检索结果-内蒙古大学图书馆

Selective and Adaptive Incremental Transfer Learning with Multiple Datasets for Machine Fault Diagnosis

Computers, Materials & Continua 2024年第1期78卷 1363-1379页

作者： Kwok Tai Chui Brij B.Gupta Varsha Arya Miguel Torres-Ruiz School of Science and Technology Hong Kong Metropolitan UniversityHong Kong999077China Department of Computer Science and Information Engineering Asia UniversityTaichung41354Taiwan Center for Advanced Information Technology Kyung Hee UniversitySeoul02447Korea Symbiosis Centre for Information Technology Symbiosis International UniversityPuneMaharashtra411042India Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon School of Computing Skyline University CollegeSharjah1797United Arab Emirates Department of Business Administration Asia UniversityTaichung41354Taiwan Center for Interdisciplinary Research University of Petroleum and Energy StudiesDehradun248007India Department of Computer Science&Engineering Chandigarh UniversityChandigarh160036India Centro de Investigación en Computación Instituto Politécnico NacionalUPALM-ZacatencoMexico City07320Mexico

The visions of Industry 4.0 and 5.0 have reinforced the industrial *** have also made artificial intelligence incorporated as a major *** machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe *** learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two *** response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning *** is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative *** algorithm also adaptively adjusts the portion of training data to balance the learning rate and training *** proposed algorithm is evaluated and analyzed using ten benchmark *** with other algorithms from existing works,SA-ITL improves the accuracy of all *** studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.

关键词： Deep learning incremental learning machine fault diagnosis negative transfer transfer learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Temporal Data Mining Technique Using Dynamic Time Warped LSTM for E-Commerce Recommendation Systems 3rd

Efficient Temporal Data Mining Technique Using Dynamic Time ...

引用

3rd International Conference on Intelligent Systems and Sustainable computing, ICISSC 2023

作者： Rajassekharan, Dinesh Subramanian, Jayasundar Lazar, Arokia Jesu Prabhu Pichuka Veera Venkata Satya, Srinivas Ray, Samrat Ammasai, Viswanathan Sengan, Sudhakar Faculty of AI Computing and Multimedia Lincoln University College Petaling Jaya47301 Malaysia Department of Computer Science and Engineering Idhaya Engineering College For Women Tamil Nadu Chinnasalem606201 India Department of Computer Science and Engineering CMR Institute of Technology Hyderabad501401 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522502 India Dean Head of International Relations IIMS Pune411033 India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627451 India

ISBN: (纸本)9789819783540

The rapid surge of the electronic commerce (Ecomm) industry has ushered in intensified competition, with platforms vying for customer attention and loyalty. Many Ecomm sites have been employing various tactics to stand out, with Recommendation Systems (RS at the forefront of their strategies. However, traditional RS faces challenges, mainly when interactions occur at irregular intervals. This article introduces the DTW + LSTM framework, a methodology combining the merits of Long Short-Term Memory Networks and Dynamic Time Warping to improve this work. This method requires consideration of DTW's time series data alignment capabilities to account for interaction interval variability. The LSTM is then designed to accurately record the key elements of user interactions in sequential order. Combining the outcomes of these two methodologies in the DTW + LSTM model presents a more flexible and extensive approach to generating online shopping recommendations. The design guarantees that forecasts continue to be reliable and accurate despite the inherent temporal deviations that can be observed in user data. This paper investigates the context of this approach, its benefits, and prospective developments, demonstrating its possibilities in the dynamic Ecomm market. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Accuracy CNN E-commerce F1-score GRU LSTM Machine learning

来源：评论

学校读者我要写书评

暂无评论

Alzheimer Disease Detection System using AlexNet a novel Eight Layered Convolutional Neural Network

Alzheimer Disease Detection System using AlexNet a novel Eig...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Jenifel, M. Geetha Shyamala Devi, M. Umanandhini, D. Srm Institute of Science and Technology Data Science and Business Systems School of Computing Tamil Nadu Chengalpattu603203 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Computer Science & Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350308167

Alzheimer's disease (AD), an incurable brain ailment that is irreversible, affects thinking and memory while also shrinking the size of the mind as a whole. Alzheimer's is a neurological illness that causes severe memory loss and makes it difficult to carry out regular chores. The development of more effective treatments for AD depends on an early diagnosis of the condition. Finding Alzheimer's disease is a difficult and time-consuming task that requires a brain imaging report and competent people. This time-consuming and frequently inaccurate method of diagnosing Alzheimer's is traditional. There has been discussion of a different strategy that is quick, inexpensive, and more dependable. Better medical care and solutions can be provided with the use of artificial intelligence technologies. Due to distractions, technological flaws, cognitive biases, and weariness, human diagnosis performance suffers. However, AI-based diagnosis tools support physicians' safe detection and decision-making and are less prone to error. This study offers a clever and trustworthy method for identifying Alzheimer's disease and its potential early stage, moderate mental impairment. The given system accurately diagnoses Alzheimer's disease and its early stages from structural MRI images and is based on deep learning. The ability to predict whether patients with moderate cognitive impairment (MCI) may develop Alzheimer's disease is essential in clinical practice and has the potential to significantly improve clinical studies. To classify Alzheimer's disease and its prodromal stages, this initiative suggests combining MRI data with the Mini-Mental State Examination (MMSE), a neuropsychological test. © 2023 IEEE.

关键词： AlexNet Alzheimer Disease Convolutional Neural Network Mild Cognitive Impairment Mini-Mental State Examination

来源：评论

学校读者我要写书评

暂无评论

Prediction of High Heating Value Using ANN Technique Aftermath Natural Disasters 21

Prediction of High Heating Value Using ANN Technique Afterma...

引用

2024 IEEE/ACS 21st International Conference on Computer Systems and Applications, AICCSA 2024

作者： Thakur, Disha Kumar, Sanjay Sharma, Bhisham Dhaou, Imed Ben UIT Himachal Pradesh University Department of Civil Engineering Shimla India UIT Himachal Pradesh University Department of Electrical Engineering Shimla India Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Centre for Research Impact & Outcome Punjab 140401 India Hekma School of Engineering Computing and Design Dar Al-Hekma University Department of Computer Science Jeddah Saudi Arabia

ISBN: (纸本)9798331518240

Natural disasters, particularly earthquakes and floods, can generate substantial waste, presenting challenges for waste management and energy recovery. This study explores the application of machine learning, specifically Artificial Neural Networks (ANN), to optimize Waste-to-Energy (WTE) conversion processes for disaster-generated Municipal Solid Waste (MSW). Using data from Sundernagar City, India, we constructed and evaluated multiple ANN models (collectively named ANNSNAGAR) to estimate High Heating Value, HHV, based on ultimate/elemental analysis of MSW. The models were rigorously assessed using statistical error metrics. Our best-performing network, with a 9-50-1 architecture (ANNMS), achieved a mean absolute percentage error (MAPE) of 1.47%, demonstrating high predictive accuracy. © 2024 IEEE.

关键词： Artificial Neural Network Energy Energy Content Machine learning Municipal Solid Waste

来源：评论

学校读者我要写书评

暂无评论

MMCo-Clus - An Evolutionary Co-clustering Algorithm for Gene Selection (Extended abstract) 39

MMCo-Clus - An Evolutionary Co-clustering Algorithm for Gene...

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Cui, Laizhong Acharya, Sudipta Mishra, Sumit Pan, Yi Huang, Joshua Zhexue Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Queen's University School of Computing ON Canada Indian Institute of Information Technology Department of Cse Assam Guwahati India Chinese Academy of Sciences Shenzhen Institute of Advanced Technology China

ISBN: (纸本)9798350322279

Dimensionality reduction through feature selection becomes inevitable to overcome the problem of the Curse of dimensionality. In this article, we propose a feature (gene) selection method for high dimensional gene expression (GE) data through a Multi-objective optimization-based Multi-view Co-Clustering algorithm (named MMCo-Clus). A thorough comparative analysis with existing feature selection algorithms using external/internal evaluation metrics supports our proposed method's potency. © 2023 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Guardians of Truth: Exploring Techniques for Veracity Identification in social media during an Infodemic

Guardians of Truth: Exploring Techniques for Veracity Identi...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： P. Suthanthiradevi G Revathy P Sathish Kumar B Karthikeyan Lakshmi.V Muthu Data Science and Business Systems School of Computing SRM institute of Science and Technology India Department of Computer science and engineering Vels Institute of science Technology and Advanced studies India Computer and Communication Engineering Rajalakshmi institute of technology India School of Computing SASTRA Deemed University India Department of Computer Science and Engineering St. Joseph’s Institute of Technology India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

With the recent advent of technology, social networks are accessible 24/7 using mobile devices. During covid-19 pandemic the propagation of misinformation are mostly related to the disease, its cures and prevention. With Twitter as the medium this information was spreaded to millions of people who lack domain specific knowledge. This can lead to bloster fear and direct damage to the people. This research focuses on identifying the veracity of the Twitter posts behind pandemic situation. The authors have proposed a Transformer Model using Bat Algorithm for identifying the fake news. This model is trained and evaluated using infodemic metadata. Our experimental results shows by which proposed model accurately detected the fake news and achieved 96.5% of f1-score.

关键词： COVID-19 Social networking (online) Pandemics Blogs Predictive models Transformers Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Student's Performance Prediction Using Machine Learning Algorithms- A Comparative Study

Student's Performance Prediction Using Machine Learning Algo...

引用

2024 OPJU International technology Conference on Smart computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Kadu, Varun Mishra, Pawan Kumar Dandhare, Sarthak Patni, Jagdish Chandra Chandel, Palash Pathak, Soham Bahadure, Nilesh Symbiosis Institute of Technology Siu Nagpur Campus Pune India Graphic Era Deemed to Be University Computer Science & Engineering Dehradun India Alliance University Alliance School of Advance Computing Dept. of Cse Karnataka Bengaluru India Nagpur Campus Pune India

ISBN: (纸本)9798350373783

Predicting and enhancing student performance has been a crucial topic of concentration in education amid the quick development of technology and the increasing need for higher-quality instruction. The use of machine learning technology to forecast pupils' academic success is covered in detail in this study report. This research project examined several prediction models that reliably predict students' performance according to a range of extracurricular and academic attributes. An overview of machine learning methods is given in this paper to automate the process of predicting students' academic performance and extracting outcomes. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

FlexAE: A Self-Conditioned Detector To Prevent Model Overfitting For Unsupervised Video Anomaly Detection

FlexAE: A Self-Conditioned Detector To Prevent Model Overfit...

引用

IEEE International Conference on Image Processing

作者： Junqi Chen Xu Tan Jiawei Yang Sylwan Rahardja Susanto Rahardja School of Marine Science and Technology Northwestern Polytechnical University China Faculty of Technology University of Turku Finland School of Computing University of Eastern Finland Finland Engineering Cluster Singapore Institute of Technology Singapore

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Unsupervised Video Anomaly Detection (VAD) has garnered significant attention for its ability to exploit unlabeled videos. However, VAD faces two primary challenges arising from the absence of labels: (i) Striking a balance between overfitting and underfitting, and (ii) Optimal parameter tuning. To tackle these challenges, we propose a novel detector named Flexible AutoEncoder (FlexAE). A fitting-parameter is introduced to regulate the model’s fitting capacity, and a novel Negative Learning (NL) mechanism is integrated to mitigate the influence of anomalies during training. For self-conditioning, a novel algorithm is devised to autonomously update the fitting-parameter and the threshold used in NL based on the reconstruction error. Comprehensive experiments on two benchmark datasets, UCF-Crime and ShanghaiTech, demonstrate that our proposed FlexAE outperforms state-of-the-art methods without the need for manual hyperparameter tuning.

关键词： Training Fitting Detectors Tail Manuals Benchmark testing Tuning

来源：评论

学校读者我要写书评

暂无评论

Short-term Household Electricity Load Forecasting Based on Non-intrusive Load Monitoring using Long-short Term Memory

Short-term Household Electricity Load Forecasting Based on N...

引用

2022 International Symposium on Computer Applications and Information Systems, ISCAIS 2022

作者： Jin, Wei Sun, Cuimin You, Hui Chao, Pingfu School of Information Technology and Electrical Engineering The University of Queensland Brisbane Australia School of Computing and Electronic Information Guangxi University Nanning China School of Mechanical Engineering Guangxi University Nanning China Institute of Artificial Intelligence Soochow University Suzhou China

ISBN: (纸本)9781510655010

Load forecasting is an essential part of the energy field. The excellent performance of the prediction algorithm can directly reduce the operation and maintenance cost of the equipment. Therefore, making load forecasting more accurate is a concern to energy experts. In the types of load forecasting, short-term load forecasting (STLF) is usually used to test the accuracy of new algorithms. In the previous papers, amounts authors provided various methods to improve load forecasting accuracy. In recent years, STLF based on the neural network has been proposed by researchers. But few papers mentioned combined energy disaggregation technique and neural networks to improve the forecasting model. Therefore, this paper proposed a new method that combined energy disaggregation and long-short term memory (LSTM) to enhance the accuracy of traditional STLF. In this article, the author will introduce a non-intrusive load monitoring tool kit (NILMTK) for getting each household appliance consumption from the total consumption and then predicting the future load value of each appliance based on its load data. Finally, sum the predicted values to get the result. Through experiments, the results of our proposed new method reduce the root mean squared error (RMSE) of traditional forecasting models by 7% and the mean absolute error (MAE) of it by 15%, respectively. © 2022 SPIE

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Optimization of Distribution System Reliability Using Dandelion Optimizer

Optimization of Distribution System Reliability Using Dandel...

引用

2023 Innovations in Power and Advanced computing Technologies, i-PACT 2023

作者： Tang, Jia-Wen Wooi, Chin-Leong Tan, Wen-Shan Afrouzi, Hadi Nabipour Hashim, Syahrun Nizam bin Md Arshad Thien, Yee Von Faculty of Electrical Engineering Technology Universiti Malaysia Perlis Pauh Putra Campus Arau Perlis02600 Malaysia Faculty of Electrical Engineering Technology Universiti Malaysia Perlis Pauh Putra Campus Arau Perlis02600 Malaysia School of Engineering and Advance Engineering Platform Monash University Malaysia Jalan Lagoon Selatan Bandar Sunway Selangor 47500 Malaysia Faculty of Engineering Computing and Science Swinburne University of Technology Sarawak Sarawak Kuching93350 Malaysia Department of Electrical and Electronics Engineering Faculty of Engineering and Technology Tunku Abdul Rahman University of Management and Technology Kuala Lumpur Malaysia

ISBN: (纸本)9798350325188

This study proposes the Dandelion Optimizer (DO), a novel nature-inspired algorithm based on dandelion plant life cycles, for optimizing lightning protection system (LPS) placement in radial distribution networks with 81 buses. The objective is to minimize System Average Interruption Frequency Index (SAIFI) and Momentary Average Interruption Frequency Index (MAIFI). The DO offers a user-friendly approach to determining optimal solutions and excels in pinpointing optimal LPS deployment locations within distribution systems, concurrently fastening the calculation of SAIFI and MAIFI. Validation involves comprehensive numerical simulations, considering lightning flashover rate, distribution feeder attributes, and LPS configuration. Comparative analysis with Grey Wolf Optimizer (GWO) and Dragonfly Algorithm (DA) affirms DO's superior performance. Notably, DO showcases better capability in finding local optima and faster convergence than GWO and DA. Applying DO to optimise the optimal placements of LPSs yields a commendable 6.16% reduction in reliability indices, surpassing GWO and DA's 6.14% and 5.14% reductions. DO also exhibits heightened convergence speed over GWO and DA. © 2023 IEEE.

关键词： Dandelion Optimizer (DO) Dragonfly Algorithm (DA) Flashover rate Grey Wolf Optimizer (GWO) Lightning protection system MAIFI SAIFI

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：