检索结果-内蒙古大学图书馆

Machine learning in concept drift detection using statistical measures

International Journal of Computers and Applications 2024年第5期46卷 281-291页

作者： Ali Abdu, Nail Adeeb Basulaim, Khaled Omer Information Technology Department Faculty of Engineering & Computing University of Science and Technology Aden Yemen Information Technology Engineering Department Faculty of Engineering University of Aden Aden Yemen

In the data stream, the data has non-stationary quality because of continual and inconsistent change. This change is represented as the concept drift in the classifying process of the streaming data. Representing this data drift concept in data stream mining requires pre-labeled samples. However, labeling samples in real-time streaming (online) is not feasible due to resource utilization and time constraints. Therefore, this paper proposes the concept of Probabilistic Concept Drift Detection (PCDD) in the group classifier. PCDD relies on the data stream classification process and provides concept drift without labeled samples. The PCDD model is evaluated through an empirical study on a dataset called Poker-Hand. The study results show a high concept drift detection rate and a significant reduction in false alarms and missed detections compared to contemporary models. Hence, the results of the experimental study prove the accuracy and scalability of the PCDD model. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Concept drift data streams detection rate for concept drift Kolmogorov–Smirnov statistical test (K–S) statistical t-test Wilcoxon signed rank statistical test

来源：评论

学校读者我要写书评

暂无评论

An arrhythmia classification using a deep learning and optimisation-based methodology

引用

Journal of Medical engineering and technology 2024年第7期48卷 253-261页

作者： Sharma, Suvita Rani Singh, Birmohan Kaur, Manpreet Department of Computer Science and Engineering Sant Longowal Institute of Engineering and Technology Longowal India Department of Electrical and Instrumentation Engineering Sant Longowal Institute of Engineering and Technology Longowal India

The work proposes a methodology for five different classes of ECG signals. The methodology utilises moving average filter and discrete wavelet transformation for the remove of baseline wandering and powerline interference. The preprocessed signals are segmented by R peak detection process. Thereafter, the greyscale and scalograms images have been formed. The features of the images are extracted using the EfficientNet-B0 deep learning model. These features are normalised using z-score normalisation method and then optimal features are selected using the hybrid feature selection method. The hybrid feature selection is constructed utilising two filter methods and Self Adaptive Bald Eagle Search (SABES) optimisation algorithm. The proposed methodology has been applied to the ECG signals for the classification of the five types of beats. The methodology acquired 99.31% of accuracy. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Finite Element Analysis on Kenaf and Kevlar Natural Fiber Reinforced Rings Using Split-Disk Tests

引用

Journal of The Institution of Engineers (India): Series E 2024年第2期105卷 129-136页

作者： bobba, Sujith Babu, Bachina Harish Department of Mechanical Engineering VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad India Department of Automobile Engineering VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad India

The aim of the paper was to investigate the mechanical parameters of two different natural fiber composite rings using the tensile and split disk tests. The tests are carried out with various thickness specimens (1.5 mm, 2.00 mm and 3.00 mm) of two different natural fibers (Kenaf and Kevlar). Hoop tensile and axial tensile properties of the samples were identified, and the effect of filament winding dispersion on the hoop tensile and longitudinal properties of the designated composites were also attained. Minor rise in the hoop and longitudinal tensile properties of rings created with Kenaf natural fiber was observed and contrasted to those designed with Kevlar natural glass fiber. The design analysis was accomplished in accordance to the American Society for Testing and Materials ASTM D 2290 standard. Split-disk analysis of Kenaf and Kevlar natural composite rings were modelled and simulated using the finite element method and analysis (Ansys 16.0). A reasonable understanding was achieved by the natural composites through the finite element simulation and the results of the two different fibers. © The Institution of Engineers (India) 2024.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Parametric analysis in the machining of gun metal using computer numerical control turning process

引用

Interactions 2025年第1期246卷 1-11页

作者： Santhanakrishnan, R. Marichamy, S. Anandavelu, K. Gomathy, V. Vinu, A. Thava Veerappan, G. Ram, S. Sheeba, T. Blesslin Department of Mechanical Engineering & Registrar Evaluation CMR University Bengaluru India Department of Mechanical Engineering MRK Institute of Technology Tamil Nadu Kattumannarkoil India Department of Electrical and Electronics Engineering Kathir College of Engineering Coimbatore India DMI College of Engineering Aralvaimozhi India Department of Mechatronics Engineering Sri Krishna College of Engineering and Technology Tamilnadu Coimbatore India Department of Mechanical Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Department of Electronics and Communication Engineering R.M.K. Engineering College Kavaraipettai India

The quality of the machining of the materials is depending on the input constrains of the process and its composition of different alloying elements. The outstanding material properties of gun metal are achieved by the composition of copper, tin and zinc. This paper to investigate the machining behaviors of gun metal through computer numerical control turning process with different input constrains. The response factors such as cutting force, tool tip temperature and surface roughness are evaluated by manipulate the input factors. The experimental results are compared with response surface methodology model (RSM). It is used to optimize the input and output factors. The minimized cutting force, tool tip temperature and surface roughness are 84.87 N, 200.10 C and 0.75 microns respectively. The surface plots are used to correlate the dependent and independent variables. The novelty of the experiment is that parametric analysis in the machining of gun metal using computer numerical control turning process. Investigate the cutting force, tool temperature and surface roughness of the gun metal and it can be recommended to rotating elements such as gears and bearings. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Cutting force Gun metal Machining behaviors RSM Tool tip temperature Turning

来源：评论

学校读者我要写书评

暂无评论

Techno economic and environmental analysis of green hydrogen generation with hybrid PV/Wind systems in southern provinces of Oman

引用

Interactions 2025年第1期246卷 1-14页

作者： Gopinath, Arun S. Al Quri, Khalifa Kalyan Kumar, B. Boddu, Muralikrishna Santhappan, Joseph Sekhar Engineering Department University of Technology and Applied Sciences Shinas Oman Engineering Department University of Technology and Applied Sciences Musandam Oman

The use of renewable energy resources is becoming increasingly critical for a sustainable power generation scenario on a global scale. Solar photovoltaics and wind are the most prominent potential renewable sources in Oman, according to the studies conducted in the zone. Various locations in Oman behaved differently depending on the region’s potential energy source. For instance, the Dhofar region has an annual average global horizontal irradiance of 6.1 kWh/m2/day and a wind speed of 5.9 m/s at a 10-meter anemometer height from the ground, respectively. The intermittency of renewable sources and the need for reliability in power systems lead to battery energy storage requirements. This study establishes the optimal hybrid system rating for a community load of 24.57 kW, considering multiple system configurations and producing 11.27 kg of hydrogen daily. Since renewable energy must replace fossil fuels in microgrids, this study compares the results with diesel generator-based systems. The study employs several criteria to identify the optimal solution, including meeting the load potential, minimizing the levelized cost of energy (LCOE), minimizing the levelized cost of hydrogen (LCOH) generation, calculating the net present cost, and calculating the CO2 emissions. The study region achieves a renewable energy fraction of more than 85%, with an LCOE of 0.421 $/kWh and an LCOH of 4.65 $/kg. Furthermore, we observed that the region has a high potential for green hydrogen generation, which can meet the country’s aim to improve the ratio of renewables in total energy supply and achieve sustainable development goals. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Healthcare:The Role of Computational Methods in Medical Innovation

引用

Computer Modeling in engineering & Sciences 2025年第1期142卷 1-48页

作者： Hariharasakthisudhan Ponnarengan Sivakumar Rajendran Vikas Khalkar Gunapriya Devarajan Logesh Kamaraj Department of Mechanical Engineering Dr.Mahalingam College of Engineering and TechnologyPollachiCoimbatoreTamil Nadu642003India Department of Mechanical Engineering JKKN College of Engineering and TechnologyKumarapalayamNamakkalTamil Nadu637209India Department of Mechanical Engineering Gharda Institute of TechnologyLavelMaharashtra415708India Department of Electrical and Electronics Engineering Sri Eshwar College of EngineeringCoimbatoreTamilnadu641202India Department of Mechanical Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai600062India

The purpose of this review is to explore the intersection of computational engineering and biomedical science,highlighting the transformative potential this convergence holds for innovation in healthcare and medical *** review covers key topics such as computational modelling,bioinformatics,machine learning in medical diagnostics,and the integration of wearable technology for real-time health *** findings indicate that computational models have significantly enhanced the understanding of complex biological systems,while machine learning algorithms have improved the accuracy of disease prediction and *** synergy between bioinformatics and computational techniques has led to breakthroughs in personalized medicine,enabling more precise treatment ***,the integration of wearable devices with advanced computational methods has opened new avenues for continuous health monitoring and early disease *** review emphasizes the need for interdisciplinary collaboration to further advance this *** research should focus on developing more robust and scalable computational models,enhancing data integration techniques,and addressing ethical considerations related to data privacy and *** fostering innovation at the intersection of these disciplines,the potential to revolutionize healthcare delivery and outcomes becomes increasingly attainable.

关键词： Computational models biomedical engineering bioinformatics machine learning wearable technology

来源：评论

学校读者我要写书评

暂无评论

A Miniaturized Quad Port Highly Isolated Triple Band Notched UWB-MIMO Diversity Antenna

引用

Progress in Electromagnetics Research C 2025年 152卷 43-53页

作者： Thotakura, Sushma Gogineni, Rajesh Nallagonda, Vijaya Ratnam Sadineni, Ramesh Babu Mandava, Sunitha Paruchuri, Venkata Krishna Kanth Department of Electronics & Communication Engineering PVP Siddhartha Institute of Technology Vijayawada India Department of Electronics & Communication Engineering Dhanekula Institute of Engineering and Technology Ganguru India Department of Electronics & Communication Engineering RVR & JC College of Engineering Guntur522019 India

In this study, a quad-port ultra-wideband (UWB) multiple input multiple output (MIMO) antenna with triple band-rejection characteristics is demonstrated. The suggested diversity MIMO antenna comprises four similar rectangular radiators positioned in orthogonal manner by utilizing polarization diversity. For superior inter-element isolation, a fan-shaped decoupler is lithographed on the back of the substrate. The MIMO antenna exhibits an operational bandwidth of 9 GHz (3–12 GHz) for each port, with |S11| ≤ −10 dB. This version is more concise and properly formatted. The MIMO aerial exhibits an impedance bandwidth 3–12 GHz) for each port (|S11| ≤ −10 dB) along with an inter-element isolation exceeding 20 dB. Additionally, to exclude the 3.5–4.1 GHz (downlink C-band), 4.43–4.79 GHz (INSAT), and 5.25–5.71 GHz (Wireless LAN) bands that coexist in UWB spectrum, the antenna elements are equipped with three U-shaped slots. The MIMO diversity metrics, including isolation, envelope correlation coefficient, diversity gain, TARC, CCL, multiplexing efficiency, and group delay, were computed and reported. The reported aerial prototype has been constructed, and the measured results have been validated against the simulated findings. © 2025, Electromagnetics Academy. All rights reserved.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

Food ingredient recognition model via image and textual feature extraction and hybrid classification strategy

引用

International Journal of Reasoning-based Intelligent Systems 2024年第1期16卷 74-90页

作者： Madival, Sharanabasappa A. Jawaligi, Shivkumar S. Department of Computer Science and Engineering Faculty of Engineering and Technology Sharnbasva University India Department of Electronic and Communication Engineering Faculty of Engineering and Technology Sharnbasva University Karanataka Kalburgi India

This research work focuses on food recognition, especially, the identification of the ingredients from food images. Here, the developed model includes two stages namely: 1) feature extraction;2) classification. Initially, the image features and textual features will be extracted, where image features like SIFT and improved CNN-based deep features, textural features are extracted. Then, the hybrid classifier is used for the identification of food ingredients that combines the models like neural network (NN) as well as long short-term memory (LSTM). In order to make the accurate results, the weights of NN and LSTM are fine-tuned via the Chebyshev map evaluated teamwork optimisation (CME-TWO) algorithm. At the final stage, the primacy of the offered scheme is proven concerning varied metrics. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Reducing Outgoing Quality Level (OQL) in Textile Manufacturing Through Six Sigma Methodology: A Case Study

Textile and Leather Review

引用

Textile and Leather Review 2024年 7卷 1252-1272页

作者： Kaka, Shuaib Maryam, Muttahira Wassan, Rano Khan Sarwar, Umair Akbar, Ali Ansari, Jansher Department of Industrial Engineering and Management Dawood University of Engineering and Technology Pakistan

Globally, the textile industry plays a significant role in production but faces many challenges that affect its operation and sustainability. Product quality remains an essential concern despite technological advancements and quality control measures. Raw materials, production methods, and skills differ, resulting in customer dissatisfaction and damage to reputation. A quality management strategy is necessary to overcome these problems and promote quality improvement. This includes the implementation of the Lean Six Sigma approach. This article focuses on improving textile quality by developing the Six Sigma DMAIC method. An analysis of three months' data from a textile company shows that an increase in the Outgoing Quality Level (OQL) from 3% to 6% resulted in significant economic losses, amounting to PKR-240,000 due to rework, residual costs, customer returns, and lost sales time. By utilizing Six Sigma tools, the company reduced OQL from 6% to 4%, thus lowering product losses and increasing operational efficiency. As a result of these findings, the textile industry can improve quality and profitability through a Lean Six Sigma approach. © 2024, idd3. All rights reserved.

关键词： DMAIC lean manufacturing outgoing quality level Six Sigma

来源：评论

学校读者我要写书评

暂无评论

Enhancing Predictive Capabilities for Cyber Physical Systems Through Supervised Learning

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第16期49卷 77-86页

作者： Dhanalakshmi, B. Tamije Selvy, P. Department of Computer Science and Engineering Dr.N.G. P Institute of technology India Department of Computer Science and Engineering Hindusthan College of Engineering and Technology India

The rapid advancement and proliferation of Cyber-Physical Systems (CPS) have led to an exponential increase in the volume of data generated continuously. Efficient classification of this streaming data is crucial for predicting system behaviors and enabling proactive decision-making. This research aims to extract actionable knowledge from the continuous data streams of CPS and predict their behavior using advanced supervised learning algorithms. The predictions facilitate timely interventions and necessary actions within the interconnected physical network. The background of this work lies in the intersection of CPS, machine learning, and data stream mining. Traditional batch processing methods are inadequate for real-time analysis of CPS data due to their inherent latency and computational inefficiency. This research employs state-of-the-art techniques for real-time data processing, including incremental learning, sliding window models, and ensemble methods tailored for streaming data. Our approach differs from existing works by focusing on a comprehensive framework that integrates real-time data ingestion, preprocessing, feature extraction, and model updating in a seamless pipeline. Unlike previous studies that often rely on static datasets and offline analysis, our method ensures continuous learning and adaptation to evolving data patterns. Comparative analysis with existing techniques demonstrates superior performance in terms of accuracy, latency, and scalability. Specifically, our models achieved an average classification accuracy of 92%, with a precision of 90%, recall of 89%, and an F1 score of 89.5%. These metrics indicate significant improvements over traditional batch processing methods, which typically lag in responsiveness and adaptability. This research provides a robust and efficient solution for the real-time classification of streaming data from CPS, enhancing the system's ability to predict behaviors and take necessary actions promptly. © 2025 Slov

关键词： Self-supervised 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：