检索结果-内蒙古大学图书馆

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Garg, Kritika Sarker, Rahul Ahmad, Aaqib Kaur, Mehakpreet Teja, A.V. Ravi Dept. of Electrical Engineering IIT Ropar Rupnagar India Dept. of Computer Science Engineering PU Patiala India

ISBN: (纸本)9781665464543

This document is a model with an accurate estimation of the battery’s State Of Charge (SOC), which is pivotal for prime performance and optimal lifespan of the rechargeable batteries. Though traditional methods, like Open Circuit Voltage (OCV) and Coulomb Counting (CC), are advantageous, they suffer from several limitations, such as sensitivity to temperature changes, frequent calibration, ageing effects, and measurement inaccuracies. This paper proposes 1-D Kalman Filter (1-D HKF) with an approach that incorporates the OCV and CC results into the state space model for better and more accurate SOC estimation. So, the model is called 1-D HKF or Hybrid Kalman filter that, influenced the long-term stability and estimation accuracy of CC and the accuracy of OCV at specific points to get over the individual limitations. The model trained by 1-D HKF adapts itself and adjusts the gain based on the uncertainties of each measured value to ensure optimal value information. So, We evaluate the performance of the 1-D HKF versus the traditional methods Kalman Filter using examples and exploratory data. The proposed approach illustrates significantly improved accuracy and robustness across various operating conditions, including varying temperatures and discharge rates. © 2024 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

Modeling of Weight Perception Based on Subjectivity by Considering Individual Differences 13

Modeling of Weight Perception Based on Subjectivity by Consi...

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： Kushida, Daisuke Nakajima, Kei Tottori University Faculty of Engineering Dept. Electrical Engineering and Computer Science Tottori Japan Graduate School of Sustainability Science Tottori University Dept. Engineering Tottori Japan

ISBN: (纸本)9798350373332

The minimum amount of perception that humans can perceive is called the stimulus threshold. This study aims to clarify the stimulus threshold of weight perception for the biceps brachii muscle based on a method of constant stimuli. In general, the stimulus threshold depends on the individual. The authors consider that physical characteristics are related to individual differences, construct a model of the relationship between physical characteristics and stimulus thresholds, and attempt to estimate stimulus thresholds from physical characteristics. The constructed model is evaluated via cross-validation and found to be able to estimate stimulus thresholds from physical characteristics with an 85% accuracy. © 2024 IEEE.

关键词： individual difference modeling stimuli threshold subjectivity weight perception

来源：评论

学校读者我要写书评

暂无评论

Power Control of Preamble Transmission for Grant-free Random Access in Cell-Free IoT Networks 15

Power Control of Preamble Transmission for Grant-free Random...

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Youn, Jiseung Cho, Sunghyun Hanyang University Dept. of Computer Science & Engineering Seoul Korea Republic of Hanyang University ERICA Dept. of Computer Science & Engineering Ansan Korea Republic of

ISBN: (纸本)9798350364637

As Internet of Things (IoT) technologies are inves-tigated to support key 5G services, significant research efforts are being made to enable machine-type communication (MTC). Cell-free IoT (CF-IoT) systems, characterized by favorable prop-agation and macro diversity, are being studied in conjunction with grant-free random access (GFRA) as a potential enabler to achieve massive connectivity for MTC. However, existing GFRA schemes in CF-IoT transmit preambles at a fixed power level resulting in severe preamble collisions at nearby access points (APs). In this paper, we analyzes the analysis of preamble collisions in massive connectivity scenario and proposes a sim-ple power control scheme to address preamble collision. The proposed scheme mitigates preamble collisions by transmitting preambles only to the nearest AP in high-density access scenes. Simulation results show that the proposed method improves the random access success rate compare to existing GFRA method by 10%. © 2024 IEEE.

关键词： cell-free massive MIMO grant-free random access Internet of Things power control

来源：评论

学校读者我要写书评

暂无评论

A Feedback-based Decision-Making Mechanism for Actor-Critic Deep Reinforcement Learning

A Feedback-based Decision-Making Mechanism for Actor-Critic ...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Yang, Guang Geng, Ziye Li, Jiahe Zhao, Yanxiao Abdelwahed, Sherif Luo, Changqing Virginia Commonwealth University Dept. of Computer Science RichmondVA United States Virginia Commonwealth University Dept. of Electrical and Computer Engineering RichmondVA United States

ISBN: (纸本)9798350362480

Deep reinforcement learning (DRL) has achieved remarkable success in solving sequential decision-making problems across various domains. However, a critical challenge is sample inefficiency, especially in real-world environments with high-dimensional solution spaces due to continuous state and action spaces. Although off-policy actor-critic algorithms have been proposed to mitigate this issue, the gains in sample efficiency remain limited, as decision-making in these algorithms relies solely on the policy function that might not always yield optimal actions. To bridge the gap, we design a novel feedback-based decision-making mechanism (FADA) that incorporates a feedback mechanism into the actor-critic framework to enhance decision-making robustness. Specifically, FADA utilizes feedback from the value function (critic) to calibrate the decisions produced by the policy function (actor). More concretely, FADA comprises four integrated modules: a decision-space expansion module (DEM) to produce a pool of candidate actions, a critic-guided evaluation module (CGEM) that estimates the efficacy of the candidate actions, an adaptive selection module (ASM) that adaptively selects a set of elite actions based on the estimated efficacy and samples the final action, and an iterative refinement module (IRM) that improves the quality of elite actions. We evaluate our approach on multiple tasks in the DeepMind Control Suite, and the experimental results demonstrate a significant improvement in sample efficiency. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of Digitized Visual Search Task for Assessment of Aging Effects 2

Design of Digitized Visual Search Task for Assessment of Agi...

引用

2nd IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2024

作者： Navalyal, Geeta Navalyal, Apoorva Naik, Sayali Dept. of Computer Science & Engineering Uttarakhand Dehradun India University of Florida Dept. of Electrical & Computer Engineering GainesvilleFL United States Grant Thornton Karnataka Bengaluru India

ISBN: (纸本)9798350372847

Mild cognitive impairments (MCI) develop in adults due to the normal aging process and may sometimes progress to a more serious cognitive decline stage resulting in Dementia. If the cognitive decline is identified at the MCI stage, it can be delayed or prevented from progressing by different interventions. A typical indicator of cognitive impairments that might be caused due to an injury, aging, or other factors is found to be a decreased search efficiency in visual search tasks. Here we propose a model to assess this efficiency by designing a digitized, easy-to-use visual search task capable of incorporating multiple variables in the visual stimulus, affecting the search capabilities. The variables under consideration include the number of distracting elements, target size, target distance from the center of the stimulus area, and habituation effects. This designed stimulus is tested on participants from different age groups. © 2024 IEEE.

关键词： aging cognitive impairments Visual search task

来源：评论

学校读者我要写书评

暂无评论

Sparse Oblique Decision Trees: A Tool to Understand and Manipulate Neural Net Features

Sparse Oblique Decision Trees: A Tool to Understand and Mani...

引用

KDD Workshop on Human-Interpretable AI 2024, HI-AI 2024

作者： Hada, Suryabhan Singh Carreira-Perpiñán, Miguel Á. Zharmagambetov, Arman LinkedIn Dept. of Computer Science & Engineering University of California Merced United States Dept. of Computer Science & Engineering University of California Merced United States

The widespread deployment of deep nets in practical applications has lead to a growing desire to understand how and why such black-box methods perform prediction. Much work has focused on understanding what part of the input pattern (an image, say) is responsible for a particular class being predicted, and how the input may be manipulated to predict a different class. We focus instead on understanding what internal features computed by the neural net are responsible for a particular class. We achieve this by mimicking part of the net with a decision tree having sparse weight vectors at the nodes. We are able to learn trees that are both highly accurate and interpretable, so they can provide insights into the deep net black box. Further, we show we can easily manipulate the neural net features in order to make the net predict, or not predict, a given class, thus showing that it is possible to carry out adversarial attacks at the level of the features. We demonstrate this robustly in MNIST and ImageNet with LeNet5 and VGG networks. © 2024 Copyright for this paper by its authors.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributionally Robust Clustered Federated Learning: A Case Study in Healthcare 63

Distributionally Robust Clustered Federated Learning: A Case...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Konti, Xenia Riess, Hans Giannopoulos, Manos Shen, Yi Pencina, Michael J. Economou-Zavlanos, Nicoleta J Zavlanos, Michael M. Duke University School of Medicine United States Duke University Dept. of Computer Science United States Duke University Dept. of Electrical and Computer Engineering United States Duke University Dept. of Mechanical Engineering & Materials Science United States

ISBN: (纸本)9798350316339

In this paper, we address the challenge of heterogeneous data distributions in cross-silo federated learning by introducing a novel algorithm, which we term Cross-silo Robust Clustered Federated Learning (CS-RCFL). Our approach leverages the Wasserstein distance to construct ambiguity sets around each client's empirical distribution that capture possible distribution shifts in the local data, enabling evaluation of worst-case model performance. We then propose a model-agnostic integer fractional program to determine the optimal distributionally robust clustering of clients into coalitions so that possible biases in the local models caused by statistically heterogeneous client datasets are avoided, and analyze our method for linear and logistic regression models. Finally, we discuss a federated learning protocol that ensures the privacy of client distributions, a critical consideration, for instance, when clients are healthcare institutions. We evaluate our algorithm on synthetic and real-world healthcare data. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Dynamic Network Slicing for Resource Optimization in 5G Networks: Implementation and Performance Evaluation

AI-Driven Dynamic Network Slicing for Resource Optimization ...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Jain, Ayushi Jain, Prateek Verma, Aditya Gopal, Lisa Chaudhary, Preeti Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Dept. of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Scholar Dept. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798331542344

We introduce in this paper an AI-based dynamic network slicing model for resource allocation targeting 5G networks. It does this by using machine learning algorithms that help the model learn and adapt to live traffic conditions so as to intelligently manage different service types, including eMBB (enhanced Mobile Broadband), URLLC (Ultra-Reliable Low Latency Communication) and mMTC (massive Machine Type Communication). This leads to substantial improvements in three of the four core performance metrics, latency, throughput and energy efficiency (at a low sacrifice of when it comes to QoS adherence). Their work also demonstrates that AI technologies hold the promise for revolutionary network management, offering a scalable solution that can address ever-increasing requirements of next-generation telecommunications, by surpassing the capabilities of well-established static slicing techniques. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Cognitive Training Systems Based on Extended Reality and BCI Technology 7

Design and Development of Cognitive Training Systems Based o...

引用

7th IEEE Eurasian Conference on Educational Innovation, ECEI 2024

作者： Lin, Pei-Jung Ku, Hsiu-Chien Lin, Li-Lun Feng Chia University Dept. of Information Engineering and Computer Science Taichung Taiwan Hungkuang University Dept. of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9798350307207

Dementia is considered a Mild Cognitive Impairment (MCI), representing a blurred transition from normal cognitive function to dementia. MCI might be a precursor to dementia being caused by various neurodegenerative diseases, including Alzheimer's disease, stroke, metabolic disorders, and mental health conditions. According to the World Health Organization (WHO), over 55 million people worldwide are suffering from dementia, with nearly 10 million new cases each year. This number is expected to rise to 78 million by 2030. Numerous studies have proposed various training methods targeting specific cognitive domains in dementia. For instance, reminiscence therapy encourages individuals to recall buried memories, while reality orientation therapy focuses on strengthening orientation cues to help patients with dementia establish a stronger sense of control. With aging, changes occur in cognitive and physical functions. Research suggests that memory functions can be improved through training. Therefore, the primary goal of this study was to develop an Extended Reality (XR) cognitive system to assist MCI patients in enhancing logical thinking, increasing independence in daily life, and improving response accuracy. The application of extended reality technology in the medical field is expanding, covering areas such as surgical assistance, medical consultation, disease treatment, and medical training. We integrated mixed reality devices with brain-computer interface (BCI) equipment. By detecting brainwave signals in the frontal region of the brain through sensors, neural activity was quantified, and digital brainwave data was transmitted to the system. This data was then visualized on screen in real-time to analyze changes in brainwave data during training. Through multifaceted task training, the system enhanced cognitive response and sensory perception, stimulating brain activity with the goal of strengthening cognitive functions. © 2024 IEEE.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

EMC and EMF Safety Aspects of Wireless Power Transfer Systems for e-Mobility

引用

IEEE Electromagnetic Compatibility Magazine 2024年第3期13卷 74-92页

作者： Maradei, Francesca Ahn, Seungyoung Campi, Tommaso Covic, Grant Cruciani, Silvano Hirata, Akimasa Wang, Shuo Feliziani, Mauro Sapienza University Dept. of Astronautic Electrical and Energy Engineering Rome Italy Daejeon Korea Republic of The University of Auckland Auckland New Zealand Tor Vergata University Dept. of Industrial Engineering Rome Italy Nagoya Institute of Technology Dept. of Electrical and Mechanical Engineering Nagoya Japan University of Florida Dept. of Electrical & Computer Engineering GainesvilleFL United States University of L'Aquila Dept. of Industrial and Information Engineering L'Aquila Italy

This paper intends to provide a comprehensive over-view of the current state-of-the-art practices in wireless power transfer (WPT) technology within the automotive sector, while addressing pertinent issues related to electromagnetic compatibility (EMC) and electromagnetic field (EMF) safety compliance, as well as highlighting ongoing challenges and areas for further exploration. © 2012 IEEE.

关键词： Inductive power transmission

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：