检索结果-内蒙古大学图书馆

5th International Symposium on Instrumentation Systems, Circuits and Transducers, INSCIT 2021

作者： Coelho, Frederico Alves, Evandro Arias-Garcia, Janier Torres, Frank Sill Graduate Program in Electrical Engineering Department of Electronic Engineering MG Belo Horizonte31270-901 Brazil Department of Electronic Engineering MG Belo Horizonte31270-901 Brazil Institute for the Protection of Maritime Infrastructures of German Aerospace Center Germany Graduate Program in Electrical Engineering MG Belo Horizonte31270-901 Brazil

ISBN: (纸本)9781728197265

Trustworthiness is an important aspect for systems for IoT application, especially when it comes to solutions in the domains of security or privacy. Integrated circuits are an essential element of IoT systems, and thus, an attractive target. Therefore, one has to assure over the complete design and fabrication cycle, that no harmful changes have been made to the circuits. This motivated several researchers to focus on the subject of reverse engineering to search for malicious circuits, also known as hardware Trojans, which have been added during design or fabrication processes. Other purposes are the identification of patent violations or the support of existing verification solutions. Having in mind the complexity of this task, this work proposes an approach towards a fully automated solution that focuses on analog circuits. Therefore, an approach for identifying analog circuit structures in netlists extracted from random layouts is presented. Its feasibility is shown at the hand of current mirror circuits with varying architecture. The results indicate that the algorithm has an average accuracy of above 80%, with a maximum detection rate of 100%. © 2021 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Three-phase Self-Excited Induction Generator Operating as Single-phase Induction Generator using Static VAR Compensator

Three-phase Self-Excited Induction Generator Operating as Si...

引用

International Conference on electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON

作者： Sawat Yukhalang Theppanom Sopapirm Vijit Kinnares The Electrical Engineering Graduate Program Faculty of Engineering and Technology Mahanakorn University of Technology Nongjok Bangkok Thailand Institute of Electrical and Electronics Faculty of Engineering and TechnologyMahanakorn University of Technology Nongjok Bangkok Thailand Department of Electrical Engineering School of Engineering King Mongkut’s Institute Technology Ladkrabang Chalongkrung Road Ladkrabang Bangkok Thailand

This paper proposes a performance analysis of using a static volt-amp-reactive (VAR) compensator for a three-phase self-excited induction generator (SEIG) operating as a single-phase induction generator. The study proposes appropriate capacitor for building up voltage supplying power to load with static VAR for regulating terminal voltage. The simulation model is analyzed by using MATLAB/Simulink under various conditions such as reactive power supplied, dynamic response, steady state, building up voltage for startup, linear load, non-linear load and harmonics in system. From the study (based on the study, the findings revealed it is found) that using the static VAR compensator connected in parallel with loads for supplying reactive power to the load systems is needed for maintaining terminal voltage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of Extended RISC-V for Q-Learning Hardware Accelerator using HW/SW Co-Design

Design of Extended RISC-V for Q-Learning Hardware Accelerato...

引用

IEEE Asia-Pacific Conference on Circuits and Systems

作者： Infall Syafalni Muhammad Sulthan Mazaya Muhammad Raihan Elfazri Eko Mursito Budi Nana Sutisna Rahmat Mulyawan Trio Adiono Makoto Ikeda School of Electrical Engineering and Informatics Bandung Institute of Technology Indonesia University Center of Excellence on Microelectronics Bandung Institute of Technology Indonesia System Design Laboratory School of Engineering The University of Tokyo Tokyo Japan Faculty of Industrial Technology Bandung Institute of Technology Indonesia Graduate School of Engineering The University of Tokyo Tokyo Japan

ISBN: (数字)9798350378771

ISBN: (纸本)9798350378788

In this paper, we propose a novel RISC-V ISA extension for a reinforcement learning-based hardware accelerator called RISC-Q. We introduce new instructions i.e., ***_constant, ***, ***, ***, and ***. Each instruction corresponds to a hardware module. The ***_constant sets necessary constants for the Q-learning by storing it in dedicated registers. The *** and *** instructions write and read the data to the main memory. The *** instruction controls the max seeker hardware module to find $\mathbf{Q}$-max values. The *** instruction accesses the $\mathbf{Q}$-updater hardware module to update the $\mathbf{Q}$-value with the corresponding state, action, and reward. Experimental result shows that the RISC-V extended reinforcement learning hardware accelerator (RISC-Q), which is implemented in the Nexys FPGA board, outperforms the software implementation up to $1.5 \times$ speed up. The work is useful for edge-computing applications such as smart navigation, smart communications, and robotics.

关键词： Q-learning Navigation Circuits and systems Asia Software Registers Hardware acceleration Robots Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Algorithms for Coloring Reconfiguration Under Recolorability Digraphs 33

Algorithms for Coloring Reconfiguration Under Recolorability...

引用

33rd International Symposium on Algorithms and Computation, ISAAC 2022

作者： Fujii, Soichiro Iwamasa, Yuni Kimura, Kei Suzuki, Akira Research Institute for Mathematical Sciences Kyoto University Japan School of Mathematical and Physical Sciences Macquarie University Sydney Australia Graduate School of Informatics Kyoto University Japan Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan Graduate School of Information Sciences Tohoku University Sendai Japan

ISBN: (纸本)9783959772587

In the k-Recoloring problem, we are given two (vertex-)colorings of a graph using k colors, and asked to transform one into the other by recoloring only one vertex at a time, while at all times maintaining a proper k-coloring. This problem is known to be solvable in polynomial time if k ≤ 3, and is PSPACE-complete if k ≥ 4. In this paper, we consider a (directed) recolorability constraint on the k colors, which forbids some pairs of colors to be recolored directly. The recolorability constraint is given in terms of a digraph -→R, whose vertices correspond to the colors and whose arcs represent the pairs of colors that can be recolored directly. We provide algorithms for the problem based on the structure of recolorability constraints -→R, showing that the problem is solvable in linear time when -→R is a directed cycle or is in a class of multitrees. © Soichiro Fujii, Yuni Iwamasa, Kei Kimura, and Akira Suzuki.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Non-Hermitian metasurface for asymmetric thermal emission

Non-Hermitian metasurface for asymmetric thermal emission

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Prasad, Ciril S. Everitt, Henry O. Naik, Gururaj V. Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States U.S. Army DEVCOM Army Research Laboratory-South HoustonTX United States

ISBN: (纸本)9781957171258

Non-Hermitian optics provides a unique platform to take advantage of absorption losses in materials and control radiative properties. We demonstrate a non-Hermitian metasurface that exhibit directional suppression of thermal radiation while maintaining transmission in mid-infrared. © Optica Publishing Group 2023 © 2023 The Author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sample Complexity of Kernel-Based Q-Learning

arXiv

引用

arXiv 2023年

作者： Yeh, Sing-Yuan Chang, Fu-Chieh Yueh, Chang-Wei Wu, Pei-Yuan Bernacchia, Alberto Vakili, Sattar MediaTek Research Graduate Program of Data Science National Taiwan University Academia Sinica Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan

Modern reinforcement learning (RL) often faces an enormous state-action space. Existing analytical results are typically for settings with a small number of state-actions, or simple models such as linearly modeled Q-functions. To derive statistically efficient RL policies handling large state-action spaces, with more general Q-functions, some recent works have considered nonlinear function approximation using kernel ridge regression. In this work, we derive sample complexities for kernel based Q-learning when a generative model exists. We propose a nonparametric Q-learning algorithm which finds an ǫ-optimal policy in an arbitrarily large scale discounted MDP. The sample complexity of the proposed algorithm is order optimal with respect to ǫ and the complexity of the kernel (in terms of its information gain). To the best of our knowledge, this is the first result showing a finite sample complexity under such a general model. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Trajectory Learning and Demonstration of a Robot Manipulator Based-on Sensor Fusion from a Hand-held Tool

Trajectory Learning and Demonstration of a Robot Manipulator...

引用

International Automatic Control Conference

作者： Kai-Tai Song Szu-Chen Ou Institute of Electrical and Control Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Yang Ming Chiao Tung University Hsinchu Taiwan ROC Graduate Degree Program of Robotics National Yang Ming Chiao Tung University Hsinchu Taiwan ROC

ISBN: (数字)9798350354904

ISBN: (纸本)9798350354911

This paper presents a programming system for a robot manipulator using a hand-held demonstration tool. In this system, a user holds the self-designed tool to demonstrate a desired motion path, and the robot arm replicates the learned trajectory. The path-demonstration tool, including optical tags (OT) and an IMU, is designed to collect trajectory data from hand motion. Sensor data fusion allows the system to track accurately the demonstrated trajectory. A calibration procedure is proposed to transform the trajectory from tool’s coordinate system to robot’s coordinate system. A cubic spline-based trajectory planning method is proposed to ensure smooth reproduction of the learned trajectory in both time and space. Experimental results show that the robot is able to replicate squared and curved trajectories collected from the path-demonstration tool. The average position error is within 2.435 mm in XYZ directions and the average orientation error is within 0.65 degrees.

关键词： Trajectory planning Tracking Robot kinematics Transforms Sensor fusion programming Robot sensing systems Manipulators Trajectory Splines (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Decentralized TDMA for Low Power IoT Devices Based on Desynchronization of Nonlinear Oscillators

Design and Implementation of Decentralized TDMA for Low Powe...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Takuma Osada Hiroyuki Yasuda Aohan Li Song-Ju Kim Mikio Hasegawa Department of Electrical Engineering Tokyo University of Science Tokyo Japan Graduate Schools for Law and Politics The University of Tokyo Tokyo Japan Graduate School of Informatics and Engineering The University of Electro-Communications Tokyo Japan SOBIN Institute LLC Hyogo Japan

The design of medium access control protocols for the Internet of Things (IoT) has become an important issue due to the rapid growth in the number of IoT devices. Autonomous distributed time division multiple access (TDMA) has been designed in previous research, but not for IoT devices. In this study, we propose a decentralized TDMA for massiveIoT networks by applying the desynchronization phenomena of nonlinear coupled oscillators. The proposed scheme is designed and implemented on actual IoT devices. The results of numerical simulations and actual experiments using IoT devices demonstrate that the timings of packet transmission of the IoT devices can be desynchronized like a TDMA system for both cases static and dynamic networks.

关键词： Performance evaluation Time division multiple access Protocols Error analysis Numerical simulation Media Access Protocol Timing

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Sleep Detection Problems

Federated Learning for Sleep Detection Problems

引用

International Conference on Smart Computing (SMARTCOMP)

作者： Guilherme Antonio Borges Julio Cesar Santos dos Anjos Jorge Sá Silva Department of Electrical and Computer Engineering University of Coimbra Coimbra Portugal Federal Institute Sul-rio-grandense (IFSUL) Rio Grande Sul Brazil Graduate Program Teleinformatics Engineering Federal University of Ceara Fortaleza Brazil Department of Electrical and Computer Engineering (DEEC) University of Coimbra Coimbra Portugal

ISBN: (数字)9798350349948

ISBN: (纸本)9798350349955

Human-in-the-loop cyber-physical Systems use data from various sources to provide valuable assistance to users, but privacy concerns arise when sensitive information is shared. Federated Learning is a promising solution that enables the processing of user data without sharing sensitive information. While this method holds great potential, its efficacy in detecting sleep problems remains an open question. In this way, using a real-world dataset application, our study meticulously evaluates and comprehends the impact of incorporating Federated Learning on sleep detection. Our study evaluates the impact of incorporating Federated Learning on sleep detection and compares it with traditional Machine Learning models. Our findings reveal that our approach delivers accurate sleep detection results over 84% on par with conventional techniques. Our results emphasize the critical importance of handling human error inputs, as this factor significantly influences the accuracy of results in both methods.

关键词： Data privacy Accuracy Uncertainty Data analysis Federated learning Flowering plants Data models

来源：评论

学校读者我要写书评

暂无评论

HAGrasp: Hybrid Action Grasp Control in Cluttered Scenes using Deep Reinforcement Learning

HAGrasp: Hybrid Action Grasp Control in Cluttered Scenes usi...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Kai-Tai Song Hsiang-Hsi Chen Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Degree Program of Robotics National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Robotic autonomous grasp requires the system to perform multiple functions such as gripper and robot control, making it a task with hybrid output nature. Existing methods based on closed-loop deep reinforcement learning rely on external models for termination evaluation. To achieve more effective grasp for novel objects, we propose a new autonomous grasp control scheme termed HAGrasp that considers the complete point cloud of the workspace. It integrates grasp pose estimation, end-effector pose evaluation, and motion planning of the robotic arm into a single model, enhancing the success rate while reducing computational load. We present a closed-loop grasp control system based on deep reinforcement learning. This control system can perform grasp tasks while dynamically adjusting to avoid end-effector collisions. The design of hybrid-action reinforcement learning module is trained with unified latent action space and further improve generalization, achieving real-time autonomous grasp control. Real robot experiments show that our method has 74.2% success rate for grasping 7 unseen objects. Comparative experiments show that the proposed HAGrasp outperforms open-loop baseline Contact-Graspnet in both success rate and inference time. It is demonstrated that with integrated multi-view input and sim-to-real training design, our method improves real-world applications of autonomous grasp.

关键词： Training Point cloud compression Robot control Pose estimation Deep reinforcement learning End effectors Real-time 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：