检索结果-内蒙古大学图书馆

Nonlinear Value Function Approximation Method with Easy Hyperparameter Tuning and Convergence Guarantee

IEEE Access 2025年 13卷 30117-30126页

作者： Watabe, Yuuya Shibuya, Takeshi University of Tsukuba Master's Program in Intelligent and Mechanical Interaction Systems Ibaraki305-8577 Japan University of Tsukuba Institute of Systems and Information Engineering Ibaraki305-8577 Japan

Reinforcement Learning is a branch of machine learning to learn control strategies that achieve a given objective through trial-And-error in the environment. Because this can be applicable even when the state transition function of the control object is unknown or it is difficult to create its model properly, this can reduce the designer's burden. Reinforcement learning repeats evaluating a policy and improving it based on that evaluation. An algorithm called value function approximation is used in this evaluation. Value function approximation is a general term for algorithms of approximating a function called value function, which maps an arbitrary state to how much reward can be obtained in the future when acting according to a policy from that state. Value function approximation should have high approximation accuracy and hyperparameter easy to tune. Although various value function approximation methods have been proposed so far, some of them does not have convergent guarantee and the others' hyperparameter tuning is difficult. The purpose of this paper is to propose a value function approximation method that have convergence guarantee even with nonlinear function approximator and whose hyperparameter tuning is easy and to verify its performance through numerical experiments. To this end, we focused on GTD2 method, which is one of the value function approximation methods that has convergence guarantee even with a nonlinear function approximator. GTD2 method has the drawback that its hyperparameter is difficult to tune appropriately so that the approximation does not diverge during learning. Therefore, we firstly clarified the cause of the divergence of GTD2 method. Secondly, based on this cause, we proposed Normalized and Regularized GTD2 (NRGTD2) method, that incorporates a method for suppressing divergence into GTD2 method. Finally, through numerical experiments, it was clarified that the proposed method suppresses the divergence and can achieve better approxim

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Techno-economic analysis of green hydrogen production by a floating solar photovoltaic system for industrial decarbonization

引用

Clean Energy 2024年第4期8卷 1-14页

作者： Rahma Muthia Anastasia Segari Putri Pramudya Mochamad Rafly Maulana Widodo Wahyu Purwanto Department of Chemical Engineering Faculty of EngineeringUniversitas IndonesiaDepok16424Indonesia Sustainable Energy Systems and Policy Research Cluster Universitas IndonesiaDepok16424Indonesia Master Program in Energy Systems Engineering Faculty of EngineeringUniversitas IndonesiaDepok16424Indonesia

This study proposes a conceptual design of green hydrogen production via proton exchange membrane electrolysis powered by a floating solar photovoltaic *** system contributes to industrial decarbonization in which hydrogen blending with natural gas is proposed as an approach to smooth the energy *** proposed design addresses the challenge of supplying a continuous flow-rate of green hydrogen,which is typically demanded by industrial end *** study particularly considers a realistic area required for the installation of a floating solar photovoltaic *** enable the green hydrogen production of 7.5 million standard cubic feet per day,the required structure includes the floating solar photovoltaic system and Li-ion batteries with the nominal capacities of 518.4 megawatts and 780.8 *** is equivalent to the requirement for 1524765 photovoltaic modules and 3718 Li-ion *** assessment confirms the technical viability of the proposed concept of green hydrogen production,transportation and *** the present commercialization is hindered by economics due to a high green hydrogen production cost of USD 26.95 per kg,this green hydrogen pathway is expected to be competitive with grey hydrogen produced via coal gasification and via natural gas steam reforming by 2043 and 2047,respectively.

关键词： floating solar photovoltaics gas blending green hydrogen industrial decarbonization lithium-ion battery photon exchange membrane electrolysis

来源：评论

学校读者我要写书评

暂无评论

Techno-economic analysis of a hybrid renewable energy system integrated with productive activities in an underdeveloped rural region of eastern Indonesia

引用

Clean Energy 2023年第6期7卷 1247-1267页

作者： Alya Nurul Shafira Subhan Petrana Rahma Muthia Widodo Wahyu Purwanto Sustainable Energy Systems and Policy Research Cluster Universitas IndonesiaDepok16424Indonesia Chemical Engineering Department Faculty of EngineeringUniversitas IndonesiaDepok16424Indonesia Master Program in Energy Systems Engineering Faculty of EngineeringUniversitas IndonesiaDepok16424Indonesia

The Southwest Maluku region in eastern Indonesia is considered a frontier,outermost and underdeveloped *** inhabitants live on isolated islands,including the residents of Mahaleta Village,where only 9.4%of the community have limited access to *** study aimed to design an economically feasible hybrid renewable energy(RE)system based on solar and wind energy to integrate with the productive activities of the *** study developed conceptual schemes to meet the demand for electricity from the resi-dential,community,commercial and productive sectors of the *** analysis was performed using a techno-economic *** hybrid system was designed using the HOMER Pro optimization function,and cold-storage and dryer systems were designed to support related productive *** optimized design of the hybrid RE system comprised 271.62 kW of solar photovoltaics,80 kW of wind turbines and a 1-MWh lead-acid *** found that the hybrid RE system would only be economically feasible with a full-grant incentive and an electricity tariff of$0.0808/***,the productive activity schemes were all economically feasible,with a cold-storage cost of$0.035/kg and a drying cost of$0.082/*** the hybrid RE system with productive activities can improve the economic feasibility of the energy system and create more jobs as well as increase income for the local community.

关键词： underdeveloped region hybrid renewable energy system photovoltaics wind turbine Indonesia

来源：评论

学校读者我要写书评

暂无评论

Toward Parallelization Technique for Stream-based Lossless Data Compression

Toward Parallelization Technique for Stream-based Lossless D...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Kato, Taiki Yamagiwa, Shinichi Wada, Koichi Master's Program in Computer Science Degree Program in Systems and Information Engineering University of Tsukuba Ibalaki Tsukuba Japan University of Tsukuba Faculty of Engineering Information and Systems Ibalaki Tsukuba Japan

ISBN: (纸本)9798350324457

IoT edge platform has become popular in various distributed environments. The edge devices need to communicate BigData among them or with the cloud servers by collaborating with AI technologies for finding events from the applications. Those devices exchange data streams from such as distributed sensors and remote image/video devices. We focus on an acceleration technique for the communication performance using a stream-based lossless data compression technology. This paper proposes a parallelization technique for the compression process in a software environment running on a multicore processor. The technique invokes concurrent compression processes assigned to multiple threads with splitting a data stream to chunks. The paper exposes three scheduling methods for assigning the chunks to the threads: in-order, hybrid and out-of-order. As an original data order of chunks must be obtained in decompression side, the proposed technique introduces packeting mechanisms in each chunk by adding headers to support the scheduling methods. Through experimental performance evaluations, we discuss the packeting overhead focusing on compression ratio and speedup by the parallelization with three scheduling methods. © 2023 IEEE.

关键词： Data Stream IoT Lossless Data Compression Multi-Threading Parallelization

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement of Stream-Based Decompression Process by Notifying Compression Buffer Size 28

Performance Enhancement of Stream-Based Decompression Proces...

引用

28th IEEE Symposium on Computers and Communications, ISCC 2023

作者： Kato, Taiki Yamagiwa, Shinichi Marumo, Koichi University of Tsukuba Master's Program in Computer Science Degree Program in Systems and Information Engineering Ibalaki Tsukuba Japan University of Tsukuba Faculty of Engineering Information and Systems Ibalaki Tsukuba Japan

ISBN: (纸本)9798350300482

This paper focuses on a performance enhancement of communication performance by compressing data stream. ASE coding is an effective lossless data compression method for data stream. The software implementation of the coding/decoding method inevitably meets a performance mismatch in memory and storage devices. In the compressor side, it is predictable to decide the size of an original data block and is available to process a flexible buffer memory. However, the decompressor is not able to predict the buffer size because the original data size is not obvious before the decompression. This causes a performance mismatch in the filesystem level. This paper proposes a novel method to address the performance mismatch by applying a notification mechanism of compression size from the compressor. This paper describes the mechanism focusing on the system call usage. Through experimental evaluations, we show the performance improvement of the decompression performance for handling data stream. © 2023 IEEE.

关键词： Virtual storage

来源：评论

学校读者我要写书评

暂无评论

Robot Tele-Operation / Teaching System using VR Device 10

Robot Tele-Operation / Teaching System using VR Device

引用

10th IEEE International Conference on Cybernetics and Intelligent systems and IEEE Conference on Robotics, Automation and Mechatronics, CIS-RAM 2023

作者： Ohsato, Minami Aiyama, Yasumichi Master's Program in Systems and Information Engineering Tsukuba Japan University of Tsukuba Inst. of Systemsand Information Engineering Tsukuba Japan

ISBN: (纸本)9798350303087

This paper proposes a "robot tele-teaching system using a VR device"as a new robot teaching method to replace the conventional robot teaching method. Currently we still need teach-pendant to teach industrial robots. It is very inconvenient method. Our novel method consists of two robots and a VR device. One robot is on site instead of the operator. A stereo camera is attached to its end of the robot, which realizes a 3D positionand posture obtained from HMD. The operator can then view the images through the HMD as if he/she are on site. The other manipulating robot is equipped with a gripper and can follow the position and orientation of the gripper-like input device held by the operator. This system is equipped with a correction and auto-teaching function that uses the geometric characteristics of the work object. This significantly reduces the time required for operation. In addition, the teaching points obtained by this system have been successfully used for playback in a real environment. © 2023 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

A Note on Even-Sized Spectral Clustering 13

A Note on Even-Sized Spectral Clustering

引用

Joint 13th International Conference on Soft Computing and Intelligent systems and 25th International Symposium on Advanced Intelligent systems, SCIS and ISIS 2024

作者： Miyakawa, Hiroki Endo, Yasunori Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master's Program in Risk and Resilience Engineering University of Tsukuba Ibaraki Tsukuba Japan Institute of Systems and Information Engineering University of Tsukuba Ibaraki Tsukuba Japan

ISBN: (纸本)9798350373332

Clustering is a typical unsupervised learning method for classifying unsupervised data. One of the clustering meth-ods, even-sized clustering based on optimization (ECBO), is a clustering algorithm that imposes a constraint to equalize the size of each cluster. ECBO has been suggested to be effective in delivery and other problems. However, it is limited to Euclidean space. On the other hand, spectral clustering with a wide range of applicability for partitioning graph data has been proposed. In this paper, we propose even-sized spectral clustering, which imposes a size-equal constraint on spectral clustering, and show that it is an extension of the graph partitioning problem. We also verify the validity of the results through numerical examples. © 2024 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A Player Position Tracking Method Based on a Wide-Area Pan-Tilt-Zoom Video 12

A Player Position Tracking Method Based on a Wide-Area Pan-T...

引用

Proceedings of the 12th International Conference on Sport Sciences Research and Technology Support, icSPORTS 2024

作者： Yamagishi, Shunzo Xie, Chun Shishido, Hidehiko Kitahara, Itaru Master's and Doctoral Program in Intelligent Mechanical Interaction Systems University of Tsukuba Ibaraki Japan Center for Computational Sciences University of Tsukuba Ibaraki Japan Faculty of Science and Engineering Department of Information Systems Engineering Soka University Tokyo Japan

ISBN: (纸本)9789897587191

This paper proposes a method to estimate the posture of an athlete moving on a vast field in a sporting event using a pan-tilt-zoom camera. In order to estimate the posture of an athlete on a sports field from a dynamic video sequence, our method extracts image features to search correspondence points among successive frames and computes the homography transformation matrix that compensates for changes the camera parameters (e.g., angle of view and posture). The effectiveness of this method is qualitatively verified using MLB TV broadcast video. The accuracy and error factors are also quantitatively verified by CG simulation. Copyright © 2024 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Pan-Tilt-Zoom Camera Player Tracking Sports Analytics Video Processing Wide-Area

来源：评论

学校读者我要写书评

暂无评论

RUL Estimation for Power Electronic Devices Using RNNs

RUL Estimation for Power Electronic Devices Using RNNs

引用

2024 Prognostics and System Health Management Conference, PHM 2024

作者： Cai, Congrui Lu, Zhonghai School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Embedded Systems Master Program Sweden School of Electrical Engineering and Computer Science Department of Electrical Engineering KTH Royal Institute of Technology Sweden

ISBN: (纸本)9798350360585

Recurrent Neural Networks (RNNs) are commonly used in data-driven approaches to estimate the Remaining Useful Lifetime (RUL) of power electronic devices. RNNs are preferred because their intrinsic feedback mechanisms are better suited to model time-series data. However, the impact of RNN complexity on estimation accuracy is rarely discussed in the literature. This issue is important because choosing a lower-complexity model that delivers the same or similar performance as a higher-complexity model can increase implementation efficiency. In the paper, we use three RNN models, namely, the vanilla version, LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) to conduct RUL estimation for power electronic devices. We use two accelerated aging datasets, one dataset targeting the package failure of MOSFETs, and the other dataset targeting package failure of power diodes. Our study shows that a lower-complexity RNN does not necessarily deliver a lower performance. Similarly, a higher-complexity model does not assure a higher performance. As such, our work highlights the importance of selecting a proper neural network for RUL estimation not biased towards complex models. This is especially useful and important for implementing such RUL estimation techniques in embedded resource-constrained and speed-limited computins platforms. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Parallel Control System PD-SMCNN for Robust Autonomous Mini-Quadcopter 23

Parallel Control System PD-SMCNN for Robust Autonomous Mini-...

引用

23rd International Seminar on Intelligent Technology and Its Applications, ISITIA 2022

作者： Wahyuadnyana, Kadek Dwi Darwito, Purwadi Agus Physics Engineering Master Program Faculty of Industrial Technology and Systems Engineering Surabaya Indonesia Faculty of Industrial Technology and Systems Engineering Physics Engineering Department Surabaya Indonesia

ISBN: (数字)9781665460811

ISBN: (纸本)9781665460811

A parallel control system with proportional-derivative (PD) and sliding mode control-neural network (SMCNN) has been designed to control the position and attitude of mini-quadcopter parrot mambo mini-drone (PMD). This PDSMCNN control scheme is implemented in the PMD system through a 3D environment using MATLAB-Simulink, which represented the real conditions. The PD controller is used to reach the minimum value of the gain for the PMD getting to take-off, while the SMC as a robust controller is adjusted using a backpropagation neural network (NN) to make the PMD more robust regarding an external disturbance. The software and hardware simulation have been conducted to validate the proposed controller with a mission plan as an input. Based on the simulation results, the PD controller shows an overshoot of 26.7% then becomes 0% of overshoot when the PD-SMCNN controller is implemented. From the hardware simulation results, it is found that the PD controller has 45.1% of robustness and the PD-SMCNN controller has 100% of robustness in the absence of external disturbance. Next, it is found that the PD controller has 26.9% of robustness and the PD-SMCNN has 74.8% of robustness in the presence of external disturbance. Based on these results, indicates that the proposed PD-SMCNN controller is superior to the PD controller in terms of robustness. © 2022 IEEE.

关键词： Neural networks

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：