检索结果-内蒙古大学图书馆

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Li, Junmin Lan, Guofeng Zhao, Wen Ma, Chenxiang Liu, Yongqiang State Grid Shanxi Electric Power Company Lvliang Power Supply Company Shanxi Lvliang033000 China

ISBN: (纸本)9798350302455

The current conventional line loss anomaly sensing algorithm mainly realizes line loss anomaly sensing by calculating the station area line loss rate and comparing it with the set threshold value, which leads to poor sensing effect due to the lack of clustering analysis of line loss characteristics. In this regard, a consistent sensing algorithm based on spectral clustering of line loss abnormal fluctuations in distributed PV station areas is proposed. The line loss data is assimilated with time granularity and data cleaning, and combined with the spectral clustering algorithm to cluster the line loss abnormal data features and set the highest threshold of the Euclidean distance of the line loss rate to realize the line loss abnormal sensing. In the experiments, the proposed method is verified for the sensing effect. The experimental results show that when the proposed method is used to sense line loss data, the algorithm can accurately sense different types of line loss data and has a more desirable sensing performance. © 2023 IEEE.

关键词： clustering analysis Consistency perception Line loss anomaly fluctuation spectral clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

A clustering Method Unifying Cell-Type Recognition and Subtype Identification for Tumor Heterogeneity Analysis

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2023年第2期20卷 822-832页

作者： Li, Xiong Lin, Yangkai Xie, Chengwang Li, Zejun Chen, Min Wang, Peng Zhou, Juan East China Jiaotong Univ Sch Software Nanchang 330013 Peoples R China South China Normal Univ Sch Data Sci & Engn Guangzhou 510000 Peoples R China Hunan Inst Technol Hengyang 421010 Peoples R China Hunan Inst Technol Sch Comp Sci & Technol Hengyang 421010 Peoples R China

The rapid development of single-cell technology has opened up a whole new perspective for identifying cell types in multicellular organisms and understanding the relationships between them. Distinguishing different cell types and subtypes can identify the components of different immune cells and different tumor clones in the tumor microenvironment, which is the basic work of tumor heterogeneity analysis and can help researchers understand the mechanism of tumor immune escape. Existing algorithms treat both cell types and subtypes as populations of cells with specific gene expression patterns, which is not conducive to accurate cell typing. For that, we proposed a cell similarity metric that unifies cell type recognition and subtype identification (UCRSI), with the assumption that selectively expressed genes represent differences in underlying cell type with on/off manner, while differences in expression level represent different cell subtype with more/less manner. Our method calculates these two kinds of differences separately, and then combines them using a consensus adjacency matrix, and finally cell typing is completed using spectral clustering algorithm. The results show that UCRSI can reconstruct expert annotation of single-cell RNA sequencing datasets more robustly than existing methods. And, UCRSI is useful for analyzing tumor heterogeneity and improving visualization of large-scale cell clustering.

关键词： Cell type assignment subtype identification tumor heterogeneity spectral clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Ordered and fixed-length bit-string fingerprint representation with minutia vicinity combined feature and spectral clustering

引用

IET IMAGE PROCESSING 2020年第16期14卷 4220-4228页

作者： Li, Yuxing Zhao, Heng Cao, Zhicheng Liu, Eryun Pang, Liaojun Xidian Univ Sch Life Sci & Technol Xian 710071 Peoples R China Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Zhejiang Peoples R China

The minutiae set defined by the ISO/IEC 19794-2 is one of the prevalent feature used in fingerprint recognition systems. Unfortunately, such characteristic of unordered and variable-sized minutiae information causes a restriction on the operation in some advanced template protection methods (e.g. fuzzy commitment), which usually require an ordered and fixed-length binary feature representation as the system input. In this study, in order to simultaneously extend the application of fingerprint recognition and provide satisfactory system performance, the authors propose a novel fixed-length bit-string conversion framework based on spectral clustering and the proposed newly designed discriminative fingerprint representation called minutia vicinity combined feature (MVCF). The proposed method consists of three stages: (i) the extraction of MVCF, (ii) bit conversion via the spectral clustering algorithm, and (iii) matching. Benefiting from feature invariance, fixed-length and bit-oriented coding, merits such as fast matching and decent accuracy are well guaranteed. The performance evaluation is conducted on six publicly available benchmark data sets: FVC2002 DB1, DB2, DB3 and FVC2004 DB1, DB2, DB3 confirms the superiority of the proposed method and suggests the promise of migrating to some other domains (e.g., template protection).

关键词： pattern clustering fuzzy set theory fingerprint identification image matching fixed-length bit-string fingerprint representation minutia vicinity combined feature prevalent feature fingerprint recognition systems variable-sized minutiae information advanced template protection methods ordered fixed-length binary feature representation system input satisfactory system performance fixed-length bit-string conversion framework newly designed discriminative fingerprint representation bit conversion spectral clustering algorithm feature invariance bit-oriented coding FVC2002 DB1 DB2 DB3 FVC2004 DB1

来源：评论

学校读者我要写书评

暂无评论

Symptom Distribution Regularity of Insomnia: Network and spectral clustering Analysis

引用

JMIR MEDICAL INFORMATICS 2020年第4期8卷 e16749页

作者： Hu, Fang Li, Liuhuan Huang, Xiaoyu Yan, Xingyu Huang, Panpan Hubei Univ Chinese Med Coll Informat Engn Wuhan Peoples R China Hubei Univ Chinese Med Coll Basic Med 16 Huangjiahu West Rd Wuhan 430065 Peoples R China

Background: Recent research in machine-learning techniques has led to significant progress in various research fields. In particular, know ledge discovery using this method has become a hot topic in traditional Chinese medicine. As the key clinical manifestations of patients, symptoms play a significant role in clinical diagnosis and treatment, which evidently have their underlying traditional Chinese medicine mechanisms. Objective: We aimed to explore the core symptoms and potential regularity of symptoms for diagnosing insomnia to reveal the key symptoms, hidden relationships underlying the symptoms, and their corresponding syndromes. Methods: An insomnia dataset with 807 samples was extracted from real-world electronic medical records. After cleaning and selecting the theme data referring to the syndromes and symptoms, the symptom network analysis model was constructed using complex network theory. We used four evaluation metrics of node centrality to discover the core symptom nodes from multiple aspects. To explore the hidden relationships among symptoms, we trained each symptom node in the network to obtain the symptom embedding representation using the Skip-Gram model and node embedding theory. After acquiring the symptom vocabulary in a digital vector format, we calculated the similarities between any two symptom embeddings, and clustered these symptom embeddings into five communities using the spectral clustering algorithm. Results: The top five core symptoms of insomnia diagnosis, including difficulty falling asleep, easy to wake up at night, dysphoria and irascibility, forgetful, and spiritlessness and weakness, were identified using evaluation metrics of node centrality. The symptom embeddings with hidden relationships were constructed, which can be considered as the basic dataset for future insomnia research. The symptom network was divided into five communities, and these symptoms were accurately categorized into their corresponding syndromes. Conclusio

关键词： insomnia core symptom symptom community symptom embedding representation spectral clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

An Experimental Comparison of algorithms for Nodes clustering in a Neural Network of Caenorhabditis Elegans 21st

An Experimental Comparison of Algorithms for Nodes Clusterin...

引用

21st International Conference on Computational Science and Its Applications (ICCSA)

作者： Hernandez, Jorge Florez, Hector Univ Dist Francisco Jose de Caldas Bogota Colombia

ISBN: (纸本)9783030870133;9783030870126

Caenorhabditis Elegans (C. Elegans) is a worm, which has had several studies to search its nerve paths. In a neuronal network simulation, it is util to know which is the first weight to assign in each link if it is not presented to determine other characteristics (e.g. distances by weights). Normally, the weight is a heuristic to solve a problem. There is a data set about connections of C. Elegans which is a result of other authors. The weights by the connection are not set in the data set. In this work, we use the data set to determine experimental weights for each connection with four cluster algorithms. The weights are to use in future work. To compare the algorithms, we created several models for each algorithm. We used metrics to evaluate the results for each model. A spectral clustering algorithm was chosen how the better algorithm to generate the weights.

关键词： clustering Caenorhabditis Elegans MiniBatch K-means algorithm DBSCAN algorithm spectral clustering algorithm clustering feature tree algorithm

来源：评论

学校读者我要写书评

暂无评论

PHISHING WEB IMAGE SEGMENTATION BASED ON IMPROVING spectral clustering

引用

Journal of Electronics(China) 2011年第1期28卷 101-107页

作者： Li Yuancheng Zhao Liujun Jiao Runhai School of Control and Computer Engineering North China Electric Power University Beijing 102206 China

This paper proposes a novel phishing web image segmentation algorithm which based on improving spectral ***,we construct a set of points which are composed of spatial location pixels and gray levels from a given ***,the data is clustered in spectral space of the similar matrix of the set points,in order to avoid the drawbacks of K-means algorithm in the conventional spectral clustering method that is sensitive to initial clustering centroids and convergence to local optimal solution,we introduce the clone operator,Cauthy mutation to enlarge the scale of clustering centers,quantum-inspired evolutionary algorithm to find the global optimal clustering *** with phishing web image segmentation based on K-means,experimental results show that the segmentation performance of our method gains much ***,our method can convergence to global optimal solution and is better in accuracy of phishing web segmentation.

关键词： spectral clustering algorithm Clonal Mutation Quantum-inspired Evolutionary algorithm(QEA) Phishing web image segmentation

来源：评论

学校读者我要写书评

暂无评论

clustering Wind Turbines for a Large Wind Farm Using spectral clustering Approach Based on Diffusion Mapping Theory

Clustering Wind Turbines for a Large Wind Farm Using Spectra...

引用

IEEE International Conference on Power System Technology (POWERCON)

作者： Lin, Li Chen, Ying Wang, Ningbo North China Elect Power Univ State Key Lab Alternate Elect Power Syst Renewabl Beijing 102206 Peoples R China Gansu Elect Power Co Lanzhou Gansu Peoples R China

ISBN: (纸本)9781467328685

Increasing number of wind farms connected to power system calls for a simplified equivalent model of wind farm so that it can be represented by only a few equivalent wind turbines for dynamic system studies. In order to aggregate wind turbines in complex terrain or irregular layout, this paper presents a new wind turbine clustering method based on spectral clustering algorithm. The clustering principle relies on the same or similar operating points of selected wind turbines. The proposed method is used to capture the similarity of characteristics of wind turbines by analyzing real-time data sets of wind turbines in a wind farm. Thus wind turbines of a wind farm can be clustered into different groups. The clustering method is demonstrated and tested in an actual wind power system. A good performance is achieved for all simulation scenarios while comparing the aggregated and detailed models.

关键词： clustering wind turbines dynamic equivalence spectral clustering algorithm wind farm diffusion mapping theory

来源：评论

学校读者我要写书评

暂无评论

spectral clustering of Events in Social Media Flood Images based on Multimodal Analysis 7

Spectral Clustering of Events in Social Media Flood Images b...

引用

7th International Conference on Electrical Energy Systems (ICEES)

作者： Pavithra, S. S. Chitrakala, S. Bhatt, C. M. Anna Univ Dept Comp Sci & Engn CEG Campus Chennai Tamil Nadu India Indian Inst Remote Sensing Disaster Management Studies Dehra Dun Uttarakhand India

ISBN: (纸本)9781728176123

In Data Science, clustering is one of the most popular techniques. It has wide potential application in data analysis, market research, pattern recognition, image processing, etc. spectral clustering is a clustering algorithm shows improved performance than the conventional clustering algorithms. To handle Social media multimodal data in Event clustering and for better understanding of the context of the post, spectral clustering of Events in Flood Images Based on Multimodal Analysis (SCEFIMA) approach is proposed. This approach makes use of Post's Image and textual content (Multimodal data) in clustering the events. Also considering Spatial and Temporal Information in understanding the post. The existing approaches lacks on multimodal analysis in social media data. Use of Multimodal data gives the better understanding of the context of the post in event clustering. In addition to this, Using Multimodal data in Event clustering significantly boost performance than the existing methods. Detecting and clustering events from multimodal data in social networks helpful in monitoring events by public organizations and authorities. Also helpful in early planning for preventive measures.

关键词： Event clustering spectral clustering algorithm Multimodal Social Media Flood Images Convolution Neural Network (CNN) POS Tagging

来源：评论

学校读者我要写书评

暂无评论

Pulmonary Parenchyma Segmentation in Thin CT Image Sequences with spectral clustering and Geodesic Active Contour Model Based on Similarity 9

Pulmonary Parenchyma Segmentation in Thin CT Image Sequences...

引用

9th International Conference on Digital Image Processing (ICDIP)

作者： He, Nana Zhang, Xiaolong Zhao, Juanjuan Zhao, Huilan Qiang, Yan Taiyuan Univ Technol Coll Comp Sci & Technol Taiyuan 030024 Shanxi Peoples R China Penn State Univ Coll Informat Sci & Technol University Pk PA 16802 USA Shanxi Coal Cent Hosp Taiyuan 030024 Shanxi Peoples R China

ISBN: (纸本)9781510613058;9781510613041

While the popular thin layer scanning technology of spiral CT has helped to improve diagnoses of lung diseases, the large volumes of scanning images produced by the technology also dramatically increase the load of physicians in lesion detection. Computer-aided diagnosis techniques like lesions segmentation in thin CT sequences have been developed to address this issue, but it remains a challenge to achieve high segmentation efficiency and accuracy without much involvement of human manual intervention. In this paper, we present our research on automated segmentation of lung parenchyma with an improved geodesic active contour model that is geodesic active contour model based on similarity (GACBS). Combining spectral clustering algorithm based on Nystrom (SCN) with GACBS, this algorithm first extracts key image slices, then uses these slices to generate an initial contour of pulmonary parenchyma of un-segmented slices with an interpolation algorithm, and finally segments lung parenchyma of un-segmented slices. Experimental results show that the segmentation results generated by our method are close to what manual segmentation can produce, with an average volume overlap ratio of 91.48%.

关键词： Geodesic active contour model spectral clustering algorithm contour interpolation CT image sequences pulmonary parenchyma segmentation similarity

来源：评论

学校读者我要写书评

暂无评论

Autoregressive Networks

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2023年第1期24卷 1-69页

作者： Jiang, Binyan Li, Jialiang Yao, Qiwei Hong Kong Polytech Univ Dept Appl Math Hong Kong Peoples R China Natl Univ Singapore Dept Stat & Appl Probabil Singapore 117546 Singapore London Sch Econ Dept Stat London WC2A 2AE England

We propose a first-order autoregressive (i.e. AR(1)) model for dynamic network processes in which edges change over time while nodes remain unchanged. The model depicts the dynamic changes explicitly. It also facilitates simple and efficient statistical inference meth-ods including a permutation test for diagnostic checking for the fitted network models. The proposed model can be applied to the network processes with various underlying structures but with independent edges. As an illustration, an AR(1) stochastic block model has been investigated in depth, which characterizes the latent communities by the transition proba-bilities over time. This leads to a new and more effective spectral clustering algorithm for identifying the latent communities. We have derived a finite sample condition under which the perfect recovery of the community structure can be achieved by the newly defined spec-tral clustering algorithm. Furthermore the inference for a change point is incorporated into the AR(1) stochastic block model to cater for possible structure changes. We have derived the explicit error rates for the maximum likelihood estimator of the change-point. Appli-cation with three real data sets illustrates both relevance and usefulness of the proposed AR(1) models and the associate inference methods.

关键词： AR(1) networks Change point Dynamic stochastic block model Hamming distance Maximum likelihood estimation spectral clustering algorithm Yule-Walker equa-tion

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：