检索结果-内蒙古大学图书馆

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Werner, Daniel Turna, Fatma Le, Hoang Thanh Middendorf, Martin Leipzig University Department of Computer Science Germany Leipzig University Swarm Intelligence and Complex Systems Group Department of Computer Science Germany

ISBN: (纸本)9781665430654

This paper has two objectives. Firstly, to introduce a new framework XF -OPTIMETA for testing and comparing Hyperparameter Optimization (HPO) methods. The framework supports model-free methods, e.g., Random Search (RS), as well as model-based methods, such as Bayesian Optimization (BO), with various surrogate models. Due to the generalized and modular structure of the XF-OPTIMETA framework, it can be easily extended to other optimization methods for dif-ferent optimization problems. The second objective is to empir-ically compare the performance of various HPO methods for population-based metaheuristics. For that the XF -OPTIMETA framework is used to apply HPO methods to the Hierarchical Simple Probabilistic Population-Based Optimization (H-SPPBO) metaheuristic for the Dynamic Traveling Salesperson Problem (DTSP) and to calculate high-performing parameter values for H-SPPBO. Promising results are obtained using the parameter values found by BO. In particular, a parameter set obtained with Gradient-Boosted Regression Trees (GBRT) outperforms a reference parameter set for H-SPPBO from an existing study. © 2023 IEEE.

关键词： Bayesian Optimization Dynamic Traveling Salesperson Problem Hierarchical Simple Probabilistic Population-Based Optimization (H-SPPBO) Hyperparameter Optimization Metaheuristics Parameter Tuning

来源：评论

学校读者我要写书评

暂无评论

Digital twinning of vertical centrifugal casting

引用

Concurrent Engineering Research and Applications 2024年第1-4期32卷 78-89页

作者： Anadkat, Dhaval Dave, Anjali Sata, Amit Shukla, Minal Jarboui, Slaheddine Department of Mechanical Engineering Marwadi University Rajkot India Department of Mechanical Engineering Lukhdhirji Engineering College Morbi India MGL Group Rajkot India Deparment of Computer Engineering College of Computer Science King Khalid University KSA Abha Saudi Arabia

This paper explores the transformative potential of digital twin technology in vertical centrifugal casting (VCC), a cornerstone manufacturing process for high-integrity cylindrical components. By integrating real-time data, physical models, and machine learning algorithms, digital twins unlock a new paradigm of process optimization, predictive maintenance, and quality control. Integration of digital twinning enhances the performance in different domains of work like enhancing the quality of research, production etc. Howbeit, digital twinning is nascent in the domain of manufacturing specially in the casting sub domain. A physical set up of VCC is integrated with Internet of Things (IoT) and data acquisition system to stream the collected data to the cloud-based server. Transformation of Internet of Things (IoT) enabled VCC integrated with different sensors into the digital twin helps in quality prognosis for future applications. The data is further fetched from the cloud and interconnection is established between the digital twin. Real time monitoring, controlling and operating can be done easily with the help of a digital twin to predict the quality and tentative defect locations. Further amplifying these benefits, emerging technologies like Virtual Reality (VR), Augmented Reality (AR), and the Metaverse hold immense promise for revolutionising VCC training, collaboration, and visualisation. © The Author(s) 2024.

关键词： Centrifugal casting

来源：评论

学校读者我要写书评

暂无评论

P2LNet: HD Map Validation Using Graph Neural Networks 1

P2LNet: HD Map Validation Using Graph Neural Networks

引用

1st International Conference on Robotics, Engineering, science, and Technology, RESTCON 2024

作者： Reji, Jeevan Omanwar, Vaibhav Birla Institute of Technology & Sciences Pilani Department of Computer Science Hyderabad Campus India Nvidia Graphics Pvt Ltd Pune India

ISBN: (纸本)9798350348842

HD Maps are a highly important part of the autonomous driving stack to perform the activities of localization and route planning on the road. Therefore, HD Map Validation is crucial to ensure the HD Maps represent the road information as accurately as possible. While heuristics have been developed to validate HD Maps with reasonable accuracy, they are unable to solve the challenging path to traffic light validation problem of HD Map junctions. Based on the success of Graph Neural Network approaches on HD Map problems, such as Vector net, we propose the P2LNet. This P2LNet architecture consists of a fully connected subgraph followed by a Graph Encoder-Decoder Architecture that finally predicts the correct associations that would exist between paths and traffic lights in the junction. We trained and evaluated P2LNet on our in-house HD Map junction dataset, with P2LNet showing 94% accuracy on predicting the correct labels for the associations from a test set. While the results could be further improved by using edge features, P2LNet provides a significant accuracy in validating incorrect light associations. It also shows how GNN based approaches can be used to solve other significant HD Map and validation issues. © 2024 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Novel Drone-Station Matching model in Smart Cities based on Strict Preferences

引用

无人系统（英文） 2023年第3期11卷 261-271页

作者： Debolina Nath Anjan Bandyopadhyay Ankit Rana Tarek Gaber Aboul Ella Hassanien Department of Computer Science and Engineering Amity University Kolkata KolkataWest BengalIndia Department of Computer Science and Engineering Gitam University BangaloreKarnatakaIndia School of Science Engineeringand Environment University of SalfordUK Faculty of Computers and Informatics Suez Canal UniversityIsmailiaEgypt Scientific Research Group in Egypt(SRGE) Egypt Faculty of Computer and Artificial Intelligence Cairo UniversityCairoEgypt Scientific Research Group in Egypt(SRGE) Egypt

There has been a considerable increase in the use of drones,or unmanned aerial vehicles(UAVs),in recent times,for a wide variety of purposes such as security,surveillance,delivery,search and rescue operations,penetration of inaccessible or unsafe areas,*** increasing number of drones working in an area poses a challenge to finding a suitable charging or resting station for each drone after completing its task or when it goes low on its *** classical methodology followed by drones is to return to their pre-assigned charging station every time it requires a *** approach is found to be inefficient as it leads to an unnecessary waste of time as well as power,which could be easily saved if the drone is allotted a nearby charging station that is ***,we propose a drone-allocation model based on a preference matching algorithm where the drones will be allotted the nearest available station to land if the station is *** problem is modeled as three entities:Drones,system controllers and charging *** matching algorithm was then used to design a Drone-Station Matching *** simulation results of our proposed model showed that there would be considerably less power consumption and more time saving over the conventional *** would save its travel time and power and ensure more efficient use of the drone.

关键词： Unmanned Aerial Vehicle(UAV) stable matching resource allocation smart city matching algorithm

来源：评论

学校读者我要写书评

暂无评论

Detection and Prevention of DoS Attack in VANET Using Artificial Neural Network 1

Detection and Prevention of DoS Attack in VANET Using Artifi...

引用

1st IEEE Karachi Section Humanitarian Technology Conference, Khi-HTC 2024

作者： Adil, Md Midha, Sugandhi Srivastav, V.K. Kavita Chandigarh University Department of Computer Science Engineering India Uttaranchal University Dehradun India Chandigarh Group of Colleges Jhanjeri Department of Computer Science and Engineering Punjab Mohali140307 India

ISBN: (纸本)9798350373042

In the realm of Vehicular Ad Hoc Networks (VANETs), seamless communication between vehicles is crucial for the exchange of essential messages, such as road traffic updates and accident-related information. The dynamic nature of vehicular movement demands timely information dissemination to ensure effective traffic management and safety. However, the continuous availability of the network is imperative for the smooth functioning of VANETs. The vulnerability of VANETs to Denial-of-Service (DoS) attacks poses a significant threat, potentially rendering the network unavailable. Such attacks can disrupt communication among vehicles, leading to adverse consequences. This paper presents an enhanced approach for detecting DoS attacks, aiming to identify and mitigate them promptly. Leveraging neural networks, our proposed technique surpasses the efficacy of previous methods, ensuring improved results in the timely detection of DoS attacks within VANETs. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Heart Stroke Risk Prediction Using Machine Learning and Deep Learning Algorithm 6th

Heart Stroke Risk Prediction Using Machine Learning and Deep...

引用

6th International Conference on Communications and Cyber-Physical Engineering, ICCCE 2023

作者： Prajwala Priyanka, M. Kumar, Sheo Lakshmi Bhargav, A. Department of Computer Science Engineering CMR Engineering College Hyderabad India Department of Computer Science Engineering Nalla Narasimha Reddy Education Society’s Group of Institutions Hyderabad India

ISBN: (纸本)9789819971367

Heart attack is a catch-all term for a variety of conditions affecting the heart. Analysis of large amounts of data and comparisons between them are essential for the prediction, prevention, and management of cardiovascular illnesses including heart attacks. This paper aims to develop an Intelligent System using various ML techniques such as Naive Bayes, KNN, Random Forest and Decision Tree. Users of this web-based software will answer a prepared series of questions. Data analytics is crucial for organizing, analyzing, and controlling large data sets. It has shown beneficial in the diagnosis, prevention, and treatment of cardiovascular disease. With this in mind, we want to apply SVM- and GA-based data analytics to the challenge of identifying cardiac problems. A comparison of these algorithms’ prediction models indicates which one is the most developed. It may aid physicians in making more educated diagnoses of heart illness than would have been possible with older, more traditional methods of decision assistance. By providing efficient treatments, it contributes to cost-effective healthcare. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Towards new realities: Implications of personalized online layers in our daily lives

引用

i-com 2024年第2期23卷 221-229页

作者： Herder, Eelco Stojko, Laura Strecker, Jannis Neumayr, Thomas Yigitbas, Enes Augstein, Mirjam Department of Information and Computing Sciences Utrecht University Utrecht Netherlands Department of Computer Science University of the Bundeswehr Munich Neubiberg Germany Institute of Computer Science University of St. Gallen St. Gallen Switzerland Research Group Personalized Environments and Collaborative Systems University of Applied Sciences Upper Austria Hagenberg Austria Faculty of Electrical Engineering Computer Science and Mathematics Paderborn University Paderborn Germany

We are currently in a period of upheaval, as many new technologies are emerging that open up new possibilities to shape our everyday lives. Particularly, within the field of Personalized Human-computer Interaction we observe high potential, but also challenges. In this article, we explore how an increasing amount of online services and tools not only further facilitates our lives, but also shapes our lives and how we perceive our environments. For this purpose, we adopt the metaphor of personalized 'online layers' and show how these layers are and will be interwoven with the lives that we live in the 'human layer' of the real world. © 2024 the author(s), published by De Gruyter, Berlin/Boston.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

SCOPE: A Synthetic Multi-Modal Dataset for Collective Perception Including Physical-Correct Weather Conditions 27

SCOPE: A Synthetic Multi-Modal Dataset for Collective Percep...

引用

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

作者： Gamerdinger, Jorg Teufel, Sven Schulz, Patrick Amann, Stephan Kirchner, Jan-Patrick Bringmann, Oliver University of Tübingen Embedded Systems Group Faculty of Science Department of Computer Science Germany Karlsruhe Germany

ISBN: (纸本)9798331505929

Collective perception has received considerable attention as a promising approach to overcome occlusions and limited sensing ranges of vehicle-local perception in autonomous driving. In order to develop and test novel collective perception technologies, appropriate datasets are required. These datasets must include not only different environmental conditions, as they strongly influence the perception capabilities, but also a wide range of scenarios with different road users as well as realistic sensor models. Therefore, we propose the Synthetic COllective PErception (SCOPE) dataset. SCOPE is the first synthetic multi-modal dataset that incorporates realistic camera and LiDAR models as well as parameterized and physically accurate weather simulations for both sensor types. The dataset contains 17,600 frames from over 40 diverse scenarios with up to 24 collaborative agents, infrastructure sensors, and passive traffic, including cyclists and pedestrians. In addition, recordings from two novel digital-twin maps from Karlsruhe and Tübingen are included. The dataset is available at https://***/scope © 2024 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Effects of Alpha Variation in Exponential Linear Unit Activation Function for Deep Neural Networks 15

Analyzing the Effects of Alpha Variation in Exponential Line...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Singh, Mahesh Kumar Mishra, Shreyansh Tiwari, Utkarsh Patel, Vikas Kumar Maurya, Sahil Department of Computer Science and Engineering Dronacharya Group of Institutions Uttar Pradesh GreaterNoida201306 India

ISBN: (纸本)9798350370249

This research paper immerses into the subtle effects of varying values within the Exponential Linear Unit (ELU) activation function, altering from 1 to 0.10. Activation functions take an important role in deep learning models, impacting their training dynamics, convergence behavior, and stereotypical capabilities. Focusing specifically on ELU, which describes advantages over conventional activation functions like ReLU, this study aims to interpret the inference of adjusting its alpha parameter. Through a meticulous relative investigation, this paper presents a comprehensive analysis of ELUactivation function with varying alpha values. Firstly, we demonstrate the relative performance of ELU activation with varying alpha values against other conventional activation functions. Secondly, we analyze the relationship between alpha values and training loss, manifesting how habituation in alpha influences the convergence behaviorof neural networks. Thirdly, we analyze the concussion onvalidation loss to determine the effect of alpha values on the model’s ability to establish unseen data. Moreover, we analyze the correlation between alpha values and all-inclusive model performance, considering measures such as accuracy, precision, and recall b y comprehensively. ©2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Classifiers for Detecting Credit Card Fraudulent Transactions 4

Anomaly Detection Classifiers for Detecting Credit Card Frau...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Singh, Prerna Singla, Khyati Piyush, Prince Chugh, Bharti Delhi-NCR Kiet Group of Institutions Department of Computer Science and Engineering Ghaziabad201206 India

ISBN: (纸本)9798350343670

The internet and e-commerce have grown quickly, which has increased credit card use but also, regrettably, increased credit card fraud. To address this, Anomaly Detection has emerged as a crucial method for identifying unusual events and data in datasets. It uses advanced algorithms to detect deviations from normal patterns, helping authorities proactively combat fraudulent activities. While digital advancements offer convenience, they also expose vulnerabilities. Anomaly Detection offers a modern defense, safeguarding financial systems by early spotting of anomalies. In this study, we employed two algorithms - the Isolation Forest (IF) and the Local Outlier Factor (LOF) for identification of anomalies. To improve the performance of these models, we also employed a variety of resampling strategies. Specifically, we used techniques like Random Undersampling, AllKNN, Synthetic Minority Oversampling Technique (SMOTE), and Synthetic Minority Oversampling Technique - Edited Nearest Neighbor (SMOTE-ENN) to balance the European Credit Card Fraudulent transactions dataset and the German Credit Card fraud dataset. Out of the different configurations, the Isolation Forest classifier demonstrated the highest accuracy, reaching 99.81%, when applied to the initially imbalanced European credit card fraudulence dataset. On the other hand, the German credit card dataset achieved a remarkable accuracy of 70.60% through the implementation of the LOF classifier, coupled with the Random Undersampling technique to address its imbalanced nature. © 2024 IEEE.

关键词： AllKNN Anomaly Detection Credit Card Fraud IF LOF Random Undersampling SMOTE SMOTE-ENN

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：