensation, conflicting time scales (e.g., seismic duration versus rainfall duration) are unified. Results show that the corrected similarity ratio resolves parameter contradictions while maintaining prototype consistency. This work establishes a theoretical framework for selecting time similarity ratios in multi-parameter geomechanical tests, addressing a critical gap in existing methodologies. Innovations include the systematic application of magnitude separation and distortion compensation to overlapping time scales, validated through a complex coupling scenario. © 2025 The Author(s)

关键词： Time measurement

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Optimizing Route Planning in Urban Traffic

Deep Reinforcement Learning for Optimizing Route Planning in...

引用

Computational, Communication and Information Technology (ICCCIT), international conference on

作者： Mudit Mittal Archana Sehgal Neeraj Varshney Sunil Prashanth Kumar Nandini Shirish Boob R. Akhilesh Reddy Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Lovely Professional University Phagwara Department of Computer Engineering and Applications GLA University Mathura Department of Mechanical Engineering New Horizon College of Engineering Bangalore Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu Department of CSE-AI&ML MLR Institute of Technology Hyderabad Telangana

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

Urban traffic networks are efficient route design problems due to the intricacy and dynamic character of contemporary cities. Conventional methods hamper real time adjustment to continually changing traffic conditions, thereby providing suboptimal routes, a greater burden on the roadways, and greater air pollution. This thesis presents a novel deep reinforcement learning (DRL) method to optimize the route planning for urban traffic networks. With this rendering of real time traffic data, we use DRL to make autonomous decisions to reduce travel time and congestion of routes. One advantage of using sophisticated neural networks for feature extraction and policy learning is that, since the model is so adaptable to changing traffic patterns, the model guarantees that. And, in comparison to common routing algorithms, the results of simulations using real world traffic data show that this method is able to greatly enhance route efficiency and overall traffic flow management. The suggested DRL based system is feasible as a smart city program based on intelligent transportation system which can scale to grand metropolitan regions. The research presents that DRL can enhance the commuter run experience, reduce the environmental effect, and alter urban transportation. Future study will also investigate how this system can be better optimized when integrated with traffic infrastructure enabled by the Internet of Things.

关键词： Adaptation models Smart cities Computational modeling Scalability Transportation Traffic control Deep reinforcement learning Real-time systems Planning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Optimization Techniques for Automatic Voltage Regulator controllers 1st

A Comprehensive Review of Optimization Techniques for Automa...

引用

1st international conference on Intelligent systems in Computing and Communications, ISCComm 2023

作者： Ali, Rumana Bhat, Vinayambika S. Electronics and Communication Engineering Mangalore Institute of Technology and Engineering Moodbidri India Electrical and Electronics Engineering Adichunchanagiri Institute of Technology Chikmagalur India

ISBN: (纸本)9783031756078

The article presents a latest literature review on issues related to the automatic voltage regulators (AVR), conventional methods for voltage regulation, application, and advancement in Voltage regulation techniques. The article also includes review of optimization of the AVR with different controllers used by researchers for efficient performance of the power system. Modern-day power system networks are intricate plus prone to a number of risks. The networks are vulnerable to instability because operating a power system is complex and unreliable. One of these problems is rotor-angle instability, which, if correctly resolved, could cause system failure. AVR is vital for the operation of power systems. Automatic voltage regulators are utilised in power systems to keep an alternator's terminal voltage at a set point. AVR controls the evenness of the terminal voltage by adjusting the generator's exciter voltage. A power system stabilizer (PSS) is essentially a power oscillation damping (POD) regulator that is used to increase rotor angle stability. AVR PSSs must be properly designed, which is a difficult yet necessary process. Several approaches are put out in the literature for the effective blueprint of PSSs or POD controllers. This provision includes an up-to-date overview of the AVR and PSS as well as optimisation methods. Based on this review, it can be imparted that there is plenty of room for developing AVR and PSS furthermore in a effective and reliable way, pondering quite a lot of uncertainties that could appear while operating current power systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Time Sensitive Multiple POIs Route Planning on Bus Networks

Time Sensitive Multiple POIs Route Planning on Bus Networks

引用

international conference on Big Data and Smart Computing (BIGCOMP)

作者： Simu Liu Kailin Jiao Junping Du Yawen Li Zhe Xue Xiaoyang Sean Wang Ziqiang Yu Yunchuan Shi Yantai University Shandong University Beijing University of Posts and Telecommunications Fudan University

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

This work addresses a route planning problem constrained by a bus road network that includes the schedules of all buses. Given a query with a starting bus stop and a set of Points of Interest (POIs) to visit, our goal is to find an optimal route on the bus network that allows the user to visit all specified POIs from the starting stop with minimal travel time, which includes both bus travel time and waiting time at bus stops. Although this problem resembles a variant of the Traveling Salesman Problem, it cannot be effectively solved using existing solutions due to the complex nature of bus networks, particularly the constantly changing bus travel times and user waiting times. In this paper, we first propose a modified graph structure to represent the bus network, accommodating the varying bus travel times and their arrival schedules at each stop. Initially, we suggest a brute-force exploration algorithm based on the Dijkstra principle to evaluate all potential routes and determine the best one; however, this approach is too costly for large bus networks. To address this, we introduce the EA-Star algorithm, which focuses on computing the shortest route for promising POI visit sequences. The algorithm includes a terminal condition that halts evaluation once the optimal route is identified, avoiding the need to evaluate all possible POI sequences. During the computation of the shortest route for each POI visiting sequence, it employs the $A^{*}$ algorithm on the modified graph structure, narrowing the search space toward the destination and improving search efficiency. Experiments using New York bus network datasets demonstrate the effectiveness of our approach.

关键词： Schedules Machine learning algorithms Heuristic algorithms Roads Traveling salesman problems Traffic control Prediction algorithms Robustness Real-time systems Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

problems and Constructive Methods of Applied control Theory for the Technical systems with Distributed Parameters 21

Problems and Constructive Methods of Applied Control Theory ...

引用

21st international conference on complex systems - control and modeling problems (CSCMP)

作者： Rapoport, Edgar Pleshivtseva, Yuliya Samara State Tech Univ ICCS RAS Samara Russia

The approaches and methods for further development of applied theory of systems with distributed parameters are suggested to solve problems of open-loop controllability, construction of program optimization, a wide ra... 详细信息

ISBN: (纸本)9781728167008

关键词： system with distributed parameters controllability optimal control vector optimization alternance method feedback control

来源：评论

学校读者我要写书评

暂无评论

Application of Singular Integral Equations to the Study of Automatic control problems 21

Application of Singular Integral Equations to the Study of A...

引用

21st international conference on complex systems - control and modeling problems (CSCMP)

作者： Boykov, Ilia Aikashev, Pavel Penza State Univ Penza Russia

ISBN: (纸本)9781728167008

The article is devoted to the modeling of some problems arising in the analysis and synthesis of automatic control systems by methods of singular integral equations. The problems of determining the impulse response functions of dynamic systems in the presence of noise, problems of optimal extrapolation and filtering of the signal, which lead to the Wiener - Hopf equations of the first kind, are considered. The study of multidimensional automatic control systems leads to the Riemann boundary value problem in n-dimensional domains. Approximate methods for solving singular and bisingular integral equations arising in the study of automatic control problems are proposed and substantiated. Numerical example is given.

关键词： automatic control Wiener-Hopf equations of the first kind Riemann boundary problem singular integral equations polysingular integral equations

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：