检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Chen, Zixiang Li, Chris Junchi Yuan, Angela Gu, Quanquan Jordan, Michael I. Department of Computer Science University of California Los Angles United States Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Department of Statistics University of California Berkeley United States

With the increasing need for handling large state and action spaces, general function approximation has become a key technique in reinforcement learning (RL). In this paper, we propose a general framework that unifies model-based and model-free RL, and an Admissible Bellman Characterization (ABC) class that subsumes nearly all Markov Decision Process (MDP) models in the literature for tractable RL. We propose a novel estimation function with decomposable structural properties for optimization-based exploration and the functional eluder dimension as a complexity measure of the ABC class. Under our framework, a new sample-efficient algorithm namely OPtimization-based ExploRation with Approximation (OPERA) is proposed, achieving regret bounds that match or improve over the best-known results for a variety of MDP models. In particular, for MDPs with low Witness rank, under a slightly stronger assumption, OPERA improves the state-of-the-art sample complexity results by a factor of dH. Our framework provides a generic interface to design and analyze new RL models and algorithms. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PharmaChain 3.0: Blockchain Integrated Efficient QR Code Mechanism for Pharmaceutical Supply Chain 20

PharmaChain 3.0: Blockchain Integrated Efficient QR Code Mec...

引用

20th OITS International Conference on Information Technology, OCIT 2022

作者： Bapatla, Anand Kumar Mohanty, Saraju P. Kougianos, Elias Puthal, Deepak University of North Texas Department of Computer Science and Engineering United States University of North Texas Department of Electrical Engineering United States Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates

ISBN: (纸本)9781665493482

Because of globalization, many different entities distributed across the locations were able to work together and achieve the availability of services even at remote locations. Supply Chains helped in leveraging such businesses globally with reduced costs and increased efficiency. Pharmaceutical Supply Chain (PSC) is one in which the prescription drugs are moved from the manufacturer to the patient. Providing the right medicine at the right time to the right patient in the right doses coming from the right route is called the five rights of medication. Due to the increased number of participating entities, and interactions between entities and adversaries trying to profit by introducing counterfeit drugs into the supply chain, efficient tracking and tracing mechanism is very much needed in PSC. The current paper proposes an architecture that is integrated with Blockchain, Inter Planetary File System (IPFS) along with QR code technologies to provide a secure QR code mechanism for addressing such tracking and tracing issues in PSC. The proposed model is evaluated for security and efficiency using different metrics. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Scattering exceptional point in the visible

引用

Light(science & Applications) 2023年第10期12卷 2228-2235页

作者： Tao He Zhanyi Zhang Jingyuan Zhu Yuzhi Shi Zhipeng Li Heng Wei Zeyong Wei Yong Li Zhanshan Wang Cheng-Wei Qiu Xinbin Cheng MOE Key Laboratory of Advanced Micro-Structured Materials Shanghai 200092China Institute of Precision Optical Engineering School of Physics Science and EngineeringTongji UniversityShanghai 200092China Shanghai Institute of Intelligent Science and Technology Tongji UniversityShanghai 200092China Shanghai Frontiers Science Center of Digital Optics Shanghai 200092China Shanghai Professional Technical Service Platform for Full-Spectrum and High-Performance Optical Thin Film Devices and Applications Shanghai 200092China Department of Electronic Science and Technology Tongji UniversityShanghai 201804China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Institute of Acoustics School of Physics Science and EngineeringTongji UniversityShanghai 200092China

Exceptional point (EP) is a special degeneracy of non-Hermitian systems. One-dimensional transmission systems operating at EPs are widely studied and applied to chiral conversion and sensing. Lately, two-dimensional systems at EPs have been exploited for their exotic scattering features, yet so far been limited to only the non-visible waveband. Here, we report a universal paradigm for achieving a high-efficiency EP in the visible by leveraging interlayer loss to accurately control the interplay between the lossy structure and scattering lightwaves. A bilayer framework is demonstrated to reflect back the incident light from the left side ( | r_(−1) | >0.999) and absorb the incident light from the right side ( | r_(+1) | < 10^(–4)). As a proof of concept, a bilayer metasurface is demonstrated to reflect and absorb the incident light with experimental efficiencies of 88% and 85%, respectively, at 532 nm. Our results open the way for a new class of nanoscale devices and power up new opportunities for EP physics.

关键词： visible exceptional incident

来源：评论

学校读者我要写书评

暂无评论

Image Visibility Patch Aided Hydrophobic Class Detection of Silicone Rubber Insulators Employing Bi-LSTM Network 3

Image Visibility Patch Aided Hydrophobic Class Detection of ...

引用

3rd IEEE International Conference on Smart Technologies for Power, Energy and Control, STPEC 2023

作者： Roy, Sayanjit Singha Paramane, Ashish Ganguly, Biswarup Das, Arup Kumar Paul, Subho Chatterjee, Soumya National Institute of Technology Silchar Electrical Engineering Department Assam Silchar India Electrical and Computer Engineering FAMU-FSU College of Engineering TallahasseeFL United States Washington State University Pullman School of Electrical Engineering and Computer Science PullmanWA United States National Institute of Technology Durgapur Department of Electrical Engineering Durgapur India

ISBN: (纸本)9798350304732

Precise detection of hydrophobicity grades (HGs) of silicone rubber insulator is necessary to prevent premature tripping of transmission lines. Keeping this in mind, in this paper, a novel HG detection framework employing image visibility graph is proposed for remote health diagnosis of silicone rubber insulators. To this end, an experiment has been designed to acquire surface images from 11kV silicone rubber suspension insulators representing different HGs. Following this, the captured images were suitably pre-processed and were further analyzed using image visibility graph (IVG). The IVG converts the captured images to a topological network preserving their pixel information. In this study, image visibility patches (s) were extracted from different IVG transformed HG images to quantify intricate pixel-level alterations taking place between different HGs on a local scale. The extracted VPS were utilized as inputs to a bi-directional long short-term memory (bi-LSTM) network for classification of HGs. Comparing against existing methods revealed that the proposed HG detection methodology is superior indicating its potential application for remote health diagnosis of outdoor insulators. © 2023 IEEE.

关键词： Condition monitoring hydrophobicity image visibility graph polymeric insulator visibility patch

来源：评论

学校读者我要写书评

暂无评论

SmartInsure: Blockchain and CNN Leveraged Secure and Efficient Cattle Insurance 21

SmartInsure: Blockchain and CNN Leveraged Secure and Efficie...

引用

21st OITS International Conference on Information Technology, OCIT 2023

作者： Bapatla, Anand Kumar Gupta, Aishani Mohanty, Saraju P. Kougianos, Elias University of North Texas Department of Computer Science and Engineering United States University of North Texas Texas Academy of Mathematics and Science United States University of North Texas Department of Electrical Engineering United States

ISBN: (纸本)9798350358230

Agriculture is one of the significant industries that encompasses various activities including crop cultivation and livestock farming to provide necessary resources to societies. Along with providing necessary resources for global stability and sustenance it also serves as the backbone for several countries economies. Agriculture is highly dependent on unpredictable weather and climatic events, making mitigation techniques futile. Due to these uncertainties, many farmers face various hardships when attempting to meet the expected yield and finances. Another major factor influencing livestock farming, especially livestock, is the spread of viral diseases like Bovine Respiratory Disease (BRD) and Foot-And-Mouth Disease (FMD). Livestock insurance is a specific type of insurance within broader agriculture insurance that serves several critical purposes for farmers such as risk mitigation, financial stability, Investment confidence, etc. Currently employed cattle insurance systems are centralized and involve multiple parties exchanging information and payments. These entities include farmers, insurers, veterinarians, and regulatory agencies which are geographically apart and cause significant delays and administrative costs. Hence, a Blockchain and Convolution Neural Network (CNN) leveraged solution SmartInsure is proposed to increase transparency, data integrity, and efficiency, along with a fool-proof way of identifying the insured cattle. The identification of cattle is a major problem in cattle insurance and the lack of a robust identification system can lead to insurance fraud. Hence CNN-based cattle identification using muzzle images can be an effective solution for avoiding such conflicts while processing insurance claims. Considering the cost-effectiveness of the proposed SmartInsure, off-chain distributed data storage is employed for storing muzzle images of insured cattle. Proposed SmartInsure Proof-of-Concept (POC) is designed, and functional analysis is perfo

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Design and Fabrication of Bengali Braille Embosser Using Solenoid 9

Design and Fabrication of Bengali Braille Embosser Using Sol...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Momin, Reshad Ibn Das, Ratan Kumar Raxit, Sourav Muna, Umme Salma Al Miraj, Abdullah University of Southern Denmark-SDU Dept. of Mechanical & Electrical Engineering Sønderborg Denmark Chittagong University of Engineering & Technology Dept. of Mechanical Engineering Chattogram4349 Bangladesh University of New Orleans Department of Computer Science United States American International University Dept. of Computer Science & Engineering Dhaka Bangladesh Chittagong University of Engineering & Technology Dept. of Electrical & Electronic Engineering Chattogram4349 Bangladesh

ISBN: (纸本)9798350394474

This paper presents the design and development of a low-cost and user-friendly Bengali braille embosser for the visually impaired population in Bangladesh. To produce braille text, the embosser employs a shifting mechanism and an Embosser head, both controlled by an Arduino microcontroller. A software has also been developed to allow users with basic printer knowledge to operate the embosser. Access to educational resources and reading materials is limited for people with disabilities in Bangladesh, and the availability of Bengali braille writing machines is scarce. The proposed solution aims to address these challenges and improve the learning and communication capabilities of visually impaired individuals. © 2024 IEEE.

关键词： arduino braille embosser portable speed

来源：评论

学校读者我要写书评

暂无评论

A Stimulus Analysis for Sustaining Attention of Video Lecture Learners 15th

A Stimulus Analysis for Sustaining Attention of Video Lectur...

引用

15th International Conference on computer science and its Applications, CSA 2023 and 17th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2023

作者： Roh, Kyoungeui Park, Ji Su Kang, Jungho Shon, Jin Gon Advanced Convergence Technology Laboratory Korea National Open University Seoul Korea Republic of Department of Computer Science and Engineering Jeonju University Jeonju-si Korea Republic of Department of Software Engineering Baewha Woman University Seoul Korea Republic of Department of Computer Science Graduate School Korea National Open University Seoul Korea Republic of

ISBN: (纸本)9789819724468

There is a concern about the learner effectiveness in video lecture. The ability of learners to effectively engage is influenced by the time they can sustain their attention. However, learners watching video lectures often struggle to maintain their attention after a certain period of time. This is primarily because video lectures are created without taking into consideration the time learners can sustain their attention. This study aims to investigate what kind of stimuli could be presented to learners during video lectures to help them sustain their attention. This study designs five experimental stimuli to be presented during video lectures playback and measures the time learners sustain attention for each stimulus. The experimental results show that when video lecture learners are received simultaneous visual stimulus in the form of dynamic text and auditory stimulus in the form of voiceover, the time they sustain attention in video lectures is the longest. This suggests that presenting dynamic text and voiceover simultaneously during video lectures can be the most effective strategy to sustain learners’ attention. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Real-time behavior recognition of animal: an IoT-based system design using acceleration data

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Tran, Duc-Nghia Manh, Do Viet Van Thanh, Pham Shankar, A. Achyut Joshi, Kireet Tran, Duc-Tan Institute of Information Technology Vietnam Academy of Science and Technology Hanoi Viet Nam University of Fire Prevention and Fighting Hanoi100000 Viet Nam Department of Cyber Systems Engineering WMG University of Warwick CoventryCV74AL United Kingdom Department of CSE University Centre for Research & ampDevelopment Chandigarh University Punjab Mohali140413 India School of Computer Science Engineering Lovely Professional University Punjab Phagwara144411 India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun248002 India Center of Research Impact and Outcome Chitkara University Punjab Chandigarh India Department of Computer Science & amp Engineering Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Faculty of Electrical and Electronic Engineering Phenikaa University Hanoi12116 Viet Nam

By analyzing large amounts of animal behavior data, humans can assess cattle’s condition. It leads to research and development a field using accelerometers and machine learning algorithms to ‘study’ behavior from acceleration data. It is challenging to analyze animal behavior due to the activity complexity. For example, acceleration data of some cow behaviors (e.g., feeding and standing) are similar if these behaviors contain similar gestures. In practical, real-time applications even bring more challenging since it is necessary to minimize a data window for behavior consideration. Using short data window often reduces the performance of classification algorithms. This study proposes a new solution for the mentioned challenges by combining neck-mounted and leg-mounted accelerometers, then using the vector of the dynamic body acceleration (VeDBA) and Mean features of synchronized acceleration data for the Decision Tree algorithm. The proposed method is demonstrated that performs well (0.94 accuracy, 0.91 sensitivity, 0.90 positive predictive value) within a low computational complexity algorithm and short data window (3-second data window, at the rate of one sample per second). It is particularly suited for the case of a real-time IoT-based system. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Fault Detection and Diagnosis in Automotive Control Systems using Machine Learning

Fault Detection and Diagnosis in Automotive Control Systems ...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Jawalkar, Anil Pandurang Kumar, S Kiran Deshmukh, Ram Mounika, P. Manohara, H.T. Malla Reddy Engineering College for Women It Department Hyderabad India Cmr Engineering College Department of Computer Science and Engineering Hyderabad India Sr University Department of Electrical and Electronics Engineering Warangal India Cmr Technical Campus Department of Computer Science and Engineering Hyderabad India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350313413

The Software Fault detection and diagnosis approaches supports to find the fault vulnerable constituents in the software development in early stages. An effective diagnosis approach can support test administrators to locate defects and defect-vulnerable software modules. The Feature Extraction (FE) process is the applicable solution to solve high dimensionality and polynomial time complexity issue in the prediction of software defect. In this research, a new fault detection approach is proposed by utilizing the Stacked Auto Encoder (SAE) with Support Vector Machine (SVM) and Artificial Neural Network (ANN). In this approach, the ANN is utilized for the diagnosis process to distribute the data named the fault type. Now, the input generates the Deep Neural Network as well as fuzzy depiction process. the outcome of these approaches is then integrated by the dense connected layers. The proposed SAE based SVM-ANN model attains better results by utilizing evaluation metrics like Accuracy, Precision, F1-score, and Area Under Curve (AUC) values about 99.87%, 99.52%, 99.82% and 0.99 respectively which is comparatively higher than existing techniques like Unsupervised Learning, SVM, Generative Adversarial Neural Network. © 2023 IEEE.

关键词： Artificial Neural Network Fault detection Fault diagnosis Stacked Auto Encoder and Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

A Study on Energy Preservability of Runge-Kutta Methods in Power System Simulation

A Study on Energy Preservability of Runge-Kutta Methods in P...

引用

2022 IEEE Power and Energy Society General Meeting, PESGM 2022

作者： Huang, Kaiyang Sun, Kai University of Tennessee Department of Electrical Engineering and Computer Science KnoxvilleTN United States

ISBN: (数字)9781665408233

ISBN: (纸本)9781665408233

Runge-Kutta methods have been widely used in power system time-domain simulations. However, conventional Runge-Kutta methods can not preserve the total energy of the simulated system because they are not symplectic integrators. For the explicit Euler method and fourth-order Runge-Kutta method, this paper first finds explicit formulae on how the total energy of the simulated system trajectory can change with the integration time step by using the Hamiltonian system formulation of a single-machine-infinite-bus system. The formulae discover the existence of a critical time step for energy-preserving simulation. Then, the formulae are used to evaluate the error in observed damping of the system as well as the correction if the simulation is conducted for an extended period with a time step different from the critical time step. Finally, the formulae are applied to Kundur's two-area four-generator system regarding its dominant mode. © 2022 IEEE.

关键词： Runge Kutta methods

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：