Data Clustering Method Research Articles

Pre-crash scenarios for safety testing of autonomous vehicles: A clustering method for in-depth crash data

Autonomous vehicles (AVs) provide an opportunity to enhance traffic safety. However, AVs market penetration is still restricted due to their safety concerns and dependability. For widespread adoption, it is crucial to thoroughly assess the safety response of AVs in various high-risk scenarios. To achieve this objective, a clustering method was used to construct typical testing scenarios based on the China In-depth Mobility Safety Study-Traffic Accident (CIMSS-TA) database. Initially, 222 car-to-powered two-wheelers (PTWs) crashes and 180 car-to-car crashes were reconstructed from CIMSS-TA database. Second, six variables were extracted and analyzed, including the motion of the two vehicles involved, relative movement, lighting condition, road condition, and visual obstruction. Third, these variables were clustered using the k-medoids algorithm, identifying five typical pre-crash scenarios for car-to-PTWs and seven for car-to-car. Additionally, we extracted the velocities and surrounding environmental information of the crash-involved parties to enrich the scenario description. The approach used in this study used in-depth case review and thus provided more insightful information for identifying and quantifying representative high-risk scenarios than prior studies that analyzed overall descriptive variables from Chinese crash databases. Furthermore, it is crucial to separately test car-to-car scenarios and car-to-PTWs scenarios due to their distinct motion characteristics, which significantly affect the resulting typical scenarios.

A Clustering Method for Single-Cell RNA-Seq Data Based on Automatic Weighting Penalty and Low-Rank Representation.

Advances in high-throughput single-cell RNA sequencing (scRNA-seq) technology have provided more comprehensive biological information on cell expression. Clustering analysis is a critical step in scRNA-seq research and provides clear knowledge of the cell identity. Unfortunately, the characteristics of scRNA-seq data and the limitations of existing technologies make clustering encounter a considerable challenge. Meanwhile, some existing methods treat different features equally and ignore differences in feature contributions, which leads to a loss of information. To overcome limitations, we introduce a weighted distance constraint into the construction of the similarity graph and combine the similarity constraint. We propose the Joint Automatic Weighting Similarity Graph and Low-rank Representation (JAGLRR) clustering method. Evaluating the contributions of each feature and assigning various weight values can increase the significance of valuable features while decreasing the interference of redundant features. The similarity constraint allows the model to generate a more symmetric affinity matrix. Benefitting from that affinity matrix, JAGLRR recovers the original linear relationship of the data more accurately and obtains more discriminative information. The results on simulated datasets and 8 real datasets show that JAGLRR outperforms 11 existing comparison methods in clustering experiments, with higher clustering accuracy and stability.

CASCC: a co-expression-assisted single-cell RNA-seq data clustering method.

Existing clustering methods for characterizing cell populations from single-cell RNA sequencing are constrained by several limitations stemming from the fact that clusters often cannot be homogeneous, particularly for transitioning populations. On the other hand, dominant cell populations within samples can be identified independently by their strong gene co-expression signatures using methods unrelated to partitioning. Here, we introduce a clustering method, CASCC (co-expression-assisted single-cell clustering), designed to improve biological accuracy using gene co-expression features identified using an unsupervised adaptive attractor algorithm. CASCC outperformed other methods as evidenced by multiple evaluation metrics, and our results suggest that CASCC can improve the analysis of single-cell transcriptomics, enabling potential new discoveries related to underlying biological mechanisms. The CASCC R package is publicly available at https://github.com/LingyiC/CASCC and https://zenodo.org/doi/10.5281/zenodo.10648327.

Clustering on heterogeneous IoT information network based on meta path.

As the Internet and Internet of Things (IoT) continue to develop, Heterogeneous Information Networks (HIN) have formed complex interaction relationships among data objects. These relationships are represented by various types of edges (meta-paths) that contain rich semantic information. In the context of IoT data applications, the widespread adoption of Trigger-Action Patterns makes the management and analysis of heterogeneous data particularly important. This study proposes a meta-path-based clustering method for heterogeneous IoT data called I-RankClus, which aims to improve the modeling and analysis efficiency of IoT data. By combining ranking with clustering algorithms, the PageRank algorithm was used to calculate the intraclass influence of objects in the network. The HITS algorithm then transfers the influence to the core objects, thereby optimizing the classification of objects during the clustering process. The I-RankClus algorithm does not process each meta-path individually, but instead integrates multiple meta-paths to enhance the interpretability and clustering performance of the model. The experimental results show that the I-RankClus algorithm can process complex IoT datasets more effectively than traditional clustering methods and provide more accurate clustering outcomes. Furthermore, through a detailed analysis of meta-paths, this study explored the influence and importance of different meta-paths, thereby validating the effectiveness of the algorithm. Overall, the research presented in this paper not only improves the application effects of HINs in IoT data analysis but also provides valuable methods and insights for future network data processing.

CTEC: a cross-tabulation ensemble clustering approach for single-cell RNA sequencing data analysis.

Cell-type clustering is a crucial first step for single-cell RNA-seq data analysis. However, existing clustering methods often provide different results on cluster assignments with respect to their own data pre-processing, choice of distance metrics, and strategies of feature extraction, thereby limiting their practical applications. We propose Cross-Tabulation Ensemble Clustering (CTEC) method that formulates two re-clustering strategies (distribution- and outlier-based) via cross-tabulation. Benchmarking experiments on five scRNA-Seq datasets illustrate that the proposed CTEC method offers significant improvements over the individual clustering methods. Moreover, CTEC-DB outperforms the state-of-the-art ensemble methods for single-cell data clustering, with 45.4% and 17.1% improvement over the single-cell aggregated from ensemble clustering method (SAFE) and the single-cell aggregated clustering via Mixture model ensemble method (SAME), respectively, on the two-method ensemble test. The source code of the benchmark in this work is available at the GitHub repository https://github.com/LWCHN/CTEC.git.

Efficient cytometry analysis with FlowSOM in Python boosts interoperability with other single-cell tools.

We describe a new Python implementation of FlowSOM, a clustering method for cytometry data. This implementation is faster than the original version in R, better adapted to work with single-cell omics data including integration with current single-cell data structures and includes all the original visualizations, such as the star and pie plot. The FlowSOM Python implementation is freely available on GitHub: https://github.com/saeyslab/FlowSOM_Python.

Multivariate Functional Clustering with Variable Selection and Application to Sensor Data from Engineering Systems

Multisensor data that track system operating behaviors are widely available nowadays from various engineering systems. Measurements from each sensor over time form a curve and can be viewed as functional data. Clustering of these multivariate functional curves is important for studying the operating patterns of systems. One complication in such applications is the possible presence of sensors whose data do not contain relevant information. Hence, it is desirable for the clustering method to equip with an automatic sensor selection procedure. Motivated by a real engineering application, we propose a functional data clustering method that simultaneously removes noninformative sensors and groups functional curves into clusters using informative sensors. Functional principal component analysis is used to transform multivariate functional data into a coefficient matrix for data reduction. We then model the transformed data by a Gaussian mixture distribution to perform model-based clustering with variable selection. Three types of penalties, the individual, variable, and group penalties, are considered to achieve automatic variable selection. Extensive simulations are conducted to assess the clustering and variable selection performance of the proposed methods. The application of the proposed methods to an engineering system with multiple sensors shows the promise of the methods and reveals interesting patterns in the sensor data. History: Kwok Tsui served as the senior editor for this article. Funding: The research by J. Min and Y. Hong was partially supported by the National Science Foundation [Grant CMMI-1904165] to Virginia Tech. The work by Y. Hong was partially supported by the Virginia Tech College of Science Research Equipment Fund. Data Ethics & Reproducibility Note: The original dataset is proprietary and cannot be shared. The full code to replicate the results in this paper, based on summary statistics of the original data, is available at https://github.com/jiem3/MultiFuncClustering . The code applied to a simplified version is available at https://codeocean.com/capsule/4041000/tree/v1 , which covers the data analysis and part of the simulation scenarios with a single dataset under each scenario using a fixed set of hyperparameters, for reducing computation time, and at https://doi.org/10.1287/ijds.2022.0034 .

Photovoltaic Solar Power Prediction Using iPSO-Based Data Clustering and AdaLSTM Network

Due to the increasing integration of photovoltaic (PV) solar power into power systems, the prediction of PV solar power output plays an important role in power system planning and management. This study combines an optimized data clustering method with a serially integrated AdaLSTM network to improve the accuracy and robustness of PV solar power prediction. During the data clustering process, the Euclidean distance-based clustering centroids are optimized by an improved particle swarm optimization (iPSO) algorithm. For each obtained data cluster, the AdaLSTM network is utilized for model training, in which multiple LSTMs are serially combined together through the AdaBoost algorithm. For PV power prediction tasks, the inputs of the testing set are classified into the nearest data cluster by the K-nearest neighbor (KNN) method, and then the corresponding AdaLSTM network of this cluster is used to perform the prediction. Case studies from two real PV stations are used for prediction performance evaluation. Results based on three prediction horizons (10, 30 and 60 min) demonstrate that the proposed model combining the optimized data clustering and AdaLSTM has higher prediction accuracy and robustness than other comparison models. The root mean square error (RMSE) of the proposed model is reduced, respectively, by 75.22%, 73.80%, 67.60%, 66.30%, and 64.85% compared with persistence, BPNN, CNN, LSTM, and AdaLSTM without clustering (Case A, 30 min prediction). Even compared with the model combining the K-means clustering and AdaLSTM, the RMSE can be reduced by 10.75%.

Regional Grouping Based on Cubic Water Using K-Means Algorithm at Perumda Air Minum Tirta Silaupiasa Asahan Regency

Perumda Air Minum Tirta Silaupiasa Asahan Regency is a regional company that has the authority to provide clean water consumption needs for the community in Asahan Regency. Currently, clean water needs, especially for households and industries in Asahan Regency, are supplied by Perumda Air Minum Tirta Silaupiasa which is located at Jalan Jend. Ahmad Yani No. 33, Kisaran, Sei Renggas, West Kisaran, Sei Renggas, West Kisaran City District, Asahan Regency, North Sumatra 21213. Currently, the need for clean water for the people of Asahan Regency comes from Perumda Air Minum Tirta Silaupiasa Asahan Regency. However, the amount of clean water provided for people living in areas with high cubic water in Asahan Regency is still relatively small, this is because the Perumda Air Minum Tirta Silaupiasa Asahan Regency does not know which areas have high, medium and low cubic water usage. Therefore, Perumda Air Minum Tirta Silaupiasa Asahan Regency needs to follow up on this problem by grouping areas based on water cubic. To manage the data, a technique is needed that can be used to extract information from the data, the technique is Data Mining. The purpose of this system is to find out how to analyze water cubic data using the K-Means Algorithm and design a website-based system with the PHP programming language and MySQL Database to determine areas with high, medium, and low water cubic. K-means clustering is a data analysis method or data mining method that performs unsupervised modeling and is one of the data clustering methods using a partition system. The data obtained in the recap of cubic water data at Perumda Air Minum Tirta Silaupiasa Asahan Regency for the period 2021-2023. The research method used in this research is quantitative research method. From the results of implementation and testing the results of the calculation of the K-means clustering method are the results of clustering cubic water in the Asahan district area with high water cubic including West Kisaran with a minimum value of 101727.9655 and East Kisaran with a minimum value of 101727.9655. Then in the Asahan district area with medium water cubic including Air Joman with a minimum value of 151144.2025 and Simpang Empat with a minimum value of 151144.2025. Then in the Asahan district area with low water cubic including B.P Mandoge with a minimum value of 66801.4373, Buntu Pane with a minimum value of 105608.8293, Desa Gajah with a value of 59925.2623, Lubuk Palas with a value of 75832.9197, Meranti with a value of 2892.8137, Sei Kamah II with a value of 47997.2206, and Sei Kepayang Barat with a value of 197781.2457.

Cross‐network service recommendation in smart cities

SummaryNowadays, Internet of Things, artificial intelligence, cloud computing, and other revolutionary technologies (e.g., edge and fog computing) have become the pillar of smart cities. These latter make users' lives easier, thanks to a wide variety of smart services offered in different dimensions (e.g., smart living, smart mobility, smart economy, smart governance). However, the rapid adoption of smart services by users and the full servicelization of several cities around the world is faced with two major issues: the lack of knowledge regarding smart services' capacities (e.g., features, contextual requirements, pricing models, privacy policies, provisioning terms, etc.), and the lack of unified rating and quantification of smart services' QoS behavior. Indeed, interested users often exploit traditional search tools (e.g., Web search engines, social networks) to find and rate the needed services. This behavior has scattered the smart services' usage data (e.g., users contexts, ratings) across multiple providers platforms, which makes the search task beyond the capacity of users and, even, other service providers. Although recommender systems are a natural solution to exempt users from exploring the huge space of the offered smart services, current recommendation approaches for smart city environments are unable to deliver correct recommendations. In fact, they have been initially designed to single‐network settings (a single service repository), while smart services' consumers often are involved in multiple provider platforms. To the best of our knowledge, there exists no approach that treated smart service recommendation across multiple information networks. Therefore, the goal of this paper is to propose a cross‐network recommender system for smart cities. We first model the multiplex network of smart services' providers as a multirelational fuzzy lattice family thanks to fuzzy relational concept analysis (fuzzy RCA), which is a powerful mathematical method for data analysis and clustering. We also use the concept of anchor users to connect providers networks via the users involved in more than one provider platform. Guided by anchors' cross‐network relations, we compute the similarity between users and we define algorithms for exploring the smart services' information network, i.e. lattice family. Extensive experiments have proved the effectiveness of cross‐network recommendation and the quality of produced recommendations, compared to state‐of‐the‐art single‐network recommendation.

EU Countries Tax Evasion Clustering

The problem of tax evasion is becoming more and more prominent, and it is causing large losses in individual state budgets. However, European policies have taken significant steps to eliminate them over the last two decades. National policies also contribute to reducing the estimated extent of tax evasion, as measured by Schneider's MIMIC model. However, these tendencies are not the same in individual countries. Therefore, in our paper, we try to find pattern in tax evasion time trajectories of European Union countries and thus to create homogenous clusters that include countries with similar tax evasion situation. To meet our goal, we use panel data clustering method on our data with information about tax evasion of EU countries from 2000 to 2019. As a next step, we compare created cluster from the perspective of quality indicators of public institutions.

State-transition dynamics of resting-state functional magnetic resonance imaging data: model comparison and test-to-retest analysis

Electroencephalogram (EEG) microstate analysis entails finding dynamics of quasi-stable and generally recurrent discrete states in multichannel EEG time series data and relating properties of the estimated state-transition dynamics to observables such as cognition and behavior. While microstate analysis has been widely employed to analyze EEG data, its use remains less prevalent in functional magnetic resonance imaging (fMRI) data, largely due to the slower timescale of such data. In the present study, we extend various data clustering methods used in EEG microstate analysis to resting-state fMRI data from healthy humans to extract their state-transition dynamics. We show that the quality of clustering is on par with that for various microstate analyses of EEG data. We then develop a method for examining test–retest reliability of the discrete-state transition dynamics between fMRI sessions and show that the within-participant test–retest reliability is higher than between-participant test–retest reliability for different indices of state-transition dynamics, different networks, and different data sets. This result suggests that state-transition dynamics analysis of fMRI data could discriminate between different individuals and is a promising tool for performing fingerprinting analysis of individuals.

Spectral clustering with linear embedding: A discrete clustering method for large-scale data

In recent decades, spectral clustering has found widespread applications in various real-world scenarios, showcasing its effectiveness. Traditional spectral clustering typically follows a two-step procedure to address the optimization problem. However, this approach may result in substantial information loss and performance decline. Furthermore, the eigenvalue decomposition, a key step in spectral clustering, entails cubic computational complexity. This paper incorporates linear embedding into the objective function of spectral clustering and proposes a direct method to solve the indicator matrix. Moreover, our method achieves a linear time complexity with respect to the input data size. Our method, referred to as Spectral Clustering with Linear Embedding (SCLE), achieves a direct and efficient solution and naturally handles out-of-sample data. SCLE initiates the process with balanced and hierarchical K-means, effectively partitioning the input data into balanced clusters. After generating anchors, we compute a similarity matrix based on the distances between the input data points and the generated anchors. In contrast to the conventional two-step spectral clustering approach, we directly solve the cluster indicator matrix at a linear time complexity. Extensive experiments across multiple datasets underscore the efficiency and effectiveness of our proposed SCLE method.

THE METHOD FOR OBJECTS DETECTION ON SATELLITE IMAGERY BASED ON THE FIREFLY ALGORITHM

The subject matter of the article is the method for detecting of objects on satellite imagery based on the firefly algorithm. The goal is to develop a method for detecting of objects on satellite imagery based on the firefly algorithm. The tasks are: analysis of existing methods for detecting of objects of interest on satellite imagery, development of a method for detecting of objects on satellite imagery, practical verification of the method for detecting of objects on satellite imagery based on the firefly algorithm, and quantitative assessment of the quality of the proposed method. The methods used are: methods of digital image processing, methods of data clustering, mathematical apparatus of matrix theory, methods of swarm intelligence, methods of mathematical modeling, methods of optimization theory, analytical and empirical methods of image comparison. The following results are obtained. The advantages and disadvantages of the main methods and approaches to the processing of satellite imagery for the purpose of detecting objects of interest on them are determined. The general principle of operation of the firefly algorithm is considered. It presents a flowchart of the method for detecting of objects on satellite imagery based on the firefly algorithm in one color channel. The values of the input data and parameters for the operation of the algorithm were selected experimentally. Experimental studies were conducted on the operation of the method for detecting of objects on a real satellite imagery based on the firefly algorithm. The values of the errors of the first and second kind for the processed image using the proposed method and the method based on the particle swarm algorithm were calculated. Conclusions. Analysis of the calculated values showed that the proposed method for detecting of objects on satellite imagery compared to the method based on the particle swarm algorithm: reduces the error of the first kind by about 11% and the error of the second kind by about 9%. The directions of further research are the study of the problem of selecting input parameters and data for the operation of the method based on the firefly algorithm.

A New and Effective Classification Method for Complex Time Series Based on Information Measure

The growing importance of time series information measure raises questions about how to effectively cluster a large number of nonlinear complex time series data and accurately extract more hidden information from them. In this paper, a clustering measurement and classification method for complex time series, the symmetrical exponential Tsallis relative information (SETRI) measure, is proposed, which aims to address these problems. The intrinsic characteristics of different types of time series information could be validly identified by this method. The modified multidimensional scaling (MDS) method, based on the SETRI measure, has the ability to display the data in the form of graphs for intuitive exhibition and accomplish the process of dimension reduction. The introduction of weighted permutation patterns allows a higher-accuracy classification not only for the time series dissimilarity quantification, but also for avoiding dispensable errors. Besides, the feasibility of the modified MDS classification method is visually and quantitatively verified by the simulated and real-world data. Compared with other MDS methods, the proposed method has better performance, which is reflected in the validity and rationality of the clustering results, thus further verifying the feasibility of the proposed method. Therefore, the new results will be helpful to develop complex data clustering and dimensionality reduction methods.

Optimal voltage set-point of automatic tap changer transformers and generators and reactive power compensation to increase power system predictability

In recent years, renewable energy sources (RESs) such as wind turbines (WTs) have received much attention in both the operating and planning of power systems. These sources have caused many uncertainties in the operation of power systems due to their unpredictable nature. Mentioned uncertainties besides load demands uncertainty, and possible failures in power system components, make the system state unpredictable. The operational decisions are completely challenging in these situations. Any efforts to increase the network operator awareness from the system state will be completely valuable for making accurate decisions.This paper tries to increase the predictability of the power system state through optimal regulating of the voltage setpoint of automatic tap changer transformers and generators besides the reactive power of shunt capacitors. However, conventional objectives such as decreasing losses are considered, simultaneously. This paper uses the K-medoids data clustering method to evaluate the effect of uncertainties. Also, the correlation between input uncertain variables is considered and handled by the Cholesky decomposition technique combined with the Nataf transformation technique. The multi-objective optimization problem is tackled using an improved version of the non-dominated sorting genetic algorithm (NSGA-II). To ensure for validity of the results, studies are repeated using the multi-objective particle swarm optimization (MOPSO) algorithm as another evolutionary-based method.The proposed approach is applied to the IEEE 14 and 30 bus standard system. The results showed that the predictability of the power system can be considerably increased while keeping the losses approximately at its minimum amount.

Functional Data Clustering Method Based on Shape Information and Functional Mahalanobis Distance

Function-type data can provide insights into the internal structure of the data and facilitate the extraction of data features from the perspective of interactive derivative functions. The paper proposes a nonparametric clustering method for function-based data that incorporates first-order and second-order derivative function information into the Marginal distance for clustering function-based data. The method is based on the traditional K-means algorithm and is designed to cluster function-based data that contains rich shape information. The paper evaluated the performance of the algorithm of the text by comparing its purity and adjusted Rand coefficients against six other clustering algorithms on three different datasets. The results show that the algorithm of the text outperforms the other algorithms, demonstrating its outstanding performance, wide applicability, and practical significance in solving real-world problems.

ИСПОЛЬЗОВАНИЕ АЛГОРИТМОВ МАШИННОГО ОБУЧЕНИЯ ДЛЯ ОБНАРУЖЕНИЯ И ДИАГНОСТИКИ НЕИСПРАВНОСТЕЙ В СИСТЕМАХ ЖИЗНЕОБЕСПЕЧЕНИЯ

The increasing interest in integrating machine learning methods into life support systems management is driven by their potential to enhance error detection, diagnostics, and forecasting capabilities. This paper focuses on analyzing current research to identify the strengths and weaknesses of machine learning models in the field of fault detection and prediction in building life support systems. It aims to provide insights into addressing issues such as data quality, algorithmic complexity, and interpretability. A review of contemporary scientific articles in this area was conducted, analyzing innovations and the practical implementation of machine learning models. The primary goal was to determine the optimal models for various scenarios, considering data characteristics, system complexity, task requirements, and desired outcomes. The information analysis led to formulating recommendations for integrating machine learning methods into life support systems, including the use of clustering methods for unlabeled data, XGBoost for handling unbalanced labeled data, support vector machines (SVM) for binary classification tasks, and decision trees (DT) or random forests (RF) for multi-class classification. Additionally, artificial neural networks (ANN) can be used for processing nonlinear data distributions. These recommendations are practically significant for enhancing the performance and energy efficiency of life support systems through the effective use of machine learning technologies. By providing guidance on model selection and implementation strategies, this work contributes to researchers, practitioners, and industry representatives in fault detection and diagnostics within life support systems.

THE FRACTIONAL DISEN–FISHER PLANE: AN EFFECTIVE APPROACH TO DISTINGUISH COMPLEX TIME SERIES

With the explosive growth of data quantity and rapid development of nonlinear dynamics as well as the growing demand for complex data classification in the field of artificial intelligence and machine learning, the research of complex time series, generated by complex systems, has attracted enormous interests. However, how to simultaneously distinguish different types of time series data and extract more accurate and detailed information from them in the light of localized and global scale perspectives remains significant and needs to be tackled. Thus, in this paper, we propose the fractional DisEn–Fisher plane, which is innovatively constructed by the fractional form of dispersion entropy and Fisher information measure. These are both effective tools to diagnose the essential properties of complex time series, to analyze the complexity of systems and to depict the contained statistical information with higher accuracy and effectiveness. Several classical entropy plane methods are selected as a comparison to design simulation experiments by simulated data and three real-world datasets. Comparative experimental results show that this method is a feasible and reliable improvement method, which will help to provide more additional information in time series recognition and dynamic characterization. It may not only provide new insights for further improvement of complex time series analysis, but also have important implications for developing complex data clustering methods.

Heterogeneous density-based clustering with a dual-functional memristive array.

In the big data era, the requirement for data clustering methods that can handle massive and heterogeneous datasets with varying distributions increases. This study proposes a clustering algorithm for data sets with heterogeneous density using a dual-mode memristor crossbar array for data clustering. The array consists of a Ta/HfO2/RuO2 memristor operating in analog or digital modes, controlled by the reset voltage. The digital mode shows low dispersion and a high resistance ratio, and the analog mode enables precise conductance tuning. The local outlier factor is introduced to handle a heterogeneous density, and the required Euclidean and K-distances within the given dataset are calculated in the analog mode in parallel. In the digital mode, clustering is performed based on the connectivity among data points after excluding the detected outliers. The proposed algorithm boasts linear time complexity for the entire process. Extensive evaluations of synthetic datasets demonstrate significant improvement over representative density-based algorithms, and the datasets with heterogeneous density are clustered feasibly. Finally, the proposed algorithm is used to cluster the single-molecule localization microscopy data, demonstrating the feasibility of the suggested method for real-world problems.