检索结果-内蒙古大学图书馆

Optimizing Bearing Fault Detection:CNN-LSTM with Attentive TabNet for Electric Motor Systems

computer Modeling in engineering & Sciences 2024年第12期141卷 2399-2420页

作者： Alaa U.Khawaja Ahmad Shaf Faisal Al Thobiani Tariq Ali Muhammad Irfan Aqib Rehman Pirzada Unza Shahkeel Nautical Science Department Faculty of MaritimeKing Abdulaziz UniversityJeddah22230Saudi Arabia Department of Computer Science COMSATS University IslamabadSahiwal CampusSahiwal57000Pakistan Marine Engineering Department Faculty of MaritimeKing Abdulaziz UniversityJeddah22230Saudi Arabia Artificial Intelligence and Sensing Technologies(AIST)Research Center University of TabukTabuk71491Saudi Arabia Electrical Engineering Department College of EngineeringNajran UniversityNajran61441Saudi Arabia

Electric motor-driven systems are core components across industries,yet they’re susceptible to bearing *** fault diagnosis poses safety risks and economic instability,necessitating an automated *** study proposes FTCNNLSTM(Fine-Tuned TabNet Convolutional Neural Network Long Short-Term Memory),an algorithm combining Convolutional Neural Networks,Long Short-Term Memory Networks,and Attentive Interpretable Tabular *** model preprocesses the CWRU(Case Western Reserve University)bearing dataset using segmentation,normalization,feature scaling,and label *** architecture comprises multiple 1D Convolutional layers,batch normalization,max-pooling,and LSTM blocks with dropout,followed by batch normalization,dense layers,and appropriate activation and loss ***-tuning techniques prevent *** were conducted on 10 fault classes from the CWRU *** was benchmarked against four approaches:CNN,LSTM,CNN-LSTM with random forest,and CNN-LSTM with gradient boosting,all using 460 *** FTCNNLSTM model,augmented with TabNet,achieved 96%accuracy,outperforming other *** establishes it as a reliable and effective approach for automating bearing fault detection in electric motor-driven systems.

关键词： Electric motor-driven systems bearing faults automation fine tunned convolutional neural network long short-term memory fault detection

来源：评论

学校读者我要写书评

暂无评论

Irrigation System Based on IOT and Machine Learning Approach

引用

International Virtual Conference on Industry 4.0, IVCI4.0 2021

作者： Stephen, Ancy Punitha, A. Chandrasekar, A. Research Scholar Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Annamalai Nagar Tamil Nadu Chidambaram India Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Annamalai Nagar Tamil Nadu Chidambaram India Department of Computer Science and Engineering St. Joseph’s College of Engineering OMR Tamil Nadu Chennai India

ISBN: (纸本)9789811999888

Irrigation is an essential role in forming. Due to technological development, it is not needed to depend on someone to do irrigation when we are away. So, this paper specifies how automatic irrigation can be per-formed. To perform automatic irrigation, the proposed system consists of a wireless sensor network along with real-time sensor and control of an irrigation system. This system helps to maintain the required water in the form and helps to avoid wastage. The automatic ON/OFF the pumping motor in automatic irrigation depends on the dampness of the soil. The dryness of the soil can be predicted using machine learning algorithms such as KNN algorithm and Naive Bayes algorithm. Then the linear algorithm is used to calculate the water quantity requirement and prediction for the next water cycle. Finally, artificial neural network algorithm is implemented for pumping ON/OFF prediction. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Irrigation

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning In Autonomous Cars To Preventing Road Accident 2

Deep Reinforcement Learning In Autonomous Cars To Preventing...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Thote, Rushikesh Barhate, Aditya Tale, Abhay Verma, Prateek Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha India

ISBN: (纸本)9798331528713

The integration of autonomous vehicles (AVs) into modern transportation systems presents both unprecedented opportunities and challenges, particularly in ensuring road safety and reducing accidents. This paper explores the application of Deep Reinforcement Learning (DRL) techniques to enhance decision-making processes in AVs, aiming to proactively prevent road accidents. By simulating complex driving environments, DRL algorithms enable AVs to learn optimal driving strategies through continuous interaction and feedback. We introduce a DRL-based framework that incorporates sensor data fusion, real-time environment analysis, and adaptive control mechanisms. Experimental results from simulated urban and highway scenarios demonstrate a significant reduction in collision rates and improved response to unforeseen obstacles compared to traditional rule-based systems. The findings underscore the potential of DRL in fortifying the reliability and safety of autonomous driving technologies. © 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

GastroFuse-Net: an ensemble deep learning framework designed for gastrointestinal abnormality detection in endoscopic images

引用

Mathematical Biosciences and engineering 2024年第8期21卷 6847-6869页

作者： Aggarwal, Sonam Gupta, Isha Kumar, Ashok Kautish, Sandeep Almazyad, Abdulaziz S. Mohamed, Ali Wagdy Werner, Frank Shokouhifar, Mohammad Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Model Institute of Engineering and Technology J&K Jammu India Chandigarh University Punjab Mohali140413 India Department of Computer Engineering College of Computer and Information Sciences King Saud University P.O. Box 51178 Riyadh11543 Saudi Arabia Operations Research Department Faculty of Graduate Studies for Statistical Research Cairo University Giza12613 Egypt Applied Science Research Center Applied Science Private University Amman11931 Jordan Faculty of Mathematics Otto-von-Guericke University Magdeburg39016 Germany Institute of Research and Development Duy Tan University Da Nang550000 Viet Nam

Convolutional Neural Networks (CNNs) have received substantial attention as a highly effective tool for analyzing medical images, notably in interpreting endoscopic images, due to their capacity to provide results equivalent to or exceeding those of medical specialists. This capability is particularly crucial in the realm of gastrointestinal disorders, where even experienced gastroenterologists find the automatic diagnosis of such conditions using endoscopic pictures to be a challenging endeavor. Currently, gastrointestinal findings in medical diagnosis are primarily determined by manual inspection by competent gastrointestinal endoscopists. This evaluation procedure is labor-intensive, time-consuming, and frequently results in high variability between laboratories. To address these challenges, we introduced a specialized CNN-based architecture called GastroFuse-Net, designed to recognize human gastrointestinal diseases from endoscopic images. GastroFuse-Net was developed by combining features extracted from two different CNN models with different numbers of layers, integrating shallow and deep representations to capture diverse aspects of the abnormalities. The Kvasir dataset was used to thoroughly test the proposed deep learning model. This dataset contained images that were classified according to structures (cecum, z-line, pylorus), diseases (ulcerative colitis, esophagitis, polyps), or surgical operations (dyed resection margins, dyed lifted polyps). The proposed model was evaluated using various measures, including specificity, recall, precision, F1-score, Mathew’s Correlation Coefficient (MCC), and accuracy. The proposed model GastroFuse-Net exhibited exceptional performance, achieving a precision of 0.985, recall of 0.985, specificity of 0.984, F1-score of 0.997, MCC of 0.982, and an accuracy of 98.5%. ©2024 the Author(s), licensee AIMS Press.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Energy Management of Networked Smart Railway Stations Considering Regenerative Braking, Energy Storage System, and Photovoltaic Units

引用

Energy engineering 2023年第1期120卷 69-86页

作者： Saeed Akbari Seyed Saeed Fazel Hamed Hashemi-Dezaki School of Railway Engineering Iran University of Science and TechnologyTehran13114-16846Iran Department of Electrical and Computer Engineering University of KashanKashan***Iran Research and Innovational Center for Electrical Engineering(RICE) Faculty of Electrical EngineeringUniversity ofWest Bohemia(UWB)Pilsen30100Czech Republic

The networking of microgrids has received significant attention in the form of a smart *** this paper,a set of smart railway stations,which is assumed as microgrids,is connected *** has been tried to manage the energy exchanged between the networked microgrids to reduce received energy from the utility ***,the operational costs of stations under various conditions decrease by applying the proposed *** smart railway stations are studied in the presence of photovoltaic(PV)units,energy storage systems(ESSs),and regenerative braking *** regenerative braking is one of the essential ***,the stochastic behaviors of the ESS’s initial state of energy and the uncertainty of PV power generation are taken into account through a scenario-based *** networked microgrid scheme of railway stations(based on coordinated operation and scheduling)and independent operation of railway stations are *** proposed method is applied to realistic case studies,including three stations of Line 3 of Tehran Urban and Suburban Railway Operation Company(TUSROC).The rolling stock is simulated in the MATLAB ***,the coordinated operation of networked microgrids and independent operation of railway stations are optimized in the GAMS environment utilizing mixed-integer linear programming(MILP).

关键词： Energy management system(EMS) smart railway stations coordinated operation photovoltaic generation regenerative braking uncertainty scenario-based model mixed-integer linear programming(MILP)

来源：评论

学校读者我要写书评

暂无评论

A Review on Digital Image Watermarking Techniques Using Neural Networks 7th

A Review on Digital Image Watermarking Techniques Using Neur...

引用

7th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2023

作者： Gorbal, Mangalagowri Shelke, Ramesh Joshi, Manuj Faculty of Computer Engineering Pacific Academy of Higher Education and Research University Udaipur India Pacific Academy of Higher Education and Research University Udaipur India

ISBN: (纸本)9789819937608

In the current digital age, the extraordinary development and usage of Internet Technology and Communication networks have made exchange and transmission of digital content much easier and quicker. This has given rise to the threat of privacy, unauthorized circulation, duplicating, copying, and editing of multimedia content. Hence copyright protection and ensuring the authenticity of digital content is still a paramount challenge. Data hiding method such as watermarking has become key player in solving this biggest challenge of the multimedia world. Digital watermarking is used to secure digital contents by embedding a watermark with the digital host image at the transmission end and extraction of a watermark is done from the watermarked image at the receiving end, to authenticate the ownership of the image. Numerous methods of watermarking have been proposed by different authors. The frequency domain methods are very prevalent approaches as they exhibit superior performance in terms of imperceptibility and robustness. Recently, several watermarking algorithms used soft computing techniques like neural networks to preferment these characteristics and attain equipoise between robustness and imperceptibility. The greatest forte of a neural network is its learning and adaptation ability. This ability of the neural network enhances the capabilities of conventional methods used in watermarking by memorizing the actual relation between the watermarked host image and watermark data. This paper gives a review of the current trends in neural network-based Image watermarking techniques to uncover the state-of-the-art approaches and their performance evaluations. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Prediction of Heart Disease Using Machine Learning Algorithms 2

Prediction of Heart Disease Using Machine Learning Algorithm...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Burle, Rushikesh Gaurkhede, Sanskruti Dewangan, Leelkanth Pacharaney, Utkarsha Datta Meghe Institute of Higher Education and Research Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Mahartashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Computer Science and Design Faculty of Engineering and Technology Mahartashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Artificial Intelligence and Data Science Faculty of Engineering and Technology Maharashtra Wardha442001 India

ISBN: (纸本)9798350360523

In India, heart disease claims the lives of about one person every day. The human body's most vital organ is the heart. The heart has two primary purposes: first, it gathers blood from body tissues and pumps it to the lungs;second, it gathers blood from the lungs and pumps it to all body *** disease has claimed the lives of many people. Predicting that disease at the appropriate moment is crucial, for this reason. Making use of machine learning Additionally, illnesses are easily identified and anticipated. It also covers the use of many algorithms on the Heart Disease Dataset. The dataset used in this research was obtained from Kaggle. Analyzing fundamental machine learning algorithms for the prediction of heart disease, such as Random Forest, K-Nearest Neighbours, Decision Tree Classifier, and Support Vector Machine, is the primary goal of this study. Our Acquired Model for The Decision Tree Classifier has a score of 79.0%. And the Random Forest Classifier has an 84.0% score. With a linear kernel, the Support Vector Classifier scores 83.0%. Next, K Neighbours Classifier~ outperformed all previously employed methods, achieving the maximum score of {87%} with ~8 nearest result. RF (Random Forest), K-Nearest Neighbours Algorithm, and Decision Tree, together with Python programming and Visual Studio, which excels at both data and code. © 2024 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Optimal coordination of Production, Logistics, and Maintenance 4.0: A framework for Multi-Site Stamping Plants 6

Optimal coordination of Production, Logistics, and Maintenan...

引用

6th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Zerrad, Raoua Diaz, Kamar Mechkouri, Meriem Hayani Sefiani, Naoufal Department of Mechanical Engineering Research Laboratory in Engineering Innovation and Management of Industrial Systems Faculty of Sciences and Techniques Abdelmalek Essaadi University Tangier Morocco Department of Industrial Engineering and Maintenance Computer Engineering Production and Maintenance Laboratory University of Lorraine Metz France

This paper presents a comprehensive framework for optimal coordination of production, logistics, and maintenance in multi-site stamping plants within the context of Industry 4.0. By integrating key technologies such as the Internet of Things, cloud computing and big data analytics, we developed a system that would enable real-time data sharing, predictive analytics, and intelligent decision-making. This framework aims to enhance operational efficiency, reduce downtime, and improve service rate. Additionally, our approach aims to optimize spare parts inventory management across different sites, minimizing inventory costs and lead times by ensuring timely availability and efficient sourcing of spare parts. © 2024 The Authors. Published by Elsevier B.V.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Parkinson's Disease Detection Through Machine Learning Techniques

A Comprehensive Study on Parkinson's Disease Detection Throu...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Burle, Rushikesh Gaurkhede, Sanskruti Fulkar, Bhushan Gundewar, Swapnil Pacharaney, Utkarsha Verma, Prateek Datta Meghe Institute of Higher Education and Research Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Mahartashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Computer Science and Design Faculty of Engineering and Technology Mahartashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Artificial Intelligence and Data Science Faculty of Engineering and Technology Mahartashtra Wardha442001 India

ISBN: (纸本)9798350375237

One of the biggest issues with worldwide public health is Parkinson's disease (PD). It is usually known that about are around one million Americans who have Parkinson's disease, whereas there are approximately five million cases of the condition globally. As a result, it's critical to identify Parkinson's disease early on and make the appropriate treatment plans. These days, machine learning is essential for analysing problems in real time and offering answers thanks to its widely used algorithms. These days, machine learning algorithms are used in the healthcare industry to identify patients' health problems. This research went into great detail about the methods used using algorithms that use machine learning to classify Parkinson's disease. A fault in the brain cells that generate dopamine, a necessary chemical for synapses to connect with one another, is the cause of Parkinson's disease. The brain's dopamine-producing neurons are in charge of control, flexibility, and event familiarity. When 60-80% of these cells disappear, inadequate dopamine is produced, which causes Parkinson's disease symptoms to manifest. In this case, the Random Forest, Decision Tree, K-Nearest Neighbours, and Support Vector Machine techniques were used to identify the illness. Compared to Decision Tree and Support Vector Machine, Random Forest and K-Nearest Neighbours offer the best performance. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Preventing Diabetes: Substituting Processed Foods and Nutritional Chatbot Assistance 1

引用

5th International Conference on Applied Technologies, ICAT 2023

作者： Solano, Pablo Herrera, Víctor Abril-Ulloa, Victoria Espinoza-Mejía, Mauricio Faculty of Engineering University of Cuenca Cuenca Ecuador Technologies Applied to Health Research Group Faculty of Medical Sciences University of Cuenca Cuenca Ecuador Computer Science Department University of Cuenca Cuenca Ecuador

ISBN: (数字)9783031589539

ISBN: (纸本)9783031589522

Type 2 Diabetes Mellitus (T2DM) is one of the biggest threats to Ecuador’s health. The intake of processed foods has been linked to a higher risk of T2DM. This paper proposes FoodSub, a mobile application to recommend substitutes for processed foods using the NOVA Classification. Nutrient-based food clustering is used to identify substitute pairs between processed and unprocessed foods. The recommendations are supported and personalized using a knowledge graph that contains foods, dietary guidelines, and user information. In addition, a chatbot is implemented to answer simple questions about foods. This chatbot is developed using a Large Language Model (LLM) to query the knowledge graph. The mobile application and the chatbot are evaluated in terms of usability;both perform well, but there is room for improvement. Additionally, the recommendations’ performance is evaluated through expert verification. The recommendations perform well when issues like food transformation processes, flavor, context, or meal time are not relevant. Future work will consider the enhancement of the chatbot and the improvement of substitute recommendations for the relevant cases. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Nutrition

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：