检索结果-内蒙古大学图书馆

Smart World Congress (SWC), IEEE

作者： Danlei Li Nirmal Nair Kevin I-Kai Wang Kouichi Sakurai Department of Electrical Computer and Software Engineering University of Auckland Auckland New Zealand Department of Informatics Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Anomaly detection is the identification of instances that substantially deviate from the majority of the data and do not conform to a well-defined normal behavior. Investigating time series anomalies has become increasingly popular in recent years due to widely deployed IoT devices and sensors. Although most existing methods apply image anomaly detection algorithms directly on time series and commonly assume the data is IID (independent and identically distributed). However, in most realworld applications, the underlying data distribution alters over time. Changes in data over time are referred to as concept drift and can significantly degrade the efficacy of an anomaly detection model. Existing research also indicates that the majority of anomaly detection frameworks ignored concept drift, resulting in poor long-term model performance. This paper presents an ensemble-based, unsupervised anomaly detection framework that is adaptive to the concept drift in time series data. Both distribution and performance-based techniques are used to detect concept drift and update the model to ensure the framework’s longterm performance reliability. The proposed method is evaluated using a real-world univariate time series data that captures sea surface temperature data over a 2 -year period. By comparing our proposed framework to other state-of-the-art algorithms, we demonstrate our proposed method has obvious benefits in accuracy and long-term stability.

关键词： Adaptation models Accuracy Concept drift Time series analysis Stability analysis Sensors Sea surface temperature Reliability Anomaly detection Thermal stability

来源：评论

学校读者我要写书评

暂无评论

DART: Deformable Anatomy-Aware Registration Toolkit for Lung CT Registration with Keypoints Supervision

DART: Deformable Anatomy-Aware Registration Toolkit for Lung...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yunzheng Zhu Luoting Zhuang Yannan Lin Tengyue Zhang Hossein Tabatabaei Denise R Aberle Ashley E Prosper Aichi Chien William Hsu Department of Radiological Sciences Medical & Imaging Informatics David Geffen School of Medicine at UCLA Department of Electrical & Computer Engineering UCLA Samueli School of Engineering Medical Informatics Home Area UCLA Graduate Programs in Bioscience Department of Computer Science UCLA Samueli School of Engineering Department of Radiological Sciences David Geffen School of Medicine at UCLA Department of Bioengineering UCLA Samueli School of Engineering

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Spatially aligning two computed tomography (CT) scans of the lung using automated image registration techniques is a challenging task due to the deformable nature of the lung. However, existing deep-learning-based lung CT registration models are not trained with explicit anatomical knowledge. We propose the deformable anatomy-aware registration toolkit (DART), a masked autoencoder (MAE)-based approach, to improve the keypoint-supervised registration of lung CTs. Our method incorporates features from multiple decoders of networks trained to segment anatomical structures, including the lung, ribs, vertebrae, lobes, vessels, and airways, to ensure that the MAE learns relevant features corresponding to the anatomy of the lung. The pretrained weights of the transformer encoder and patch embeddings are then used as the initialization for the training of downstream registration. We compare DART to existing state-of-the-art registration models. Our experiments show that DART outperforms the baseline models (Voxelmorph, ViT-V-Net, and MAE-TransRNet) in terms of target registration error of both corrField-generated keypoints with 17%, 13%, and 9% relative improvement, respectively, and bounding box centers of nodules with 27%, 10%, and 4% relative improvement, respectively. Our implementation is available at https://***/yunzhengzhu/DART.

关键词： Training Image registration Computed tomography Computational modeling Lung Brain modeling Transformers

来源：评论

学校读者我要写书评

暂无评论

Tentative design and Feasibility assessment of Grid connected Hydro-Power based Hybrid Renewable Energy-A Case Study

Tentative design and Feasibility assessment of Grid connecte...

引用

2022 International Conference on Recent Progresses in Science, engineering and Technology, ICRPSET 2022

作者： Al Rafi, Jobair Islam, Md. Ariful Nath, Imon Deb Mashiat, Lamisa Islam, Sakibul Chowdhury, Pushan Mahmood, Ifraz Nagoya Institute of Technology Department of Physical Science and Engineering Nagoya Japan Dept. of Electrical and Electronic Engineering Bangladesh International Islamic University Chittagong Dept. of Computer Science and Engineering Chittagong Bangladesh

ISBN: (纸本)9798350332704

Energy production with less impact on the environment is a great challenge for third world countries like Bangladesh, due to excessive power demand and fewer access to power production technology. The current state of Global warming holds a big responsibility to look at how we generate electricity and how much of it we utilize. This leads the researchers to combine the green resources together and conjugate with the grid. This study proposes a hybrid model of green energy (Solar and Wind) incorporating a Hydropower system for Dhania, Bhola, a rural area in Bangladesh. We have presented a unique approach for analyzing consumer data in the Excel spreadsheet and Simulink in order to create a more authentic load profile of the user. Here excel spreadsheet is used to keep consumer's daily load data and a load curve is drawn from it which is quite similar to the real one. The users' 24-hour load profile was replicated using a MATLAB Simulink model built using data from spreadsheets. Here we strive to illustrate the supply of green power to accomplish the residential demand. The standard data of solar radiation and wind speeds are collected from NASA surface methodology. The outcome of this study is a solution to the power crisis using green resources. © 2022 IEEE.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

Design, Benefits and Barriers of Local Electricity Markets: Insights from a UK Innovation Project

Design, Benefits and Barriers of Local Electricity Markets: ...

引用

International Conference on Smart Energy Systems and Technologies (SEST)

作者： Dimitrios Papadaskalopoulos Makedon Karasavvidis Department of Electrical and Computer Engineering University of Patras Patras Greece Department of Electrical and Electronic Engineering Imperial College London London U.K.

ISBN: (数字)9798350386493

ISBN: (纸本)9798350386509

Local electricity markets (LEMs) have recently emerged as a promising paradigm towards realizing the value of distributed energy resources (DERs), by enabling a) provision of flexibility services (FS) by the DERs to system operators, and b) local energy trading among prosumers. However, existing work has only explored these two market functions in silos and has not comprehensively considered the effect of regulated charges. The recent UK innovation project Liverpool Energy Xchange aims at addressing these gaps, by designing a LEM that enables co-optimized local energy trading and FS provision. This paper firstly outlines the market design aspects of the proposed LEM. Secondly, it presents a quantitative validation of its benefits, based on a test case involving actual UK market data and operating data from prosumer sites in Liverpool, demonstrating a 27% reduction of the yearly net electricity cost. Finally, it discusses barriers the project has identified towards the realization of LEMs.

关键词： Technological innovation Costs Electricity Electricity supply industry Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

Losses Evaluation in Current Source Inverter Topologies for Automotive Traction Applications

Losses Evaluation in Current Source Inverter Topologies for ...

引用

European Conference on Power electronics and Applications

作者： Gaetano Turrisi Luigi Danilo Tornello Giacomo Scelba Mario Cacciato Giuseppe Scarcella Department of Electrical Electronic and Computer Engineering University of Catania Catania Italy

In this paper, an analytical modelling of power loss distribution has been addressed for different traction current source inverters. After having described the topologies and modulation strategies, modelling of losses for each semiconductor device composing the inverters is provided. Then, the theoretical study has been validated through extensive simulations performed on a 35kW permanent magnet synchronous motor drive fed by the considered current source inverter topologies. Furthermore, the power loss and overall efficiency of current source inverter-based motor drives have been compared to a traditional two-level voltage source inverter fed motor drive including an output LC filter. Results underline pros and cons of using current source inverter topologies based on wide bandgap semiconductor devices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control

引用

IEEE Transactions on Mobile Computing 2025年

作者： Ouyang, Jinhao Liu, Yuan Liu, Hang South China University of Technology School of Electronic and Information Engineering Guangzhou510641 China Cornell University Department of Electrical and Computer Engineering Cornell Tech NY10044 United States

Federated learning (FL) enables distributed devices to train a shared machine learning (ML) model collaboratively while protecting their data privacy. However, the resource-limited mobile devices suffer from intensive computation-and-communication costs of model parameters. In this paper, we observe the phenomenon that the model parameters tend to be stabilized long before convergence during training process. Based on this observation, we propose a two-timescale FL framework by joint optimization of freezing stabilized parameters and controlling transmit power for the unstable parameters to balance the energy consumption and convergence. First, we analyze the impact of model parameter freezing and unreliable transmission on the convergence rate. Next, we formulate a two-timescale optimization problem of parameter freezing percentage and transmit power to minimize the model convergence error subject to the energy budget. To solve this problem, we decompose it into parallel sub-problems and decompose each sub-problem into two different timescales problems using the Lyapunov optimization method. The optimal parameter freezing and power control strategies are derived in an online fashion. Experimental results demonstrate the superiority of the proposed scheme compared with the benchmark schemes. © 2002-2012 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Backpropagation Through Agents

arXiv

引用

arXiv 2024年

作者： Li, Zhiyuan Zhao, Wenshuai Wu, Lijun Pajarinen, Joni School of Computer Science and Engineering University of Electronic Science and Technology of China China Department of Electrical Engineering and Automation Aalto University Finland

A fundamental challenge in multi-agent reinforcement learning (MARL) is to learn the joint policy in an extremely large search space, which grows exponentially with the number of agents. Moreover, fully decentralized policy factorization significantly restricts the search space, which may lead to sub-optimal policies. In contrast, the auto-regressive joint policy can represent a much richer class of joint policies by factorizing the joint policy into the product of a series of conditional individual policies. While such factorization introduces the action dependency among agents explicitly in sequential execution, it does not take full advantage of the dependency during learning. In particular, the subsequent agents do not give the preceding agents feedback about their decisions. In this paper, we propose a new framework Back-Propagation Through Agents (BPTA) that directly accounts for both agents’ own policy updates and the learning of their dependent counterparts. This is achieved by propagating the feedback through action chains. With the proposed framework, our Bidirectional Proximal Policy Optimisation (BPPO) outperforms the state-of-the-art methods. Extensive experiments on matrix games, StarCraftII v2, Multiagent MuJoCo, and Google Research Football demonstrate the effectiveness of the proposed method. Copyright © 2024, The Authors. All rights reserved.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

A Novel KL Divergence Optimization Method for Aligning Neural Population Patterns During Task Learning

A Novel KL Divergence Optimization Method for Aligning Neura...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Zhiwei Song Xiang Zhang Yiwen Wang Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong China Department of Electronic and Computer Engineering & Department of Chemical and Biological Engineering Hong Kong University of Science and Technology Hong Kong China

Numerous studies suggest that learning related but different tasks prior to a new task makes it easier, possibly because of our brain's neural pattern alignment mechanism. Specifically, the neural patterns in the new task align with those in the learned task, enabling the reuse of knowledge from the previous task to aid learning in the new task. Brain-machine interface (BMI) is an excellent tool for analyzing the dynamics of neural population patterns during new task learning by directly recording neural signals from the brain. If we can repeat the process of aligning neural pattern using a point registration algorithm with the recorded neural signals, it would provide a computational tool to help us understand the brain mechanism during task learning. Additionally, the pre-trained decoder parameters from the old task can be reused to expedite learning in the new task. However, the existing Iterative Closest Point (ICP) method easily fails as it is sensitive to neural data distribution. This paper proposes a pair-wise Kullback Leibler (KL) divergence optimizing framework for stable neural pattern alignment. The KL divergence measures the difference between the data distribution of the previous task and the aligned new task. The alignment process is formulated as an optimization problem by minimizing the KL divergence. The proposed algorithm is tested in a simulated experiment where a rat learns a two-lever discrimination task from a one-lever pressing task. Three scenarios are designed to test the feasibility of our algorithm, including non-Gaussian neural pattern shapes, noisy neural data, and different alignment angles. The results demonstrate that the proposed method is more robust than ICP, indicating its potential to discover the brain's alignment mechanism more accurately.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variability Tolerance Analysis of Memristive Wave Cellular Automata

Variability Tolerance Analysis of Memristive Wave Cellular A...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Theodoros Panagiotis Chatzinikolaou Ioannis K. Chatzipaschalis Emmanouil Stavroulakis Evangelos Tsipas Iosif-Angelos Fyrigos Antonio Rubio Georgios Ch. Sirakoulis Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi Greece Department of Electronic Engineering Universitat Politécnica de Catalunya Barcelona Spain

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

In the era of high-performance computing, the integration of Cellular Automata (CA) principles into low-power hardware is a challenging but intriguing endeavor. At the same time, memristors have gained attention due to their potential in in-memory neuromorphic computing. As such, the concept of Wave Cellular Automata (WCA) is presented a novel computing paradigm that leverages CA principles and memristive devices for in-memory computing. However, memristive devices are subject to variability effects, which can impact their performance and, in the case of WCAs, the generation of oscillations crucial for computation. This paper explores the variability tolerance analysis of WCA both in CBRAM device level, but also in its oscillatory behavior. The analysis reveals that WCA operation remains robust even in the presence of variability, with the impact on oscillation amplitude being minor. All in all, proper circuit design and element selection play a significant role in mitigating the effects of variability.

关键词： Performance evaluation Neuromorphic engineering High performance computing Automata Memristors Tolerance analysis In-memory computing

来源：评论

学校读者我要写书评

暂无评论

Human-Aligned Longitudinal Control for Occluded Pedestrian Crossing With Visual Attention

Human-Aligned Longitudinal Control for Occluded Pedestrian C...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Vinal Asodia Zhenhua Feng Saber Fallah Department of Mechanical Engineering Sciences University of Surrey Guildford UK School of Computer Science and Electronic Engineering University of Surrey Guildford UK

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Reinforcement Learning (RL) has been widely used to create generalizable autonomous vehicles. However, they rely on fixed reward functions that struggle to balance values like safety and efficiency. How can autonomous vehicles balance different driving objectives and human values in a constantly changing environment? To bridge this gap, we propose an adaptive reward function that utilizes visual attention maps to detect pedestrians in the driving scene and dynamically switch between prioritizing safety or efficiency depending on the current observation. The visual attention map is used to provide spatial attention to the RL agent to boost the training efficiency of the pipeline. We evaluate the pipeline against variants of an occluded pedestrian crossing scenario in the CARLA Urban Driving simulator. Specifically, the proposed pipeline is compared against a modular setup that combines the well-established object detection model, YOLO, with a Proximal Policy Optimization (PPO) agent. The results indicate that the proposed approach can compete with the modular setup while yielding greater training efficiency. The trajectories collected with the approach confirm the effectiveness of the proposed adaptive reward function.

关键词： YOLO Training Visualization Adaptation models Pedestrians Pipelines Switches

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：