检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Big Data, BigData 2024

作者： Wang, Danny Y. C. Jordanger, Lars Arne Lin, Jerry Chun-Wei Western Norway University of Applied Sciences Department of Computer Science Electrical Engineering and Mathematical Sciences Bergen Norway

ISBN: (纸本)9798350362480

In the rapidly evolving e-commerce industry, the ability to select high-quality data for model training is essential. This study introduces the High-Utility Sequential Pattern Mining using SHAP values (HUSPM-SHAP) model, a utility mining based active learning strategy, to tackle this challenge. We found that the parameter settings for positive and negative SHAP values affect the mining results of the model, introducing a key consideration into the active learning framework. Unlike traditional SHAP, which evaluates individual elements, HUSPM-SHAP utilizes SHAP values in combination with HUSPM to identify the valuable of high-utility sequential patterns for improving prediction models. In experiments to predict behaviors that actually lead to purchases, the developed HUSPM-SHAP model shows its superiority in different scenarios. The model's ability to reduce labeling requirements while maintaining high predictive performance is highlighted. Our results show that the model is able to refine the processing of e-commerce data and lead to optimized, cost-efficient prediction modeling. © 2024 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Automatic classification of normal/AD brain MRI slices using whale-algorithm optimized hybrid image features

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 14237-14248页

作者： Kadry, Seifedine Jessy, V. Elizabeth Rajinikanth, Venkatesan Crespo, Rubén González Department of Applied Data Science Noroff University College Kristiansand4612 Norway College of Engineering and Information Technology Ajman University Ajman United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Division of Research and Innovation Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai602105 India Department of Computer Science and Technology Universidad Internacional de La Rioja La Rioja Logroño Spain

In recent years, the prevalence of Age-Related Illnesses (ARL) has been increasing among older individuals, and early recognition and treatment will result in better living conditions. It is well known that Alzheimer's Disease (AD) is among the ARD, and severe cases may result in dementia as well. It is the purpose of this study to propose a technique for distinguishing normal/AD brain MRI slices with improved accuracy utilizing the T2-modality. This scheme consists following phases: (i) Brain MRI collection and preprocessing, (ii) Deep feature extraction with the chosen scheme, (iii) Handcrafted feature extraction, (iv) Whale Algorithm (WA) based feature reduction and serial integration, and (v) binary classification using five-fold cross-validation. A total of 2000 MRI slices (1000 normal and 1000 AD class) are examined during this task using images collected from Alzheimer’s Disease Neuroimaging Initiative (ADNI). This study confirms that the proposed scheme provides a classification accuracy of > 98% when applied with the K-Nearest Classifier. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SSRepL-ADHD: Adaptive Complex Representation Learning Framework for ADHD Detection from Visual Attention Tasks

SSRepL-ADHD: Adaptive Complex Representation Learning Framew...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Rehman, Abdul Heldal, Ilona Lin, Jerry Chun-Wei Western Norway University of Applied Sciences Department of Computer Science Electrical Engineering and Mathematical Sciences Bergen Norway

ISBN: (纸本)9798350362480

Self Supervised Representation Learning (SSRepL) can capture meaningful and robust representations of the Attention Deficit Hyperactivity Disorder (ADHD) data and have the potential to improve the model's performance on also downstream different types of Neurodevelopmental disorder (NDD) detection. In this paper, a novel SSRepL and Transfer Learning (TL)-based framework that incorporates a Long Short-Term Memory (LSTM) and a Gated Recurrent Units (GRU) model is proposed to detect children with potential symptoms of ADHD. This model uses Electroencephalogram (EEG) signals extracted during visual attention tasks to accurately detect ADHD by preprocessing EEG signal quality through normalization, filtering, and data balancing. For the experimental analysis, we use three different models: 1) SSRepL and TL-based LSTM-GRU model named as SSRepL-ADHD, which integrates LSTM and GRU layers to capture temporal dependencies in the data, 2) lightweight SSRepL-based DNN model (LSSRepL-DNN), and 3) Random Forest (RF). In the study, these models are thoroughly evaluated using well-known performance metrics (i.e., accuracy, precision, recall, and F1-score). The results show that the proposed SSRepL-ADHD model achieves the maximum accuracy of 81.11% while admitting the difficulties associated with dataset imbalance and feature selection. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Customer Behavior Prediction and Interpretability

Enhancing Customer Behavior Prediction and Interpretability

引用

2024 IEEE International Conference on Big Data, BigData 2024

ISBN: (纸本)9798350362480

This paper leverages insights from my previous works to analyze and predict customer behavior in different areas using data mining and machine learning techniques. The research focuses on identifying and interpreting customer preferences, purchasing patterns and risk factors for customer churn to develop predictive models that support decision making. By analyzing various datasets such as tabular data, clickstream data, and digital interactions, this study aims to provide a comprehensive framework for extracting actionable insights and enhancing the accuracy and transparency of customer behavior predictions. The proposed approach enables businesses to anticipate customer behavior, personalize marketing strategies, and improve the explainability and effectiveness of customer behavior prediction models. Future work will incorporate advanced visualization techniques and various data structures to further improve the model's transparency and predictive capability. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Power of Sparse Neural Networks for Feature Selection 27

Unveiling the Power of Sparse Neural Networks for Feature Se...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Atashgahi, Zahra Liu, Tennison Pechenizkiy, Mykola Veldhuis, Raymond Mocanu, Decebal Constantin van der Schaar, Mihaela Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Netherlands Department of Applied Mathematics and Theoretical Physics University of Cambridge United Kingdom Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands Department of Computer Science University of Luxembourg Luxembourg

ISBN: (纸本)9781643685489

Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically reducing computational overheads. Despite these advancements, several critical aspects remain insufficiently explored for feature selection. Questions persist regarding the choice of the DST algorithm for network training, the choice of metric for ranking features/neurons, and the comparative performance of these methods across diverse datasets when compared to dense networks. This paper addresses these gaps by presenting a comprehensive systematic analysis of feature selection with sparse neural networks. Moreover, we introduce a novel metric considering sparse neural network characteristics, which is designed to quantify feature importance within the context of SNNs. Our findings show that feature selection with SNNs trained with DST algorithms can achieve, on average, more than 50% memory and 55% FLOPs reduction compared to the dense networks, while outperforming them in terms of the quality of the selected features. © 2024 The Authors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rapid computational algorithm with minimum user input for reconstructing phase images in structured illumination Digital Holographic Microscopy

Rapid computational algorithm with minimum user input for re...

引用

3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2024 - Part of Optica Imaging Congress

作者： Obando-Vásquez, Sofía Castaneda, Raúl Restrepo, René Trujillo, Carlos Doblas, Ana Applied Optics Group School of Applied Science and Engineering EAFIT University Medellin Colombia Electrical and Computer Engineering Department University of Massachusetts Dartmouth United States

A rapid computational algorithm is presented for Structured Illumination in Digital Holographic Microscopy. The proposed algorithm is based on the minimization of two cost functions to reconstruct improved resolution ... 详细信息

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Integrated dominating and hit set-inspired unequal clusteringbased data aggregation in wireless sensor networks

引用

International Journal of Intelligent Computing and Cybernetics 2022年第4期15卷 642-655页

作者： G.Vennira Selvi V.Muthukumaran A.C.Kaladevi S.Satheesh Kumar B.Swapna Department of Computer Science and Engineering Global Institute of Engineering and TechnologyVelloreIndia Department of Mathematics School of Applied SciencesREVA UniversityBangaloreIndia Department of Computer Science and Engineering Sona College of TechnologySalemIndia Department of Computer Science School of Applied SciencesREVA UniversityBangaloreIndia Department of Electronics and Communication Engineering Dr MGR Educational and Research InstituteChennaiIndia

Purpose-In wireless sensor networks,improving the network lifetime is considered as the prime objective that needs to be significantly addressed during data *** the traditional data aggregation techniques,cluster-based dominating set algorithms are identified as more effective in aggregating data through cluster ***,the existing cluster-based dominating set algorithms suffer from a major drawback of energy deficiency when a large number of communicating nodes need to collaborate for transferring the aggregated ***,due to this reason,the energy of each communicating node is gradually decreased and the network lifetime is also *** increase the lifetime of the network,the proposed algorithm uses two sets:Dominating set and hit ***/methodology/approach-The proposed algorithm uses two sets:Dominating set and hit *** dominating set constructs an unequal clustering,and the hit set minimizes the number of communicating nodes by selecting the optimized cluster head for transferring the aggregated data to the base *** simulation results also infer that the proposed optimized unequal clustering algorithm(OUCA)is greater in improving the network lifetime to a maximum amount of 22%than the existing cluster head selection approach considered for ***-In this paper,lifetime of the network is prolonged by constructing an unequal cluster using the dominating set and electing an optimized cluster head using hit *** dominator set chooses the dominator based on the remaining energy and its node degree of each *** optimized cluster head is chosen by the hit set to minimize the number of communicating nodes in the *** proposed algorithm effectively constructs the clusters with a minimum number of communicating nodes using the dominating and hit *** simulation result confirms that the proposed algorithm prolonging the lifetime of the network efficiently when compared with the existing algorithms.

关键词： Unequal clustering Hit set Dominating set Network lifetime

来源：评论

学校读者我要写书评

暂无评论

Asset Management Strategies for District Heating Networks 8

Asset Management Strategies for District Heating Networks

引用

8th International Conference on System Reliability and Safety, ICSRS 2024

作者： Grønberg, Jens Tahavori, Maryamsadat Bacher, Peder Dtu Engineering Technology Ballerup Denmark Dtu Department of Applied Mathematics and Computer Science Kongens Lyngby Denmark

ISBN: (纸本)9798350354508

District Heating (DH) became widely adopted in European cities during the 20th century to meet demand for heating from a growing urban population. Today, the desire to decarbonize Europe's heat consumption has lead to an renewed interest in increasing the adoption of DH. To meet this end, DH has to be a price competitive alternative to other heating technologies. Over time the underground heat distribution network that DH companies operate suffers from faults that require replacement of pipes. On-demand replacement is more expensive than planned large scale replacement projects. The only question is, when is the optimal time to renew the pipes? In this article this question will be formulated using Reliability Theory. Our approach is to use historical records of time to failure and a bounding result to estimate the optimal time for replacement. The method can be used by DH companies with historical fault records to form an Asset Management strategy on the question of when to renew which pipes. © 2024 IEEE.

关键词： Asset management

来源：评论

学校读者我要写书评

暂无评论

Secure Watermarking Scheme for Color DICOM Images in Telemedicine Applications

引用

computers, Materials & Continua 2022年第2期70卷 2525-2542页

作者： Kamred Udham Singh Hatem Salem Abu-Hamatta Abhishek Kumar Achintya Singhal Mamoon Rashid A.K.Bashir Department of Computer Science and Information Engineering National Cheng Kung UniversityTainanTaiwan Department of Applied Sciences Aqaba University CollegeAl Balqa Applied UniversityAqabaJordan School of Computer Science&IT JAIN(to be Deemed University)BangaloreIndia Department of Computer Science Banaras Hindu UniversityVaranasiIndia Department of Computer Engineering Faculty of Science and TechnologyVishwakarma UniversityPune411048India Department of Computing and Mathematics ManchesterMetropolitan UniversityUK

Teleradiology plays a vital role in the medical field,which permits transmitting medical and imaging data over a communication *** ensures data reliability and provides convenient communication for clinical interpretation and diagnostic *** transmission of this medical data over a network raises the problems of legal,ethical issues,privacy,and copyright *** copyright protection of medical images is a significant issue in the medical *** schemes are used to address these issues.A gray-level or binary image is used as a watermark frequently in color image watermarking *** this paper,the authors propose a novel non-blind medical image watermarking scheme based on 2-D LiftingWavelet Transform(LWT),Multiresolution Singular Value Decomposition(MSVD),and LU factorization to improve the robustness and authenticity of medical *** this scheme,multiple color watermarks are embedded into the colored DICOM(Digital Imaging and Communications inMedicine)images obtained from Color Doppler images(DICOM format),and the average results achieved by our proposed scheme is 46.84 db for Peak Signal-to-Noise Ratio(PSNR),37.46 db for Signal-to-Noise Ratio(SNR),0.99 for Quality of Image and 0.998 for Normalized Correlation for various image processing *** results make our watermarking technique an ideal candidate for medical image watermarking.

关键词： Digital imaging medicine multiresolution medical image watermarking

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-agency Collaboration Medical Images Analysis and Classification System based on Federated Learning 24

Research on Multi-agency Collaboration Medical Images Analys...

引用

2024 International Conference on Biomedicine and Intelligent Technology, ICBIT 2024

作者： Huang, Shijia Diao, Su Wan, Yajie Song, Chaoda Fu Foundation School of Engineering and Applied Science Columbia University United States Department of Industrial & Systems Engineering Auburn University United States Department of Computer Science Brown University United States School of Engineering Department of Computer and Data Sciences United States

ISBN: (纸本)9798400710063

In the field of medical image analysis, with the growth of data volume and the increasing demand for privacy protection, traditional centralized learning methods are facing the problems of data silos and privacy leakage. Therefore, federated learning, as an emerging distributed machine learning framework, provides a solution to protect data privacy while effectively utilizing decentralized data. The purpose of this study is to develop a federated learning-based medical image analysis and classification system to solve the data isolation and privacy problems existing in traditional methods. This study uses a distributed federated learning framework that allows multiple healthcare organizations to share updates to their models instead of raw data. Data privacy protection is further enhanced through the use of differential privacy and secure multi-party computation techniques. In addition, a deep convolutional neural network (CNN) is used to improve the accuracy of feature extraction and classification of medical images. Experimental analysis shows that the system can significantly improve the classification accuracy of medical images. Specifically, our system achieved a 15% improvement in classification accuracy compared to traditional centralized methods. Additionally, the implementation of differential privacy and secure multi-party computation resulted in a privacy leakage reduction of 25%. These results verify the application potential of federated learning in the field of medical image processing, demonstrating superior performance and enhanced privacy protection compared to traditional centralized learning methods. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

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：