检索结果-内蒙古大学图书馆

Multi-scene design analysis of integrated energy system based on feature extraction algorithm

ENERGY REPORTS 2022年 8卷 466-476页

作者： Huang, Sihua Ali, Noor Azizi Mohd Shaari, Nazlina Noor, Mohd Sallehuddin Mat Univ Putra Malaysia Fac Design & Architecture Seri Kembangan 43400 Selangor Malaysia Museum Chinese Culture Tiger Designed Ceram Wuhan 430073 Hubei Peoples R China

The specific analysis of a region's energy needs to model and simulate various types of energy, quantify energy information, and clearly and intuitively reflect the energy situation and energy potential of a region. In this paper, according to the input attributes of various energy load forecasting models, the correlation degree of main control factors is analyzed, and the influence degrees of environmental factors on electric power, gas, heating and cooling loads are obtained respectively. Then, convolution neural network is used to extract the feature vectors of comprehensive environmental factors. Finally, according to the given feature vectors, the feature clustering models of various energy loads are established by using K-means clustering algorithm, and the load forecasting results of multi-energy systems are obtained. The errors between the predicted results of various energy loads and the actual load records in the study area are 1.105%, 1.876%, 3.102% and 2.834%, respectively. The load forecasting method based on feature clustering proposed in this paper can effectively extract the influence of different environmental factors on the load forecasting results, and get more accurate load forecasting results. (C) 2022 The Author(s). Published by Elsevier Ltd.

关键词： feature extraction algorithm Integrated energy system Scene design

来源：评论

学校读者我要写书评

暂无评论

Safety Protection Technology of Power Monitoring System Based on feature extraction algorithm

引用

Distributed Generation and Alternative Energy Journal 2022年第2期37卷 311-326页

作者： Xiangbei, Che Yuhong, Ouyang Wenqian, Kang Jing, Su Shenzhen Power Supply Bureau Co. Ltd. Guangdong Shenzhen518000 China

The network security protection technology of power monitoring systems is of great significance. Aiming at the power network monitoring and protection technology problem, the paper proposes an active monitoring and protection strategy based on a feature extraction algorithm. The algorithm can calculate the transfer degree of security incidents based on evidence theory. First, the paper obtains a specific state transition diagram based on the security topology of a generalized random power communication network. Then, we analyze the relationship between power system information security and engineering security based on the system’s operating results and feature extraction algorithms. The experimental results demonstrate the rapid effectiveness of this method. © 2021 River Publishers.

关键词： evidence theory feature extraction algorithm Power monitoring network security protection technology

来源：评论

学校读者我要写书评

暂无评论

Detection and classification of disturbances in the islanded micro-grid by using wavelet transformation and feature extraction algorithm

引用

JOURNAL OF ENGINEERING-JOE 2019年第18期2019卷 5284-5286页

作者： Wang, Yunqi Raza, Ahmed Mohammed, Faisal Parvez Ravishankar, Jayashri Phung, Toan Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia

Digital signal processing (DSP) methods have been used by many researchers for detection and classification of transient disturbances because of their fast and powerful abilities to recognise waveform distortions. However, some DSP methods such as the wavelet transformation (WT) show less accuracy when applied to noisy real data. In this study, disturbance features are extracted in the wavelet domain based on the WT levels. Moreover, a new feature extraction algorithm namely normalised Renyi entropy with the signal energy is applied. This algorithm has been proven to be effective and robust for noisy signals. However, their application in power systems has not yet been tested. Using a laboratory setup of an islanded micro-grid, experimental results validate the efficacy of the wavelet-based normalised Renyi entropy in the detection and classification of four disturbance types (voltage sag, interruption, harmonics, mixture of harmonics and sag).

关键词： digital signal processing chips signal processing power distribution faults distributed power generation power supply quality signal classification feature extraction wavelet transforms medical signal processing entropy classification wavelet transformation feature extraction algorithm digital signal processing methods detection transient disturbances fast abilities powerful abilities waveform distortions DSP methods noisy real data disturbance features wavelet domain signal energy noisy signals power systems islanded microgrid wavelet-based normalised Renyi entropy disturbance types

来源：评论

学校读者我要写书评

暂无评论

Neural network-based strategies for automatically diagnosing of COVID-19 from X-ray images utilizing different feature extraction algorithms

引用

NETWORK MODELING AND ANALYSIS IN HEALTH INFORMATICS AND BIOINFORMATICS 2023年第1期12卷 28-28页

作者： Prity, Farida Siddiqi Nath, Nishu Nath, Antara Uddin, K. M. Aslam Noakhali Sci & Technol Univ Dept Informat & Commun Engn Noakhali Bangladesh Montana State Univ Gianforte Sch Comp Bozeman MT 59717 USA Mainamoti Med Coll Cumilla Bangladesh

The COVID-19 pandemic has had an obliterating impact on the health and well-being of the worldwide populace. It has recently become one of the most severe and acute diseases and has spread globally. Therefore, an automated detection system should be implemented as the fastest diagnostic option to control the spread of COVID-19. This study aims to introduce neural network-based strategies for classifying and detecting COVID-19 early through image processing utilizing X-ray images. Despite the extensive use of directly fed X-ray images into the classifier, there is a lack of comparative analysis between the feature-based system and the direct imaging system in the classification of COVID-19 to evaluate the efficiency of feature extraction methods. Therefore, the proposed system represents introductory experiments of feature-based system using image feature extraction algorithms [Texture, Grey-Level Co-occurrence Matrix (GLCM), Grey-Level Dependence Matrix (GLDM), Fast Fourier Transform (FFT), and Discrete Wavelet Transform (DWT)], Dimensionality Reduction algorithms (Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), Sparse Autoencoder, and Stacked Autoencoder), feature Selection algorithms (Anova F-measure, Chi-square Test, and Random Forest), and Neural Networks [Feed-Forward Neural Network (FFNN) and Convolutional Neural Network (CNN)] on generated datasets consisting of Normal, COVID-19, and Pneumonia-infected chest X-ray images. Tenfold Cross-Validations are implemented during the classification process. A baseline model is created where no feature extraction algorithm is implemented. Accuracy, sensitivity, specificity, precision, and F-measure metrics are utilized to assess classification performance. Finally, a comprehensive comparison of the success of the feature-based system (feature extraction algorithms, Dimensionality Reduction algorithms, and feature Selection algorithms) in COVID-19 classification from X-ray images is made w

关键词： COVID-19 X-ray image Neural network feature extraction algorithm Dimensionality reduction algorithm feature selection algorithm

来源：评论

学校读者我要写书评

暂无评论

Design of the 3D Digital Reconstruction System of an Urban Landscape Spatial Pattern Based on the Internet of Things

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGIES AND SYSTEMS APPROACH 2023年第2期16卷 1-14页

作者： Li, Fan Zhou, Tian Dong, Yuping Zhou, Wenting Shenyang Inst Engn Shenyang Peoples R China Shenyang Inst Engn Communist Youth League Shenyang Peoples R China

Given the rapid development of modern science and technology, people are no longer satisfied with the planar composition and two-dimensional (2D) composition. Moreover, digitalization has entered the spatial layout of urban landscapes. The three-dimensional (3D) digital reconstruction technology can obtain the 3D effect map of urban garden landscapes, thereby improving the scientificity and timeliness of garden design. It is an important research direction in the field of computer vision. It transforms two or more planar graphics into visible 3D geometric graphics. It also restores their spatial coordinates and color information. The appearance of 3D digital reconstruction technology provides real-time and efficient information for landscape design, cost, and construction;improves the efficiency of landscape construction;and saves construction costs.

关键词： Digital Reconstruction System feature extraction algorithm Internet of Things Technology Spatial Pattern Urban Landscape

来源：评论

学校读者我要写书评

暂无评论

Research on Motion Posture Based on Convolutional Neural Network algorithm

Research on Motion Posture Based on Convolutional Neural Net...

引用

2024 IEEE International Conference on Cognitive Computing and Complex Data

作者： Tang, Yunpeng Zou, Yu Guizhou Business Sch Phys Educ Teaching Dept Guiyang 550014 Peoples R China Guizhou Kangsitian Sci & Technol Dev Co Ltd Guiyang 550002 Peoples R China

ISBN: (纸本)9798350352900;9798350352894

Recognition of motion postures has been a highly popular research field, aiming to analyze and identify human movements and behavior patterns through observations and description using natural language and other methods. This study introduces a posture motion feature extraction algorithm that incorporates spatiotemporal weighting and utilizes a deep convolutional neural network (CNN) approach. The algorithm extracts spatiotemporal motion key frames from selected motion samples and presents them as static images. It then performs initial motion image preprocessing, such as motion target detection and image enhancement, and vectorizes motion features using CNN. The spatiotemporal weighted adaptive interpolation method is employed to minimize errors in motion edge detection, enabling the extraction of posture motion features by combining posture edge features and spatiotemporal features. The extraction results are presented as the output. Comparative experiments with traditional algorithms demonstrate that the proposed neural network intelligent recognition algorithm not only achieves intelligent recognition of motion postures but also improves overall accuracy and reduces computational load compared to some other algorithms.

关键词： Convolutional neural networks Temporal and spatial weights Sports posture Movement characteristics feature extraction algorithm

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Subway Plug Door based on EEMD and Adaptive feature extraction 16

Fault Diagnosis of Subway Plug Door based on EEMD and Adapti...

引用

16th IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Wang, Wei Jiang, Qilong Heng, Xidan Liu, Dong Li, Zhenwei Xie, Le Southwest Jiaotong Univ Sch Elect Engn Chengdu Peoples R China

ISBN: (纸本)9781665422482

Fault diagnosis of the subway plug door plays an essential role in the safe operation of the city subway. To improve the diagnosis accuracy of the subway plug door, fault diagnosis of the plug door based on Ensemble Empirical Mode Decomposition (EEMD) and adaptive feature extraction was presented in this paper. Firstly, EEMD was used for decomposition of raw data, and the intrinsic mode function (IMF) after decomposition was selected by correlation coefficient criteria. Then, the fault features in IMFs was extracted and the sensitive features among which was selected by the sensitive index. Finally, the faults were classfied by Gray Wolf optimized Support Vector Machine (GWO-SVM). The experiment with the measured data of a subway door shows that this fault diagnosis method can adaptively extract the relative optimal characteristic quantity . , identify the normal state and four different fault states effectively . with the recognition accuracy of 89.35%, which is valuable in the engineering application.

关键词： subway plug door fault diagnosis EEMD feature extraction algorithm GWO-SVM

来源：评论

学校读者我要写书评

暂无评论

Systematic investigation of keywords selection and processing strategy on search engine forecasting: a case of tourist volume in Beijing

引用

INFORMATION TECHNOLOGY & TOURISM 2022年第4期24卷 547-580页

作者： Yuan, Ziqi Jia, Guozhu Sichuan Normal Univ Coll Phys & Elect Engn Chengdu 610000 Peoples R China

The timeliness, precision, and low cost of search data have great potential for projecting tourist volume. Obtaining valuable information for decision-making, particularly for predicting, is hampered by the vast amount of search data. A systematic investigation of keyword selection and processing has been conducted. Using Beijing tourist volume as an example, 11 different feature extraction algorithms were selected and combined with long short-term memory (LSTM), random forest (RF) and fuzzy time series (FTS) for forecasting tourist volume. A total of 1612 keywords were retrieved from Baidu Index demand mapping using the direct word extraction method, range word extraction method and empirical selection method. The remaining 813 keywords were subjected to feature extraction. Based on the forecasting results of medium and short-term (1-day, 7-days and 10-days), the forecasting results of Kernel principal component analysis (KPCA) and locally linear embedding (LLE) are relatively stable when the dimensionality is reduced to 5 dimensions. The forecasting results of t-stochastic neighbor embedding (t-SNE), isometric mapping (IsoMap) and locally linear embedding (LLE), locality preserving projections (LPP), independent component correlation (ICA) are relatively stable when the dimensionality is reduced to 10 dimensions. Accurately forecasting many factors (transportation, attraction, food, lodging, travel, tips, tickets, and weather) provides a solid foundation for tourism demand optimization and scientific management and a resource for tourists' holistic vacation planning.

关键词： Tourist volume forecasting Search engine data feature extraction algorithm LSTM FTS RF

来源：评论

学校读者我要写书评

暂无评论

Prediction of TNM stage in head and neck cancer using hybrid machine learning systems and radiomics features

Prediction of TNM stage in head and neck cancer using hybrid...

引用

Conference on Medical Imaging - Computer-Aided Diagnosis

作者： Salmanpour, Mohammadreza R. Hosseinzadeh, Mahdi Akbari, Azizeh Borazjani, Kasra Mojallal, Kasra Askari, Dariush Hajianfar, Ghasem Rezaeijo, Seyed Masoud Ghaemi, Mohammad M. Nabizadeh, Amir Hossein Rahmim, Arman Univ British Columbia Vancouver BC Canada BC Canc Res Inst Vancouver BC Canada Technol Virtual Collaborat TECVICO Corp Vancouver BC Canada Tarbiat Modares Univ Tehran Iran Hakim Sabzevari Univ Sab Zevar Iran Univ Tehran Tehran Iran Amirkabir Univ Technol Tehran Iran Shahid Beheshti Univ Med Dept Radiol Technol Tehran Iran Iran Univ Med Sci Rajaie Cardiovasc Med & Res Ctr Tehran Iran Ahvaz Jundishapur Univ Med Sci Sch Med Dept Med Phys Ahvaz Iran Kerman Univ Med Sci Kerman Iran IST Univ Lisbon P-1000029 Lisbon Portugal

ISBN: (数字)9781510649422

ISBN: (纸本)9781510649422;9781510649415

The tumor, node, metastasis (TNM) staging system enables clinicians to describe the spread of head-and-neck-squamous-cell-carcinoma (HNSCC) cancer in a specific manner to assist with the assessment of disease status, prognosis, and management. This study aims to predict TNM staging for HNSCC cancer via Hybrid Machine Learning Systems (HMLSs) and radiomics features. In our study, 408 patients were included from the Cancer Imaging Archive (TCIA) database, included in a multi-center setting. PET images were registered to CT, enhanced, and cropped. We created 9 sets including CT-only, PET-only, and 7 PET-CT fusion sets. Next, 215 radiomics features were extracted from HNSCC tumor segmented by the physician via our standardized SERA radiomics package. We employed multiple HMLSs, including 16 feature-extraction (FEA) + 9 feature selection algorithms (FSA) linked with 8 classifiers optimized by grid-search approach, with model training, fine-tuning, and selection (5-fold cross-validation;319 patients), followed by external-testing of selected model (89 patients). Datasets were normalized by z-score-technique, with accuracy reported to compare models. We first applied datasets with all features to classifiers only;accuracy of 0.69 +/- 0.06 was achieved via PET applied to Random Forest classifier (RFC);performance of external testing (similar to 0.62) confirmed our finding. Subsequently, we employed FSAs/FEAs prior to the application of classifiers. We achieved accuracy of 0.70 +/- 0.03 for Curvelet transform (fusion) + Correlation-based feature Selection (FSA) + K-Nearest Neighbor (classifier), and 0.70 +/- 0.05 for PET + LASSO (FSA) + RFC (classifier). Accuracy of external testing (0.65 & 0.64) also confirmed these findings. Other HMLSs, applied on some fused datasets, also resulted in close performances. We demonstrate that classifiers or HMLSs linked with PET only and PET-CT fusion techniques enabled relatively low improved accuracy in predicting TNM stage. Meanwhile, th

关键词： prediction of TNM Stage hybrid machine learning system radiomics feature fusion techniques head and neck squamous cell carcinoma feature extraction algorithm feature selection algorithm classifier

来源：评论

学校读者我要写书评

暂无评论

LearningADD: Machine learning based acoustic defect detection in factory automation

引用

JOURNAL OF MANUFACTURING SYSTEMS 2021年 60卷 48-58页

作者： Zhang, Tao Ding, Biyun Zhao, Xin Liu, Ganjun Pang, Zhibo Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China ABB Corp Res Sweden Dept Automat Technol S-72178 Vasteras Sweden Royal Inst Technol KTH Dept Intelligent Syst S-11428 Stockholm Sweden

Defect inspection of glass bottles in the beverage industrial is of significance to prevent unexpected losses caused by the damage of bottles during manufacturing and transporting. The commonly used manual methods suffer from inefficiency, excessive space consumption, and beverage wastes after filling. To replace the manual operations in the pre-filling detection with improved efficiency and reduced costs, this paper proposes a machine learning based Acoustic Defect Detection (LearningADD) system. Moreover, to realize scalable deployment on edge and cloud computing platforms, deployment strategies especially partitioning and allocation of functionalities need to be compared and optimized under realistic constraints such as latency, complexity, and capacity of the platforms. In particular, to distinguish the defects in glass bottles efficiently, the improved Hilbert-Huang transform (HHT) is employed to extend the extracted feature sets, and then Shuffled Frog Leaping algorithm (SFLA) based feature selection is applied to optimize the feature sets. Five deployment strategies are quantitatively compared to optimize real-time performances based on the constraints measured from a real edge and cloud environment. The LearningADD algorithms are validated by the datasets from a real-life beverage factory, and the F-measure of the system reaches 98.48 %. The proposed deployment strategies are verified by experiments on private cloud platforms, which shows that the Distributed Heavy Edge deployment outperforms other strategies, benefited from the parallel computing and edge computing, where the Defect Detection Time for one bottle is less than 2.061 s in 99 % probability.

关键词： Acoustic defect detection Edge computing Factory automation feature extraction algorithm

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

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

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：