检索结果-内蒙古大学图书馆

International Electrical Engineering Congress (iEECON)

作者： Waris Rattanimit Thanyarat Nomponkrang Electrical Technology and Automation System Faculty of Engineering and Technology Siam Technology College Bangkok Thailand Department of Computer Education King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

In the digital era, learning programming has become an essential skill, and assessing students' understanding in this area plays a crucial role in enhancing educational quality. However, evaluating subjective programming exam responses, especially those involving conceptual explanations or procedural descriptions, remains a challenging task due to the diversity and complexity of answers. Manual grading can lead to delays and inconsistencies in scoring. This research aims to develop an automated system for evaluating Thai subjective programming exams using Natural Language Processing (NLP) techniques to assess the correctness of responses. The system is implemented in Python, utilizing the ThaiNLP library for word tokenization, alongside Machine Learning algorithms such as Naive Bayes, Decision Tree, and Support Vector Machine (SVM) for classification and prediction of answers. The experimental dataset includes responses from 120 students who answered subjective questions about Python commands. Expert testing indicated high user satisfaction with an average score of 4.05. The findings show that SVM achieved the highest accuracy at 85.33%. This system can enhance efficiency and consistency in exam evaluation, reducing grading time and contributing to standardized scoring.

关键词： Support vector machines Electrical engineering Machine learning algorithms Manuals Machine learning Tokenization Libraries Programming profession Python Testing

来源：评论

学校读者我要写书评

暂无评论

GILV: An integrated GNSS/IMU positioning method enhanced by lane line and template matching VO 2

GILV: An integrated GNSS/IMU positioning method enhanced by ...

引用

2nd International Conference on Frontiers of Applied Optics and computer Engineering, AOCE 2025

作者： Wang, Rongchen Zeng, Qingxi Huang, Yuhua Ji, Xufang Shi, Yanwei Yuan, Liying College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing211106 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Xuzhou Power Supply Branch of State Grid Jiangsu Electric Power Co. Ltd. Xuzhou221000 China

ISBN: (纸本)9781510689404

Ensuring precise and flexible positioning is a fundamental prerequisite for autonomous mobility of unmanned ground vehicles. In the context of Global Navigation Satellite System (GNSS) signals facing suppression, the traditional joint GNSS and IMU positioning is subject to positioning drift due to the cumulative error of the IMU. In this paper, we propose a low-cost integrated localization system called GILV that fuses inertial and visual data through an error state Kalman filter (ESKF) framework to achieve continuous localization under GNSS rejection. GILV utilizes a downward-facing camera to provide vehicle position constraints through a template matching algorithm that is used to smooth out IMU predictions and mitigate dispersion of localization errors. At the same time, the forward-facing camera detects lane lines and combines this information with high-precision maps to provide lateral position constraints without cumulative errors, ensuring that the Integrated Positioning System (IPS) accuracy is stabilized at the decimeter level without degradation due to cumulative IMU errors. The Integrated Positioning System (IPS) is realized on the ROS platform and has been verified through outdoor experiments. The results show that GILV consistently limits the position error to within 0.5 meters and maintains an average position error within 10 centimeters during a 100-second GNSS signal outage. This resilience greatly reduces the dependence of the positioning system on the quality of GNSS signals. © The Authors.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning-Based Image Mapping-Topology Optimization for Antenna Design

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Dou, Jiangling Gong, Hao Chen, Haokang Chen, Yujie Shen, Tao Song, Jian Kunming University of Science and Technology Faculty of Information Engineering and Automation Yunnan Key Laboratory of Computer Technologies Application Kunming650500 China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming Yunnan650500 China College of Mechanical and Electrical Engineering Yunnan Electromechanical Vocational and Technical College China

A Reinforcement Learning (RL)-based Image Mapping Topology (IMT) optimization approach is proposed. To enable RL to optimize antenna topology and increase the efficiency of the optimization process. Two crucial components, Stratified Sampling Balance (SSB) and IMT are introduced. SSB is utilized to balance different types of data samples. IMT is utilized to facilitate the interaction between RL and simulation software, it also pretrains the actor network within the RL algorithm. This methodology allows the RL agent to acquire knowledge from the interaction of the antenna topology with the environment. Subsequently, the agent outputs antenna topology with the maximum reward signal. Compared with other machine learning-based optimization methods, the proposed method significantly alleviates the issue of learning inefficiency and reduces the exploration time for feasible solutions. To validate the effectiveness of the optimization method, a microstrip antenna is optimized. The measurement results show that the impedance bandwidth is doubled while maintaining the realized gain with fewer simulation samples and less optimization time. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Linear-Nonlinear Feature Reconstruction Network for Emotion Recognition from Brain Functional Connectivity

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Fu, Baole Yu, Xiangkun Liu, Yinhua Qingdao University Institute for Future School of Automation Qingdao266071 China Qingdao University College of Computer Science & Technology Qingdao266071 China Qingdao University Institute for Future School of Automation Shandong Provincial Key Laboratory of Industrial Control Technology Qingdao266071 China

Electroencephalogram (EEG) records both static performance and dynamic changes in brain electrical activity, with linear and nonlinear features capable of modelling these static and dynamic aspects. However, traditional EEG-based emotion recognition methods rely excessively on linear features (static analysis) without fully considering nonlinear features (dynamic changes). This limitation hinders a comprehensive capture of the complex interactions and dynamic variations between brain regions. This study proposes an EEG emotion recognition method based on a linear-nonlinear feature reconstruction network using brain functional connectivity. The method comprehensively captures the complex interactions and dynamic changes between brain regions by extracting linear and nonlinear features from dynamic and static connectivity. To enhance feature discriminability, a feature self-reconstruction encoder (FSRE) is introduced, which refines feature representation and improves the accuracy and discrimination of features. A feature interaction and reconstruction module (FIR Module) uses a bidirectional reconstruction strategy to interact with and reconstruct features based on their relationships, thereby enhancing the correlation between features and target classification. Experiments conducted on the SEED and SEED-IV datasets validate the effectiveness of this method, demonstrating that it achieves higher accuracy and robustness in emotion classification tasks compared to other advanced methods. © 1963-2012 IEEE.

关键词： Feature extraction Electroencephalography Emotion recognition Finite impulse response filters Data mining Brain modeling Accuracy Correlation Transformers Fluctuations

来源：评论

学校读者我要写书评

暂无评论

Linear Convergent Distributed Nash Equilibrium Seeking With Compression

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 3316-3323页

作者： Chen, Xiaomeng Wu, Yuchi Yi, Xinlei Huang, Minyi Shi, Ling Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Shanghai University School of Mechatronic Engineering and Automation Shanghai200444 China College of Electronics and Information Engineering Tongji University Department of Control Science and Engineering Shanghai201804 China Massachusetts Institute of Technology Lab for Information & Decision Systems CambridgeMA02139 United States Carleton University School of Mathematics and Statistics OttawaONK1S 5B6 Canada

Information compression techniques are majorly employed to reduce communication cost over peer-to-peer links. In this article, we investigate distributed Nash equilibrium (NE) seeking problems in a class of noncooperative games over directed graphs with information compression. To improve communication efficiency, a compressed distributed NE seeking (C-DNES) algorithm is proposed to obtain an NE for games, where the differences between decision vectors and their estimates are compressed. The proposed algorithm is compatible with a general class of compressors, including both unbiased and biased compressors. Moreover, our approach only requires the adjacency matrix of the directed graph to be row-stochastic, in contrast to past works that relied on balancedness or specific global network parameters. It is shown that C-DNES not only inherits the advantages of conventional distributed NE algorithms, achieving linear convergence rate for games with restricted strongly monotone mappings, but also saves communication costs in terms of transmitted bits. Finally, numerical simulations illustrate the advantages of C-DNES in saving communication cost by an order of magnitude under different compressors. © 1963-2012 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

fMRI2GES: Co-speech Gesture Reconstruction from fMRI Signal with Dual Brain Decoding Alignment

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Zhu, Chunzheng Shao, Jialin Lin, Jianxin Wang, Yijun Wang, Jing Tang, Jinhui Li, Kenli Hunan University College of Information Science and Engineering Changsha China Tsinghua University Department of Automation Beijing100084 China Nanjing University of Science and Technology School of Computer Science and Technology Nanjing210094 China

Understanding how the brain responds to external stimuli and decoding this process has been a significant challenge in neuroscience. While previous studies typically concentrated on brain-to-image and brain-to-language reconstruction, our work strives to reconstruct gestures associated with speech stimuli perceived by brain. Unfortunately, the lack of paired {brain, speech, gesture} data hinders the deployment of deep learning models for this purpose. In this paper, we introduce a novel approach, fMRI2GES, that allows training of fMRI-to-gesture reconstruction networks on unpaired data using Dual Brain Decoding Alignment. This method relies on two key components: (i) observed texts that elicit brain responses, and (ii) textual descriptions associated with the gestures. Then, instead of training models in a completely supervised manner to find a mapping relationship among the three modalities, we harness an fMRIto- text model, a text-to-gesture model with paired data and an fMRI-to-gesture model with unpaired data, establishing dual fMRI-to-gesture reconstruction patterns. Afterward, we explicitly align two outputs and train our model in a self-supervision way. We show that our proposed method can reconstruct expressive gestures directly from fMRI recordings. We also investigate fMRI signals from different ROIs in the cortex and how they affect generation results. Overall, we provide new insights into decoding co-speech gestures, thereby advancing our understanding of neuroscience and cognitive science. © 1991-2012 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Syn-Aug: An Effective and General Synchronous Data Augmentation Framework for 3D Object Detection

引用

CAAI Transactions on Intelligence technology 2025年

作者： Liu, Huaijin Du, Jixiang Zhang, Yong Zhang, Hongbo Zeng, Jiandian School of Artificial Intelligence Guangzhou Maritime University China and College of Mechanical Engineering and Automation Huaqiao University Xiamen China College of Computer Science and Technology Huaqiao University Xiamen China College of Mechanical Engineering and Automation Huaqiao University Xiamen China Institute of Artificial Intelligence and Future Networks Beijing Normal University Zhuhai China

Data augmentation plays an important role in boosting the performance of 3D models, while very few studies handle the 3D point cloud data with this technique. Global augmentation and cut-paste are commonly used augmentation techniques for point clouds, where global augmentation is applied to the entire point cloud of the scene, and cut-paste samples objects from other frames into the current frame. Both types of data augmentation can improve performance, but the cut-paste technique cannot effectively deal with the occlusion relationship between the foreground object and the background scene and the rationality of object sampling, which may be counterproductive and may hurt the overall performance. In addition, LiDAR is susceptible to signal loss, external occlusion, extreme weather and other factors, which can easily cause object shape changes, while global augmentation and cut-paste cannot effectively enhance the robustness of the model. To this end, we propose Syn-Aug, a synchronous data augmentation framework for LiDAR-based 3D object detection. Specifically, we first propose a novel rendering-based object augmentation technique (Ren-Aug) to enrich training data while enhancing scene realism. Second, we propose a local augmentation technique (Local-Aug) to generate local noise by rotating and scaling objects in the scene while avoiding collisions, which can improve generalisation performance. Finally, we make full use of the structural information of 3D labels to make the model more robust by randomly changing the geometry of objects in the training frames. We verify the proposed framework with four different types of 3D object detectors. Experimental results show that our proposed Syn-Aug significantly improves the performance of various 3D object detectors in the KITTI and nuScenes datasets, proving the effectiveness and generality of Syn-Aug. On KITTI, four different types of baseline models using Syn-Aug improved mAP by 0.89%, 1.35%, 1.61% and 1.14% respectiv

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-Fault Diagnosis, Quantitative Analysis and Warning Strategy for Lithium-ion Battery System: When LSTM Meets the Fuzzy Logic Theory

引用

IEEE Transactions on Transportation Electrification 2025年第3期11卷 8224-8235页

作者： Chen, Hui Tian, Engang Wang, Licheng Zheng, Yuejiu University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Shanghai University of Electric Power College of Automation Engineering Shanghai200090 China University of Shanghai for Science and Technology College of Mechanical Engineering Shanghai200093 China

This paper is concerned with the multi-level secure warning problem for lithium-ion battery systems subject to multi-fault scenarios. First, the long short-term memory (LSTM) network is employed to design a series of cell voltage estimators. In comparison with the estimation of the cell voltage and its measurement, the estimation residual is constructed in terms of the Euclidean distance, which plays an essential index for the multi-fault detection issue. Furthermore, in combination of the voltage envelope relationship, a specific type of the faults is subsequently identified. Then, for the subsequent fault warning purpose, a novel fault quantitative analysis method is proposed to further determine not only the fault amplitude but also its duration. In addition, on the basis of specific characteristics of the fault such as the type, count, duration and the amplitude, a fuzzy-logic-based multi-level secure warning strategy is put forward. Finally, the effectiveness of the developed multi-level fault warning approach is substantiated through a comprehensive experimental validation. © 2015 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

A study of advanced mathematical modeling and adaptive control strategies for trajectory tracking in the Mitsubishi RV-2AJ 5-DOF Robotic Arm

引用

Discover Robotics 2025年第1期1卷 1-38页

作者： Ben Hazem, Zied Guler, Nivine Altaif, Ali Husain Automation and Sustainability Research Centre (ASRC) Department of Mechatronics Engineering College of Engineering (COE) University of Technology Bahrain Salmabad Kingdom of Bahrain Department of Computer Science University of Central Asia Naryn Kyrgyzstan

This study is focused on the advanced mathematical modeling and control strategies for a Mitsubishi RV-2AJ 5-DOF Robotic Arm, with an emphasis on achieving precision in trajectory tracking. Robotic trajectory tracking has long been challenged by the constraints of conventional modeling techniques and control methods. Prior contributions have been limited by the use of traditional dynamic models and classical controllers, which often failed to adapt to complex trajectory requirements. To address these challenges, a comprehensive dynamic model has been developed using Euler–Lagrange equations and validated through a comparison with a 3D CAD Simscape model in MATLAB/Simulink. For the control approach, a PID controller and an Adaptive Neuro-Fuzzy Inference System (ANFIS) controller have been implemented to regulate the robotic arm’s joints. The ANFIS controller has been demonstrated to outperform the PID controller, achieving improved stability and adaptability in trajectory tracking. The robustness of the proposed system has been confirmed through simulation results for various trajectory types, including N-shaped, circular, and complex paths. This study underscores the importance of advanced modeling and hybrid control strategies in overcoming the limitations of traditional methods. By establishing a solid foundation in precise trajectory tracking through advanced mathematical modeling, this work contributes to the development of more adaptive and efficient robotic systems, with potential applications in industrial and research domains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantifying the Upper Limit of Backflash Attack in Quantum Key Distribution

arXiv

引用

arXiv 2025年

作者： Su, Jialei Liu, Junxuan Chen, Zihao Zhong, Mingyang Peng, Qingquan Ding, Jiangfang Wang, Yijun Huang, Anqi Guo, Ying School of Automation Central South University Changsha410083 China College of Computer Science and Technology National University of Defense Technology Changsha410073 China School of Computer Beijing University of Posts and Telecommunications Beijing100876 China

Quantum Key Distribution (QKD) theoretically provides information-theoretic security based on physical laws. However, imperfections in practice lead to the possibility of quantum hacking on the QKD implementation, especially the passive attacks that are difficult to be detected. In this paper, we study experimentally and theoretically the upper limit of a backflash attack, as one of the vital passive attacks, on a fiber-based QKD system. We experimentally demonstrate the backflash attack on a full equipped fiber-based QKD receiver to show its feasibility and limited distinguish ratio of decoding. More importantly, we have developed a simulation model to analyze the maximum distinguish ratio of decoding can be achieved considering the wide-spectrum feature of backflash photons, which indicates that Eve can extract effective key information from 95.7% of the backflash photons. Consequently, the secure key rate of the decoy-state BB84 QKD system under backflash attack is calculated. This work provides a general methodology to comprehensively evaluate the effect of the backflash attack on a QKD system. Copyright © 2025, The Authors. All rights reserved.

关键词： Decoding

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：