检索结果-内蒙古大学图书馆

On the convergence and sample efficiency of variance-reduced policy gradient method

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Junyu Ni, Chengzhuo Yu, Zheng Szepesvari, Csaba Wang, Mengdi Department of Electrical and Computer Engineering Princeton University Department of Industrial Systems Engineering and Management National University of Singapore Department of Electrical and Computer Engineering Princeton University Department of Computer Science University of Alberta Deepmind Department of Electrical and Computer Engineering Princeton University Deepmind

Policy gradient (PG) gives rise to a rich class of reinforcement learning (RL) methods. Recently, there has been an emerging trend to accelerate the existing PG methods such as REINFORCE by the variance reduction techniques. However, all existing variance-reduced PG methods heavily rely on an uncheckable importance weight assumption made for every single iteration of the algorithms. In this paper, a simple gradient truncation mechanism is proposed to address this issue. Moreover, we design a Truncated Stochastic Incremental Variance-Reduced Policy Gradient (TSIVR-PG) method, which is able to maximize not only a cumulative sum of rewards but also a general utility function over a policy's long-term visiting distribution. We show an Õ(ϵ−3) sample complexity for TSIVR-PG to find an ϵ-stationary policy. By assuming the overparameterizaiton of policy and exploiting the hidden convexity of the problem, we further show that TSIVR-PG converges to global ϵ-optimal policy with Õ(ϵ−2) samples. © 2021, CC BY.

关键词： Stochastic systems

Analysis of Some Parameters of Synthesized Anodized Aluminum Oxide Matrices 17

学校读者我要写书评

暂无评论

Analysis of Some Parameters of Synthesized Anodized Aluminum...

17th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and computer engineering, TCSET 2024

作者： Bukliv, Roxoliana Adamiv, Volodymyr Bordun, Ihor Andrushchak, Nazariy Teslyuk, Ihor Andrushchak, Anatoliy Institute of Chemistry and Chemical Technologies Lviv Polytechnic National University Department of Chemistry and Technology of Inorganic Substances Lviv Ukraine O. G. Vlokh Institute of Physical Opics Ivan Franko National University of Lviv Lviv Ukraine Czestochowa University of Technology Department of Electrical Power Engineering Czestochowa Poland Lviv Polytechnic National University Department of Ecology and Sustainable Environmental Management Lviv Ukraine Lviv Politechnic National University Computer-Aided Design Systems Lviv Ukraine Lviv Polytechnic National University Department of Applied Physics and Nanomaterials Science Lviv Ukraine

ISBN: (纸本)9798331520564

Studies have been conducted on anodized aluminum oxide (AAO) nanomatrices manufactured by SmartMembranes (SM) (Germany) and InRedox (USA). An X-ray fluorescence analyzer determined the quantitative and qualitative composition of AAO matrices. It is shown that the AAO matrices have a large transparency window (250 - 2750 nm) and the dependence of the second harmonic generation (SHG) signal on the pore size. The parameters of the porous structure of the samples were estimated by isothermal processes of nitrogen adsorption/desorption at its boiling point (T = 77 K). © 2024 IEEE.

关键词： Harmonic generation

H observer-based control for fuzzy Hadamard fractional-order systems

学校读者我要写书评

暂无评论

Computational and Applied Mathematics 2025年第4期44卷 1-14页

作者： Rhaima, Mohamed Gassara, Hamdi Mchiri, Lassaad El Hajjaji, Ahmed Ben Makhlouf, Abdellatif Department of Statistics and Operations Research College of Science King Saud University Riyadh Saudi Arabia Laboratory of Sciences Techniques of Automatic Control and Computer Engineering National School of Engineering of Sfax University of Sfax Sfax Tunisia Panthéon-Assas University Paris II Paris France Modeling Information and Systems Laboratory University of Picardie Jules Verne UFR of Sciences Amiens France Department of Mathematics Faculty of Sciences Sfax University Sfax Tunisia

While the $$H_\infty $$ observer-based control has found widespread application in the literature for integer-order systems, researchers have shown less interest in addressing the same issue within the fractional-order framework. In this context, this study delves into the application of $$H_\infty $$ observer-based control for the Hadamard fractional-order system (HFOS) described by the Takagi–Sugeno fuzzy models (TSFM). Using Lyapunov approach and by employing a matrix decoupling technique, LMI based conditions ensuring the existence of an observer and controller, are proposed. To minimize the impact of disturbances on the controlled output, $$H_\infty $$ optimization technique is used. The validity of our approach is substantiated through an example, underscoring the robustness and reliability of our proposed findings.

关键词：

Olive Disease Classification Based on VGGNET and Fine-Tuning Process

学校读者我要写书评

暂无评论

Olive Disease Classification Based on VGGNET and Fine-Tuning...

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： N. Dhaffouli S. Hidouri N. Nasri Telecommunications Departement Higher Institute Applied Science and Technology Gafsa University Gafsa Tunisia SETIT Laboratory on Smart Systems for Engineering & E-Health Sfax Tunisia Department of Computer Sciences Campus Universitaire Sidi Ahmed Zarrouk Gafsa Tunisia

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

Agriculture serves as a fundamental pillar of Tunisia’s economy, providing employment and livelihood for a large segment of the population, thereby making it an essential sector for the country. Nevertheless, the sector faces challenges such as reduced agricultural output and quality due to factors like pesticide usage, water scarcity, climate change, and notably, plant diseases. These plant diseases represent one of the most significant threats to global agricultural productivity and quality. Traditional methods of plant disease detection heavily rely on expert identification, which can quickly cause delays in field management and crop disease control. The best strategy to manage these diseases and reduce crop loss is to put protective measures in place as soon as possible. To this purpose, machine learning and deep learning models-based method for the detection and classification of olive leaf disease is developed in order to improve the speed and precision of disease classification. In this study, we explore how machine learning and deep learning techniques may be used to improve agricultural practices and solve these issues. We specifically review the state-of-the-art literature on the use of deep learning and machine learning algorithms in diverse agricultural applications. We also presented a novel method for categorizing olive leaf diseases, by integrating deep learning architectures, VGG16, and fine tuning. Also, in this approach, we simulated a total of two distinct deep models utilizing pre-trained convolutional neural network architectures (VGG19 and VGG16) and along with four machine learning classifiers (RF, SVM, KNN and DT). In addition, we simulated a novel method for categorizing olive leaf diseases, by integrating deep learning architectures, VGG16, and fine tuning, our results findings showed that VGG16 with fine-tuning classifier is the best method for classification of healthy and diseased plant leaves. It achieves a testing accuracy score of 98%

关键词： Deep learning Support vector machines Plant diseases Accuracy Crops Nearest neighbor methods Loss measurement Tuning Testing Classification tree analysis

Star-Searcher: A Complete and Efficient Aerial System for Autonomous Target Search in Complex Unknown Environments

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Luo, Yiming Zhuang, Zixuan Pan, Neng Feng, Chen Shen, Shaojie Gao, Fei Cheng, Hui Zhou, Boyu Sun Yat-Sen University China State Key Laboratory of Industrail Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

This paper tackles the challenge of autonomous target search using unmanned aerial vehicles (UAVs) in complex unknown environments. To fill the gap in systematic approaches for this task, we introduce Star-Searcher, an aerial system featuring specialized sensor suites, mapping, and planning modules to optimize searching. Path planning challenges due to increased inspection requirements are addressed through a hierarchical planner with a visibility-based viewpoint clustering method. This simplifies planning by breaking it into global and local sub-problems, ensuring efficient global and local path coverage in real-time. Furthermore, our global path planning employs a history-aware mechanism to reduce motion inconsistency from frequent map changes, significantly enhancing search efficiency. We conduct comparisons with state-of-the-art methods in both simulation and the real world, demonstrating shorter flight paths, reduced time, and higher target search completeness. Our approach will be open-sourced for community benefit. Copyright © 2024, The Authors. All rights reserved.

关键词： Stars

Swin Transformer-Based Dynamic Semantic Communication for Multi-User with Different Computing Capacity

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Nguyen, Loc X. Tun, Ye Lin Tun, Yan Kyaw Nguyen, Minh N.H. Zhang, Chaoning Han, Zhu Hong, Choong Seon The Department of Computer Science and Engineering Kyung Hee University Gyeonggi-do Yongin-si17104 Korea Republic of The Division of Network and Systems Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Brinellvägen 8 Stockholm114 28 Sweden The Digital Science and Technology Institute The University of Danang Vietnam-Korea University of Information and Communication Technology Da Nang550000 Viet Nam The Department of Artificial Intelligence School of Computing Kyung Hee University Yongin-si17104 Korea Republic of The Electrical and Computer Engineering Department University of Houston HoustonTX77004 United States

Semantic communication has gained significant attention from researchers as a promising technique to replace conventional communication in the next generation of communication systems, primarily due to its ability to reduce communication costs. However, little literature has studied its effectiveness in multi-user scenarios, particularly when there are variations in the model architectures used by users and their computing capacities. To address this issue, we explore a semantic communication system that caters to multiple users with different model architectures by using a multi-purpose transmitter at the base station (BS). Specifically, the BS in the proposed framework employs semantic and channel encoders to encode the image for transmission, while the receiver utilizes its local channel and semantic decoder to reconstruct the original image. Our joint source-channel encoder at the BS can effectively extract and compress semantic features for specific users by considering the signal-to-noise ratio (SNR) and computing capacity of the user. Based on the network status, the joint source-channel encoder at the BS can adaptively adjust the length of the transmitted signal. A longer signal ensures more information for high-quality image reconstruction for the user, while a shorter signal helps avoid network congestion. In addition, we propose a hybrid loss function for training, which enhances the perceptual details of reconstructed images. Finally, we conduct a series of extensive evaluations and ablation studies to validate the effectiveness of the proposed system. Copyright © 2023, The Authors. All rights reserved.

关键词： Image reconstruction

Personalised and Adjustable Interval Type-2 Fuzzy-Based PPG Quality Assessment for the Edge

学校读者我要写书评

暂无评论

Personalised and Adjustable Interval Type-2 Fuzzy-Based PPG ...

IEEE International Conference on Fuzzy systems (FUZZ-IEEE)

作者： Jose A. Miranda Celia López-Ongil Javier Andreu-Perez Embedded Systems Laboratory EPFL Laussane Switzerland Electronic Technology Department Universidad Carlos III of Madrid Leganés Spain School of Computer Science and Electronic Engineering University of Essex Colchester UK

Most of today's wearable technology provides seamless cardiac activity monitoring. Specifically, the vast majority employ Photoplethysmography (PPG) sensors to acquire blood volume pulse information, which is further analysed to extract useful and physiologically related features. Nevertheless, PPG-based signal reliability presents different challenges that strongly affect such data processing. This is mainly related to the fact of PPG morphological wave distortion due to motion artefacts, which can lead to erroneous interpretation of the extracted cardiac-related features. On this basis, in this paper, we propose a novel personalised and adjustable Interval Type-2 Fuzzy Logic System (IT2FLS) for assessing the quality of PPG signals. The proposed system employs a personalised approach to adapt the IT2FLS parameters to the unique characteristics of each individual's PPG signals. Additionally, the system provides adjustable levels of personalisation, allowing healthcare providers to adjust the system to meet specific requirements for different applications. The proposed system obtained up to 93.72% for average accuracy during validation. The presented system has the potential to enable ultra-low complexity and real-time PPG quality assessment, improving the accuracy and reliability of PPG-based health monitoring systems at the edge.

关键词：

A Switch Architecture for Time-Triggered Transmission with Best-Effort Delivery

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Zonghui Zhu, Wenlin Shin, Kang G. Wan, Hai Song, Xiaoyu Yang, Dong Ai, Bo The Beijing Key Laboratory of Transportation Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China The Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109-2121 United States The Software School Tsinghua University Beijing100084 China The Department of Electrical and Computer Engineering Portland State University PortlandOR United States The School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China

In Time-Triggered (TT) or time-sensitive networks, the transmission of a TT frame is required to be scheduled at a precise time instant for industrial distributed real-time control systems. Other (or best-effort (BE)) frames are forwarded in a BE manner. Under this scheduling strategy, the transmission of a TT frame must wait until its scheduled instant even if it could have been transmitted sooner. On the other hand, BE frames are transmitted whenever possible but may miss deadlines or may even be dropped due to congestion. As a result, TT transmission and BE delivery are incompatible with each other. To remedy this incompatibility, we propose a synergistic switch architecture (SWA) for TT transmission with BE delivery to dynamically improve the end-to-end (e2e) latency of TT frames by opportunistically exploiting BE delivery. Given a TT frame, the SWA generates and transmits a cloned copy with BE delivery. The first frame arriving at the receiver device is delivered with a configured jitter and the other copy ignored. So, the SWA achieves shorter latency and controllable jitter, the best of both worlds. We have implemented SWA using FPGAs in an industry-strength TT switches and used four test scenarios to demonstrate SWA's improvements of e2e latency and controllable jitter over the state-of-the-art TT transmission scheme. Copyright © 2023, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

A Comparison of CdS and Zn(O,S) Buffer Layers in (Ag,Cu)(In,Ga)Se2 Solar Cells

学校读者我要写书评

暂无评论

A Comparison of CdS and Zn(O,S) Buffer Layers in (Ag,Cu)(In,...

IEEE Conference Photovoltaic Specialists (PVSC)

作者： Michael F. Miller Ana Kanevce Marzieh Baan Rico Gutzler Darius Kuciauskas Theresa Magorian Friedlmeier Tyler J. Grassman Aaron R. Arehart Department of Electrical & Computer Engineering The Ohio State University Columbus OH USA Zentrum fuer Sonnenenergie-und Wasserstoff-Forschung (ZSW) Stuttgart Germany Department of Materials Science & Engineering The Ohio State University Columbus OH USA National Renewable Energy Laboratory Golden CO USA

ISBN: (数字)9781665464260

ISBN: (纸本)9781665475822

Cu(In,Ga)Se 2 -based solar cells typically use a $C$ dS buffer layer, even though its relatively low bandgap causes parasitic absorption. While alternatives to CdS have been explored in other studies, limited results have been shown for Ag-alloyed CIGS (ACIGS). In this study, ACIGS solar cells with both CdS and Zn(O,S) buffer layers were fabricated and compared for solar cell performance. The Zn(O,S) buffer slightly improved J sc through reduced absorption, although surface optimization is necessary. The Zn(O,S) ACIGS also had improved FF through reduced series resistance and ideality factor, which could be improved further through optimization. However, the Voc in the Zn(O,S) samples was reduced, likely due to increased bulk and front interface recombination. This study shows the promise of Zn(O,S) as a buffer layer in ACIGS solar cells and suggests pathways for further improvement.

关键词： Buffer layers Photovoltaic systems Absorption Photonic band gap Photovoltaic cells Surface resistance Loss measurement Capacitance measurement Optimization