检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Dey, Sonali Radha, D. Kirthika Devi, V.S. Department of Computer Science Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

Predicting Customer Lifetime Value (CLV) is one of the most critical tasks that businesses undertake in order to improve customer retention and optimize marketing strategies. The present paper proposes a predictive model for CLV using several machine learning techniques. The features considered include customer demographics, purchasing behavior, and transaction history. All these features were preprocessed using feature engineering and missing value handling. Several regression models, including Linear Regression, Decision Tree, and Random Forest Regressor, were compared in terms of predictive performance. The study includes the decision trees,hash tables as advance data structures such that they can handle large datasets effectively. Of the ones tested, Random Forest Regressor proved to be superior to the others, having the lowest Mean Squared Error (MSE) and highest R2 score, thereby validating its robustness in identifying the complex patterns within the data. The work highlights the time and space complexities of different models. This study contributes to the application of machine learning in customer analytics and provides a foundation for future research to integrate more diverse data sources and enhance model performance through hyperparameter optimization. Future work will also explore real-time prediction capabilities and the integration of multimodal data to further refine CLV forecasting. © 2025 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Framework for Churn Prediction using Stratifed Bagging and Stacked Multi-Output Random Forests 3

An Enhanced Framework for Churn Prediction using Stratifed B...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Bhardwaj, Anay Radha, D. Kirthika Devi, V.S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidhyapeetham Bengaluru India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidhyapeetham Bengaluru India

ISBN: (纸本)9798331527549

Customer churn prediction is an important task in customer relationship management because it helps businesses know who is at risk of leaving and retain such at-risk *** and time-efficient churn prediction is essential to identify the factors driving churn, enabling businesses to implement timely and effective retention strategies.A framework is proposed which combines stratified bagging with multi-output Random Forest and stacked feature transformation, to enhance prediction accuracy. This approach balances the dataset, trains a custom Random Forest using stratified bagging, and applies stacked learning using Logistic Regression on transformed features. Tested on real-world data, the model demonstrated 99% accuracy, showing improvements over the classic Random Forest in precision, recall, and prediction time. © 2025 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Optimizing Hiring Practices: A Machine Learning Approach for Candidate Selection 3

Optimizing Hiring Practices: A Machine Learning Approach for...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Dogiparthy, Naga Datta Radha, D. Kirthika Devi, V.S. Department of Computer Science and Engineering Amrita school of computing Amrita Vishwa Vidhyapeetham Bengaluru India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidhyapeetham Bengaluru India

ISBN: (纸本)9798331527549

Recruitment is one of the most crucial factors in shaping efficient and high-performing teams within organizations. However, the traditional recruitment processes are often plagued by biases and subjective judgments that lead to inconsistent and suboptimal hiring decisions. This project uses machine learning(ML) to make recruitment more objective, efficient, and data-driven. By taking the age, gender, education level, experience, interview scores, and personality traits of the applicants as key features, the model predicts candidate suitability without bias. The methodology uses robust preprocessing, Chi-Square feature selection, and the SMOTE technique to overcome class imbalance in the dataset. The proposed system uses various different machine learning algorithms like CatBoost, KD-Trees, Random Forest, and Logistic Regression and many more. All these models are trained and fine-tuned with GridSearchCV for hyperparameter optimization. Among them, the best model was CatBoost with 95% accuracy. This work shows how machine learning can change the recruitment game for organizations to make unbiased, data-driven hiring decisions and ultimately increase workforce efficiency and organizational success. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Aligning Task- and Reconstruction-Oriented Communications for Edge Intelligence

引用

IEEE Journal on Selected Areas in Communications 2025年第7期43卷 2575-2588页

作者： Diao, Yufeng Zhang, Yichi She, Changyang Zhao, Philip Guodong Li, Emma Liying University of Glasgow School of Computing Science Glasgow United Kingdom University of Manchester Department of Computer Science Manchester United Kingdom University of Glasgow School of Engineering Glasgow United Kingdom University of Sydney School of Electrical and Information Engineering Sydney Australia

Existing communication systems aim to reconstruct the information at the receiver side, and are known as reconstruction-oriented communications. This approach often falls short in meeting the real-time, task-specific demands of modern AI-driven applications such as autonomous driving and semantic segmentation. As a new design principle, task-oriented communications have been developed. However, it typically requires joint optimization of encoder, decoder, and modified inference neural networks, resulting in extensive cross-system redesigns and compatibility issues. This paper proposes a novel communication framework that aligns reconstruction-oriented and task-oriented communications for edge intelligence. The idea is to extend the Information Bottleneck (IB) theory to optimize data transmission by minimizing task-relevant loss function, while maintaining the structure of the original data by an information reshaper. Such an approach integrates taskoriented communications with reconstruction-oriented communications, where a variational approach is designed to handle the intractability of mutual information in high-dimensional neural network features. We also introduce a joint source-channel coding (JSCC) modulation scheme compatible with classical modulation techniques, enabling the deployment of AI technologies within existing digital infrastructures. The proposed framework is particularly effective in edge-based autonomous driving scenarios. Our evaluation in the Car Learning to Act (CARLA) simulator demonstrates that the proposed framework significantly reduces bits per service by 99.19% compared to existing methods, such as JPEG, JPEG2000, and BPG, without compromising the effectiveness of task execution. © 1983-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Locational FDIA Detection in Smart Grids: A Scalable Distributed Framework 4

Enhanced Locational FDIA Detection in Smart Grids: A Scalabl...

引用

4th International Conference on Smart Grid and Renewable Energy, SGRE 2024

作者： Eddin, Maymouna Ez Massaoudi, Mohamed Shadmand, Mohammad Abdallah, Mohamed Texas A&M University at Qatar Department of Electrical and Computer Engineering Doha Qatar Texas A&M University Department of Electrical and Computer Engineering College Station United States University of Illinois at Chicago Department of Electrical and Computer Engineering Chicago United States Hamad Bin Khalifa University Information and Computing Technology Division Doha Qatar

ISBN: (纸本)9798350306262

Locational detection of the false data injection attack (FDIA) is essential for smart grid cyber-security. However, the FDIA detection techniques often falter in scalability as power network complexity increases. To address the research gap, this paper introduces an innovative distributed framework for locational FDIA detection that optimizes both performance and scalability. The proposed framework initially partitions the power grid using the improved Louvain community detection algorithm. The proposed solution utilizes the electrical Functional Strength (EFS) matrix and power supply modularity. Subsequently, a dedicated multi-label one-dimensional convolutional neural network model (1D CNN) locational detector is designed for each derived cluster. The proposed methodology is designed to increase detection accuracy and enhance the scalability of the model. This is achieved by reducing training and detection times, as well as lowering memory requirements, compared to traditional centralized approaches. The effectiveness of the proposed framework is validated through simulations on the IEEE 39-bus system. These simulations demonstrate the framework's capability to enhance detection accuracy by simplifying the locational FDIA detection challenge, achieved through strategic grid partitioning. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network-Based Node Clustering for Dual-Focused Power Network Partitioning 50

Graph Neural Network-Based Node Clustering for Dual-Focused ...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Eddin, Maymouna Ez Massaoudi, Mohamed Abu-Rub, Haitham Shadmand, Mohammad Abdallah, Mohamed Department of Electrical and Computer Engineering Texas A&M University at Qatar Doha Qatar Department of Electrical and Computer Engineering Texas A&M University College Station United States Department of Electrical and Computer Engineering University of Illinois at Chicago Chicago United States Information and Computing Technology Division Hamad Bin Khalifa University Doha Qatar

ISBN: (纸本)9781665464543

Partitioning the power system into smaller, manageable units facilitates better grid monitoring and control, thereby improving the grid’s stability and reliability. However, large-scale power networks consist of thousands of nodes and edges, which complicates the process of learning appropriate node embeddings and aggregating information from neighboring nodes. By representing power grids as undirected weighted graphs, this study proposes a novel power network partitioning approach using Graph Neural Networks (GNN). The proposed model simplifies the clustering objective by focusing on a single balancing term, which reduces computational complexity while maintaining competitive clustering performance. The power network is represented as a graph where the proposed GNN uses the normalized graph Laplacian, which effectively captures the complex connectivity of the nodes, instead of the traditional adjacency matrix. Active power levels serve as nodal attributes, ensuring that clusters represent both the physical and operational characteristics of the network. This dual-focused approach promotes a partitioning that is topologically coherent and functionally homogeneous, vital for enhanced grid management. When applied to the IEEE 14, 39, and 118 bus systems, the proposed method has successfully delineated coherent clusters of buses, underlining its potential for improving power grid management. The simulation results confirm the method’s efficacy and applicability. © 2024 IEEE.

关键词： Undirected graphs

来源：评论

学校读者我要写书评

暂无评论

QRCODE: Quasi-Residual Convex Deep Network for Fusing Misaligned Hyperspectral and Multispectral Images

引用

IEEE Transactions on Geoscience and Remote Sensing 2024年 62卷 1-15页

作者： Lin, Chia-Hsiang Hsu, Chih-Chung Young, Si-Sheng Hsieh, Cheng-Ying Tai, Shen-Chieh National Cheng Kung University Department of Electrical Engineering Miin Wu School of Computing Tainan70101 Taiwan Institute of Data Science Miin Wu School of Computing National Cheng Kung University Tainan70101 Taiwan National Cheng Kung University Institute of Computer and Communication Engineering Department of Electrical Engineering Tainan70101 Taiwan Institute of Data Science National Cheng Kung University Tainan70101 Taiwan

Considering that hyperspectral image (HSI) is often of lower spatial resolution when compared to multispectral image (MSI), an economical approach for obtaining a high-spatial-resolution (HSR) HSI is to fuse the acquired HSI and MSI, thereby greatly facilitating the subsequent material identification and classification in satellite remote sensing. As satellite-acquired HSI and MSI are often misaligned, the proposed deep neural network does not require the input HSI/MSI to be spatially co-registered, making the challenging fusion network design even more difficult. In this study, we propose a streamlined and efficient convex model integrated into the subnetwork, which obviates the need for complex network structures in learning spatial-spectral relationships, effectively guiding the quasi-residual learning task in our alignment-free fusion network. The convex subnetwork is a low-rank model that leverages the convex geometric structure implicitly embedded in the hyperspectral signature space. To address the misalignment between HSI and MSI effectively, we introduce a novel shifted window attention module (SWAM) that exploits the neighboring correlation in the feature domain, significantly enhancing the performance and stability of the fusion task. Capitalizing on the redundancy among spectrums, we employ grouped convolution to decrease the computational complexity without causing additional performance degradation. The proposed quasi-residual convex deep (QRCODE) network demonstrates the state-of-the-art performance in alignment-free HSI/MSI fusion tasks. © 1980-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach 31

HPC Application Parameter Autotuning on Edge Devices: A Band...

引用

31st Annual IEEE International Conference on High Performance computing, Data, and Analytics, HiPC 2024

作者： Hossain, Abrar Badawy, Abdel-Hameed A. Islam, Mohammad A. Patki, Tapasya Ahmed, Kishwar Department of Electrical Engineering and Computer Science The University of Toledo United States Department of Electrical and Computer Engineering New Mexico State University United States Department of Computer Science and Engineering The University of Texas Arlington United States Center for Applied Scientific Computing Lawrence Livermore National Laboratory United States

ISBN: (纸本)9798331509095

The growing necessity for enhanced processing capabilities in edge devices with limited resources has led us to develop effective methods for improving high-performance computing (HPC) applications. In this paper, we introduce LASP (Lightweight Autotuning of Scientific Application Parameters), a novel strategy designed to address the parameter search space challenge in edge devices. Our strategy employs a multi-armed bandit (MAB) technique focused on online exploration and exploitation. Notably, LASP takes a dynamic approach, adapting seamlessly to changing environments. We tested LASP with four HPC applications: Lulesh, Kripke, Clomp, and Hypre. Its lightweight nature makes it particularly well-suited for resource-constrained edge devices. By employing the MAB framework to efficiently navigate the search space, we achieved significant performance improvements while adhering to the stringent computational limits of edge devices. Our experimental results demonstrate the effectiveness of LASP in optimizing parameter search on edge devices. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A MLP-Mixer and mixture of expert model for remaining useful life prediction of lithium-ion batteries

引用

Frontiers of computer Science 2024年第5期18卷 1-10页

作者： Lingling ZHAO Shitao SONG Pengyan WANG Chunyu WANG Junjie WANG Maozu GUO Faculty of Computing Harbin Institute of TechnologyHarbin 150001China School of Electrical Engineering Liaoning University of TechnologyJinzhou 121004China School of Computer Science Northeast Electric Power UniversityJilin 132000China Department of Medical Informatics School of Biomedical Engineering and InformaticsNanjing Medical UniversityNanjing 211166China School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Accurately predicting the Remaining Useful Life(RUL)of lithium-ion batteries is crucial for battery management *** learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series ***,the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be *** address this challenge,this paper proposes a novel deep learning model,the MLP-Mixer and Mixture of Expert(MMMe)model,for RUL *** MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level ***,we devise an ensemble predictor based on a Mixture-of-Experts(MoE)architecture to generate reliable RUL *** experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods,providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation *** code and dataset are available at the website of github.

关键词： lithium-ion battery remaining useful life deep learning MLP-Mixer mixture-of-experts

来源：评论

学校读者我要写书评

暂无评论

Seamless Graph Task Scheduling over Dynamic Vehicular Clouds: A Hybrid Methodology for Integrating Pilot and Instantaneous Decisions

引用

IEEE Transactions on Services computing 2025年第3期18卷 1753-1768页

作者： Guo, Bingshuo Liwang, Minghui Xia, Xiaoyu Li, Li Jiao, Zhenzhen Hosseinalipour, Seyyedali Wang, Xianbin Xiamen University School of Informatics Fujian China Rmit University School of Computing Technologies MelbourneVIC Australia Tongji University Department of Control Science and Engineering Shanghai China Beijing Teleinfo Technology Co. Ltd. Caict IF-Labs China University at Buffalo-SUNY Department of Electrical Engineering NY United States Western University Department of Electrical and Computer Engineering ON Canada

Vehicular clouds (VCs) play a crucial role in the Internet-of-Vehicles (IoV) ecosystem by securing essential computing resources for a wide range of tasks. This paPertackles the intricacies of resource provisioning in dynamic VCs for computation-intensive tasks, represented by undirected graphs for parallel processing over multiple vehicles. We model the dynamics of VCs by considering multiple factors, including varying communication quality among vehicles, fluctuating computing capabilities of vehicles, uncertain contact duration among vehicles, and dynamic data exchange costs between vehicles. Our primary goal is to obtain feasible assignments between task components and nearby vehicles, called templates, in a timely manner with minimized task completion time and data exchange overhead. To achieve this, we propose a hybrid graph task scheduling (P-HTS) methodology that combines offline and online decision-making modes. For the offline mode, we introduce an approach called risk-aware pilot isomorphic subgraph searching (RA-PilotISS), which predicts feasible solutions for task scheduling in advance based on historical information. Then, for the online mode, we propose time-efficient instantaneous isomorphic subgraph searching (TE-InstaISS), serving as a backup approach for quickly identifying new optimal scheduling template when the one identified by RA-PilotISS becomes invalid due to changing conditions. Through comprehensive experiments, we demonstrate the superiority of our proposed hybrid mechanism compared to state-of-the-art methods in terms of various evaluative metrics, e.g., time efficiency such as the delay caused by seeking for possible templates and task completion time, as well as cost function, upon considering different VC scales and graph task topologies. © 2025 IEEE.

关键词： Undirected graphs

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：