检索结果-内蒙古大学图书馆

International symposium on Applied computational intelligence and Informatics ( SACI)

作者： Raul Brumar Mihai-Alexandru Grosu Stelian Nicola Horia Ciocârlie Automation and Applied Informatics University Politehnica Timisoara Timisoara Romania Computer and Informtion Technology University Politehnica Timisoara Timisoara Romania

ISBN: (数字)9798350329520

ISBN: (纸本)9798350329537

In recent years, serious games have gained traction as an aid to traditional teaching and training methods. While releasing a serious game which can run on multiple platforms is desired, this comes with its own problems, mainly the need to develop multiple projects in parallel. We have identified this as a significant obstacle preventing people from developing cross-platform serious games, and in this paper propose a solution in the form of a system which unifies platform-specific controls. This results in the need to maintain a single code base, with platform-specific code being written only for reading and processing the inputs. The system identifies on which platform the game is currently running and selects the correct code to process inputs. The processed inputs are abstracted, and the rest of the game uses the abstracted inputs, regardless of the current platform.

关键词： Training Human computer interaction Codes control systems Serious games Task analysis Informatics

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of GPU Performance and Energy Efficiency Across Generational Architectures: A Systematic Literature

Comparative Study of GPU Performance and Energy Efficiency A...

引用

control & automation, Electronics, Robotics, Internet of Things, and Artificial intelligence (CERIA), ieee International Conference on

作者： Risang Faiz Muhammad Muhammad Edo Syahputra Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331511166

ISBN: (纸本)9798331511173

In this study, the evolution of GPU architectures across multiple generations is explored, focusing on their computational performance and energy efficiency. Using a systematic literature review and comparative analysis, this study examines key advancements in GPU technology, particularly in AI workloads, ray tracing, gaming, and scientific simulations. The analysis reveals that modern GPUs, such as those based on the Ampere architecture, demonstrate significant improvements in both performance and energy efficiency, with a $\mathbf{3 0 \%}$ increase in AI task performance and a $\mathbf{2 0 \%}$ reduction in power consumption compared to previous generations. This study also highlights how innovations in specialized cores and optimized memory management have enabled GPUs to excel in domain-specific applications. Additionally, the broader implications of these advancements for other computational fields, including gaming and scientific research, are addressed. By providing a comprehensive view of these developments, this review offers valuable insights into future GPU design trends and the ongoing challenges in balancing high performance with energy efficiency.

关键词： Technological innovation Tensors computational modeling Graphics processing units Ray tracing Transformer cores Energy efficiency computational efficiency Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Based System Identification for Linear Time-Invariant Systems

Data-Driven Based System Identification for Linear Time-Inva...

引用

2023 China automation Congress, CAC 2023

作者： Yang, Shaobudao Fu, Anqi Qiao, Junfei Faculty of Information Technology Beijing University of Technology Beijing China Key Laboratory of Computational Intelligence and Intelligent Systems Beijing University of Technology Beijing China Beijing Laboratory of Smart Environmental Protection Beijing Artificial Intelligence Institute Beijing China

ISBN: (纸本)9798350303759

System identification is an important basis for understanding the behavior characteristics of unknown systems and for further optimization and control purposes. In this brief, we focus on the model identification for LTI systems using a finite set of sampled data and noise bounds. In order to precisely capture the dynamics of the unknown system, a 2-step approach is proposed. Imprimis, a set operation based on zonotope is applied to compute all the possible matrices that describe the system dynamics with an estimated noise set. The computed result is consistent with all data points and noise bound which is represented by matrix zonotope. Secondly, by solving a proposed optimization problem to find the fittest system dynamic matrix. The aim of the problem is to minimize the noise zonotope. The foregoing 2-step approach is capable of effectively approximating the actual systems. Numerical example demonstrates the validity of the proposed method. © 2023 ieee.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Primary Study on the Face-recognition Framework with anti-spoofing function 4

Primary Study on the Face-recognition Framework with anti-sp...

引用

4th International Conference on Data intelligence and Security, ICDIS 2022

作者： Wu, Xiao Zhang, Dekang Liu, Xiaorui Automation School of Qingdao University Qingdao266000 China Shandong Key Laboratory of Industrial Control Technology Qingdao266071 China

ISBN: (数字)9781665459686

ISBN: (纸本)9781665459686

In pracyical life scene, most access control systems (ACS) cannot solve the problem of various sproofing ways and mask-wearing recognition. In this paper, a new security classification framework based on face recognition is proposed. This framework uses face recognition algorithm with anti-spoofing function. In order to evaluate the performance of the framework, this paper employs the Chinese Academy of Science Institute of automation-Face Anti-spoofing Datasets (CASIA-FASD) as benchmarks. Performance evaluation indicates that the Half Total Error Rate (HTER) is 9.7%, the Equal Error Rate (EER) is 5.5%. The results demonstrate that this framework has a high anti-spoofing capability and can be employed on the embedded system to complete the mask detection in real-time. © 2022 ieee.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Vision Transformer with Local-Global Attention 4

Multi-Scale Vision Transformer with Local-Global Attention

引用

4th International Conference on Industrial automation, Robotics and control Engineering, IARCE 2024

作者： Zhang, Ruomiao Du, Shengdong Hu, Jie Zhao, Xiaole Yang, Yan School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China

ISBN: (纸本)9798350380323

The extraction of multi-scale features from input images is crucial for computer vision tasks. However, some backbone networks based on visual transformers lack the ability to effectively extract multi-scale features or use relatively simplistic methods to do so. This paper proposes a novel multi-scale visual transformer, called Multi-Scale Extraction Transformer (MSET), designed to proficiently tackle a range of downstream visual tasks. MSET incorporates innovative concepts of Multi-Scale feature extraction Embedding (MS Embedding) and Local-Global self-attention (LGSA). MS Embedding uses a unique architecture convolutional layer method that constructs hierarchical residual-like connections, allowing for the extraction of multi-scale features at finer granularity levels. Meanwhile, LGSA integrates local and global dependencies within the self-attention module, reducing computational complexity while facilitating connections between the global and local features of the image. The importance of position information in the embeddings and the impact of amplitude on model performance are also considered, allowing MSET to handle position bias information of variable size in the input image and to ensure stability during training. Numerous experiments have demonstrated the significant advantages of MSET over most existing state-of-the-art backbone networks across various visual tasks, including image classification, object detection, instance segmentation, and semantic segmentation tasks. © 2024 ieee.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Analysis of Max-Plus Algebraic Model for Intelligent Manufacturing Systems Based on Heap Method 8

Analysis of Max-Plus Algebraic Model for Intelligent Manufac...

引用

8th International symposium on Computer Science and Intelligent control, ISCSIC 2024

作者： Rao, Taiwen Liu, Zuojun Hebei University of Technology School of Ai Tianjin China Central South University School of Automation Changsha China Hebei University of Technology School of Ai Control Engineering Technology Innovation Centre of Hebei Tianjin China

ISBN: (纸本)9798350380286

Max-plus algebra is a mathematical method with special operational rules that can describe the temporal logic characteristics of discrete event systems and optimize the intelligent manufacturing system. The heap model in the max-plus algebra is an intuitive dynamic system description method that can be used to model various Tetris like systems. Each block in the model can be used to identify a single work-piece in the intelligent manufacturing process, with the goal of manufacturing a set of products in a specific order, thereby minimizing the total manufacturing time. In this paper, the heap method based on max-plus algebra is used to model and analyse discrete manufacturing processes involving multiple devices and tasks. The research addresses both rigid heaps, which do not impose restrictions on the order of processing objects, and complex rigid heaps, which also allow for flexible processing object order. To enhance the analytical accuracy in scenarios involving machining tasks comprising intricate stacks of rigid heaps, an enhanced 3D heap modelling method is proposed. This approach aims to improve the production scheduling outcome. Moreover, by investigating non-rigid heaps with limited processing object order, the proposed method is compared with the simulated annealing algorithm in the field of production scheduling, and further analysis was conducted. Finally, a comprehensive analysis is presented to identify the applicable fields for the proposed method. © 2024 ieee.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving

Space, Time, and Interaction: A Taxonomy of Corner Cases in ...

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Roesch, Kevin Heidecker, Florian Truetsch, Julian Kowol, Kamil Schicktanz, Clemens Bieshaar, Maarten Sick, Bernhard Stiller, Christoph FZI Res Ctr Informat Technol Mobile Percept Syst Schonfeldstr 8 D-76131 Karlsruhe Germany Univ Kassel Intelligent Embedded Syst Wilhelmshoher Allee 73 D-34121 Kassel Germany Univ Wuppertal Sch Math & Nat Sci Lise Meitner Str 27-31 Wuppertal Germany German Aerosp Ctr DLR Inst Transportat Syst Rutherfordstr 2 D-12489 Berlin Germany Robert Bosch GmbH D-31132 Hildesheim Germany Karlsruhe Inst Technol Inst Measurement & Control Syst Engler Bunte Ring 21 D-76131 Karlsruhe Germany

ISBN: (纸本)9781665487689

Trajectory data analysis is an essential component for highly automated driving. Complex models developed with these data predict other road users' movement and behavior patterns. Based on these predictions - and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users - the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e.g., moving from point A to B. Ideally, the HAV moves safely through its environment, just as we would expect a human driver to do. However, if unusual trajectories occur, so-called trajectory corner cases, a human driver can usually cope well, but an HAV can quickly get into trouble. In the definition of trajectory corner cases, which we provide in this work, we will consider the relevance of unusual trajectories with respect to the task at hand. Based on this, we will also present a taxonomy of different trajectory corner cases. The categorization of corner cases into the taxonomy will be shown with examples and is done by cause and required data sources. To illustrate the complexity between the machine learning (ML) model and the corner case cause, we present a general processing chain underlying the taxonomy.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Passivity-Based controller Design of Grid-Connected Inverters Using PCC Voltage Feedforward Active Damping 4

Passivity-Based Controller Design of Grid-Connected Inverter...

引用

4th International symposium on Electrical, Electronics and Information Engineering, ISEEIE 2024

作者： Huang, Yukai Xu, Jinbang Huang, Songtao Hu, Yihua Zheng, Bingying Li, Zhuang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China King's College London Department of Engineering London United Kingdom

ISBN: (纸本)9798350355772

The stability of LCL-filter grid-connected inverters with grid current feedback (GCF) and active damping control methods has been extensively researched. However, current sensors are more commonly placed on the inverter side for a more compact structure, leading to different stability analyses due to the LCL filter. Therefore, this paper focuses on passivity-based point of common coupling (PCC) voltage active damping for inverter-current feedback (ICF) grid-connected inverters. PCC voltage active damping is utilized to achieve output admittance passivity across the entire frequency domain. The general controller phase constraint conditions are stated, providing a helpful basis for the design of the controller. Moreover, a detailed design scheme is demonstrated for the control form and parameter selection. The chosen controller can achieve good performance for ICF inverters under different grid impedances. Finally, the simulation results verify the effectiveness of the proposed design methods. © 2024 ieee.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

Modeling Digital Personality: A Fuzzy-Logic-Based Myers-Briggs Type Indicator for Fine-Grained Analytics of Digital Human

引用

ieee TRANSACTIONS ON computational SOCIAL SYSTEMS 2024年第1期11卷 1096-1107页

作者： Wang, Tan Ye, Peijun Lv, Hongqiang Gong, Weichao Lu, Hao Wang, Fei-Yue Macau Univ Sci & Technol Fac Innovat Engn Dept Engn Sci Macau Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Fac Innovat Engn Dept Engn Sci Macau Peoples R China Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China

Digital human in cyberspace can help provide humanized services in specific applications, such as question & answer systems, recommender systems, chatter robots, and intelligent assistants. While most researches focus on behavior analytics, few of them integrate the personality that is also a closely related factor. As a classic indicator for personality representation, Myers-Briggs type indicator (MBTI) categorizes an individual into mutually exclusive types from four dichotomous axes (extraversion versus introversion, sensing versus intuition, thinking versus feeling, judging versus perceiving). Traditional recognition method using MBTI simply measures the user's preference frequency in each axis through questionnaires, treating the dominant value as the identified result. Such a paradigm, however, represents all the people with only 16 types and cannot distinguish heterogeneous users clearly. This article proposes a novel personality recognition method using fuzzy logic. Different from previous classifications, our new method categorizes the individual in a continuous space and represents one's personality in a more fine-grained level. We have designed comparative psychological tests for 77 people. The validation experiments on such tests indicate that the fuzzy-logic-based method is not only consistent with the classic MBTI tests (in the sense of defuzzification) but also provides the uncertainty for each personality type. Therefore, it can be viewed as a generalization of the classic MBTI tests and promotes the representation of individual's heterogeneity for fine-grained analytics of digital human.

关键词： Psychology Fuzzy logic automation Technological innovation Uncertainty Soft sensors Social networking (online) Digital human digital personality fuzzy logic reasoning fuzzy personality recognition Myers-Briggs type indicator (MBTI)

来源：评论

学校读者我要写书评

暂无评论

A Jump-Gain Integral Recurrent Neural Network for Solving Noise-Disturbed Time-Variant Nonlinear Inequality Problems

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第4期35卷 5793-5806页

作者： Zhang, Zhijun Song, Yating Zheng, Lunan Luo, Yamei South China Univ Technol Sch Automat Sci & Engn Guangzhou 510640 Peoples R China Guangdong Univ Petrochem Technol Sch Automat Maoming 525000 Peoples R China Guangdong Artificial Intelligence & Digital Econ L Pazhou Lab Guangzhou 510335 Peoples R China Shaanxi Univ Technol Sch Mech Engn Shaanxi Prov Key Lab Ind Automat Hanzhong 723001 Peoples R China Hunan Univ Finance & Econ Sch Informat Technol & Management Changsha 410205 Peoples R China East China Jiaotong Univ Sch Automation Sci & Engn Nanchang 330052 Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Continental NTU Corp Lab Future Oriented Continentals Urban Soc FOCUS Lab Singapore 639798 Singapore

Nonlinear inequalities are widely used in science and engineering areas, attracting the attention of many researchers. In this article, a novel jump-gain integral recurrent (JGIR) neural network is proposed to solve noise-disturbed time-variant nonlinear inequality problems. To do so, an integral error function is first designed. Then, a neural dynamic method is adopted and the corresponding dynamic differential equation is obtained. Third, a jump gain is exploited and applied to the dynamic differential equation. Fourth, the derivatives of errors are substituted into the jump-gain dynamic differential equation, and the corresponding JGIR neural network is set up. Global convergence and robustness theorems are proposed and proved theoretically. Computer simulations verify that the proposed JGIR neural network can solve noise-disturbed time-variant nonlinear inequality problems effectively. Compared with some advanced methods, such as modified zeroing neural network (ZNN), noise-tolerant ZNN, and varying-parameter convergent-differential neural network, the proposed JGIR method has smaller computational errors, faster convergence speed, and no overshoot when disturbance exists. In addition, physical experiments on manipulator control have verified the effectiveness and superiority of the proposed JGIR neural network.

关键词： Antidisturbance global convergence nonlinear inequalities recurrent neural network (RNN) time-variant systems

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：