检索结果-内蒙古大学图书馆

A Dynamic Interval Multi-Objective Evolutionary Algorithm Based on Multi-Task Learning and Inverse Mapping

IEEE Transactions on Evolutionary Computation 2025年

作者： Wang, Feimeng Sun, Jing Gan, Xingjia Gong, Dunwei Wang, Gaige Guo, Yongde Qingdao University of Science and Technology College of Automation and Electronic Engineering Qingdao Shandong266061 China Qingdao University of Science and Technology School of Data Science Qingdao Shandong266061 China Central South University School of Automation Changsha Hunan410083 China Ocean University of China Department of Computer Science and Technology Qingdao Shandong266071 China City University of Macau Faculty of Data Science Macau999078 China

Dynamic interval multi-objective optimization problems, such as those encountered in wireless sensor network scheduling and portfolio selection, are increasingly prevalent. However, they present significant challenges due to the inherent uncertainty and variability of their parameters. This paper proposes a dynamic interval multi-objective evolutionary algorithm in terms of multi-task learning and inverse mapping. The algorithm employs an interval-based MOEA/D as its foundational framework. Upon encountering environmental changes, prediction models for the midpoints and widths of intervals are developed using multi-task learning combined with a self-evolving fuzzy system. These models generate a predicted Pareto front (PF) in the objective space. Subsequently, inverse mappings of the objective functions at the new time are established to identify solutions that correspond to the predicted PF in the decision space. Finally, these solutions are expanded to form an initial population at the new time. Testing on eighteen benchmark optimization problems and an uncertain scheduling of underwater wireless sensor networks, the proposed algorithm demonstrates both competitiveness and superiority when compared to five state-of-the-art algorithms. © 1997-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Implementing Hadoop and Moodle Integrated Student Support System

Implementing Hadoop and Moodle Integrated Student Support Sy...

引用

International Conference on Advanced Information Technologies (ICAIT)

作者： Myint Myat Aung Shin Min Htet Hein Myo Set Aung Hpone Thant Sithu Htut Kyaw Zin Htet Nwe Nwe Myint Thein Data Distribution Management Lab University of Information Technology Yangon Myanmar Data Distribution Management Lab Faculty of Computer Science University of Information Technology Yangon Myanmar

ISBN: (数字)9798331510046

ISBN: (纸本)9798331510053

Learning management systems (LMS) generate large amounts of real-time data which has the potential to provide valuable insights. Hadoop MapReduce is a scalable framework that is designed to handle such data. This paper presents a system architecture that integrates Hadoop MapReduce into Moodle, a popular LMS, for analyzing academic data. The implementation of the architecture allows users to generate a variety of reports from student attendance logs through a Moodle plugin which utilizes the Hadoop cluster for processing data. Users such as lecturers can then utilize these reports to identify which students do and do not engage in which courses as well as monitor their eligibility for exams. The use of Hadoop MapReduce provides high performance computing (HPC) capabilities that offer distributed parallel processing and economical scalability by means of adding commodity nodes to the cluster.

关键词： Learning management systems Scalability Systems architecture computer architecture Parallel processing Market research Real-time systems Synchronization Information technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

Vehicle Check-In data-driven POI Recommendation Based on Improved SVD and Graph Convolutional Network 19

Vehicle Check-In Data-driven POI Recommendation Based on Imp...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Liu, Yuwen Zhang, Jie Dou, Ruihan Zhou, Xiaokang Xu, Xiaolong Wang, Shoujin Qi, Lianyong College of Computer Science and Technology Qingdao China Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology China Shanghai Meteorological Information and Technology Support Center China University of Waterloo Faculty of Mathematics Waterloo Canada Shiga University Faculty of Data Science Japan Riken Center for Advanced Intelligence Project Riken Japan Nanjing University of Information Science and Technology School of Computer and Software China Macquarie University School of Computing Australia Qufu Normal University School of Computer Science China

ISBN: (纸本)9798350346558

The application of automobile tool software is becoming increasingly widespread, and its functions are becoming increasingly diverse. Using vehicle traffic data to give users with recommendations for Points-of-interest (POI) is becoming an intriguing research challenge. However, the current POI recommendation is either a sequence-based method, ignoring the interaction information between users and POIs. Or it needs a lot of model training time to use graph correlation method to mine the interaction between users or vehicles and POIs. In order to address these issues, we propose a method for vehicle check-in data-driven POI recommendation based on improved Singular Value Decomposition (SVD) and Graph Convolutional Network (GCN). First, we apply SVD to replace the neighborhood aggregation update method in traditional GCN, update the node embedding with fewer parameters and faster speed. Second, we propose an information enhancement strategy to make up for the information loss caused by the SVD. Experiments on large vehicle check-in datasets demonstrate that our method is both faster and more effective when making POI recommendations. © 2022 IEEE.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Multi-Temporal Cloud Removal of Satellite Image for Surface Water Segmentation

Multi-Temporal Cloud Removal of Satellite Image for Surface ...

引用

International Conference on computer, Control, Informatics and Its Applications (IC3INA)

作者： Suhardiman Roni Salambue Andre Sihombing Ira Maryati Lia Sadita Aruni Yasmin Azizah Zul Indra Gita Sastria Department of Computer Science Universitas Riau Pekanbaru Indonesia Research Center for Data and Information Sciences National Research and Innovation Agency (BRIN) Bandung Indonesia Faculty of Computer Science Universitas Indonesia Depok Indonesia

ISBN: (数字)9798331542313

ISBN: (纸本)9798331542320

Satellite imagery utilization for water surface monitoring faces challenges in the presence of clouds that interfere with the segmentation process. This study aims to overcome the problem by implementing and developing the Multi-temporal Cloud Removal MCR method at the pre-processing stage. This research uses (MCR) approach to produce cloud-free satellite images. The difference from the current MCR method comes from using a red band in the cloud detection step, adding a dilation process on the cloud masking result, and the pixel mapping process. The best MCR results are obtained from cloud cover percentages below 20% with an NRMSE value of 0.156 and a PSNR of 29.815. In addition, this research compares the accuracy of the U-net water segmentation model between the original satellite image and the resulting MCR data. The model evaluation process uses binary cross-entropy loss, dice coefficient, and intersection over union (IoU) to check the model's performance. The model achieved a Dice coefficient of 0,842, IoU of 0.913 and a binary cross-entropy loss of 0,137 for MCR images. For images with cloud cover below 20%, the Dice coefficient and IoU slightly decreased to 0.819 and 0.892 (loss: 0.1563). As cloud cover increased to 20-40%, these values dropped to 0.687 and 0.812 (loss: 0.25) and further decreased to 0.546 and 0.706 (loss: 0.2656) for 40-60% cloud cover. The results demonstrate that the percentage of cloud cover in satellite images significantly influences the accuracy of surface water segmentation.

关键词： Digital control Image segmentation Accuracy data models Satellite images Informatics Surface treatment Monitoring Faces

来源：评论

学校读者我要写书评

暂无评论

CLEANSURVIVAL: AUTOMATED data PREPROCESSING FOR TIME-TO-EVENT MODELS USING REINFORCEMENT LEARNING

arXiv

引用

arXiv 2025年

作者： Koka, Yousef Selby, David Großmann, Gerrit Vollmer, Sebastian Media Engineering Technology Faculty German University in Cairo Cairo Egypt Data Science and its Applications DFKI GmbH Kaiserslautern67663 Germany Data Science and its Applications DFKI GmbH Department of Computer Science University of Kaiserslautern–Landau Kaiserslautern 67663 Kaiserslautern67663 Germany

data preprocessing is a critical yet frequently neglected aspect of machine learning, often paid little attention despite its potentially significant impact on model performance. While automated machine learning pipelines are starting to recognize and integrate data preprocessing into their solutions for classification and regression tasks, this integration is lacking for more specialized tasks like survival or time-to-event models. As a result, survival analysis not only faces the general challenges of data preprocessing but also suffers from the lack of tailored, automated solutions in this area. To address this gap, this paper presents CleanSurvival, a reinforcement-learning-based solution for optimizing preprocessing pipelines, extended specifically for survival analysis. The framework can handle continuous and categorical variables, using Q-learning to select which combination of data imputation, outlier detection and feature extraction techniques achieves optimal performance for a Cox, random forest, neural network or user-supplied time-to-event model. The package is available on GitHub: https://***/datasciapps/CleanSurvival. Experimental benchmarks on real-world datasets show that the Q-learning-based data preprocessing results in superior predictive performance to standard approaches, finding such a model up to 10 times faster than undirected random grid search. Furthermore, a simulation study demonstrates the effectiveness in different types and levels of missingness and noise in the data. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hotel Customer Segmentation Using the Integrated Entropy-CRITIC Method and the 2T-RFMB Model

Hotel Customer Segmentation Using the Integrated Entropy-CRI...

引用

International Conference on Marketing and Technologies, ICMarkTech 2022

作者： Shu, Ziwei Carrasco González, Ramón Alberto García-Miguel, Javier Portela Sánchez-Montañés, Manuel Department of Statistics and Data Science Faculty of Statistics Complutense University of Madrid Avenida Puerta de Hierro S/N Madrid28040 Spain Department of Marketing Faculty of Statistics Complutense University of Madrid Avenida Puerta de Hierro S/N Madrid28040 Spain Department of Computer Science Universidad Autónoma de Madrid Madrid28049 Spain

ISBN: (纸本)9789811990984

Customer segmentation helps the company better understand its target audience, which is vital to optimizing marketing strategies and maximizing the customer value for the company. This paper improves the original RFM model by including the potential loss to the hotel from a customer canceling their reservation in the indicator "Monetary" and adding a new indicator "Bonding" to indicate the degree of customer bonding with the hotel. The proposed model also includes the 2-tuple linguistic model to give hotel managers or decision-makers more easily understandable customer segmentation results. The aggregation of the four indicators (recency, frequency, monetary, and bonding) into a unique value is a Multi-Criteria Decision-Making (MCDM) problem. To generate the weights that can consider the relationship between various indicators and the level of data diversification contained in each indicator, the Entropy method and the CRiteria Importance Through Intercriteria Correlation (CRITIC) method have been integrated. Customer overall values are generated based on the 2T-RFMB model and the integrated Entropy-CRITIC method. Finally, various customer segments are obtained with K-means clustering. This proposal has been evaluated by a real dataset from a hotel in Lisbon. The results show that the proposed model can increase the linguistic interpretability of clustering results. It also demonstrates that the proposed model can provide hotel managers with more realistic customer values to assist them in allocating their Customer Relationship Management (CRM) resources efficiently. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Hotels

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Classification for Intrusion Detection on computer Networks

Machine Learning Classification for Intrusion Detection on C...

引用

International Conference on Computational Intelligence and Applications (ICCIA)

作者： Abhibhu Tachaapornchai Somkiat Kosolsombat Chiabwoot Ratanavilisagul Data Science and Innovation College of Interdisciplinary Studies Thammasat University Pathum Thani Thailand Department of Computer and Information Science Faculty of Applied Science King Mongkut's University of Technology North Bangkok Thailand

ISBN: (数字)9798350352214

ISBN: (纸本)9798350352221

To build an intelligent intrusion detection system, it is essential to have a suitable and high-quality dataset with a sufficiently large quantity to simulate real-world scenarios. The NSL-KDD dataset is an improved version derived from the previous KDD 99 dataset. In this article, an analysis of the NSL-KDD dataset was conducted to study the efficiency of classification machine learning in detecting abnormalities in network data transmission patterns. The study achieved the highest accuracy by XGBoost method using 14 features important and grid search for hyperparameter tuning and revealing many interesting insights. This research has significant implications and can be further applied in the field of cybersecurity by leveraging machine learning for network intrusion detection systems.

关键词： Accuracy Computational modeling Machine learning NSL-KDD Feature extraction computer networks Decision trees data communication computer security Tuning

来源：评论

学校读者我要写书评

暂无评论

Classification Attack on IoT Devices with Machine Learning

Classification Attack on IoT Devices with Machine Learning

引用

International Conference on Computational Intelligence and Applications (ICCIA)

作者： Nutcha Charoenwong Somkiat Kosolsombat Chiabwoot Ratanavilisagul Data Science and Innovation College of Interdisciplinary Studies Thammasat University Pathum Thani Thailand Department of Computer and Information Science Faculty of Applied Science King Mongkut's University of Technology North Bangkok Thailand

ISBN: (数字)9798350352214

ISBN: (纸本)9798350352221

Internet of Things (IoT) devices are small, low-power devices used for detecting and processing data remotely through the internet. These devices have increasingly been integrated into our daily lives, both in the digital and physical world. However, this interconnectedness poses risks of being targeted by malware due to limited resources and connectivity. Machine learning (ML) techniques can be used to identify and prevent malware attacks on IoT devices. In this research report, we investigate the use of ML techniques for classifying malware in IoT devices. Our research includes the implementation and evaluation of decision tree, k-nearest neighbors (KNN), and XGBoost algorithms. Our evaluation metrics include accuracy, precision, recall, and the average of precision and recall. Our method is tested using a dataset of real-world malware attacks on IoT devices, and the XGBoost algorithm achieves the highest accuracy of 98.44%, demonstrating its effectiveness in detecting and classifying malware in IoT devices.

关键词： Measurement Machine learning algorithms Accuracy Machine learning Nearest neighbor methods Malware Classification algorithms Internet of Things Object recognition Decision trees

来源：评论

学校读者我要写书评

暂无评论

PDF Malware Detection Using Machine Learning

PDF Malware Detection Using Machine Learning

引用

International Conference on Computational Intelligence and Applications (ICCIA)

作者： Naragorn Tantikulvichit Somkiat Kosolsombat Chiabwoot Ratanavilisagul Data Science and Innovation College of Interdisciplinary Studies Thammasat University Pathum Thani Thailand Department of Computer and Information Science Faculty of Applied Science King Mongkut's University of Technology North Bangkok Thailand

ISBN: (数字)9798350352214

ISBN: (纸本)9798350352221

In today's world, cyber-attacks are on the rise, and PDF files are commonly used as a means of attack. One common type of attack through PDF files is the covert embedding of dangerous malware and tricking users into clicking on malicious links. The victims may have their important data stolen and suffer various forms of damage. Detecting malware embedded in PDF files can help mitigate the harm to users. This project aims to study methods for detecting malware embedded in PDF files using machine learning techniques, with the best-performing model being Gradient Boosting, achieving an accuracy of 99% in 5-fold cross-validation and 97% using 10 features. Using Feature Selection Technique Voting from 3 Models consist of Logistic Regression, Random Forest, Lasso Regression, Each model will choose matching features to use for machine learning analysis. This project approach reduce feature for machine learning to detect PDFMalware.

关键词： Training Analytical models Logistic regression Machine learning Feature extraction Boosting Malware data models Random forests Cyberattack

来源：评论

学校读者我要写书评

暂无评论

Season-Independent PV Disaggregation Using Multi-Scale Net Load Temporal Feature Extraction and Weather Factor Fusion

Season-Independent PV Disaggregation Using Multi-Scale Net L...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Xiaolu Chen Chenghao Huang Yanru Zhang Hao Wang School of Computer Science and Technology University of Electronic Science and Technology of China Chengdu China Department of Data Science and AI Faculty of Information Technology Monash University Melbourne Australia Shenzhen Institute for Advanced Study Shenzhen China Department of Data Science and AI Faculty of Information Technology and Monash Energy Institute Monash University Melbourne Australia

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

With the advancement of energy Internet and energy system integration, the increasing adoption of distributed photovoltaic (PV) systems presents new challenges on smart monitoring and measurement for utility companies, particularly in separating PV generation from net electricity load. Existing methods struggle with feature extraction from net load and capturing the relevance between weather factors. This paper proposes a PV disaggregation method that integrates Hierarchical Interpolation (HI) and multi-head self-attention mechanisms. By using HI to extract net load features and multi-head self-attention to capture the complex dependencies between weather factors, the method achieves precise PV generation predictions. Simulation experiments demonstrate the effectiveness of the proposed method in real-world data, supporting improved monitoring and management of distributed energy systems.

关键词： Photovoltaic systems Interpolation Time series analysis Energy Internet Distributed databases System integration Companies Feature extraction Monitoring Meteorology

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：