检索结果-内蒙古大学图书馆

31st IEEE International Conference on High Performance Computing, Data, and Analytics Workshops, HiPCW 2024

作者： Bhat, Ranjan Aditya, Konduri Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Computational and Data Sciences Indian Institute of Science Bengaluru India

ISBN: (纸本)9798331509118

In this study, we outline the design and implementation of a portable massively parallel asynchronous solver for time-dependent partial differential equations (PDEs). The solver is implemented using Kokkos library for portability across different node architectures and is coupled with the communication-avoiding algorithm that relaxes the communication across nodes, thus improving the scalability. Asynchrony-tolerant finite difference schemes for spatial derivatives along with the low storage Runge-Kutta scheme for time integration are used to achieve high-order accuracy. The efficacy of the implementation is demonstrated using a mini-app that solves the three-dimensional diffusion problem. © 2024 IEEE

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Improved channel estimation for underwater wireless optical communication OFDM systems by combining deep learning and machine learning models

引用

Optical and Quantum Electronics 2025年第3期57卷 1-21页

作者： Salama, Wessam M. Aly, Moustafa H. Department of Computer Engineering Faculty of Engineering Pharos University Canal El Mahmoudia Street Beside Green Plaza Complex 21648 Alexandria Egypt OSA Member Department of Electronics and Communications Engineering College of Engineering and Technology Arab Academy for Science Technology and Marine Transport Alexandria1029 Egypt

Recent studies on channel estimation in wireless communication systems have focused on deep learning methods. Our primary contribution is based on the use of DenseNet121 hybrid with Random Forest (RF), Gated Recurrent Units (GRU), Long Short-Term Memory Networks (LSTM), and Recurrent Neural Networks (RNN) to improve the channel estimation and lower the error rate. In order to mitigate inter-symbol interference and map the datasets, this paper introduces M-quadrature amplitude modulation (16-QAM) and orthogonal frequency division multiplexing (OFDM), which is based on quadrature phase shift keying (QPSK). Additionally, the existence or lack of cyclic prefixes forms the basis of our simulation. Additionally, the suggested models are investigated using pilot samples 2, 4, 8, and 64. Labeled OFDM signal samples, where the labels match the signal received after applying OFDM and passing through the medium, are used to train the proposed models. The DenseNet121 functions as a powerful feature extractor to extract intricate spatial information from received signal data. Sequential models like as RNN, LSTM, and GRU are used to model temporal dependencies in the retrieved features. RF is also utilized to exploit non-linear relationships and interactions between features to further increase prediction accuracy and reduce bit error rate (BER). By comparing the models using key metrics like accuracy, bit error rate (BER), and mean squared error (MSE), superior performance is attained based on the DenseNet121_RNN_GRU_RF model. Additionally, the DLMs are assessed against traditional methods like minimal mean square error (MMSE) and least squares (LS). Using the DenseNet121_RNN_GRU_RF model indicates a considerable gain over alternative architectures, with an improvement of 36.3% over DensNet121-RNN-LSTM-RF, according to a comparison of the suggested models without cyclic prefix for OFDM_QPSK. The improvement in percentages of roughly 63.3% over DensNet121-RNN-LSTM, 68.18% over De

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Tumor type classification and candidate cancer-specific biomarkers discovery via semi-supervised learning

引用

Biophysics Reports 2023年第2期9卷 57-66页

作者： Peng Chen Zhenlei Li Zhaolin Hong Haoran Zheng Rong Zeng School of Computer Science and Technology University of Science and Technology of China Anhui Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Department of Systems Biology University of Science and Technology of China CAS Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences School of Life Science and Technology ShanghaiTech University

Identifying cancer-related differentially expressed genes provides significant information for diagnosing tumors, predicting prognoses, and effective treatments. Recently, deep learning methods have been used to perform gene differential expression analysis using microarray-based high-throughput gene profiling and have achieved good results. In this study, we proposed a new robust multiple-datasetsbased semi-supervised learning model, MSSL, to perform tumor type classification and candidate cancer-specific biomarkers discovery across multiple tumor types and multiple datasets, which addressed the following long-lasting obstacles:(1) the data volume of the existing single dataset is not enough to fully exert the advantages of deep learning;(2) a large number of datasets from different research institutions cannot be effectively used due to inconsistent internal variances and low quality;(3) relatively uncommon cancers have limited effects on deep learning methods. In our article, we applied MSSL to The Cancer Genome Atlas(TCGA) and the Gene Expression Comprehensive Database(GEO) pan-cancer normalized-level3 RNA-seq data and got 97.6% final classification accuracy, which had a significant performance leap compared with previous approaches. Finally, we got the ranking of the importance of the corresponding genes for each cancer type based on classification results and validated that the top genes selected in this way were biologically meaningful for corresponding tumors and some of them had been used as biomarkers, which showed the efficacy of our method.

关键词： Deep learning Tumor type classification Cancer-specific biomarkers MSSL

来源：评论

学校读者我要写书评

暂无评论

Adaptive residual convolutional neural network for moiré image restoration

引用

International Journal of Information technology (Singapore) 2025年第2期17卷 783-791页

作者： Malagi, Vindhya P. Naresh, E. Mithra, C. Suresh, B. V. N. V. Krishna Department of AI & amp ML Dayananda Sagar College of Engineering Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Chennai 600062 India Computer Science & amp Engineering KLEF KL University Andhra Pradesh Vaddeswaram India

Restoring Moiré images presents significant challenges due to the complex interference patterns that obscure image details. These patterns often degrade the quality of images, making accurate restoration crucial for various applications. Effective Moiré image restoration requires advanced techniques to overcome the difficulties posed by these intricate artifacts. This study introduces an Adaptive Residual Convolutional Neural Network (RCNN) for Moiré image restoration, augmented with the Zebra Optimization Algorithm (ZOA) to enhance both feature extraction and restoration accuracy. The hybrid model leverages ZOA's capability to balance exploration and exploitation, optimizing network parameters to improve learning efficiency. Tested on the DIV2K dataset, this approach demonstrates significant improvements in handling complex Moiré patterns, as evidenced by enhanced Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values. © The Author(s) 2024.

关键词： Adaptive residual convolutional neural network Moiré images Peak signal-to-noise ratio Structural similarity index measure Zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Robust Malicious Domain Detection Based on Spatio-Temporal Hypergraph Networks 22

Robust Malicious Domain Detection Based on Spatio-Temporal H...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Gong, Liangyi Lv, Kunxian Long, Chun Fu, Hao Wang, Huanran Wan, Wei Yang, Wu Chinese Academy of Sciences Computer Network Information Center Beijing China University of Chinese Academy of Sciences Beijing China Harbin Engineering University School of Computer Science and Technology Heilongjiang China

ISBN: (纸本)9798331509712

Malicious domains serve as significant resources for adversaries to execute cyber attacks and are crucial indicators for detecting network intrusions. In practical scenarios, malicious domains associated with various attacks are intermingled within DNS traffic, leading to variability in the performance of machine learning-based detection methods. To address this challenge, we have collected extensive DNS traffic data spanning 12 months from a real-world large-scale network with 1 million users. From this dataset, we have extracted numerous requested domains, encompassing 267 attacks that exploit malicious domain names. Furthermore, we have observed that the distinct properties of malicious domains associated with different attacks contribute to the fluctuating performance of machine learning-based detection models. Consequently, we have introduced a spatiotemporal hypergraph network model, which establishes high-order relationships among domain properties to enhance the generalization capability and robustness of the detection model. The results of extensive testing experiments demonstrate that our model achieves remarkable performance, with an average precision of 97% and recall of 98%. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Advanced Classification Models Combined with Feature Selection for Credit Risk Performance 3

Performance Evaluation of Advanced Classification Models Com...

引用

3rd International Conference on Machine Learning and Data engineering, ICMLDE 2024

作者： Tribuvan, Sarakam Kamath, Sandeep Deepak Mishra, Sparsh Usha, M. Shreyas, J. Gururaj, H.L. Dayananda, P. Karthik, S.A. Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

In this study, we propose an advanced methodology utilizing machine learning models for predicting home equity credit risk on a real-world dataset. Traditional credit risk models often rely on outdated statistical methods that fail to capture complex, non-linear relationships in data, resulting in suboptimal accuracy and limited interpretability. Furthermore, existing models lack transparency, making it difficult for stakeholders to understand and act on the predictions. To address these issues, we employ state-of-the-art machine learning algorithms such as Decision Trees, AdaBoost, Support Vector Machine (SVM), Neural Networks, and Random Forest, along with feature selection techniques like Boruta and Principal Component Analysis (PCA) to enhance both accuracy and explainability. Our approach aims to provide improved credit risk assessment tools, offering better interpretability for loan companies, regulators, and applicants, while ensuring robust performance. The results demonstrate that our proposed models outperform traditional methods and offer actionable insights for stakeholders, enhancing decision-making processes. © 2025 The Author(s).

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Hybrid Adam Coati Optimization with DLSTM for Biomedical Parameter Prediction Using Sensor 3

Hybrid Adam Coati Optimization with DLSTM for Biomedical Par...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Rajesh, L. Mohan, H.S. Bindiya, M.K. Visvesvaraya Technological University Dayananda Sagar Academy Of Technology And Management Department Of Information Science And Engineering Karnataka Bengaluru India Karnataka Bengaluru India Sjb Institute Of Technology Department Of Computer Science And Engineering Karnataka Bengaluru India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318609

A real-time patient monitoring system procesfses a wide range of biomedical parameters and can store and safely capture biomedical parameters. It lowers the diagnosis time of the several diseases that are prevalent in healthcare services. Accurate prediction of biomedical parameters can significantly reduce healthcare costs and assist in effective decision-making. This research proposes a deep learning approach with hybrid optimization for biomedical parameter prediction by using sensors. At first, a healthcare centre with many patients having various disorders is considered. Several biomedical sensors are placed on the patients and these sensors include a respiratory Rate (RR) sensor, Heart rate (HR) sensor, Pulse Rate (PR) sensor, Ambulatory Blood Pressure (ABP)-sensor, and Saturation of Peripheral Oxygen (SpO2). Based on these sensed parameters, biomedical parameter prediction by using sensor based Deep Long Short-Term Memory (DLSTM)is executed. The DLSTM is trained using the proposed Hybrid Adam Coati Optimization(HAdCO). Here, the HAdCO is developed by incorporating of Coati Optimization Algorithm (COA) with Adam Optimizer. Furthermore, the HAdCO-DLSTM is evaluated by utilising metrics, like Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Squared Error (MSE). The HAdCO-DLSTM had a minimal value of MAE at 0.0063, MSE at 0.0062, and RMSE at 0.0078. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Compact Home-Based Training System for Preventing Frailty Using a Mapping Model and Cross-Dataset Transfer Learning

IEEE Journal of Selected Areas in Sensors

引用

IEEE Journal of Selected Areas in Sensors 2025年 2卷 1-8页

作者： Liu, Lizheng Hu, Hsuan Yeh, Shih-Ching Wu, Eric Hsiao-Kuang Chen, Chun-Chuan Fudan University Department of Academy of Engineering and Technology Shanghai200437 China National Central University Department of Computer Science and Information Engineering Taoyuan320 Taiwan National Central University Department of Biomedical Sciences and Engineering Taoyuan320 Taiwan

Frailty is becoming a more serious issue as the population ages. Numerous studies have shown that exercise can effectively slow the development of frailty. Compared with vigorous exercise, Baduanjin (BDJ), a kind of traditional Chinese Qigong with eight simple movements, is more suitable for frailty patients. BDJ has been used to train frailty patients by physical therapists. To provide an enhanced training method, we designed a lightweight family-based frailty training system via a virtual BDJ coach. To achieve a compact system, we use a webcam as the main device. The system also supports the Kinect framework. We use pose estimation and motion recognition methods to analyze the user's movements. In addition, a novel transfer learning method is proposed. We designed a mapping model called "Skeleton Mapnet" to convert skeletal data from different frameworks. This method enables datasets from different frameworks to share classification models. It can also mix skeletal data from different frameworks to solve the lack of webcam datasets. Such a design allows the system to be easily ported into other platforms. In addition, the system is also suitable for the use of the artificial intelligence of things. Our design ensures that frailty patients can easily learn and operate the system. © 2024 The Authors.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Balancing communication overhead and accuracy in compression integration: a survey

引用

Journal of Supercomputing 2025年第8期81卷 1-63页

作者： Yang, Aiqiang Liu, Jie Yang, Bo Mo, Zeyao Li, Keqin College of Computer Science and Technology National University of Defense Technology Changsha410000 China Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology Changsha410073 China National Key Laboratory of Parallel and Distributed Computing National University of Defense Technology Changsha410073 China China Academy of Engineering Physics Beijing China Department of Computer Science State University of New York New PaltzNY12561 United States

In large-scale distributed training, communication compression techniques are widely used to reduce the significant communication overhead caused by the frequent exchange of model parameters or gradients between training nodes. However, these techniques often introduce additional computational complexity and may lead to data loss, thereby affecting model convergence and performance. This review examines key optimization methods in communication compression, including pruning techniques that remove irrelevant weights, quantization techniques that convert floating-point parameters to low-precision representations, and sparsification techniques that transmit only critical gradients. Low-rank approximation techniques, which compress parameters through matrix factorization, are particularly useful for large-scale models. These techniques have also been widely applied in various application scenarios, demonstrating their effectiveness in different environments. Application scenarios include distributed training, federated learning, and edge computing, where bottlenecks are carefully identified and evaluated in common scenarios, providing a basis for further optimization. Future development directions emphasize co-design of hardware and algorithms, dynamic strategies, and cross-layer optimization. This study provides valuable comparisons of key methods and theoretical analysis for efficient communication compression in distributed systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Solarsense: Enhancing Energy Efficiency Through Iot-Enabled Solar Tracking 2

Solarsense: Enhancing Energy Efficiency Through Iot-Enabled ...

引用

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

作者： Thopate, Kaushalya Gawade, Mayuri Kakade, Surabhi Bahir, Suvarna Kulkarni, Mukund Jaiswal, Krishna Nilesh Computer Engineering Vishwakarma Institute of Technology Pune India Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune India Computer Engineering Trinity Academy of Engineering Pune India Electronics and Telecommunication Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9798350360523

The surging global demand for energy is primarily fueled by a burgeoning world population and elevated living standards. However, with traditional fossil fuels like oil dwindling in availability, there is an urgent need to shift towards renewable energy sources. Given the rapid progress in renewable energy technologies, a key objective of the project is to develop a solar energy tracking panel that can rotate for enhanced power generation. This innovative panel, capable of adjusting its position to optimize energy output by tracking the sun, proves invaluable in monitoring power consumption. The design of this rotatable solar energy tracking panel, incorporating four essential components (solar energy tracking panels, light-dependent resistors (LDRs), an Arduino, and a motor), is intricately explained in this study. This configuration not only serves as an advanced educational tool but also provides engineering technology students with a comprehensive understanding of alternative energy sources like solar power. © 2024 IEEE.

关键词： Fossil fuels

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：