检索结果-内蒙古大学图书馆

Sim-to-Real Reinforcement Learning Techniques for Double Inverted Pendulum Control with Recovery Property

Transactions of the Korean Institute of Electrical Engineers 2023年第12期72卷 1705-1713页

作者： Lee, Taegun Ju, Doyoon Lee, Young Sam Dept.of Electrical and Computer Engineering Inha University Incheon Korea Republic of

In recent years with the rapid advancement of artificial intelligence, there has been extensive research to address control problems, which was previously unsolvable with traditional control techniques, using reinforcement learning-based controllers. This paper discusses a challenge in controlling a double inverted pendulum system. With the commonly used 2-DOF control technique, once the swing-up control is performed and a strong disturbance is applied, the system becomes uncontrollable and fails to perform another swing-up. However, the reinforcement learning-based controller proposed in this paper overcomes this limitation using the Sim-to-Real learning technique. To ensure successful application of Sim-to-Real learning, this paper proposes a design method for the real-world system that minimizes the reality gap, a chronic issue with the Sim-to-Real technique. Utilizing these techniques, we introduce a characteristic termed 'recovery property' denoting the ability to recover from strong disturbances, a feature difficult to achieve with traditional control methods. We design a controller with this characteristic and validate its successful operation in a real-world system. © 2023 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

ZEROTH-ORDER OPTIMIZATION WITH TRAJECTORY-INFORMED DERIVATIVE ESTIMATION 11

ZEROTH-ORDER OPTIMIZATION WITH TRAJECTORY-INFORMED DERIVATIV...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Shu, Yao Dai, Zhongxiang Sng, Weicong Verma, Arun Jaillet, Patrick Low, Bryan Kian Hsiang Dept.of Computer Science National University of Singapore Singapore Dept.of Electrical Engineering and Computer Science MIT United States

Zeroth-order (ZO) optimization, in which the derivative is unavailable, has recently succeeded in many important machine learning *** algorithms rely on finite difference (FD) methods for derivative estimation and gradient descent (GD)-based approaches for ***, these algorithms suffer from query inefficiency because many additional function queries are required for derivative estimation in their every GD update, which typically hinders their deployment in real-world applications where every function query is *** this end, we propose a trajectory-informed derivative estimation method which only employs the optimization trajectory (i.e., the history of function queries during optimization) and hence can eliminate the need for additional function queries to estimate a ***, based on our derivative estimation, we propose the technique of dynamic virtual updates, which allows us to reliably perform multiple steps of GD updates without reapplying derivative *** on these two contributions, we introduce the zeroth-order optimization with trajectory-informed derivative estimation (ZORD) algorithm for query-efficient ZO *** theoretically demonstrate that our trajectory-informed derivative estimation and our ZORD algorithm improve over existing approaches, which is then supported by our real-world experiments such as black-box adversarial attack, non-differentiable metric optimization, and derivative-free reinforcement learning. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

A framework for locating multiple RFID tags using RF hologram tensors

引用

Digital Communications and Networks 2025年第2期11卷 337-348页

作者： Xiangyu Wang Jian Zhang Shiwen Mao Senthilkumar CG Periaswamy Justin Patton Dept.of Electrical and Computer Engineering Auburn UniversityAuburnAL 36849-5201USA Department of Electrical and Computer Engineering Kennesaw State UniversityKennesawGA 30144USA RFID Lab Auburn UniversityAuburnAL 36849USA

In this paper,we present a Deep Neural Network(DNN)based framework that employs Radio Frequency(RF)hologram tensors to locate multiple Ultra-High Frequency(UHF)passive Radio-Frequency Identification(RFID)*** RF hologram tensor exhibits a strong relationship between observation and spatial location,helping to improve the robustness to dynamic environments and *** RFID data is often marred by noise,we implement two types of deep neural network architectures to clean up the RF hologram *** the spatial relationship between tags,the deep networks effectively mitigate fake peaks in the hologram tensors resulting from multipath propagation and phase *** contrast to fingerprinting-based localization systems that use deep networks as classifiers,our deep networks in the proposed framework treat the localization task as a regression problem preserving the ambiguity between *** also present an intuitive peak finding algorithm to obtain estimated locations using the sanitized hologram *** proposed framework is implemented using commodity RFID devices,and its superior performance is validated through extensive experiments.

关键词： Radio-frequency identification(RFID) Ultra-high frequency(UHF)passive RFID tag RF hologram tensor Indoor localization Deep learning(DL) Swin Transformer Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of Pattern Matching Techniques used for Information Leakage 15

Analysis of Pattern Matching Techniques used for Information...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kumar, Abhishek Senapati, K.K. Patnaik, K.S. Dept.of Computer Science & Engineering Birla Institute of Technology Mesra Ranchi India

ISBN: (纸本)9798331300579

In the rapidly evolving digital landscape, ensuring the utmost security of sensitive information against the pervasive risks of information leakage has become a paramount *** study dives deep into a critical facet of information security-the intricate world of pattern matching algorithms-vital tools in the ongoing battle against Information *** research embarks on a comprehensive exploration of a diverse array of pattern matching algorithms, shedding light on their pivotal roles in the identification and effective mitigation of potential information *** meticulously analyze their inherent strengths, nuanced limitations, and practical applications across real-world contexts, understanding their multifaceted ***, we delve into the complexities of commonly utilized datasets for training and rigorous testing, strategically accentuating essential evaluation criteria that guide algorithmic *** this extensive exploration, we seek to elucidate the landscape of pattern matching algorithms, placing emphasis on their dynamic nature and promising potential in advancing information ***, we put forth insightful proposals for pective research directions within this vital domain, aiming to shape the future of information protection and fortification. © Grenze Scientific Society, 2024.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient LEDCA Analysis for Improved Throughput in Wireless Sensor Networks 6

Energy Efficient LEDCA Analysis for Improved Throughput in W...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Padmageetha, B.G. Naik, Pramod Kumar Patil, Mallanagouda Dept.of Computer Applications Dayananda Sagar University Bengaluru India Dept. of Computer science and Engineering Dayananda Sagar University Bengaluru India Dept. of Computer science and Engineering RVITM Bengaluru India

ISBN: (纸本)9798331522667

Wireless Sensor Networks (WSNs) face significant challenges in terms of energy conservation, scalability, and data throughput owing to their limited node energy resources. This paper presents a low-energy data-centric algorithm (LEDCA), a novel energy-aware clustering and routing protocol designed to optimize energy efficiency and improve throughput in WSNs. Through simulations, LEDCA demonstrated a Packet Delivery Ratio (PDR) of up to 90%, throughput of 255,217 bps, and average latency of 159 ms, validating its efficiency in resource-constrained environments. The algorithm integrates residual energy awareness by prioritizing high-energy nodes for Cluster Head (CH) roles, dynamically adjusting routing paths, and balancing the network load to prevent premature node failure. By applying an Energy Mapping Node and a real-time Energy Mapping Table, LEDCA minimizes re-clustering, reduces data redundancy, and ensures stable data transmission even under high-density networks. Simulation results also show LEDCA's scalability of LEDCA, with A9_T_200 achieving the highest throughput under extended transmission ranges and A3_T_200 achieving the lowest latency, making it suitable for energy-sensitive and latency-critical applications. Future enhancements, such as integrating Non-Orthogonal Multiple Access (NOMA) and dynamic resource allocation, could further improve LEDCA’s interference management and scalability of LEDCA for IoT and 5G/6G networks, addressing the needs of next-generation applications. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

E-ATM For Card Less Transactions Using Machine Learning 1

E-ATM For Card Less Transactions Using Machine Learning

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Aishwarya, D. Muralikumar, A. Mohammed Inthiyaz, M. Sathyabama Institute of Science and Technology Dept.of Computer Science and Engineering Tamilnadu Chennai600119 India

ISBN: (数字)9798350371802

ISBN: (纸本)9798350371802

A fingerprint recognition technique in the ATM system is the foundation of this study. We chose this to improve client security and facilitate simple transactions. Since every person has unique fingerprint details, this method will be more widely applicable. It is not necessary to keep your ATM card on hand at all times, nor is there any concern that your card will be lost. It is shown that fingerprint recognition technology outperforms and is safer than other technologies when compared to other ATM security systems already in use. This facilitates safe and simple transactions while maintaining a user-friendly environment. Without a doubt, service providers should also consider security when designing their ATM products, in order to protect financial transactions against security threats. And a lot about security holes, identity theft, credit card fraud, and ways for hackers and criminals to get any sensible passwords or pin numbers. Similar to a username, identification is employed in the present architecture to provide access to the system. To ensure that the intended user is indeed who say they are, since passwords may be stolen or lost. Biometric identity and authentication technologies are the most modern answers to security and privacy problems. The study of traits that may be used to identify a person is known as face recognition. These bodily attributes include, among other things, faces, voices, fingerprints, and hand shapes. The different security system authentication techniques are surveyed in this paper. This face biometric with QR code verification offers the highest degree of security in authentication. One of the most promising technologies for electronic money transactions is this procedure. The need for quick and precise user identification and authentication has increased due to the expansion of the electronic transaction industry. The Automated Teller Machine (ATM) is a fantastic convenience for people to satisfy their financial requirements. Not

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Storage Security with Multi-Authority Authentication and File Encryption 7

Enhancing Cloud Storage Security with Multi-Authority Authen...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Jorsen Fredlin, J. Rahul Vijay, P. Janani, S. St.Joseph's College of Engineering Dept.of Computer Science And Engineering Chennai India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359299

The integration of a multi-authority system poses significant challenges but offers numerous benefits for effective collaboration and decision-making across departments or organizations. Harmonizing laws, regulations, and policies, as well as integrating diverse technologies and data sources, are key hurdles in this process, requiring thorough planning, coordination, and implementation. Active participation from relevant authorities is essential, facilitated by open communication, collaborative environments, and ongoing training. Security and privacy considerations must also be addressed to safeguard sensitive information and ensure compliance with legislation. Successfully integrated multi-authority systems yield advantages such as increased communication, operational efficiency, and decision-making skills, while encouraging innovation, streamlining procedures, and reducing redundancy. This study emphasizes the importance of cooperation, decision-making, coordination, data management, technology integration, and security in achieving the potential benefits of a unified multi-authority system. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Smart AI-Based Delivery Robot

Smart AI-Based Delivery Robot

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Vemulapalli, Lavanya Charitha, Kolanti Harshitha, Kuralla Durga Lakshmi Sri, Vallepu Udaya Velagapudi Ramakrishna Siddhartha Engineering College Dept.of Computer Science and Engineering Vijayawada India Velagapudi Ramakrishna Siddhartha Engineering College Dept.of Artificial Intelligence and Data Science Vijayawada India

ISBN: (纸本)9798331512965

Humans are responsible for the majority of delivering the packets over the area of a network. When compared to classic delivery system the Autonomous Delivery Robot(ADR's) is meant to deliver the goods instead of a human involvement. The delivery robots are a contact-less and alternative to human interaction. At their core, we design a budget-friendly prototype for an Autonomous Delivery Robot (ADR) that can deliver packages to their destinations safely. This robot uses a GPS (like a car's navigation system) to find its way around. We use a special kind of computer brain called Artificial Intelligence to understand the best way to go. Once delivery robot know the right path, it follows until it reaches to the final stop. The robot keeps packets secure by putting them in a special container that needs a secret code to open. The secret code to open the container can be sent to the customer mobile when they order something. Once the robot delivers your package, it can find its own way back to where it started. © 2025 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Worker's Monitoring System using Deep Learning 15

A Real-Time Worker's Monitoring System using Deep Learning

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Harshavardhan, L. Kumar, Girish T.P. Gowda, Jayanth B.R. Keerthan, B.K. Bevinatti, Mohan K.S. Dept.of Computer Science and Engineering BGS Institute of Technology Karnataka BG Nagara India

ISBN: (纸本)9798331300579

The Real-Time Worker Monitoring System employing deep learning and web integration represents a cutting-edge solution for enhancing workplace safety and *** advanced deep learning algorithms, this system continuously analyzes real-time data from various sensors, such as cameras and wearable devices, to monitor workers' activities and *** integration with web platforms enables instant access to the monitored information, facilitating seamless communication and *** providing timely insights into worker behavior and environmental factors, this innovative system not only promotes a safer work environment but also optimizes productivity through informed management *** the convergence of deep learning technology and web integration, this monitoring system stands at the forefront of workplace safety solutions, offering a robust framework for real-time insights and proactive intervention. © Grenze Scientific Society, 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Modeling Conditional Relationships in the Management and Monitoring of Type 1 and Type 2 Diabetes through Bayesian Network

Modeling Conditional Relationships in the Management and Mon...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Cascone, Lucia Napolitano, Margherita Maria Nappi, Michele Nappi, Severino Tortora, Genoveffa University of Salerno Dept.of Computer Science Fisciano Italy

ISBN: (纸本)9798350386226

Diabetes mellitus is one of the most prevalent chronic diseases, affecting millions of people worldwide. Effective management of diabetes, particularly type 1 (T1DM) and type 2 diabetes (T2DM), requires a deep understanding of the complex interactions between clinical, behavioral, and socio-demographic factors. This study leverages Bayesian networks (BNs) to model these interactions, providing a transparent and interpretable visual framework that reveals how variables such as insulin use, BMI, and socio-economic status influence diabetes outcomes. However, constructing the graphical structure of a BN poses significant challenges due to the intricate and multifaceted relationships involved. To ensure a meaningful comparison between T1DM and T2DM, we utilized a cohort of subjects selected to be as demographically homogeneous as possible. This allowed us to reduce confounding effects and focus on the intrinsic differences between the two conditions. We compared network structures derived from three data samples (50%, 80%, and 100%) to explore how variable relationships evolve as the dataset size increases, ensuring that critical interactions were captured at different levels of data availability. The findings highlight key differences in the management of T1DM and T2DM, particularly with regard to behavioral and socio-economic factors. © 2024 IEEE.

关键词： Bayesian networks Interpretability Risk factor analysis Type 1 diabetes Type 2 diabetes

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：