检索结果-内蒙古大学图书馆

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2024年第4期86卷 183-198页

作者： Vasilică, Bogdan-Valentin Anton, Florin-Daniel Ioniță, Anca Daniela Faculty of Automatic Control and Computer Science National University of Science and Technology POLITEHNICA Bucharest Romania

In this paper, the free services offered by IBM Watson are evaluated for the purpose of implementing an Intrusion Detection System in the context of offline network traffic analysis. It examines IBM Watson's role in IDS, detailing system architecture, network traffic capture, data processing, and algorithm selection with IBM Watson Studio, using the CIC-IDS2017 dataset. The study assesses AI algorithms like LGBM, XGB, Random Forest, and Extra Trees Classifier for detecting intrusions, concluding with an analysis of these algorithms' performance through precision, recall, and F measure metrics, evaluating the effectiveness of IBM Watson in a cloud-based IDS implementation. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Evaluating the usage of Text to3D scene generation methods in Game-Based Learning 24

Evaluating the usage of Text to3D scene generation methods i...

引用

24th International Conference on control Systems and computer science, CSCS 2023

作者： Gradinaru, Alexandru Vrejoiu, Mihnea Moldoveanu, Florica Balutoiu, Maria-Anca University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania National Institute for Research and Development in Informatics Bucharest Romania

ISBN: (纸本)9798350313390

computer games as an educational tool significantly improved information retention, student involvement, and motivation. Despite the growing popularity and the demonstrated positive impact, little progress is made to let educators create games without learning game programming or investing massive amounts of time, money, and human resources. This paper considers the usage of procedural content generation in simplifying the generation of game environments. Given that most educational material is in text format, we evaluate the possibility of generating 3D scenes starting from natural language text. A comprehensive survey of the current methods is presented, analyzing whether they can be successfully used in game-based learning. The study discusses several current limitations and possible improvements, highlighting a need for better progress in the domain. © 2023 IEEE.

关键词： computer games

来源：评论

学校读者我要写书评

暂无评论

The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models

arXiv

引用

arXiv 2024年

作者： Catruna, Andy Cosma, Adrian Radoi, Emilian Faculty of Automatic Control and Computer Science POLITEHNICA Bucharest Romania

Gait, an unobtrusive biometric, is valued for its capability to identify individuals at a distance, across external outfits and environmental conditions. This study challenges the prevailing assumption that vision-based gait recognition, in particular skeleton-based gait recognition, relies primarily on motion patterns, revealing a significant role of the implicit anthropometric information encoded in the walking sequence. We show through a comparative analysis that removing height information leads to notable performance degradation across three models and two benchmarks (CASIA-B and GREW). Furthermore, we propose a spatial transformer model processing individual poses, disregarding any temporal information, which achieves unreasonably good accuracy, emphasizing the bias towards appearance information and indicating spurious correlations in existing benchmarks. These findings underscore the need for a nuanced understanding of the interplay between motion and appearance in vision-based gait recognition, prompting a reevaluation of the methodological assumptions in this field. Our experiments indicate that"in-the-wild" datasets are less prone to spurious correlations, prompting the need for more diverse and large scale datasets for advancing the field. © 2024, CC BY-NC-ND.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild

arXiv

引用

arXiv 2024年

作者： Catruna, Andy Cosma, Adrian Radoi, Emilian Faculty of Automatic Control and Computer Science POLITEHNICA Bucharest Romania

Gaze estimation, the task of predicting where an individual is looking, is a critical task with direct applications in areas such as human-computer interaction and virtual reality. Estimating the direction of looking in unconstrained environments is difficult, due to the many factors that can obscure the face and eye regions. In this work we propose CrossGaze, a strong baseline for gaze estimation, that leverages recent developments in computer vision architectures and attention-based modules. Unlike previous approaches, our method does not require a specialized architecture, utilizing already established models that we integrate in our architecture and adapt for the task of 3D gaze estimation. This approach allows for seamless updates to the architecture as any module can be replaced with more powerful feature extractors. On the Gaze360 benchmark, our model surpasses several state-of-the-art methods, achieving a mean angular error of 9.94◦. Our proposed model serves as a strong foundation for future research and development in gaze estimation, paving the way for practical and accurate gaze prediction in real-world scenarios. © 2024, CC BY-NC-ND.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Research on path planning algorithm of takeaway robots for terminal delivery

Research on path planning algorithm of takeaway robots for t...

引用

2nd International Conference on Mechatronic Automation and Electrical Engineering (ICMAEE 2024)

作者： Yuhang Wan Faculty of Automatic Control Electronics and Computer Science Silesian Technical University Gliwice 44-100 Poland

ISBN: (数字)9781837242672

Takeaway delivery has become an important part of urban life. However, terminal deliveries are often blocked by security measures that often prevent them from arriving on time. Designing a takeaway delivery robot can solve this problem to a large extent. In this paper, path planning algorithm level of designing a takeaway robot is researched. In this paper, the research is carried out by closely focusing on the current stage of the path planning algorithm related difficulties. Three typical algorithms are selected for simulation testing within the scope of graph search algorithms. These three algorithms are Dijkstra algorithm, A* algorithm and rapidly-exploring random tree (RRT) algorithm. The final comparison is made with the simulation test results. And to find the optimal path planning algorithm for takeaway delivery robots within the range of graph search algorithms. This paper provides a reference for the path planning algorithm level of takeaway delivery robot design. At the same time, it helps to improve the delivery service of takeaway terminal.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Applying NoSQL Data Adapter with the Learning Paths mechanism for better knowledge transfer in the age of distance learning 26

Applying NoSQL Data Adapter with the Learning Paths mechanis...

引用

26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022

作者： Werner, Aleksandra Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Str. Gliwice44-100 Poland

Database technology applies to many engineering problems. Hence it is the subject of study at many university majors. Since teaching practical usage of theory at a distance is difficult or even impossible, we present novel mechanisms that significantly enrich e-learning platform functionalities in individualized learning of databases installed on the teacher-managed server. The crucial component of our proposal, Data Adapter, allows for interactive querying and manipulating of the NoSQL databases through an e-learning platform. The Adapter is complemented by the Learning Paths component, which enables teachers the creation of individualized didactic paths for students with special educational needs. The e-learning platform load tests confirm that new activities do not substantially affect the comfort of students' work. Its impact on learning effectiveness was verified by rating the competence test for the group of 104 course participants. Half of them were the participants of the e-learning NoSQL course and used the developed mechanisms, while the remaining, control, group was taught with the conventional methods. The research shows that the proposal successfully improves teaching modern NoSQL languages. The scores improvement in the e-learning group of students compared to results in the control group is noticeable, and observed differences are statistically significant. © 2022 The Authors. Published by Elsevier B.V.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Output Stabilization control for Nonlinear Systems With Generalized Disturbances 25

Reinforcement Learning-Based Output Stabilization Control fo...

引用

25th IEEE International Conference on Industrial Technology, ICIT 2024

作者： Tang, Zezhi Rossiter, J Anthony Dong, Yi Panoutsos, George University Of Sheffield Department Of Automatic Control And Systems Engineering SheffieldS13JD United Kingdom University Of Southampton Department Of Electronics And Computer Science Southampton United Kingdom

ISBN: (纸本)9798350340266

This paper proposes a new disturbance observer (DO)-based reinforcement learning (RL) control approach for nonlinear systems with unmatched (generalized) disturbances. While a nonlinear disturbance observer (NDO) is utilized to measure the plant uncertainties, disturbances can exist in the plant via distinct channels from those of the control signals;so-called mismatched disturbances are theoretically difficult to attenuate within the channel of the system's states. A generalized disturbance observer-based compensator is implemented to address the uncertainty cancellation problem by removing the influence of uncertainties from the output channels. Con-currently, a composite actor-critic RL scheme is utilized for approximating the optimal control policy as well as the ideal value function pertaining to the compensated system by solving a Hamilton-Jacobi-Bellman (HJB) equation for both online and offline iterations simultaneously. Stability analysis verifies the convergence of the proposed framework. Simulation results are included to illustrate the effectiveness of the proposed scheme. © 2024 IEEE.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Follow me droney! Will UWB technology do it right? 12

Follow me droney! Will UWB technology do it right?

引用

12th Asia Conference on Mechanical and Aerospace Engineering, ACMAE 2021

作者： Hanzel, Krzysztof Department of Electronics Electrical Engineering and Microelectronics Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice44-100 Poland

Object tracking for consumer drones is currently a rapidly developing technology. Its implementation is currently carried out with the use of object-in-image detection, which often limits the latest possibilities of this technology. The disadvantage of such a solution is also the increase in energy demand and the need to provide additional computing power, or delays resulting from the transfer of this operation to the control device. The proposed solution to this problem in this article is the use of UWB (Ultra-wideband) technology, which is increasingly appearing in consumer devices. The possible yield related to the accuracy of determining the position of the object as well as the experimentally determined frequency of receiving information about the position was presented. Additional advantages, such as resistance to NLOS (non-line of sight) conditions, were also presented. © Published under licence by IOP Publishing Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Faults Recognition of Dissolved Oxygen Sensor in Wastewater Treatment Plants 28

A Deep Learning Approach for Faults Recognition of Dissolved...

引用

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

作者： Ghinea, Liliana Maria Miron, Mihaela Ratnaweera, Harsha Electrical Engineering and Electronics Faculty of Automation Computers Department of Automatic Control and Electrical Engineering Department Galaţi Romania Computers Electrical Engineering and Electronics Faculty of Automation Department of Computer Science and Information Technology Galaţi Romania Norwegian University of Life Sciences Faculty of Science and Technology Oslo Norway

ISBN: (纸本)9798350339918

Fault diagnosis in wastewater treatment plants (WWTPs) is important to protect communities and ecosystems from toxic elements discharged into water. In this sense, fault identification of sensors plays an important role as they are the key components of the water plants control, especially because environmental legislation is very strict when referring to failures or anomalies in WWTPs. This paper analyzes the performances of two Deep Learning models, a Feedforward Neural Network (FFNN) and a 1D Convolution Neural Network (1DCNN) for identifying five operating states of the dissolved oxygen (DO) sensor: normal and faulty (bias, stuck, spike and precision degradation faults). The experiments were conducted on the Benchmark Simulator Model No 2 (BSM2) developed by the IWA Task Group. The performance of the Deep Learning (DL) classifiers was evaluated via accuracy, precision, recall, and F1-score metrics. The best overall classification accuracy was obtained by FFNN, 98.32% for training and 98.30% for testing. © 2023 IEEE.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement for Facial Landmark Detection 21

Image Enhancement for Facial Landmark Detection

引用

21st RoEduNet Conference on Networking in Education and Research, RoEduNet 2022

作者： Ciuntu, Victor Chiornita, Traian Boiangiu, Costin-Anton Tarba, Nicolae Voncila, Mihai-Lucian Rosner, Daniel Politehnica University Faculty of Automatic Control and Computers Computer Science and Engineering Department Bucharest Romania

ISBN: (数字)9781665455282

ISBN: (纸本)9781665455282

Facial landmark detection (FLD) is a field of study in computer vision that specializes in detecting and tracking key points from human faces. There are many applications, such as detecting a human's head pose (position and rotation), tracking whether drivers are paying attention or not, applying augmented reality, etc. This paper proposes to evaluate and decide what are the optimal techniques of image enhancement that can be used to improve different algorithms of FLD. After proposing different pipelines of contrast enhancement and grayscale conversion to enhance the image before applying the FLD algorithm, the results show that the performance will not increase drastically if an image enhancement pipeline is used, but for the reason that this step will not consume a lot of time in the process of detection, it is a step worth considering. © 2022 IEEE.

关键词： Face recognition

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：