检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pattanaik, Anay Varshney, Lav R. Department of Computer Science Coordinated Science Laboratory University of Illinois Urbana-Champaign United States Department of Electrical and Computer Engineering Coordinated Science Laboratory University of Illinois Urbana-Champaign United States

This paper considers an online reinforcement learning algorithm that leverages pre-collected data (passive memory) from the environment for online interaction. We show that using passive memory improves performance and further provide theoretical guarantees for regret that turns out to be near-minimax optimal. Results show that the quality of passive memory determines sub-optimality of the incurred regret. The proposed approach and results hold in both continuous and discrete state-action spaces. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

InfantMotion2Vec: Unlabeled Data-Driven Infant Pose Estimation Using a Single Chest IMU

InfantMotion2Vec: Unlabeled Data-Driven Infant Pose Estimati...

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Mohammad Nur Hossain Khan Nancy L. McElwain Mark Hasegawa-Johnson Bashima Islam Department of Electrical and Computer Engineering Worcester Polytechnic Institute Department of Human Development and Family Studies University of Illinois Beckrnan Institute for Advanced Science and Technology University of Illinois Department of Electrical and Computer Engineering University of Illinois

ISBN: (数字)9798331530143

ISBN: (纸本)9798331530150

Early identification of neuro-developmental risks in infants is crucial for timely intervention and improved quality of life. Current screening methods are costly, intrusive, and limited by artificial environments or require the infant to wear multiple sensors. To address these challenges, we propose a novel approach leveraging inertial measurement units (IMUs) to monitor infants' spontaneous motor abilities in natural settings. Our method introduces a hierarchical semi-supervised classifier and the InfantMotion2Vec embedding to capture detailed motion patterns, accommodating a wide age range (up to 36 months) while minimizing reliance on labeled data and cumbersome sensor setups. We collected labeled IMU data from 25 families and unlabeled data from 42 families using a single wearable sensor. Pretraining an embedding network using unlabeled data with a hierarchical pose estimator resulted in a 26% increase in F1-score and a 77.7% increase in Cohen's Kappa score compared to using only labeled data. The InfantMotion2Vec embedding adequately handles highly unbalanced labeled data, demonstrating its effectiveness in infant posture classification.

关键词： Body sensor networks Measurement units Pose estimation Inertial navigation Motors Wearable sensors Monitoring

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Management and Tracking using AI and IoT

Electric Vehicle Management and Tracking using AI and IoT

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart electrical Systems, ICSES 2023

作者： Packialatha, A. Vadlamudi, Bindu Sai Thrinath, B.V. Sundar Ganesh, C.S. Ishrat, Mohammad Bhaskar, Archana Vels Institute of Science Technology & Advanced Studies Department of Computer Science and Engineering Tamil Nadu Chennai600117 India Velagapudi Ramakrishna Siddhartha Engineering College Department of Electrical and Electronics Engineering Andhra Pradesh Vijayawada520007 India Mohan Babu University School of Engineering Department of Electrical and Electronics Engineering Andhra Pradesh Tirupati517102 India Karpagam College of Engineering Department of Electrical and Electronics Engineering Tamil Nadu Coimbatore641032 India KoneruLakshmaiah Education Foundation Vaddeswaram Department of Computer Science and Engineering Andhra Pradesh Guntur522502 India REVA University School of CSA Karnataka Bengaluru560064 India

ISBN: (纸本)9798350319200

Technology has come a long way, and now many problems can be solved with the help of new developments in the field. With this technology, we can finally put an end to the suffocating effects of air pollution. Air pollution is on the rise due to the widespread use of automobiles powered by internal combustion engines. By replacing internal combustion engines with electric motors, we can end our reliance on polluting fossil fuels and ensure future generations have access to clean air. Electric vehicles are similar to machines in that they are powered by a rechargeable battery. To what extent an EV functions depends on its battery. Voltage, current, and temperature are the indicators of battery health. These factors are used to calculate the state of charge (SOC). These results are tracked by a BMS (Battery Management System). This article details how to create an EV monitoring system that makes use of AI and IoT to collect data from the vehicle's battery and send it to the cloud. Using a cloud-based smartphone app, we can track how well the battery is doing. © 2023 IEEE.

关键词： AI and the cloud are all components of this project battery monitoring current sensor Internet of Things NodeMCU temperature sensor voltage sensor

来源：评论

学校读者我要写书评

暂无评论

Energy Management System for a Smart Green Nanogrid feeding a Research laboratory with Autonomous Mobile Robots

引用

IFAC-PapersOnLine 2024年第2期58卷 156-161页

作者： Matteo Fresia Lorenzo De Simone Ilaria Traverso Stefano Bracco Silvia Siri Department of Electrical Electronic Telecommunication Engineering and Naval Architecture University of Genoa 16145 Genova Italy Department of Computer Science Bioengineering Robotics and Systems Engineering University of Genoa 16145 Genova Italy

This paper proposes a mixed-integer linear programming optimization model used to define an energy management system tailored for nanogrids in buildings, integrating renewable energy sources, battery energy storage systems and task-executing autonomous mobile robots. Focused on a nanogrid to be realised at the Savona Campus of the University of Genoa, the energy management system optimizes power flows and robot task scheduling in order to minimize the operating costs, the curtailment of the photovoltaic source and the number of unperformed tasks. Its novelty lies in combining energy and task planning constraints, offering significant potential for sustainable building energy management.

关键词： Energy management system Optimal operation Nanogrids Prosumer building Autonomous mobile robots Renewable energy sources Battery energy storage system

来源：评论

学校读者我要写书评

暂无评论

Effective Spline-GMPPT Approach Performance for Photovoltaic Systems under Uniform Irradiance and Partial Shading Conditions 2

Effective Spline-GMPPT Approach Performance for Photovoltaic...

引用

2nd International Conference on Energy Transition and Security, ICETS 2023

作者： Ahmed, Saidi Touhami, Abdelouahed Abdelghani, Draoui Amine, Meziane Mohamed Abdelkader, Harrouz Ahmed Draia University Laboratory of Sustainable Development and Computer Science Department of Electrical Engineering Adrar01000 Algeria University of Tahri Mohamed Laboratory of Smart Grid and Renewable Energy Department of Electrical Engineering Bechar08000 Algeria Tindouf37000 Algeria Naama University Center Naama45000 Algeria

ISBN: (纸本)9798350372182

In the literature, there are several criteria techniques classified to achieve the point of maximum power tracking (MPPT) in photovoltaic (PV) power systems, such as accuracy, speed, and simplicity. These criteria are often trade-offs;in this case, the higher accuracy generally achieved at the expense of two other criteria: speed and *** contribution proposes a new technique based on the Spline-Global-MPPT approach to provide its reliability in multiple criteria as an accurate, fast, and simple technique to find the MPP of PV power generation systems under two cases, such as uniform irradiance and partial shading conditions (PSCs), in the total distorted characteristics of the PV string. A cubic spline interpolation approach has proposed in this method, which defines from a few simple points an approximate *** localize the GMPP under standard (uniform) irradiance conditions, there are a huge number of interpolation-based approaches proposed in the literature. Unfortunately, this interpolation approach became incapable of detecting the point of the global maximum power (GMPP) under PSCs. The MPP of the system predicted by this new Spline-GMPPT method using a limited sample set of current and voltage, and it maintains this position as long as the external conditions stay unchanged. In the last part, the simulation results prove the reliability and robustness of the proposed approach. © 2023 IEEE.

关键词： Maximum power point trackers

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Hybrid Cryptography Model for Online Banking Authentication and Security 2nd

An Enhanced Hybrid Cryptography Model for Online Banking Aut...

引用

2nd International Conference on Connected Objects and Artificial Intelligence, COCIA 2024

作者： Awotunde, Joseph Bamidele Brahma, Biswajit Adeniyi, Abidemi Emmanuel Lauretta Nkonyeasua, Edogbo Imoize, Agbotiname Lucky Mejdoub, Youssef Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Ilorin240003 Nigeria McKesson Corporation 32559 Lake Bridgeport Street FremontCA94555 United States Department of Computer Science Bowen University Iwo Nigeria Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Lagos100213 Nigeria RITM Laboratory Higher School of Technology ESTC Hassan II University Casablanca Morocco

ISBN: (纸本)9783031704109

In the digital age, protecting the security and privacy of sensitive data has become of the utmost importance, particularly while conducting online financial transactions. This paper intends to build an advanced hybrid cryptography model, combining the strengths of the Rivest-Shamir-Adleman (RSA) and advanced Encryption Standard (AES) algorithms, to improve the authentication and security procedures of online banking systems. To provide a strong and effective encryption framework, the suggested model makes use of RSA’s asymmetric key advantages and AES’s symmetric key capabilities. Because AES is quick and efficient at encrypting large amounts of data, it is used to optimize performance while encrypting the actual data being transmitted. Meanwhile, RSA is used to solve the problem of key distribution, secure the exchange of symmetric keys, and enable secure communication. The goal of the paper is to create an extensive system that incorporates this improved hybrid cryptography model into the online banking authentication procedure. User authentication, transaction verification, and data secrecy are the system’s three main building blocks. To ensure the viability and feasibility of the suggested paradigm in real-world online banking scenarios, implementation difficulties such as key management, algorithm integration, and performance optimization are addressed. This research advances cryptographic methods of contemporary banking security by utilizing the advantages of AES and RSA in a hybrid approach. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

When Does Sora Show:The Beginning of TAO to Imaginative Intelligence and Scenarios engineering

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 809-815页

作者： Fei-Yue Wang Qinghai Miao Lingxi Li Qinghua Ni Xuan Li Juanjuan Li Lili Fan Yonglin Tian Qing-Long Han School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Department of Electrical and Computer Engineering Indiana University-Purdue University IndianapolisIndianapolisIN 46202USA Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Virtual Reality Fundamental Research Laboratory Department of Mathematics and TheoriesPeng Cheng LaboratoryShenzhen 518000China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia

DURING our discussion at workshops for writing“What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence”[1],we had expected the next milestone for Artificial Intelligence(AI)would be in the direction of Imaginative Intelligence(II),i.e.,something similar to automatic wordsto-videos generation or intelligent digital movies/theater technology that could be used for conducting new“Artificiofactual Experiments”[2]to replace conventional“Counterfactual Experiments”in scientific research and technical development for both natural and social studies[2]-[6].Now we have OpenAI’s Sora,so soon,but this is not the final,actually far away,and it is just the beginning.

关键词： something Intelligence replace

来源：评论

学校读者我要写书评

暂无评论

Efficient Hardware Implementation of Artificial Neural Networks on FPGA

Efficient Hardware Implementation of Artificial Neural Netwo...

引用

IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

作者： Kasem Khalil Tamador Mohaidat Mahmoud Darwich Ashok Kumar Magdy Bayoumi Department of Electrical and Computer Engineering University of Mississippi Mississippi USA Department of Electrical Engineering Assiut University Egypt Department of Mathematics and Computer Science University of Mount Union Alliance OH USA The Center for Advanced Computer Studies University of Louisiana at Lafayette LA USA Department of Electrical and Computer Engineering University of Louisiana at Lafayette LA USA

ISBN: (数字)9798350383638

ISBN: (纸本)9798350383645

A neural network finds widespread applications across various domains, with the primary challenge being the design of a network characterized by low area and power consumption. This paper introduces an efficient design strategy for a cost-effective neural network architecture. It leverages a shared multiplier and accumulator arrangement between neighboring nodes, halving the number of these units and subsequently reducing the overall area of the neural network. A configuration mechanism is employed to synchronize the operation between the two common nodes. The proposed method is implemented and tested using VHDL on an Altera 10 GX FPGA, and evaluations include testing with two datasets: MNIST and CIFAR-10. The results demonstrate that the proposed method maintains classification accuracy while achieving a 76% reduction in area compared to traditional methods, with a power consumption of 82 mW. These findings underscore the efficiency and suitability of the proposed method for applications prioritizing both area and energy efficiency.

关键词： Power demand VHDL Accuracy Circuits and systems Hardware Energy efficiency Synchronization

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Co-located Shared VR Experiences: Representing Non-HMD Observers on Both HMD and 2D Screens 23

Enhancement of Co-located Shared VR Experiences: Representin...

引用

23rd IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2024

作者： Guo, Zixuan Xu, Wenge Wang, Hongyu Wan, Tingjie Baghaei, Nilufar Lo, Cheng-Hung Liang, Hai-Ning Xi'an Jiaotong-Liverpool University School of Advanced Technology Suzhou China The University of Liverpool Department of Computer Science Liverpool United Kingdom Birmingham City University College of Computing Birmingham United Kingdom The University of Queensland School of Electrical Engineering and Computer Science Brisbane Australia Xi'an Jiaotong-Liverpool University Department of Industrial Design Suzhou China Computational Media and Arts Thrust Guangzhou China

ISBN: (纸本)9798331516475

Virtual reality (VR) not only allows head-mounted display (HMD) users to immerse themselves in virtual worlds but also to share them with others. When designed correctly, this shared experience can be enjoyable. However, in typical scenarios, HMD users are isolated by their devices, and non-HMD observers lack connection with the virtual world. To address this, our research investigates visually representing observers on both HMD and 2D screens to enhance shared experiences. The study, including five representation conditions, reveals that incorporating observer representation positively impacts both HMD users and observers. For how to design and represent them, our work shows that HMD users prefer methods displaying real-world visuals, while observers exhibit diverse preferences regarding being represented with real or virtual images. We provide design guidelines tailored to both displays, offering valuable insights to enhance co-located shared VR experiences for HMD users and non-HMD observers. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

NEARLY MINIMAX OPTIMAL OFFLINE REINFORCEMENT LEARNING WITH LINEAR FUNCTION APPROXIMATION: SINGLE-AGENT MDP AND MARKOV GAME 11

NEARLY MINIMAX OPTIMAL OFFLINE REINFORCEMENT LEARNING WITH L...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Xiong, Wei Zhong, Han Shi, Chengshuai Shen, Cong Wang, Liwei Zhang, Tong Department of Mathematics The Hong Kong University of Science and Technology Hong Kong Center for Data Science Peking University China Department of Electrical and Computer Engineering University of Virginia United States National Key Laboratory of General Artificial Intelligence Peking University China School of Intelligence Science and Technology Peking University China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Offline reinforcement learning (RL) aims at learning an optimal strategy using a pre-collected dataset without further interactions with the environment. While various algorithms have been proposed for offline RL in the previous literature, the minimax optimality has only been (nearly) established for tabular Markov decision processes (MDPs). In this paper, we focus on offline RL with linear function approximation and propose a new pessimism-based algorithm for offline linear MDP. At the core of our algorithm is the uncertainty decomposition via a reference function, which is new in the literature of offline RL under linear function approximation. Theoretical analysis demonstrates that our algorithm can match the performance lower bound up to logarithmic factors. We also extend our techniques to the two-player zero-sum Markov games (MGs), and establish a new performance lower bound for MGs, which tightens the existing result, and verifies the nearly minimax optimality of the proposed algorithm. To the best of our knowledge, these are the first computationally efficient and nearly minimax optimal algorithms for offline single-agent MDPs and MGs with linear function approximation. © 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

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：