Heavy-Tailed Linear Regression and <i>K</i>-Means by Mario Sayde, Jihad Fahs, Ibrahim Abou-Faycal

“…For such a scenario, classical linear regression techniques and the standard <i>K</i>-means algorithm fail. We formulate and validate heavy-tailed versions of these machine learning methods for both scalar and multidimensional settings. …”
Get full text

Modeling the Relationship between Financial Stability and Banking Risks: Artificial Intelligence Approach by Hakeem Faraj Gumar, Parviz Piri, Mehdi Heydari

“…Spatial clustering and k-means algorithms could group banks based on their financial stability with an accuracy of nearly 100%. …”
Get full text

EU Travel and Tourism Industry - A Cluster Analysis of Impact and Competitiveness by DANIEL BULIN

“…This paper proposes a classification of EU countries based on cluster analysis, using K-means algorithm.…”
Get full text

K-means clustering of a soil sampling scheme with data on the morphography of the Ogosta valley northwestern Bulgaria by Assen TCHORBADJIEFF, Tsvetan KOTSEV, Velimira STOYANOVA, Emilia TCHERKEZOVA

“…The field sites are split into 4 clusters using K-means algorithm with the following variables: elevation, distance to the river, vertical distance to channel network, multiresolution index of valley bottom flatness and a modified topographic SAGA wetness index. …”
Get full text

Early warning prediction of external force destruction in transmission lines based on automatic clustering model by Dayan MA

“…The external force destruction has become a major threat to the safe and stable operation of overhead transmission lines,bringing difficulties to the defense and early warning work.In order to solve the problem that the traditional clustering center is difficult to accurately determined and susceptible to abnormal points,an automatic clustering method for data analysis work of transmission lines was presented,and external damage data was analyzed from time and space latitude.Firstly,the cluster center was initialized in this method by using Canopy algorithm.Then,the optimized K-means algorithm was used to perform clustering.Finally,the effectiveness of this method was proved by experimental analysis.This method will be applied to the GIS module in the power information system,which can realize the spatio-temporal visualization of the analysis results and provide powerful decision support for finding cause of the external force damage of the transmission line.…”
Get full text

State Evaluation and Risk Assessment for Relay Protection System by WANG Shenghe, YE Yuanbo, LIU Hongjun, XIE Min, CONG Lei, CHEN Jun

“…The performance of supervised multiple regression analysis algorithm and unsupervised k-means algorithm is compared with that of the new algorithm proposed in this paper in terms of accuracy, processing time and feasibility.The comparison results show that the proposed algorithm has better evaluation accuracy and stronger adaptability compared to the other two algorithms. …”
Get full text

K-means clustering of a soil sampling scheme with data on the morphography of the Ogosta valley northwestern Bulgaria by Assen TCHORBADJIEFF, Tsvetan KOTSEV, Velimira STOYANOVA, Emilia TCHERKEZOVA

“…The field sites are split into 4 clusters using K-means algorithm with the following variables: elevation, distance to the river, vertical distance to channel network, multiresolution index of valley bottom flatness and a modified topographic SAGA wetness index. …”
Get full text

An Extension of the Fuzzy Possibilistic Clustering Algorithm Using Type-2 Fuzzy Logic Techniques by Elid Rubio, Oscar Castillo, Fevrier Valdez, Patricia Melin, Claudia I. Gonzalez, Gabriela Martinez

“…With the purpose of observing the performance of the proposal against the Interval Type-2 Fuzzy C-Means algorithm, several experiments were made using both algorithms with well-known datasets, such as Wine, WDBC, Iris Flower, Ionosphere, Abalone, and Cover type. …”
Get full text

A Bi-Level Optimization Scheme for Energy Storage Configuration in High PV-Penetrated Distribution Networks Based on Improved Voltage Sensitivity Strategy by Bo Gao, Qing Du, Gonghao Zhan, Jian Han

“…Before applying the proposed bi-level optimization scheme, the PV output data are clustered by the K-means algorithm, and an active power–voltage sensitivity strategy is presented to identify nodes with high sensitivity in the clustered PV output data. …”
Get full text

3D Point Cloud Simplification Based on k-Nearest Neighbor and Clustering by Abdelaaziz Mahdaoui, El Hassan Sbai

“…Initially, 3D point cloud is divided into clusters using k-means algorithm. Then, an entropy estimation is performed for each cluster to remove the ones that have minimal entropy. …”
Get full text

A Comparative Study of Customized Algorithms for Anomaly Detection in Industry-Specific Power Data by Minsung Jung, Hyeonseok Jang, Woohyeon Kwon, Jiyun Seo, Suna Park, Beomdo Park, Junseong Park, Donggeon Yu, Sangkeum Lee

“…In the metal industry, a Z-Score-based statistical approach with threshold optimization was used; in the food industry, a hybrid model combining K-Means, Isolation Forest, and Autoencoder was designed; and in the chemical industry, the DBA K-Means algorithm (Dynamic Time Warping Barycenter Averaging) was employed. …”
Get full text

Block ciphers identification scheme based on the distribution character of randomness test values of ciphertext by Yang WU, Tao WANG, Meng XING, Jin-dong LI

“…By researching deficiency of current encryption algorithms identification schemes，a block ciphers identification scheme is proposed based on the distribution character of randomness test values for ciphertext.Firstly，the numbers of randomness test values for AES，Camellia，DES，3DES，SMS4 are respectively calculated based on the frequency test，frequency test in block，run test and originally clustered by the k-means algorithm.Secondly，in order to identify the block ciphers in each clustering，the dimensions of eigenvectors to the frequency test，frequency test in block，run test are calculated on the principle of reducing the comparability between eigenvectors.Eventually，the experimental results of AES，Camellia，DES，3DES，SMS4 demonstrate that the proposed scheme effectively identified the above representative block ciphers，and the correlative research can promote the further encryption algorithms identification research.…”
Get full text

A blockchain sharding scheme in edge computing by Jun WANG, Jianwei MA, Jinxi LUO

“…The low security and poor privacy of the data in edge computing restrict the development of edge computing.Block chains can provide security for data in edge computing using their own tamper resistance, while protecting privacy by use of traceability.But the bottleneck of blockchain's scalability has become a barrier to their application in the field of edge computing.To solve the problem that blockchain can not meet the needs of a large number of nodes to process data at the same time when applied to edge computing, a two-layer sharding scheme was presented, which meets the needs of edge computing scenarios.Geographic location-based partitioning of nodes was implemented using the improved K-means algorithm, and a local blockchain network consensus (LBNC) algorithm was designed based on the idea of delegated proof of stake (DPoS) and practical Byzantine fault tolerance (PBFT).Simulation results show that the proposed scheme has less delay and higher throughput than those of PBFT, and the total throughput increases with the number of shards.…”
Get full text

Adaptive k-means clustering algorithm based on grid and domain centroid weight by Wei CAI, Guangyu SUN, Fei YANG, Bo YAO, Chuanxian LI

“…Furthermore, when the clustering accuracy exceeded 99％ compared to the k-means algorithm, the computational efficiency was significantly improved. …”
Get full text

A Fast Global Center Fuzzy Clustering Method by SUN Dong-pu, TAN Jie-qiong

“… In terms of the problems that the fuzzy C-means algorithm is sensitive to the initial center, easy to fall into the local optimal solution, and the algorithm iteration speed is slow, a rapid global center fuzzy clustering system model is established according to the global center theory of fuzzy clustering, and the relevant theoretical analysis and algorithm process is given. …”
Get full text

PV Power Short-Term Forecasting Method Based on VMD-GWO-ELMAN by Na ZHANG, Qiang REN, Guangchen LIU, Liping GUO, Jingyu LI

“…Considering the blindness and randomness of weights and thresholds of traditional Elman neural networks and the fluctuation and nonstationarity of PV output power signal, the paper proposes a short-term prediction model of PV output power based on variational mode decomposition (VMD) and an Elman neural network optimized by grey wolf optimization (GWO) algorithm. Firstly, the K-means algorithm is used to cluster the original data according to weather types. …”
Get full text

Evaluation of spatial clustering methods for regionalisation of hydrogen ecosystems by Friedrich Mendler, Barbara Koch, Björn Meißner, Christopher Voglstätter, Tom Smolinka

“…Although the best algorithm depends on the focus of the regionalisation process, the method REDCAP proved to be the best overall, especially with higher intra-cluster homogeneity compared to the widely used k-means algorithm. The developed indicators and their evaluation regarding different objectives are seen to be transferable to other clustering and regionalisation applications, like energy system analysis or general supply chain analysis.…”
Get full text

Energy-efficient selection of cluster headers in wireless sensor networks by Adem Fanos Jemal, Redwan Hassen Hussen, Do-Yun Kim, Zhetao Li, Tingrui Pei, Young-June Choi

“…In this work, we propose a cluster-based energy-efficient router placement scheme for wireless sensor networks, where the K-means algorithm is used to select the initial cluster headers and then a cluster header with sufficient battery energy is selected within each cluster. …”
Get full text

A Deep Neural Network-Based Approach to Media Hotspot Discovery by Pan Luo

“…First, the text data features are extracted based on the graphical convolutional neural network, and the temporal correlation of numerical information is modeled using gated recurrent units, and the numerical feature vectors are fused with the text feature vectors. Then, the K-means algorithm is optimized for the initial point selection problem, and a clustering algorithm based on the maximum density selection method in the moving range is proposed. …”
Get full text

A New Feature Extraction Method for Bearing Faults in Impulsive Noise Using Fractional Lower-Order Statistics by Qianqian Xu, Kai Liu

“…Fractional lower-order p-function optimization is obtained by the calculation of the distance ratio based on K-means algorithms. Finally, a fault feature dataset is established by the optimal FLOS and lower-dimensional mapping matrix of covariation to accurately and intuitively describe various bearing faults. …”
Get full text