检索结果-内蒙古大学图书馆

Deep Learning Approaches for Battery Capacity and State of Charge Estimation with the NASA B0005 Dataset

computers, Materials & Continua 2025年第6期83卷 4795-4813页

作者： Zeyang Zhou Zachary James Ryan Utkarsh Sharma Tran Tien Anh Shashi Mehrotra Angelo Greco Jason West Mukesh Prasad School of Computer Science Faculty of Engineering and Information TechnologyUniversity of Technology SydneyUltimoNSW 2007Australia School of Data Science and Engineering Indian Institute of Science Education and ResearchBhopal462066India Research Institute of Marine Systems Engineering Seoul National UniversitySeoul08826Republic of Korea Department of Computer Science and Engineering Faculty of Engineering and TechnologySRM Institute of Science and TechnologyDelhi NCR CampusGhaziabad201204India Battery System Modelling Department CLARIOS VARTA Hannover GmbHHanover30419Germany Science and Innovation Group Bureau of MeteorologyBrisbane4000Australia

Accurate capacity and State of Charge(SOC)estimation are crucial for ensuring the safety and longevity of lithium-ion batteries in electric *** study examines ten machine learning architectures,Including Deep Belief Network(DBN),Bidirectional Recurrent Neural Network(BiDirRNN),Gated Recurrent Unit(GRU),and others using the NASA B0005 dataset of 591,458 *** indicate that DBN excels in capacity estimation,achieving orders-of-magnitude lower error values and explaining over 99.97%of the predicted variable’s *** computational efficiency is paramount,the Deep Neural Network(DNN)offers a strong alternative,delivering near-competitive accuracy with significantly reduced prediction *** GRU achieves the best overall performance for SOC estimation,attaining an R^(2) of 0.9999,while the BiDirRNN provides a marginally lower error at a slightly higher computational *** contrast,Convolutional Neural Networks(CNN)and Radial Basis Function Networks(RBFN)exhibit relatively high error rates,making them less viable for real-world battery *** of error distributions reveal that the top-performing models cluster most predictions within tight bounds,limiting the risk of overcharging or deep *** findings highlight the trade-off between accuracy and computational overhead,offering valuable guidance for battery management system(BMS)designers seeking optimal performance under constrained *** work may further explore advanced data augmentation and domain adaptation techniques to enhance these models’robustness in diverse operating conditions.

关键词： Battery capacity estimation state of charge deep learning prediction efficiency energy storage systems

来源：评论

学校读者我要写书评

暂无评论

A4FL: Federated Adversarial Defense via Adversarial Training and Pruning Against Backdoor Attack

引用

IEEE Access 2025年 13卷 91070-91088页

作者： Saeed-Uz-zaman Li, Bin Hamid, Muhammad Saleem, Muhammad Aman, Muhammad Yangzhou University School of Information Engineering Yangzhou China Government College Women University Department of Computer Science Sialkot51310 Pakistan Faculty of Engineering King Abdulaziz University Department of Industrial Engineering Rabigh Jeddah21589 Saudi Arabia University of Business and Technology College of Engineering Department of Industrial Engineering Jeddah21448 Saudi Arabia

Backdoor attacks threaten federated learning (FL) models, where malicious participants embed hidden triggers into local models during training. These triggers can compromise crucial applications, such as autonomous systems, when they activate specific inputs, causing a targeted misclassification in the global *** recommend a strong defense mechanism that combines statistical testing, model refinement, and adversarial training methods. The primary goal is to develop a robust defense against backdoor attacks in federated learning (FL), where malicious participants embed hidden triggers into local models. This defense aims to preserve the integrity of the global model and ensure high reliability in real-world FL deployments, even when facing sophisticated adversarial strategies. Our defense strategy incorporates "Messy" samples with obvious triggers and "wrap" samples with similar but nonidentical triggers during adversarial training. This dual approach enhances the model’s ability to detect and resist hidden manipulations. We facilitate applying neuron pruning to remove compromised neurons, further refining the model architecture for improved security. Continuous statistical testing, including variance analysis and cosine similarity checks, ensures that only legitimate and significant updates are integrated into the global model. A key innovation of our method is a significance-based filtering mechanism that effectively identifies and excludes malicious updates, preventing backdoor triggers from affecting the global model. This iterative defense process adapts to attack strategies, maintaining the model’s robustness. Empirical results confirm that this defense mechanism significantly improves FL models’ resilience to sophisticated backdoor attacks while preserving high accuracy and reliability. Balancing defensive strategies from adversarial training and sample diversification to model pruning provides a dependable framework for safeguarding FL models where integ

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Code transformation impact on compiler-based optimization: A case study in the cmssw 11

Code transformation impact on compiler-based optimization: A...

引用

2021 11th International Conference on Applied Physics and Mathematics, ICAPM 2021

作者： Ploensin, Teerit Piromsopa, Krerk Srimanobhas, Norraphat Department of Computer Engineering Faculty of Engineering Chulalongkorn University Thailand Department of Physics Faculty of Science Chulalongkorn University Thailand

In this paper, we study the benefit of applying loop transformations to a part of module in the CMS software. Particularly, we focus at the effect of loop transformations in term of performance improvement from the optimization process of compilers. Loop optimizations have been considered at low-level phase, such as loop unrolling using compiler directive. For high-level code transformations such as index set splitting and loop reordering, we adopt the polyhedral model to simplify the transformations. In this study, our loop optimization has been evaluated quantitatively. We study the impact on loops execution speed up and its instruction executed. Our observation shows that high-level loop optimizations can reduce both execution time and the number of instruction. This behavior suggested that simple loop transformations can trigger other optimizations. Moreover, we not only improve the overall performance, but also reduce the number of instruction. The results show that loop optimizations yield the speed up between 1.5 and 1.7. © Published under licence by IOP Publishing Ltd.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Prediction and Analysis of Power Consumption and Power Loss at Industrial Facilities

Prediction and Analysis of Power Consumption and Power Loss ...

引用

2023 International Conference on Clean Electrical Power, ICCEP 2023

作者： Gracheva, Elena Ivanovna Eduard Elsovich, Ibatullin Sinyukova, Tatiana Valtchev, Stanimir Miceli, Rosario Campagna, Nicola Kazan State Power Engineering University Departm. of Power Supply of Industrial Enterprises Kazan Russia Lipetsk State Technical University Automation and Computer Science Faculty Lipetsk Russia University Nova of Lisbon Faculty Fct and Uninova -CTS Portugal University of Palermo Department of Engineering Italy

ISBN: (纸本)9798350348378

In this article, a study of radial and trunk circuits of networks was carried out and power losses were determined using the proposed coefficients. Equivalent resistances of the investigated circuits were calculated considering the changes in circuit and mode parameters. Results of calculations are presented, considering equipment layout and technical parameters. © 2023 IEEE.

关键词： Equivalent circuits

来源：评论

学校读者我要写书评

暂无评论

MetaCon: Revitalizing Internet Congestion Control with Meta-Reinforcement Learning

MetaCon: Revitalizing Internet Congestion Control with Meta-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： He Bai Hui Li Jianming Que Minglong Zhang Peter Han Joo Chong Kalupahana Liyanage Kushan Sudheera Xinyuan Pei School of Electronic and Computer Engineering Peking University Shenzhen China School of Computer Science Fuyao University of Science and Technology Fuzhou China Department of Electrical and Computer Engineering Mississippi State University Starkville USA School of Engineering Computer and Mathematical Sciences Auckland University of Technology Auckland New Zealand Department of Electrical and Information Engineering Faculty of Engineering University of Ruhuna Sri Lanka

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Effective congestion control algorithms (CCAs) are crucial for the smooth operation of Internet communication infrastructure. CCAs adjust transmission rates based on congestion signals, optimizing resource utilization and user experience. However, existing studies, both rule-based and learning-based CCAs, often struggle with generalization and underperform when deployed in real-world environments. When applied to unseen network conditions, hand-crafted schemes or pre-trained models may experience significant performance degradation. To address this challenge, we propose MetaCon, a novel adaptive Internet congestion control approach based on meta-reinforcement learning. MetaCon leverages knowledge learned from prior scenarios to quickly adapt to new environments. Experimental results show that MetaCon outperforms existing algorithms by exhibiting superior generalization and achieving better transmission performance across a wide variety of network conditions.

关键词： Degradation Adaptation models Signal processing algorithms Signal processing User experience Acoustics Internet Resource management Speech processing

来源：评论

学校读者我要写书评

暂无评论

IoT Based Health Monitoring System with AI-Powered Disease Prediction 9

IoT Based Health Monitoring System with AI-Powered Disease P...

引用

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Radha Mahendran, S. Khan, Mohammad Shahbaz Hari Priya, M.P. Obaid, Ahmed J. Mohsen, Karrar Shareef Shareef, Ashraf Mohammed Department of Bioinformatics Chennai Pallavaram117 India Operations And Regulatory Affairs Children's National Hospital WashingtonDC United States Department of Computer Science Kothanur K.Narayanapura Karnataka Bangalore560077 India University of Kufa Technical Engineering College Al-Ayen University Faculty of Computer Science And Mathematics Najaf Iraq Department of Computer Technical Engineering Thi-Qar Iraq Scientific Research Center Al-Ayen University Information And Communication Technology Research Group Thi-Qar Iraq National University of Science And Technology DhiQar Iraq

ISBN: (纸本)9798350365092

Healthcare monitoring systems have advanced significantly in emergency rooms and many other health settings. Today, many nations are deeply concerned about the rise of small healthcare monitoring systems. In-person advising and telemedicine are two different ways that the Internet of Things (IoT) is further developing healthcare. The Internet of Things makes things and individuals reliably available, and its relationship with the cloud improves our personal satisfaction. Proactive clinical exploration can help change a responsive healthcare approach into a proactive one, as man-made reasoning (AI) and high-level human insight become increasingly more coordinated into the healthcare area. Within the field of machine learning, deep learning holds significant potential in precisely and swiftly analysing vast quantities of data, producing perceptive experiences, and resolving intricate issues. Preventive treatment and early intervention for persons who are at risk depend on accurate and useful illness prediction. The constant inflow of electronic medical information necessitates the need for more accurate prediction models in recurrent neural network versions of deep learning that handle successive time-series data. Devices connected to the Internet of Things provide data to the proposed system, and future analysis will be conducted on cloud-stored electronic clinical records pertaining to patient histories. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Based System to Predict the Plant Disease Using Streamlit

A Deep Learning Based System to Predict the Plant Disease Us...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Mohan K. Warbhe Joy Jordan Bore Shiv Nath Chaudari Department of Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Sawangi Wardha Maharashtra India Department of Computer Science and Medical Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research(DU)Sawangi Wardha Maharashtra India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

The proposed web application for tomato leaf disease detection exemplifies the transformative power of Artificial Intelligence and computer Vision in modern agriculture. Addressing the critical issue of early and accurate disease detection, this solution bridges the gap between advanced technological innovations and the practical needs of farming. The application is designed using Streamlit and Python to combine the usability of a friendly interface with the power of robust analytical capabilities in CNN, offering real-time reliable diagnosis and actionable insights to farmers. This application provides the highest possible accuracy and adaptability through the thorough training and evaluation of models and is a good asset for disease management. Deployment on scalable cloud platforms ensures access, reliability, and global reach. Future improvements, including extending disease detection to other crops, multilingual support, real-time recommendations, and integration with IoT devices, promise to expand its reach and utility. This initiative is a shining example of how AI-based solutions can transform agricultural practices by enhancing productivity, reducing losses, and ensuring sustainability. The application empowers farmers and contributes to a resilient agricultural ecosystem, addressing the pressing need for innovative and sustainable solutions in a rapidly evolving world.

关键词： Training Technological innovation Accuracy Crops Real-time systems Multilingual Internet of Things Artificial intelligence Diseases Farming

来源：评论

学校读者我要写书评

暂无评论

Intelligent Sentiment Analysis on Cellphone Checking by Police Officer 9

Intelligent Sentiment Analysis on Cellphone Checking by Poli...

引用

9th International Conference on Electrical engineering, computer science and Informatics, EECSI 2022

作者： Prasetyo, Barep Triana, Yaya Sudarya Budiarto, Rahmat Stiawan, Deris University of Mercu Buana Faculty of Computer Science Tangerang Indonesia Universitas Mercu Buana Faculty of Computer Science Jakarta Indonesia Universitas Sriwijaya Faculty of Computer Science Computer Engineering Department Palembang Indonesia

ISBN: (数字)9786239213565

ISBN: (纸本)9781665470438

Twitter is one of social media used by the public to send and read tweets that have been shared, making it easier to express their opinions. The opinions found on Twitter are perceptions, both positive and negative. The abundance of public opinion can be used as research material to find information. The use of this information requires appropriate analytical techniques so that the gained information may help many parties in making decisions. Sentiment analysis technique is one of them. In this study, sentiment analysis was carried out to find out the publics opinion on the case of civilians cellphone inspection/checking by a police officer. Naïve Bayes classifier and Support Vector Machine (SVM) classifier as comparison are employed and combined with RapidMiner and Python tools. Experimental results show SVM classifier provides the highest accuracy value of 94% for a 90:10 split ratio dataset with automatic labeling. © 2022 Institute of Advanced engineering and science (IAES).

关键词： Naïve Bayes Sentiment Analysis Social Media Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

XU-NetI: Simple U-shaped encoder-decoder network for accurate imputation of multivariate missing data

Franklin Open

引用

Franklin Open 2024年 8卷

作者： Firdaus, Firdaus Nurmaini, Siti Tutuko, Bambang Rachmatullah, Muhammad Naufal Islami, Anggun Darmawahyuni, Annisa Sapitri, Ade Iriani Karim, Muhammad Irfan Fachrurrozi, Muhammad Zarkasi, Ahmad Intelligent System Research Group Faculty of Computer Science Universitas Sriwijaya South Sumatera 30139 Indonesia Department of Informatic Engineering Faculty of Computer Science Universitas Sriwijaya Palembang 30139 Indonesia Department of Computer Engineering Faculty of Computer Science Universitas Sriwijaya Indonesia

Patients in intensive care unit (ICU) often have multiple vital signs monitored continuously. However, missing data is common in ICU settings, negatively impacting clinical decision-making and patient outcomes. In this study propose a multivariate data imputation method based on simple U-Shaped encoder-decoder network imputation (XU-NetI) method to learn the underlying patterns in the data and generate imputations for missing values of vital signs data with ICU patients. To evaluate the performance of this study's imputation methods, this study employed a publicly available database such the medical information mart for intensive care III (MIMIC III) v1.4. In this study proposed model has been developed to analyze 219.281 vital sign worth of data, focusing on eight essential vital sign features: body temperature, heart rate, respiration rate, systolic blood pressure, diastolic blood pressure, mean blood pressure, oxygen saturation, and glucose. The evaluation results demonstrates the effectiveness of the imputation techniques in improving the accuracy of predictive models. This study compared the XU-NetI approach to other state-of-the-art imputation methods including Autoencoder and Convolutional Neural Networks. As a result found, the technique using XU-NetI architecture outperformed them, in terms of root mean square error (RSME) by approximately 0.01, mean absolute error (MAE) by approximately 0.009, and R square (R2) by approximately 0.99. The XU-NetI method has the potential to enhance clinical decision-making and improve patient outcomes. © 2024 The Author(s)

关键词： Convolutional neural network Deep Learning Missing data imputation U-shaped encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in Smart IoT Devices for People with Disabilities 8

Intrusion Detection in Smart IoT Devices for People with Dis...

引用

8th IEEE International Smart Cities Conference, ISC2 2022

作者： Naveed, Muhammad Usman, Syed Muhammad Satti, Muhammad Islam Aleshaiker, Sama Anwar, Aamir Shaheed Zulfikar Ali Bhutto Institute of Science and Technology Department of Computer Science Islamabad Pakistan Ai Air University Faculty of Computing Department of Creative Technologies Islamabad Pakistan Riphah University Faculty of Computer Science and Software Engineering Islamabad Pakistan School of Computing & Engineering University of West London London United Kingdom

ISBN: (数字)9781665485616

ISBN: (纸本)9781665485616

An intrusion Detection System (IDS) is a system that resides inside the network and monitors all incoming and outgoing traffic. It prevents unethical activities from happening over the network. With the use of IoT devices, network traffic is also increased. Intruders and hackers are attracted to this network because of its low processing power and openness. IoT has transformed diagnostic and monitoring systems for patients in the healthcare industry. However, a secure network is needed for these health care devices. This research proposes a hybrid model to secure the IoT network from external intrusions. The proposed method consists of preprocessing data with the help of normalization and feature selection by removing high correlated features with the help of the Pearson correlation coefficient and Support Vector Machine (SVM) for classification. The proposed approach has achieved an accuracy of 99.3%, precision of 99.1% and an F-1 score of 99.25% on the standard dataset. Results have been compared with state-of-the-art, and the proposed method outperforms all performance measures. © 2022 IEEE.

关键词： Support vector machines

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：