检索结果-内蒙古大学图书馆

Wind Turbine Condition Monitoring Based on Improved Active Learning Strategy and kNN algorithm

IEEE ACCESS 2023年 11卷 13545-13553页

作者： Bao, Chengjia Zhang, Tianyi Hu, Zhixi Feng, Wangjing Liu, Ru State Grid Gansu Elect Power Co Lanzhou 730030 Gansu Peoples R China State Grid Lanzhou Elect Power Supply Co Lanzhou 730070 Gansu Peoples R China

As the damage of the gearbox of wind turbines (WTs) will cause economic losses, it is necessary to conduct online condition monitoring (CM) on the gearbox. Most WTs are equipped with SCADA system, and CM method based on Supervisory Control and Data Acquisition (SCADA) data is one of the most economical methods. k nearest neighbor (kNN) algorithm has good robustness, and WTs are typical nonlinear objects. Based on this, kNN regression model is established for CM, and Distance Correlation (DC) coefficient is used to select modeling variables to improve the shortcomings of traditional feature selection algorithm. A large amount of redundant data will be generated during the operation of WTs, and the efficiency of kNN algorithm is affected by the size of training set. Therefore, an active learning (AL) algorithm combining multiple strategies is proposed to select high-quality training data. The validity of the proposed method is verified by the data of an actual WT. The experimental results show that the method presented in this paper performs well in the comparative experiments, and the online CM results are about 20 days earlier than the SCADA system.

关键词： Wind turbine gearbox condition monitoring k-nearest neighbor algorithm active learning distance correlation coefficient

来源：评论

学校读者我要写书评

暂无评论

Research on line loss anomaly identification method of distribution network considering distributed photovoltaic access 24

Research on line loss anomaly identification method of distr...

引用

International Conference on Power Electronics and Artificial Intelligence (PEAI)

作者： Zhang, ke Li, Jian Li, Shuoyu Jiang, Zetao Zhao, Yun Lu, Yuxin Guangdong Power Grid Co Ltd Metrol Ctr New Energy Applicat R&D Technol Pk Qingyuan Guangdong Peoples R China Dongguan Power Supply Bur Power Supply Serv Dongguan Guangdong Peoples R China CSG Elect Power Res Inst Guangzhou Guangdong Peoples R China Guangdong Prov Key Lab Intelligent Measurement & Guangzhou Guangdong Peoples R China

ISBN: (纸本)9798400716638

For a long time, the identification of 10kV distribution network line loss anomalies has been a very difficult task, with the large number of distributed photovoltaics (DPV) access, the distribution network power flow from one-way flow to two-way flow, which greatly affects the line power flow, voltage and network loss, and increases the difficulty of identifying abnormal distribution network line loss. Therefore, a method for identifying line loss anomalies in distribution network considering distributed photovoltaic access is proposed. Firstly, the characteristic index of distribution network line loss after distributed photovoltaic access is extracted, and the correlation between the line loss index and line loss of the distribution network is calculated by using the gray correlation analysis method, and the correlation degree is ranked. Then, according to the order of gray correlation degree, appropriate indicators are selected for fuzzy C-means clustering, and outliers in each category are detected based on the k-nearest neighbor algorithm to determine whether there is an abnormal line loss in the distribution network. Finally, the verification analysis is carried out through the example, and the results show that the proposed method can effectively identify whether abnormal line loss occurs in the distribution network containing distributed photovoltaics.

关键词： Distributed photovoltaic Abnormal line loss Grey correlation analysis k-nearest neighbor algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of white matter lesion segmentation in multiple sclerosis patients' MRIs: evaluating the results of FCNN architecture and CVIPtools software on compressed image data 47

Comparative analysis of white matter lesion segmentation in ...

引用

Conference on Applications of Digital Image Processing XLVII

作者： Ajami, Hanieh Chakradhar, Heena Nigjeh, Mandi kargar Al Mahmud Ul Hogue, Md Sami Umbaugh, Scott E. Southern Illinois Univ Edwardsville Dept Elect & Comp Engn Comp Vis & Image Proc Lab Edwardsville IL 62026 USA

ISBN: (纸本)9781510679344;9781510679351

This study builds upon our previous investigations into identifying and classifying white matter lesions on the brain surfaces of multiple sclerosis patients using both traditional machine learning and novel deep learning models. Our prior work demonstrated the effectiveness of these methods with high-resolution MRI modalities. In this paper, we evaluate the performance of these methodologies using a degraded dataset instead of high-resolution images. Specifically, we compared a traditional machine learning approach using k-nearest neighbors (kNN) with a deep learning approach employing ResNet-18 with transfer learning. The kNN-based approach achieved moderate performance metrics, with an accuracy of 71.15% for lesions and 72.22% for non-lesions. These results indicate a balanced performance;however, the algorithm's efficacy was significantly compromised by the compressed images, highlighting the limitations of traditional machine learning methods in handling lossy compression artifacts. In contrast, the ResNet-18 deep learning model demonstrated remarkable performance, achieving an overall accuracy of 94% on the compressed dataset. The model's success was further reflected in high sensitivity, specificity, precision, and F1-score metrics, all hovering around 94% to 95%. By leveraging transfer learning, the deep learning approach excelled even with compressed medical images, showcasing the potential of modern deep learning techniques in handling degraded datasets, and enhancing the disease diagnosis process.

关键词： MRI segmentation multiple sclerosis white matter lesions unsupervised methodology CVIPtools pattern classification k-nearest neighbor algorithm Deep learning ResNet18 Gray level enhancement Neural Networks Automated classification

来源：评论

学校读者我要写书评

暂无评论

Research on motor imaging EEG signals based on VMD 4

Research on motor imaging EEG signals based on VMD

引用

4th International Conference on Bioinformatics and Intelligent Computing (BIC)

作者： Liu, Dingrui Awudong, Buhailiqiemu Li, Xiujun Li, Qi Changchun Univ Sci & Technol Sch Comp Sci & Technol 7089 Weixing Rd Changchun Jilin Peoples R China Changchun Univ Sci & Technol Zhongshan Res Inst Zhongshan Guangdong Peoples R China

ISBN: (纸本)9798400716645

With the rapid development of brain-computer interface (BCI) technology, it is particularly important to improve the recognition rate of motor imagery (MI) Electroencephalogram (EEG) signals. In this paper, we proposed a method based on variational modal decomposition (VMD) to recognize the left- and right-handed MI EEG signals. Firstly, the EEG signals of right and left hand MI are decomposed by VMD to obtain multiple VMD components;Secondly, the center frequency feature vectors are extracted from the selected modal components;Thirdly, the t-test of statistical analysis is used to analyze the significance of the selected features, and the features that do not have significant differences are excluded;Finally, the selected feature vectors are sent to kNN algorithm to be classified. The method is validated on the OpenBMI dataset as well as different classifiers, and its final results show that the three classification result metrics, i.e., accuracy, sensitivity, and specificity, reach 70.6%, 70.2%, and 73.1%, respectively, under this method. From the final classification results, it can be seen that this type of method can distinguish the EEG signals of left and right hand MI very well. In addition, the Area Under Curve (AUC) under the Receiver Operating Characteristic (ROC) curve under this method also reached 0.99, thus also proving the advantages and feasibility of the method used in this paper.

关键词： motor imagination EEG signals variational modal decomposition Center frequency t-test k-nearest neighbor algorithm

来源：评论

学校读者我要写书评

暂无评论

kNN and Decision Trees based SPPM demodulators applicable to synchronous modulation techniques

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GA...

引用

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY 2022年第3期37卷 1247-1261页

作者： Sunnetci, kubilay Muhammed Alkan, Ahmet Osmaniye Korkut Ata Univ Fac Engn Dept Elect Elect Engn TR-80010 Osmaniye Turkey Kahramanmaras Sutcu Imam Univ Fac Engn Dept Elect Elect Engn TR-46000 Kahramanmaras Turkey

It is thought that data mining can solve many problems in visible light communication. In the VLC systems, different receiver and transmitter units are usually designed for each modulation technique. Here, the proposed systems are designed for shortened pulse position modulation. In the paper, k-nearest neighbor algorithm and Decision Trees based demodulators that can be applied to synchronous modulation techniques are proposed. Afterwards, a generalized entropy expression is obtained for M-SPPM signals. Additionally, demodulators that can decode signals according to the Manhattan and Minkowski distance and other demodulators are compared in terms of accuracy and bit error rate. From the numerical results, it can be seen that the proposed kNN and Decision Trees based demodulators can be used as traditional systems for synchronous modulation techniques. Furthermore, it is seen that bit error rate performances and accuracy rates of the proposed kNN based demodulator and decision trees based demodulator that is optimally designed are completely the same. In 4-SPPM signals, it is seen that the accuracy of kNN (Demodulator-1) and Decision Trees (Demodulator-3) is 98.78% for SNR=10 dB. Here, the accuracy of the kNN (Demodulator-2) and Decision Trees (Demodulator-5) is 99.07% for 8-SPPM signals.

关键词： Data mining k-nearest neighbor algorithm decision tree entropy communication

来源：评论

学校读者我要写书评

暂无评论

The interaction force model of soft tissue for virtual surgery system based on kNN algorithm 35

The interaction force model of soft tissue for virtual surge...

引用

35th Chinese Control and Decision Conference (CCDC)

作者： Hu, Lingyan Zheng, Zijian Hu Dongxia Nanchang Univ Sch Informat Engn Nanchang Jiangxi Peoples R China Shanghai Univ Engn Sci Sch Elect & Elect Engn Nanchang Jiangxi Peoples R China Nanchang Univ Affiliated Hosp 2 Nanchang Jiangxi Peoples R China

ISBN: (纸本)9798350334722

It is difficult to simulate haptic interactions in a virtual surgical system due to the complexity of biomechanical features. Most prevalent methods simulate the viscoelasticity of soft tissues by establishing spring and damping models or neural networks, but the former often have poor accuracy while the latter cannot satisfy the real-time requirements of virtual surgical systems. This paper proposes an interaction force model based on k-nearest neighbor algorithm (kNN algorithm) and applies it to a virtual surgical system. The experimental result shows that the model to predict the force feedback of the soft tissue based on kNN algorithm can calculate the interactive force accurately during the puncture process. It meets the requirements of real-time and yields a range of error narrower than that incurred in case of manual perception.

关键词： Virtual surgical system Interaction force Soft tissue k-nearest neighbor algorithm

来源：评论

学校读者我要写书评

暂无评论

Estimating potential evapotranspiration based on self-optimizing nearest neighbor algorithms: a case study in arid-semiarid environments, Northwest of China

引用

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH 2020年第30期27卷 37176-37187页

作者： Feng, kepeng Tian, Juncang Ningxia Univ Sch Civil & Hydraul Engn 539 Helan Mt Rd Yinchuan 750021 Ningxia Peoples R China Engn Res Ctr Efficient Utilizat Water Resources M Yinchuan Peoples R China Ningxia Res Ctr Technol Water Saving Irrigat & Wa Yinchuan Peoples R China

Changes in potential evapotranspiration will affect the surface ecology and environment of the land. Accurate and quick estimation of potential evapotranspiration will help to analyze environmental change. In this study, in combination with the canonical correlation analysis (CCA) and k-nearest neighbor algorithm (k-NN), a new method for calculating potential evapotranspiration (CCA-k-NN) based on self-optimizing nearest neighbor algorithm was proposed, in which less meteorological data were used for estimation. By analyzing the basic principles of CCA and k-NN and according to the requirement of estimating ET0, the CCA-k-NN method was constructed, and its basic principles and key steps were described. In this method, CCA algorithm was used to find the most relevant meteorological data for potential evapotranspiration, and the dimensionality of meteorological data for subsequent estimation of ET0 was reduced. Then, k-NN algorithm was used to estimate ET0. The Northwest of China was chosen as the research area to evaluate the applicability of this method. The 148 data stations in the region were divided into training datasets, testing datasets, and validation datasets. ET0 was estimated on three datasets using the proposed method, and the estimation accuracy of the CCA-k-NN method was evaluated with FAO-56 Penman-Monteith as a reference. The results show that the CCA-k-NN method maintains a high correlation with FAO-56 Penman-Monteith (correlation coefficient is greater than 0.9) and has a good estimation accuracy. RMSE and MAE are both less than 1 mm day(-1), and the overall performance of NSCE is greater than 0.5, all of which reach the level of "applicable" and above. At the same time, the CCA-k-NN method has low time complexity O(n). Comparison of the results of the CCA-k-NN method with those of other empirical models showed that the CCA-k-NN method is more accurate and can be employed successfully in estimating ET0.

关键词： Potential evapotranspiration Canonical correlation analysis k-nearest neighbor algorithm Limited meteorological data Northwest China Arid semiarid environments

来源：评论

学校读者我要写书评

暂无评论

Exploring user cognition difference and pleasure balance guidance method for product perceptible features in vehicle-mounted system

引用

INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT 2022年第SUPPL 3期13卷 1019-1030页

作者： Zhang, Chao Changsha Univ Sci Technol Sch Art & Design Changsha 410004 Peoples R China

The cognition difference and pleasure balance guidance method are studied for the vehicle-mounted human-computer interaction system to reduce the user and designers' cognition differences. First, the perceivable innovation design is introduced, and the user-designers cognition correlation model is established based on perceivable product innovation. Then, the physiological signals of users are collected through related equipment, and the recognition model for users' positive and negative emotions and physiological signals is constructed through the support vector machine (SVM) algorithm and the k nearest neighbor (kNN) algorithm. Finally, the pleasure balance guidance method is proposed based on the user and designers' cognition differences. The experimental results show that the recognition rate of emotion extracted from wavelet packet energy using the kNN and the SVM algorithm is 80.66% and 76.23%, respectively. The recognition rate of physical load extracted from the time-domain features and wavelet packet energy features through the SVM algorithm is 79.51% and 57.23%, respectively. The results are of great engineering significance for the design of the automobile interaction system.

关键词： Machine learning User experience Human-computer interaction Emotional calculation k-nearest neighbor algorithm

来源：评论

学校读者我要写书评

暂无评论

Robust Polar Coordinate System-Based kNN algorithm Suitable for FSO Communication Systems with Turbulence Distortions

Robust Polar Coordinate System-Based KNN Algorithm Suitable ...

引用

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Wang, Xishuo Lv, kai Pan, Xiaolong Zhang, Qi Xin, Xiangjun Huo, Xiaoli Jing, Ruiquan China Telecom Research Institute Network Technology Research Department Beijing China School of Information and Electronics Beijing Institute of Technology Beijing China

A Polar kNN classification algorithm suitable for turbulence-distorted QAM signals is proposed, which can robustly achieve optimized decision at low training lengths. Simulation results show that, the proposed algorit... 详细信息

ISBN: (纸本)9798350312614

关键词： free space optical communication k-nearest neighbor algorithm polar coordinate system robustness turbulenceinduced distortion

来源：评论

学校读者我要写书评

暂无评论

Stochastic reservoir operation with data-driven modeling and inflow forecasting

引用

JOURNAL OF APPLIED WATER ENGINEERING AND RESEARCH 2022年第3期10卷 212-223页

作者： Fontes Santana, Raul Celeste, Alcigeimes B. Univ Fed Sergipe Grad Program Engn & Environm Sci Sao Cristovao Sergipe Brazil Univ Fed Sergipe Dept Civil Engn Sao Cristovao Sergipe Brazil

This work applied implicit stochastic optimization (ISO) refined by long-term mean inflow forecasting and instance-based learning for the operation of the Sobradinho reservoir, Brazil. For efficiency assessment, the reservoir was also operated by perfect-forecast deterministic optimization, the standard operating policy, stochastic dynamic programming and two parameterization-simulation-optimization models, which were compared in terms of vulnerability, reliability and resilience found in each of the 100 synthetic inflow scenarios they were applied to. Evidence of long-term persistence was found in Sobradinho's records and this was replicated in the scenarios. The ISO model was employed with forecast horizons of 0, 1, 3, 6, 9, 12, 18 and 24 months. The operations demonstrated that the model with forecast horizons of 3 months or more was less vulnerable than all other models, revealing that it may be used efficiently for reservoir operation.

关键词： Reservoir operation optimization implicit stochastic optimization instance-based learning k-nearest neighbor algorithm long-term memory

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：