检索结果-内蒙古大学图书馆

11th International Conference on Signal and Information Processing, Network and Computers, ICSINC 2023

作者： Chen, Long Zhao, Pin Chen, Huajun Liu, Xintan Beijing Institute of Control Engineering Beijing China North China Institute of Computing Technology Langfang China Beijing Institute of Spacecraft Environment Engineering Beijing China

ISBN: (纸本)9789819721153

The 3D reconstruction technology is of great significance for the research of Martian topography. In this paper, an unmanned aerial vehicle (UAV) based Mars topography mapping and 3D reconstruction system is proposed. In the system, an on-board range-visual-inertial odometry (on-board range-VIO) is applied to solve UAV navigation and flight path planning problems. The pictures of simulated Mars topography are photted. Images are processed and 3D model is reconstructed by applying high-performance computing unit (HPCU). By building an experimental system on the ground and conducting flight simulation and 3D reconstruction experiments, the effectiveness of the system was verified. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Topography

来源：评论

学校读者我要写书评

暂无评论

A proposal of Android services generator for inter-connection with ADAS

A proposal of Android services generator for inter-connectio...

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Boskovic, Ognjen Kokinovic, Aleksandar Kenjic, Dusan Kastelan, Ivan University of Novi Sad Faculty of Technical Science Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798350347722

The integration of software in the automotive industry has become increasingly complex and time-sensitive, necessitating the implementation of efficient tools. One such tool is the utilization of a generator. Over the past decade, the implementation of In-Vehicle-Infotainment systems has become ubiquitous, occupying a central position within vehicles. Another system present in vehicles is the Advanced Driver Assistance System. Despite their prevalence, these systems operate in isolation. However, the utilization of Android services and a service-client architecture can facilitate communication between disparate systems through the implementation of various service-client-based protocols. This study proposes the development of a generator for Android services that enable communication between Advanced Driver Assistance System systems through the use of CommonAPI proxy. The implementation of this generator will expedite the production process of code that integrates these independent systems. © 2023 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

One solution of providing ADAS data to the IVI domain via the Android Java service

One solution of providing ADAS data to the IVI domain via th...

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Stanisic, Dusan Antic, Marija Kenjic, Dusan Bilac, Luka University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798350347722

In recent years, manufacturers are working parallel in developing and integrating two in-vehicle systems, an Advanced Driver Assistance System (ADAS) and In-Vehicle Infotainment (IVI). ADAS's purpose is to increase safety and aid the driver while the vehicle is in motion, by using various sensors to perceive the vehicle surrounding or the driver's errors and respond accordingly. Consumer applications in the IVI domain would significantly benefit from accessing such vehicle-specific data. Unfortunately, due to active vehicle system architecture requirements, the IVI domain cannot achieve communication with the ADAS by following traditional signal-oriented mechanisms. In addition, Android paved its way into the IVI domain as the most common Operating System because of its high flexibility and customization, but without being adapted for communication with ADAS. This paper offers a solution for enabling Android applications to access ADAS data via Java services. Data is procured over GENIVI company's SOME/IP-based communication middleware, integrated within the services. Communication performance is measured, evaluated, and limitations are identified. © 2023 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

A novel fractional physics-informed neural networks method for solving the time-fractional Huxley equation

引用

Neural computing and Applications 2024年第30期36卷 19097-19119页

作者： Shi, Jieyu Yang, Xiaozhong Liu, Xinlong School of Control and Computer Engineering North China Electric Power University Beijing102206 China Institute of Information and Computing School of Mathematics and Physics North China Electric Power University Beijing102206 China

The neural network methods in solving differential equations have significant research importance and promising application prospects. Aimed at the time-fractional Huxley (TFH) equation, we propose a novel fractional physics-informed neural networks (fPINNs) method. By integrating the physical information of the TFH equation into neural networks, the fPINNs are trained as a precise approximation model for solving the TFH equation. The fPINNs method involves calculating the Caputo fractional derivative using the L1 formula and estimating the integer-order derivative through the chain rule. The Adam algorithm is employed to optimize two kinds of loss functions constructed by hard and soft constraints, respectively. Through an analysis of the impact of fPINNs parameters on training results, we identify the optimal parameter configuration for solving both one-dimensional and two-dimensional (2D) TFH equations. Numerical examples validate the efficiency and robustness of the fPINNs method in solving TFH equations. Furthermore, numerical simulation of the 2D TFH problem demonstrates the method’s practical applicability to engineering problem. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-model Fusion Attitude Detection and Velocity-Based Power System 1

引用

8th International Conference on Life System Modeling and Simulation, LSMS 2024 and 8th International Conference on Intelligent computing for Sustainable Energy and Environment, ICSEE 2024

作者： Zhang, PengCheng Bai, JunZhe Ouyang, Peng Zhuang, YiFei Zhang, Kun School of Electrical Engineering and Automation Nantong University Nantong China Nantong Key Laboratory of Intelligent Control and Intelligent Computing Nantong China

ISBN: (数字)9789819603138

ISBN: (纸本)9789819603121

In the context of the close integration of artificial intelligence and sports, the precise measurement and intelligent coach-free scientific guidance remain one of the hotly debated topics. However, most current technologies are still limited to manual supervision and measurement of relevant indicators through hardware sensors. This approach is time-consuming and labor-intensive, not only prone to interfering with athletes’ actual performance but also requiring coaches’ real-time supervision to prevent irrecoverable injuries. Therefore, this paper proposes the LW-Pose model, which introduces Depth-Wise (DW) convolutions and channel attention mechanisms to optimize the backbone network. We replace the original decoupled head section with the Vision Transformer method and analyze the output vectors using Simcc technology to ultimately obtain accurate posture outputs. The proposed method achieves an AP50 of 92.6% and AP of 71.8%. Based on this technology, a velocity-based power training system has been developed with accuracy of 97%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Channel attention Depth-Wise convolutions Simcc Velocity-based power training system Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Predicting Students’ Final Exam Scores Based on Their Regularity of Engagement with Pre-Class Activities in a Flipped Classroom 16

Predicting Students’ Final Exam Scores Based on Their Regul...

引用

16th International Conference on Computer Supported Education, CSEDU 2024

作者： Francišković, Teodor Sakal Anđelić, Ana Slivka, Jelena Luburić, Nikola Kovačević, Aleksandar Department of Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Trg Dositeja Obradovića 6 Novi Sad Serbia

ISBN: (纸本)9789897586972

Flipped Classroom (FC) is an active learning design requiring the students to engage in pre-class learning activities to prepare for face-to-face sessions. Identifying FC learning behaviors that lead to academic success remains a challenge. This paper addresses this challenge by conducting an empirical study in an undergraduate software engineering course employing the FC model. The empirical study draws on the data from an intelligent tutoring system that captured the learning traces of students performing pre-class activities. These traces provided indicators of students’ regularity of engagement, which were then matched to their final exam scores. Regression models were trained to predict final exam scores based on the regularity of engagement indicators. Students were clustered based on their regularity of engagement indicators to uncover actionable feedback for future course iterations. The case study confirms the generalizability of earlier findings that the regularity of engagement is vital for student performance and that course-specific predictors significantly impact the models’ prediction performance. Copyright © 2024 by Paper published under CC license (CC BY-NC-ND 4.0)

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Generating Adversarial Patterns in Facial Recognition with Visual Camouflage

引用

Journal of Shanghai Jiaotong University (Science) 2024年 1-12页

作者： Bao, Qirui Mei, Haiyang Wei, Huilin Lü, Zheng Wang, Yuxin Yang, Xin Key Laboratory of Social Computing and Cognitive Intelligence of Ministry of Education School of Control Science and EngineeringSchool of Computer Science and Technology Dalian University of Technology Liaoning Dalian116024 China Systems Engineering Institute Academy of Military Sciences Beijing100141 China

Deep neural networks, especially face recognition models, have been shown to be vulnerable to adversarial examples. However, existing attack methods for face recognition systems either cannot attack black-box models, are not universal, have cumbersome deployment processes, or lack camouflage and are easily detected by the human eye. In this paper, we propose an adversarial pattern generation method for face recognition and achieve universal black-box attacks by pasting the pattern on the frame of goggles. To achieve visual camouflage, we use a generative adversarial network (GAN). The scale of the generative network of GAN is increased to balance the performance conflict between concealment and adversarial behavior, the perceptual loss function based on VGG19 is used to constrain the color style and enhance GAN’s learning ability, and the fine-grained meta-learning adversarial attack strategy is used to carry out black-box attacks. Sufficient visualization results demonstrate that compared with existing methods, the proposed method can generate samples with camouflage and adversarial characteristics. Meanwhile, extensive quantitative experiments show that the generated samples have a high attack success rate against black-box models. © 2023, Shanghai Jiao Tong University.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Unit Test Generation Multi-Agent AI System for Enhancing Software Documentation and Code Coverage 32

Unit Test Generation Multi-Agent AI System for Enhancing Sof...

引用

32nd Telecommunications Forum, TELFOR 2024

作者： Stojanovic, Dimitrije Pavkovic, Bogdan Cetic, Nenad Krunic, Momcilo Vidakovic, Luka University of Novi Sad Faculty of Technical Sciences Departmant of Computing and Control Engineering Novi Sad Serbia LabSoft Novi Sad Serbia

ISBN: (纸本)9798350391053

Software development necessitates a robust testing plan though test development can be laborious and nonappealing task. We explore the utilization of the application artificial intelligence agents for generating and executing unit tests, enhancing the 'Mostly Basic Python Problems' dataset. We employ behavior-driven development within a three-agent system to generate user stories and unit tests. Empirical results indicate improvements in branch coverage, illustrating the effective utilization of large language models in software testing and development processes. © 2024 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Detection of Hyperbolic Reflections on Real GPR Data Using YOLO Model Trained with Synthetic Data 47

Detection of Hyperbolic Reflections on Real GPR Data Using Y...

引用

47th International Conference on Telecommunications and Signal Processing, TSP 2024

作者： Bugarinović, Željko Gavrilović, Milan Ristić, Aleksandar Bugarinović, Milka Šarkanović Radulović, Aleksandra Govedarica, Miro University of Novi Sad Faculty of Technical Sciences Department for Computing and Control Engineering Trg Dositeja Obradovića 6 Novi Sad Serbia

ISBN: (纸本)9798350365597

This paper analyzes the application of the YOLO algorithm to automatically recognize hyperbolic reflections on radargrams. A specific shape of hyperbolic reflection on radargrams occurs with objects of circular cross-section that are scanned perpendicular to their axis, such as underground pipes. Requirements for processing a large number of radargrams are increasingly being imposed in practice. Therefore, the development of algorithms for the automated finding of hyperbolic reflections on radargrams has been intensified in recent years. Conventional methods take a lot of time and are more susceptible to noise than algorithms based on deep learning. One of such algorithms is also applied in this paper. The model was trained with 2000 synthetic radargrams generated using gprMax software. The basic idea is reflected in the analysis of the successful detection of hyperbolic reflections on real radargrams using a model trained only with synthetic radargrams. Experimental results show a high level of success. © 2024 IEEE.

关键词： Ground penetrating radar systems

来源：评论

学校读者我要写书评

暂无评论

4K Video Coding Efficiency in UAV Systems 45

4K Video Coding Efficiency in UAV Systems

引用

45th Jubilee International Convention on Information, Communication and Electronic Technology, MIPRO 2022

作者： Benjak, J. Hofman, D. Faculty of Electrical Engineering and Computing Department of Control and Computer Engineering Zagreb Croatia

ISBN: (纸本)9789532331035

With increasing requirements for high quality, low bandwidth video transmission systems, comes a demand for more ad hoc video encoders. Unmanned Aerial Vehicles (UAVs), or just drones, have recently grown in popularity and use. Therefore, in this paper, we provide an efficiency comparison of the two most popular video encoders in a First-person view (FPV) drone piloting system. We film all the test sequences ourselves, using a drone with an attached 4K camera. Each sequence captures a scene with different spatiotemporal characteristics. Because video encoders are sensitive to video content or scene complexity, instead of doing a comprehensive comparison of all sequences at once, we first classify all the sequences into four groups. Finally, we examine the compression efficiency by varying the parameters with the highest impact on encoder operation. The quality of compressed footage is determined using four objective video quality measures. Due to high computational complexity, tests were performed on several nodes of a supercomputer and the relative encoding times were also considered. © 2022 Croatian Society MIPRO.

关键词： Antennas

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：