Clustering Algorithm Research Articles

Enhanced recognition of insulator defects on power transmission lines via proposal-based detection model with integrated improvement methods

Deep learning-driven transmission line inspection is a critical area for smart power grid development. Despite advances in deep learning for insulator defect detection, challenges remain in model robustness and adaptability for the varying real-world adaptability, especially for insignificant defects in complex backgrounds. This study presents a comprehensive improvement strategy for detecting insulators and cross-scale broken defects on transmission lines, employing a proposal-based detection model. The model introduces a holistic pipeline of improved methods, including backbone modification, anchor box scale recalibration, and improvements in Region of Interest (RoI) downsampling alignment and Intersection over Union (IoU) loss function. Various backbone networks, including convolutional network (ConvNet) and Vision Transformer (ViT) structures, are constructed and integrated with attention modules, specifically designed to amplify the perception of insulators and defective regions. The geometric scale of anchor boxes is reconstructed using a developed clustering algorithm, considering the elongated characteristics of insulator strings to improve the adaptability of anchor boxes. Bilinear interpolation is utilized to mitigate spatial misalignment issues during the downsampling process of Region Proposal Network (RPN)-based proposals. The experimental results indicate that the improved models with the Swin Transformer (Swin-T) backbone framework achieve the mean Average Precision (mAP)@0.5 of 88.42% and mAP@0.7 of 60.52%, with a defect recall rate of 81.94%. Additionally, the improved IoU loss function contributes to the performance of the model at higher IoU thresholds. The results of this study contribute to the further development of defect detection frameworks for power vision applications.

Ensemble of machine learning techniques to predict survival in kidney transplant recipients

Kidney transplant recipients face a high cardiovascular risk, which is a leading cause of death in this patient group. This article proposes the application of clustering techniques and feature selection to predict the survival outcomes of kidney transplant recipients based on machine learning techniques and mainstream statistical methods. First, feature selection techniques (Boruta, Random Survival Forest and Elastic Net) are used to detect the most relevant variables. Subsequently, each set of variables obtained by each feature selection technique is used as input for the clustering algorithms used (Consensus Clustering, Self-Organizing Map and Agglomerative Clustering) to determine which combination of feature selection, clustering algorithm and number of clusters maximizes intercluster variability. Next, the mechanism called False Clustering Discovery Reduction is applied to obtain the minimum number of statistically differentiable populations after applying a control metric. This metric is based on a variance test to confirm that reducing the number of clusters does not generate significant losses in the heterogeneity obtained. This approach was applied to the Organ Procurement and Transplantation Network medical dataset (n = 11,332). The combination of Random Survival Forest and consensus clustering yielded the optimal result of 4 clusters starting from 8 initial ones. Finally, for each population, Kaplan-Meier survival curves are generated to predict the survival of new patients based on the predictions of the XGBoost classifier, with an overall multi-class AUC of 98.11%.

Automatic Methodology for Forest Fire Mapping with SuperDove Imagery.

The global increase in wildfires due to climate change highlights the need for accurate wildfire mapping. This study performs a proof of concept on the usefulness of SuperDove imagery for wildfire mapping. To address this topic, we present an automatic methodology that combines the use of various vegetation indices with clustering algorithms (bisecting k-means and k-means) to analyze images before and after fires, with the aim of improving the precision of the burned area and severity assessments. The results demonstrate the potential of using this PlanetScope sensor, showing that the methodology effectively delineates burned areas and classifies them by severity level, in comparison with data from the Copernicus Emergency Management Service (CEMS). Thus, the potential of the SuperDove satellite sensor constellation for fire monitoring is highlighted, despite its limitations regarding radiometric distortion and the absence of Short-Wave Infrared (SWIR) bands, suggesting that the methodology could contribute to better fire management strategies.

Evaluation of Different Classification Algorithms for Land Use Land Cover Mapping

For efficient sustainable management and monitoring landscape changes over times, reliable land use land cover (LULC) mapping using the most accurate classification algorithms is required. Increasing innovative classification algorithms and satellite data demands finding the most suitable classifier to create accurate maps of different features efficiently. The challenge addressed in this study is to identify the most accurate algorithm for classifying and generating reliable LULC. The objective of this research was to identify the best classification among several algorithms both overall and in each individual class by using ArcGIS Pro and Google Earth Engine with Landsat 8 and Sentinel-2 datasets for Ranya city as the study area. Support vector machine (SVM), maximum likelihood, random tree, classification and regression tree, K-Nearest Neighbor and iterative self organizing cluster algorithms were used to classify the satellite image of the study area. The kappa coefficient matrix was used to assess the performance of each classifier and method. The study showed that the random tree algorithm achieved highest overall accuracy using Sentinel-2 with 83%. Meanwhile, when the specific class accuracy is priority, the result suggests the use of SVM algorithm using Sentinel-2 for building footprint extraction with 92% accuracy. The result also showed that the outcomes of most algorithms were better using Sentinel-2 rather than Landsat 8, making Sentinel-2 more suitable for accurate LULC mapping. The outcomes of the research assessed different classification algorisms to find the best algorithms and methods that can be used to generate accurate and efficient LULC maps.

Streamlining NMR Chemical Shift Predictions for Intrinsically Disordered Proteins: Design of Ensembles with Dimensionality Reduction and Clustering.

By merging advanced dimensionality reduction (DR) and clustering algorithm (CA) techniques, our study advances the sampling procedure for predicting NMR chemical shifts (CS) in intrinsically disordered proteins (IDPs), making a significant leap forward in the field of protein analysis/modeling. We enhance NMR CS sampling by generating clustered ensembles that accurately reflect the different properties and phenomena encapsulated by the IDP trajectories. This investigation critically assessed different rapid CS predictors, both neural network (e.g., Sparta+ and ShiftX2) and database-driven (ProCS-15), and highlighted the need for more advanced quantum calculations and the subsequent need for more tractable-sized conformational ensembles. Although neural network CS predictors outperformed ProCS-15 for all atoms, all tools showed poor agreement with HN CSs, and the neural network CS predictors were unable to capture the influence of phosphorylated residues, highly relevant for IDPs. This study also addressed the limitations of using direct clustering with collective variables, such as the widespread implementation of the GROMOS algorithm. Clustered ensembles (CEs) produced by this algorithm showed poor performance with chemical shifts compared to sequential ensembles (SEs) of similar size. Instead, we implement a multiscale DR and CA approach and explore the challenges and limitations of applying these algorithms to obtain more robust and tractable CEs. The novel feature of this investigation is the use of solvent-accessible surface area (SASA) as one of the fingerprints for DR alongside previously investigated α carbon distance/angles or ϕ/ψ dihedral angles. The ensembles produced with SASA tSNE DR produced CEs better aligned with the experimental CS of between 0.17 and 0.36 r2 (0.18-0.26 ppm) depending on the system and replicate. Furthermore, this technique produced CEs with better agreement than traditional SEs in 85.7% of all ensemble sizes. This study investigates the quality of ensembles produced based on different input features, comparing latent spaces produced by linear vs nonlinear DR techniques and a novel integrated silhouette score scanning protocol for tSNE DR.

The Application of Big Data in the Management of Ideological and Political Education in the Development of Education Network

Based on a brief analysis of the current situation of university education management and research on intelligent algorithms, this article constructs a university education management system based on big data. For the clustering and prediction modules in higher education management, corresponding algorithms are used for optimization design. A fuzzy clustering algorithm based on entropy weight is proposed to address the shortcomings of the C-means clustering algorithm. This algorithm adds weighting coefficients on the basis of improvement and continuously updates the clustering centers. The prediction module uses Apriori algorithm to map and compress the target transaction database, reduces the number of candidate item sets through pruning process, and designs simulation experiments to measure the performance of the algorithm. The simulation results show that the clustering results of this algorithm are closer to the actual clustering situation, with shorter running time and better algorithm performance.

COPS: A novel platform for multi-omic disease subtype discovery via robust multi-objective evaluation of clustering algorithms.

Recent research on multi-view clustering algorithms for complex disease subtyping often overlooks aspects like clustering stability and critical assessment of prognostic relevance. Furthermore, current frameworks do not allow for a comparison between data-driven and pathway-driven clustering, highlighting a significant gap in the methodology. We present the COPS R-package, tailored for robust evaluation of single and multi-omics clustering results. COPS features advanced methods, including similarity networks, kernel-based approaches, dimensionality reduction, and pathway knowledge integration. Some of these methods are not accessible through R, and some correspond to new approaches proposed with COPS. Our framework was rigorously applied to multi-omics data across seven cancer types, including breast, prostate, and lung, utilizing mRNA, CNV, miRNA, and DNA methylation data. Unlike previous studies, our approach contrasts data- and knowledge-driven multi-view clustering methods and incorporates cross-fold validation for robustness. Clustering outcomes were assessed using the ARI score, survival analysis via Cox regression models including relevant covariates, and the stability of the results. While survival analysis and gold-standard agreement are standard metrics, they vary considerably across methods and datasets. Therefore, it is essential to assess multi-view clustering methods using multiple criteria, from cluster stability to prognostic relevance, and to provide ways of comparing these metrics simultaneously to select the optimal approach for disease subtype discovery in novel datasets. Emphasizing multi-objective evaluation, we applied the Pareto efficiency concept to gauge the equilibrium of evaluation metrics in each cancer case-study. Affinity Network Fusion, Integrative Non-negative Matrix Factorization, and Multiple Kernel K-Means with linear or Pathway Induced Kernels were the most stable and effective in discerning groups with significantly different survival outcomes in several case studies.

An autonomous centreless approach to chunk-wise data partitioning

AbstractIn this paper, a novel autonomous centreless algorithm is proposed for data partitioning. The proposed algorithm firstly constructs the nearest neighbour affinity graph and identifies the local peaks of data density to build micro-clusters. Unlike the vast majority of partitional clustering algorithms, the proposed algorithm does not rely on singleton prototypes, namely, centres or medoids of the micro-clusters to partition the data space. Instead, these micro-clusters are directly utilised to attract nearby data samples to form shape-free Voronoi tessellations, hence, being centreless and robust to noisy data. A fusion scheme is further implemented to fuse these data clouds with higher intra-cluster similarity together to attain a more compact partitioning of data. The proposed algorithm is able to perform data partitioning on a chunk-wise basis and is highly computationally efficient with the default distance measure. Therefore, it is suitable for both static data partitioning in offline scenarios and streaming data partitioning in online scenarios. Numerical examples on a variety of benchmark datasets demonstrate the efficacy of the proposed algorithm.

Aperiodic small signal stability method for detection and mitigation of cascading failures in smart grids

The occurrence of cascading failures poses significant risks to the stability and reliability of modern smart grids. This article presents a novel hybrid algorithm designed to assess and mitigate these failures. The technique combines advanced clustering algorithms, specifically Affinity Propagation Graph (APG) and Self-Propagating Graph (SPG), to detect critical nodes, and Unified Power Flow Controllers (UPFCs) to provide compensation to grid networks. The algorithm first uses APG to divide the network into clusters and considers the center bus as the critical node. If the center bus is not critical, SPG is applied to identify the critical node. This hybrid approach identifies the critical node in just 0.02 s (for both APG and SPG) and with improved accuracy compared to existing methods. After identifying critical nodes, UPFCs are strategically installed to regulate power flow and reduce the probability of cascading failures, with compensation taking approximately 0.14 s. Simulation results demonstrate the effectiveness of the proposed method in enhancing grid resilience and reducing the likelihood of cascading failures. By strategically deploying UPFCs at critical nodes, this approach ensures resilient grid operation in various scenarios. This research significantly contributes to the development of smart grid technologies by providing a comprehensive framework to address cascading failures in power distribution networks. The proposed method shows potential for improving the reliability and stability of power grids amid changing system dynamics and uncertainties.

Performance Evaluation of Different Clustering Techniques and Parameters of Hybrid PSO- and GA-ANFIS on Optimization and Prediction of Biomethane Yield of Alkali-Pretreated Groundnut Shells

AbstractThe study focuses on optimizing biomethane yield in the anaerobic digestion of alkali-pretreated groundnut shells, involving varied input parameters. Biomethane optimization will improve the economy of the technology, which will assist in managing the environmental challenges of fossil fuel combustion. Traditional methods prove challenging, inaccurate, and uneconomical, necessitating efficient optimization models. This research hybridizes particle swarm optimization (PSO) and genetic algorithms (GA) with adaptive neuro-fuzzy inference system (ANFIS) models, assessing input parameters’ influence on biomethane yield through renowned performance metrics. Comparing the best model in the hybrid analysis, encompassing pretreatments A-E, the PSO-ANFIS (RMSE = 1.1719, MADE = 0.6525, MAE = 0.9314, Theil’s U = 0.1844, and SD = 0.7737) outperformed the GA-ANFIS (RMSE = 1.9338, MADE = 0.9318, MAE = 1.6557, Theil’s U = 0.2734, SD = 1.0598), using the same cluster radius of 0.50. Furthermore, compared to the GA-ANFIS model, the PSO-ANFIS model demonstrated significant improvements across various metrics: RMSE by 39.40%, MADE by 29.97%, MAE by 43.75%, Theil’s U by 32.56%, and SD by 27.00%. Results indicate that the PSO-ANFIS model outperforms the GA-ANFIS model, emphasizing the importance of suitable clustering algorithms and precise parameter adjustment for optimal performance in predicting biomethane yield from pretreated lignocellulose feedstocks. Graphical Abstract

Adaptive feature selection and optimized multiple histogram construction for reversible data hiding

Reversible data hiding (RDH) algorithms have been extensively employed in the field of copyright protection and information dissemination. Among various RDH algorithms, the multiple histogram modification (MHM) algorithm has attracted significant attention because of its capability to generate high-quality marked images. In previous MHM methods, the prediction error histograms were mostly generated in a fixed way. Recently, clustering algorithms automatically classify prediction errors into multiple classes, which enhances the similarity among prediction errors within the same class. However, the design of features and the determination of clustering numbers are crucial in clustering algorithms. Traditional algorithms utilize the same features and fix the number of clusters (e.g., empirically generate 16 classes), which may limit the performance due to the lack of adaptivity. To address these limitations, an adaptive initial feature selection scheme and a clustering number optimization scheme based on the Fuzzy C-Means (FCM) clustering algorithm are proposed in this paper. The superiority of the proposed scheme over other state-of-the-art schemes is verified by experimental results.

Machine Learning-based Differentiation of Japanese Plum Cultivars Based on Metabolite Profiling

This study investigates the metabolite diversity of twelve Japanese plum cultivars grown in South Africa to understand their differential organoleptic characteristics and nutritional properties. The goal is to differentiate or associate these plum cultivars based on their metabolic profiles. Metabolite profiling was conducted using gas chromatography-mass spectrometry (GC-MS) at different postharvest ripening stages. Different unsupervised machine learning algorithms were applied: hierarchical clustering, K-means clustering, Density-Based Spatial Applications with Noise, and principal component analysis (PCA). Results revealed that each cultivar contains a unique combination of 13 amino acids, 4 sugars (contributing to organoleptic characteristics), and numerous phenolic compounds and antioxidant activities (contributing to nutritional value). The levels of these compounds are cultivar-dependent and vary with postharvest stages. The number of clusters of plum cultivars varied with both the clustering algorithm and postharvest stages. However, certain cultivars were consistently grouped regardless of the clustering method, indicating similar characteristics and responses to storage and shelf-life conditions. Similar consistent groupings were observed after cold storage and shelf life. Our findings also showed that K-means clustering is the most effective model for plum cultivar differentiation based on the Silhouette Score and Davies-Bouldin Index. This study enhances our understanding of how metabolites evolve over different postharvest stages and provides a robust framework for differentiating plum cultivars, which can aid in sorting and grading operations. The research offers actionable insights to improve postharvest handling and storage practices, which are critical for maintaining the nutritional quality of plums, an important fruit for human health.

Optimization of UWB indoor positioning based on hardware accelerated Fuzzy ISODATA

With the development of wireless communication technology, Ultra-Wideband (UWB) has become an important solution for indoor positioning. In complex indoor environments, the influence of non-line-of-sight (NLOS) factors leads to increased positioning errors. To improve the positioning accuracy, fuzzy iterative self-organizing data analysis clustering algorithm (ISODATA) is introduced to process a large amount of UWB data to reduce the influence of NLOS factors, and to stabilize positioning error within 2 cm, enhances the accuracy of the positioning system. To further improve the running efficiency of the algorithm, FPGA is used to accelerate the key computational part of the algorithm, compared with running on the MATLAB platform, which improves the speed about 100 times, enhances the algorithm’s computational speed dramatically.

MapReduce algorithms for robust center-based clustering in doubling metrics

Clustering is a pivotal primitive for unsupervised learning and data analysis. A popular variant is the (k,ℓ)-clustering problem, where, given a pointset P from a metric space, one must determine a subset S of k centers minimizing the sum of the ℓ-th powers of the distances of points in P from their closest centers. This formulation covers the well-studied k-median (ℓ=1) and k-means (ℓ=2) clustering problems. A more general variant, introduced to deal with noisy pointsets, features a further parameter z and allows up to z points of P (outliers) to be disregarded when computing the sum. We present a distributed coreset-based 3-round approximation algorithm for the (k,ℓ)-clustering problem with z outliers, using MapReduce as a computational model. An important feature of our algorithm is that it obliviously adapts to the intrinsic complexity of the dataset, captured by its doubling dimension D. Remarkably, for D=O(1), our algorithm requires sublinear local memory per reducer, and yields a solution whose approximation ratio is an additive term O(γ) away from the one achievable by the best known sequential (possibly bicriteria) algorithm, where γ can be made arbitrarily small. To the best of our knowledge, no previous distributed approaches were able to attain similar quality-performance tradeoffs for metrics with constant doubling dimension.

A CREAM model optimization method based on fatigue testing experiments and machine learning techniques for maritime transportation applications

Maritime transportation has a crucial position in world trade, but maritime transportation accidents still occur frequently. To assess human errors in maritime transportation more accurately by CREAM and thus improve the reliability of maritime transportation, the study is the first to obtain the quantitative effects of different anti-fatigue capability groups on task performance in the field of maritime transportation by combining fatigue test experiments with machine learning. First, a dataset reflecting the fatigue changes of participants in maritime transportation tasks is constructed by 91 subjects participating in fatigue test experiments. Second, anti-fatigue capability classifications were performed by machine learning algorithms based on Density Peak Clustering Algorithm and fitness. Again, the failure probability correction coefficients of different anti-fatigue capability classes are obtained based on the classification results. Finally, the proposed model optimization method is experimentally verified. The results show that the optimized model is more accurate for the estimation of human-caused errors in maritime transportation. The proposed model effectively improves the inaccuracy of the traditional CREAM due to the lack of attention to individual physiological differences in the reliability assessment.

A digital twin-based traffic light management system using BIRCH algorithm

Urban transportation networks are vital for the economic and environmental well-being of cities and they are faced with the integration of Human-Driven Vehicles (HVs) and Connected and Autonomous Vehicles (CAVs) challenge. Most of the traditional traffic management systems fail to effectively manage the dynamic and complex flows of mixed traffic, mainly because of large computational requirements and the restrictions that control models of traffic lights directly based on extensive and continuous training data. Most of the times, the operational flexibility of CAVs is severely compromised for the safety of HVs, or CAVs are given high priority without taking into account the efficiency of HVs leading to lower performance, especially at low CAV penetration rates. On the other hand, the existing adaptive traffic light approaches were usually partial and could not adapt to the real-time behaviors of the traffic system. Some systems operate with inflexible temporal control plans that cannot react to variations in traffic flow or use adaptive control strategies that are based on a limited set of static traffic conditions. This paper presents a novel traffic light control approach utilizing the BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) clustering algorithm combined with digital twins for a more adaptive and efficient system. The BIRCH is effective in processing large datasets because it clusters data points incrementally and dynamically into a small set of representatives. The suggested method does not only enable better simulation and prediction of traffic patterns but also makes possible the real-time adaptive control of traffic signals at signalized intersections. It also improves traffic flow, reduces congestion, and minimizes vehicle idling time by adjusting the green and red light durations dynamically based on both real-time and historical traffic data. This approach is assessed under different traffic intensities, which include low, moderate, and high, while efficiency, fuel consumption, and the number of stops are being compared with the traditional and the existing adaptive traffic management systems.

Dynamic relationships and propagation characteristics between meteorological drought and vegetation drought based on a three-dimensional identification algorithm

Drought is a regional phenomenon and progressive in specific dimensions of time and space, with significant continuity and dynamic characteristics on a spatiotemporal scale. The meteorological drought acts as a driving factor for vegetation drought, and studying the response characteristics of vegetation drought to meteorological drought is crucial for comprehending the mechanisms of drought evolution. In this study, based on a three-dimensional spatiotemporal clustering algorithm, meteorological and vegetation drought events in the Yellow River Basin (YRB) from 1982 to 2020 were identified, and the dynamic characteristics of typical drought events were depicted, elucidating the inherent correlations and propagation features between meteorological and vegetation drought events. Additionally, according to the spatiotemporal matching criteria of drought events, the meteorological-vegetation drought event pairs were successfully matched, which can reveal the lag time between meteorological drought and vegetation drought. From a three-dimensional perspective, we revealed the dynamic propagation characteristics of meteorological and vegetation drought events, which could provide an effective way for monitoring and mitigating regional vegetation drought, restoring ecosystem functionality, and promoting sustainable development of the ecological environment.

Assessment of living quality in Guangdong: A hybrid knowledge-based and data-driven approach

Air, water, and radiation in urban living environments are crucial factors affecting human health, societal well-being, and sustainable development. This study developed a novel hybrid knowledge-based and data-driven approach for analyzing air, water, and radiation monitoring data to assess the quality of urban living natural environments (ULNEQ) in Guangdong Province. Fuzzy set-pair analysis was employed for data preprocessing, effectively incorporating domain knowledge into the raw data. Then, a hierarchical clustering algorithm was utilized to evaluate the ULNEQ level. The proposed approach enhanced data interpretability and optimized the clustering process, yielding more robust and reliable analytical results. The results revealed a diverse environmental landscape across the province, with Heyuan and Meizhou consistently maintaining high standards, whereas Dongguan and Jieyang exhibited notably poor conditions, ranking at Level IV or V for over 72% of the observed months. Key factors such as monthly average concentration ozone (0.56), the city water quality index (0.49), and the proportion of days with standard air quality (PDSAQ) (−0.39) significantly influenced the ULNEQ, with PDSAQ showing a negative correlation. Notably, a province-wide observation in June 2022 showed all cities maintaining ULEQ gradings of Level II or better. This innovative approach can be adapted to enhance the management and control of ULNEQ.

An application of clustering to classify movement patterns in men’s professional grand slam hard court tennis

ABSTRACT The movement cycles from Australian Open player tracking data were analysed using the Lloyd k-means clustering algorithm to classify movement patterns that exist in men’s grand-slam tennis. The elbow criterion method identified six movement patterns, and the k-means model allocated each movement cycle into one of these discrete groups. A description of each movement pattern is presented, outlining three inner range and three end range movement patterns, which are distinguishable by distance, direction, time pressure, and starting location. These findings provide objective details for coaches and athletes to understand tennis movement, overcoming vague descriptions of the inner range and end range in tennis vernacular. The amalgam of distance, direction, and time pressure demands that categorise the six movement patterns can enhance the specificity of training drill design and movement evaluation. Furthermore, evaluating the movement patterns a player typically elicits during match-play can inform typical load exposure and be useful in load monitoring practices. Additionally, understanding the prevalence of movement patterns in a typical match may help understand the strategic approaches players use during match-play.

Processing calibration data of low-temperature thermometer based on clustering algorithm.

The scarcity of cryogenic thermometers often stems from their high cost and lengthy lead times for calibration. Establishing an in-lab temperature calibration system is necessary to quickly make use of uncalibrated sensors or self-made sensors. This paper introduces a straightforward and high-accuracy thermometer calibration system. By employing copper screws as thermal links between the sensor platform and the cryogen-free refrigerator, temperature oscillation on the sensor platform is suppressed to a few millikelvins. In addition, this paper presents a data processing model based on clustering algorithms. These algorithms sort and group data based on distance, which is similar to human visual judgment of data. This paper discusses the parameter optimization process of the clustering algorithm to interpret the automated data process. The cryogenic temperature sensors calibrated by this system exhibited high accuracy, with relative errors of less than 1% compared to standard thermometers. Moreover, automatically processing calibration data from two uncalibrated thermometers takes just over 10min, highlighting the effectiveness of this calibration system.