Spectral Clustering Technique Research Articles

Greedy recursive spectral bisection for modularity-bound hierarchical divisive community detection

Spectral clustering techniques depend on the eigenstructure of a similarity matrix to assign data points to clusters, so that points within the same cluster exhibit high similarity and are compared to those in different clusters. This work aimed to develop a spectral method that could be compared to clustering algorithms that represent the current state of the art. This investigation conceived a novel spectral clustering method, as well as five policies that guide its execution, based on spectral graph theory and embodying hierarchical clustering principles. Computational experiments comparing the proposed method with six state-of-the-art algorithms were undertaken in this study to evaluate the clustering methods under scrutiny. The assessment was performed using two evaluation metrics, specifically the adjusted Rand index, and modularity. The obtained results furnish compelling evidence, indicating that the proposed method is competitive and possesses distinctive properties compared to those elucidated in the existing literature. This suggests that our approach stands as a viable alternative, offering a robust choice within the spectrum of available same-purpose tools.

Clustering techniques performance comparison for predicting the battery state of charge: A hybrid model approach

Abstract Batteries are a fundamental storage component due to its various applications in mobility, renewable energies and consumer electronics among others. Regardless of the battery typology, one key variable from a user’s perspective is the remaining energy in the battery. It is usually presented as the percentage of remaining energy compared to the total energy that can be stored and is labeled State Of Charge (SOC). This work addresses the development of a hybrid model based on a Lithium Iron Phosphate (LiFePO4) power cell, due to its broad implementation. The proposed model calculates the SOC, by means of voltage and electric current as inputs and the latter as the output. Therefore, four models based on k-Means, Agglomerative Clustering, Gaussian Mixture and Spectral Clustering techniques have been tested in order to obtain an optimal solution.

Deep Attentional Implanted Graph Clustering Algorithm for the Visualization and Analysis of Social Networks

As the user base expands, social network data becomes more intricate, making analyzing the interconnections between various entities challenging. Various graph visualization technologies are employed to analyze extensive and intricate network data. Network graphs inherently possess intricacy and may have overlapping elements. Graph clustering is a basic endeavor that aims to identify communities or groupings inside networks. Recent research has mostly concentrated on developing deep learning techniques to acquire a concise representation of graphs, which is then utilized with traditional clustering methods such as k-means or spectral clustering techniques. Multiplying these two-step architectures is challenging and sometimes results in unsatisfactory performance. This is mostly due to the lack of a goal-oriented graph encoding developed explicitly for the clustering job. This work introduces a novel Deep Learning (DL) method called Deep Attentional Implanted Graph Clustering (DAIGC), designed to achieve goal-oriented clustering. Our approach centers on associated graphs to thoroughly investigate both aspects of data in graphs. The proposed DAIGC technique utilizes a Graph Attention Autoencoder (GAA) to determine the significance of nearby nodes about a target node. This allows encoding a graph's topographical structure and node value into a concise representation. Based on this representation, an interior product decoder has been trained to rebuild the graph structure. The performance of the proposed approach has been evaluated on four distinct types and sizes of real-world intricate networks, varying in vertex count from 𝑁=102 𝑡𝑜 𝑁=107. The performance of the suggested methods is evaluated by comparing them with two established and commonly used graph clustering techniques. The testing findings demonstrate the effectiveness of the proposed method in terms of processing speed and visualization compared to the state-of-the-art algorithms.

Spectral Clustering Approximation For Large Scale Crew Disruption Data Of An Airline Company For Intelligent Crew Recovery

In the airline industry, after fuel costs, the crew costs con- stitute airlines’ second-highest cost items. For this reason, an airline needs to manage the valuable crew resource effi- ciently. Deviations from plans are fact in airline business and fixing deviations from crew schedules that occurred during operations by minimizing the crew-related delays and associated costs is one of the most important opera- tional burdens of airlines. In this context, the analysis of crew disruption data is vital in order to find disruption characteristics. Clustering analysis is one of the key meth- ods for analyzing the disruption characteristics. In this context, although there have been satisfactory studies in the literature and applications in the industry for small and medium-sized airlines, there is no good solution or industry practice for airlines with extensive networks and fleets. This study aims to analyze and categorize large- scale crew disruption data of a European airline. The relationship between categories of crew disruption and variables such as flight and crew types etc., are determined, and the disruption characteristics are revealed. For this purpose, clusters hidden in the large data set are extracted by spectral clustering. Due to the large size of the input data, a new approximation approach for spectral clustering is introduced. With the help of this new approximation approach, spectral clustering techniques are applied within a limited computational power and time frame as most real world scenario require. Even if the data set is gathered from one airline, the characteristics that are derived from the data is representing most of the cases an airline may face today. and will serve as a basis for further estimation and analysis of crew disruption.

Cyber-security attack prediction using cognitive spectral clustering technique based on simulated annealing search

Data protection and security is a big challenging portion in a modern technical world against the cyber-attacks like; ransomware, man-in-the-middle, DDoS, etc. In order to overcome this scenario, there are lot of artificial intelligence framework have been introduced to detect and classify the cyber-attacks. In particular, neural networks, with their solid speculation execution ability, are capable to address an extensive variety of cyber-attacks. This article frames the training and testing of a neural network group such a way to deal with detection of cyber-attack using cognitive spectral clustering technique based on simulated annealing search method. The optimization of individual networks can be made by using adaptive memetic algorithm with simulated annealing search. It is used to enhance the neural network weights and hidden neurons respectively. This algorithm is a combination of both local and global search enhancement method and used to get rid of the premature convergence, and used to achieve the adaptive search output. The testing outcome of the proposed framework shows a better result 99.5% of overall accuracy, and effectively adaptive in terms of detecting the cyber-attacks.

Fuzzy Graph Modeling and Clustering Analysis of Nonlinear Dynamical Systems

Analyzing stability and designing control strategies for interconnected nonlinear dynamical systems poses mathematical challenges due to combinatorial growth in complexity. This paper develops a methodology integrating fuzzy graph theory with spectral clustering techniques to enable tractable certification of stability properties. Fuzzy similarity relations between state variables model imprecise couplings within the nonlinear dynamics. Representing these relations through graph adjacency matrices facilitates partitioning strongly connected states using spectral algorithms. Stability of the overall fuzzy state graph is inferred from the spectral radii of decoupled fuzzy subgraphs. The graph-theoretic abstraction provides a coarse-grained lens into nonlinear stability properties while circumventing computational barriers. The fuzzy graph modeling and spectral partitioning pipeline ultimately streamlines control synthesis targeting local clustered subdynamics. Case studies on power network stabilization, swarm navigation, and process operations showcase scalable applications to high-dimensional complex systems. The integrated fuzzy graph and spectral clustering approach provides a systematic toolkit for analysis and control of heavily interconnected nonlinear dynamical systems across engineering domains.

Clustering future scenarios based on predicted range maps

Abstract Predictions of biodiversity trajectories under climate change are crucial in order to act effectively in maintaining the diversity of species. In many ecological applications, future predictions are made under various global warming scenarios, as described by a range of different climate models. We propose a clustering methodology to synthesize and interpret the outputs of these various predictions. We propose an interpretable and flexible two‐step methodology to measure the similarity between predicted species range maps and to cluster the future scenario predictions utilizing a spectral clustering technique. We implement and provide code for this method. We find that clustering based on predicted species range maps is mainly driven by the amount of warming rather than climate model or future scenario. We contrast this with clustering based only on predicted climate variables, which is driven primarily by climate models, that is, scenarios of the same climate model are clustered together, even when the amount of warming input to the models is varied. The differences between species‐based and climate‐based clusterings illustrate that it is crucial to incorporate ecological information to understand the relevant differences between climate models. Our findings can be used to better synthesize forecasts of biodiversity change under the wide spectrum of results that emerge when considering potential future scenarios.

Reverse stress testing: Scenario design for macroprudential stress tests

AbstractWe propose a systematic algorithmic reverse‐stress testing methodology to create “worst case” scenarios for regulatory stress tests by accounting for losses that arise from distressed portfolio liquidations. First, we derive the optimal bank response for any given shock. Then, we introduce an algorithm which systematically generates scenarios that exploit the key vulnerabilities in banks' portfolio holdings and thus maximize contagion despite banks' optimal response to the shock. We apply our methodology to data of the 2016 European Banking Authority (EBA) stress test, and design worst case scenarios for the portfolio holdings of European banks at the time. Using spectral clustering techniques, we group 10,000 worst‐case scenarios into twelve geographically concentrated families. Our results show that even though there is a wide range of different scenarios within these 12 families, each cluster tends to affect the same banks. An “Anna Karenina” principle of stress testing emerges: Not all stressful scenarios are alike, but every stressful scenario stresses the same banks. These findings suggest that the precise specification of a scenario is not of primal importance as long as the most vulnerable banks are targeted and sufficiently stressed. Finally, our methodology can be used to uncover the weakest links in the financial system and thereby focus supervisory attention on these, thus building a bridge between macroprudential and microprudential stress tests.

Affinely Adjustable Robust Volt/VAr Control Without Centralized Computations

This paper proposes a completely non-centralized Volt/VAr control (VVC) algorithm for active distribution networks which are faced with voltage magnitude violations due to the high penetration of solar photovoltaics (PVs). The proposed VVC algorithm employs a two-stage architecture where the settings of the classical voltage control devices (VCDs) are decided in the first stage through a distributed optimization engine powered by the alternating direction method of multipliers (ADMM). In contrast, the PV smart inverters are instructed in the second stage through linear Q(P) decision rules - which are computed in a decentralized manner by leveraging robust optimization theory. The key to this non-centralized VVC routine is a proposed network partition methodology (NPM) which uses an electrical distance metric based on node <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$Q-|V|^{2}$</tex-math></inline-formula> sensitivities for computing an intermediate reduced graph of the network, which is subsequently divided into the final partitions using the spectral clustering technique. As a result, the final network partitions are connected, stable, close in cardinality, contain at least one PV inverter for zonal reactive power support, and are sufficiently decoupled from each other. Numerical results on the UKGDS-95 and IEEE-123 bus systems show that the non-centralized solutions match closely with the centralized robust VVC schemes, thereby significantly reducing the voltage violations compared to the traditional deterministic VVC routines.

Acoustic Emission Signal Characterisation of Failure Mechanisms in CFRP Composites Using Dual-Sensor Approach and Spectral Clustering Technique.

The characterisation of failure mechanisms in carbon fibre-reinforced polymer (CFRP) materials using the acoustic emission (AE) technique has been the topic of a number of publications. However, it is often challenging to obtain comprehensive and reliable information about individual failure mechanisms. This situation was the impetus for elaborating a comprehensive overview that covers all failure mechanisms within the framework of CFRP materials. Thus, we performed tensile and compact tension tests on specimens with various stacking sequences to induce specific failure modes and mechanisms. The AE activity was monitored using two different wideband AE sensors and further analysed using a hybrid AE hit detection process. The datasets received from both sensors were separately subjected to clustering analysis using the spectral clustering technique, which incorporated an unsupervised k-means clustering algorithm. The failure mechanism analysis also included a proposed filtering process based on the power distribution across the considered frequency range, with which it was possible to distinguish between the fibre pull-out and fibre breakage mechanisms. This functionality was particularly useful in cases where it was evident that the above-mentioned damage mechanisms exhibited very similar parametric characteristics. The results of the clustering analysis were compared to those of the scanning electron microscopy analysis, which confirmed the conclusions of the AE data analysis.

A Spectral Clustering Approach for the Evolution of the COVID-19 Pandemic in the State of Rio Grande do Sul, Brazil

The aim of this paper is to analyse the evolution of the COVID-19 pandemic in Rio Grande do Sul by applying graph-theoretical tools, particularly spectral clustering techniques, on weighted graphs defined on the set of 167 municipalities in the state with population 10,000 or more, which are based on data provided by government agencies and other sources. To respond to this outbreak, the state has adopted a system by which pre-determined regions are assigned flags on a weekly basis, and different measures go into effect according to the flag assigned. Our results suggest that considering a flexible approach to the regions themselves might be a useful additional tool to give more leeway to cities with lower incidence rates, while keeping the focus on public safety. Moreover, simulations show that the combination of pendulum migration and isolation data used in this paper leads to a coherent qualitative description of the evolution of the pandemic in Rio Grande do Sul. These simulations also confirm the dampening effect of isolation on the dissemination of the disease.

Combination Grouping Techniques and Association Rules For Marketing Analysis based Customer Segmentation

Changes in people's transaction behavior using the internet resulted in the exponential growth of e-commerce. With the growth of digital shopping transactions, it is difficult to predict customer segments and patterns using traditional mathematical models. Timely identification of emerging trends from large volumes of data plays a major role in business processes and decision making. This is different from previous research works that apply the RFM model based on K-Means Clustering to find potential customers as an ingredient in determining marketing targets. In this study, a clustering technique approach is proposed to classify customer data which is evaluated using the Davies Bouldin, Calinski Harabasz and Silhouette methods to determine the optimal number of clusters, then the results are used in the Apriori algorithm to find patterns of goods that are often purchased together. Based on the test results on the K-Means Clustering, Spectral Clustering, and Gaussian Mixture Model techniques produced 5 clusters with 76% more accurate the K-Means Clustering method than the other two methods so that it was determined as a method in the RMF model, then the results of customer grouping were used on the Apriori algorithm to find patterns of concurrent product purchases by customers that are expected to be useful in future marketing management.

An efficient supply management in water flow network using graph spectral techniques.

An efficient way of distributing water in urban cities is one of the major global challenges of our time. A Water Distribution Network (WDN) is a vital infrastructure, intended to provide fresh water to households within a city or designated boundary. Given the WDN's complexity, effective numerical techniques are required to aid in the development of an ideal monitoring system. Flow meters and gate valves should be placed in low-connected areas of the WDN with water flow reaching several regions of the network. This study proposes a general strategy for assisting water utilities in making decisions for effective water supply. The aim of the research is to use weighted spectral clustering algorithms to outline water districts while addressing hydraulic restrictions via weighted adjacency and Laplacian matrices of the weighted network. This work aims to identify influenced nodes in the network based on Eigen centrality and effectively distribute water across those nodes. This project also looks at how to measure the network's connection strength to avoid water leaks. The best clusters are found using Eigenvalues and Eigenvectors of weighted adjacency matrices and Laplacian matrices of the water network in the proposed graph spectral framework. In order to establish the optimum water network division approach, topological and graph metrics were used to compare multiple spectral clustering techniques. The proposed graph spectral approach is tested using a genuine water distribution network serving an urban area of Coimbatore city in India and offering a method for partitioning complex networks that employ the spectral graph partitioning algorithm.

A fast spectral clustering technique using MST based proximity graph for diversified datasets

Spectral clustering is a popular unsupervised learning technique used for exploratory analysis of complex datasets. In spectral clustering, the efficient construction of a sparse similarity graph is one of the primary concerns because it influences both the clustering performance as well as the computational time. The sparser the similarity graph, the faster the computation of the eigenvectors, thus improving the overall clustering time. In this paper, we propose a parameter-free method to construct a sparse proximity graph based on the intrinsic structural information of the data points. The proposed method first divides the data into several partitions and then determines the pairs of neighboring partitions using the representative points of each partition. We propose a method called inter-partition MST (IPM) to capture the local proximity information of a neighboring pair. The size of the proposed graph is O(N), where N is the number of data points. For clustering, we apply multi-way spectral clustering on the proposed sparse similarity graph. Experimental analyses demonstrate that in terms of cluster quality, computational time and sparsity of the graph, the proposed algorithm outperforms the other spectral clustering methods.

Multimodal Dimension Reduction and Subtype Classification of Head and Neck Squamous Cell Tumors.

Traditional analysis of genomic data from bulk sequencing experiments seek to group and compare sample cohorts into biologically meaningful groups. To accomplish this task, large scale databases of patient-derived samples, like that of TCGA, have been established, giving the ability to interrogate multiple data modalities per tumor. We have developed a computational strategy employing multimodal integration paired with spectral clustering and modern dimension reduction techniques such as PHATE to provide a more robust method for cancer sub-type classification. Using this integrated approach, we have examined 514 Head and Neck Squamous Carcinoma (HNSC) tumor samples from TCGA across gene-expression, DNA-methylation, and microbiome data modalities. We show that these approaches, primarily developed for single-cell sequencing can be efficiently applied to bulk tumor sequencing data. Our multimodal analysis captures the dynamic heterogeneity, identifies new and refines subtypes of HNSC, and orders tumor samples along well-defined cellular trajectories. Collectively, these results showcase the inherent molecular complexity of tumors and offer insights into carcinogenesis and importance of targeted therapy. Computational techniques as highlighted in our study provide an organic and powerful approach to identify granular patterns in large and noisy datasets that may otherwise be overlooked.

Control chart pattern recognition using spectral clustering technique and support vector machine under gamma distribution

Most studies on control chart patterns (CCPs) recognition assume that the measured values of process characteristic follow a normal distribution. However, by collecting large-size on-line datasets, it could be found that this assumption may not be tenable. In the present study, a method to combine spectral clustering technique with support vector machine (SVM) for recognizing CCPs under a gamma distribution, which is typically employed to represent various probability distributions, is proposed. Spectral clustering is a useful tool for segmenting the observation window to obtain the correct feature set. Multiple SVM classifiers are applied to recognize CCPs. Recognition accuracy and average run length (ARL) are indicators that are used to validate the CCP recognition ability of our proposed method. Based on the comparative studies, our proposed method in the recognition efficiency of most CCP types generally outperforms the Shewhart X¯ chart and EWMA chart with run rules. It is also noted that a more skewed underlying distribution always leads to a higher false alarm rate for our proposed method. A real-world case study of the tire manufacturing process is given to illustrate how our proposed method can be practically applied to identify and recognize the CCPs.

GEOMETRIC STRUCTURE GUIDED MODEL AND ALGORITHMS FOR COMPLETE DECONVOLUTION OF GENE EXPRESSION DATA.

Complete deconvolution analysis for bulk RNA-seq data is important and helpful to distinguish whether the differences of disease-associated GEPs (gene expression profiles) in tissues of patients and normal controls are due to changes in cellular composition of tissue samples, or due to GEPs changes in specific cells. One of the major techniques to perform complete deconvolution is nonnegative matrix factorization (NMF), which also has a wide-range of applications in the machine learning community. However, the NMF is a well-known strongly ill-posed problem, so a direct application of NMF to RNA-seq data will suffer severe difficulties in the interpretability of solutions. In this paper, we develop an NMF-based mathematical model and corresponding computational algorithms to improve the solution identifiability of deconvoluting bulk RNA-seq data. In our approach, we combine the biological concept of marker genes with the solvability conditions of the NMF theories, and develop a geometric structures guided optimization model. In this strategy, the geometric structure of bulk tissue data is first explored by the spectral clustering technique. Then, the identified information of marker genes is integrated as solvability constraints, while the overall correlation graph is used as manifold regularization. Both synthetic and biological data are used to validate the proposed model and algorithms, from which solution interpretability and accuracy are significantly improved.

3D Quantum Cuts for automatic segmentation of porous media in tomography images

Binary segmentation of volumetric images of porous media is a crucial step towards gaining a deeper understanding of the factors governing biogeochemical processes at minute scales. Contemporary work primarily revolves around primitive techniques based on global or local adaptive thresholding that have known common drawbacks in image segmentation. Moreover, the absence of a unified benchmark prohibits quantitative evaluation, which further undermines the impact of existing methodologies. In this study, we tackle the issue on both fronts. First, by drawing parallels with natural image segmentation, we propose a novel, and automatic segmentation technique, 3D Quantum Cuts (QCuts-3D) grounded on a state-of-the-art spectral clustering technique. Secondly, we curate and present a publicly available dataset of 68 multiphase volumetric images of porous media with diverse solid geometries, along with voxel-wise ground truth annotations for each constituting phase. We provide comparative evaluations between QCuts-3D and the current state-of-the-art over this dataset across a variety of evaluation metrics. The proposed systematic approach achieves a 26% increase in AUROC (Area Under Receiver Operating Characteristics) while achieving a substantial reduction of the computational complexity over state-of-the-art competitors. Moreover, statistical analysis reveals that the proposed method exhibits significant robustness against the compositional variations of porous media.

Data correlation and fuzzy inference system-based data replication in federated cloud systems

Federated cloud is a promising solution for cloud providers that enables collaboration and leasing resources among multiple cloud providers. However, resource management in such system is very challenging, as each cloud provider must maintain its own economic profit while meeting the requirement of service level agreement (SLA). In this respect, we propose a dynamic and periodic data replication strategy in federated cloud systems. It aims to guarantee the monetary profit of a cloud provider while satisfying its users’ requirements in terms of response time and minimum availability. To identify replicas, we perform a periodical analysis of the users’ tasks using the spectral clustering technique to extract the existing correlations between remote data related to SLA violations. The adaptation of such correlations can significantly reduce data transfer amount and the time required to transfer it, thereby reducing tasks’ response time and the number of future SLA violations. Then, we rely on a fuzzy inference system to place the groups of replicas considering four main parameters to choose replicas placements among his owned or leased resources from other providers. Furthermore, a replicas number adjustment is performed when SLA is satisfied over time. To demonstrate the efficiency of our strategy, performance of the proposed strategy are compared alongside existing single-clouds-based and interconnected-clouds-based data replication strategies. The obtained results indicate that our strategy decreases the amount of SLA violations while preserving the monetary profit of providers.

Metamodeling and On-Line Clustering for Loss-of-Flow Accident Precursors Identification in a Superconducting Magnet Cryogenic Cooling Circuit

In the International Thermonuclear Experimental Reactor, plasma is magnetically confined with Superconductive Magnets (SMs) that must be maintained at the cryogenic temperature of 4.5 K by one or more Superconducting Magnet Cryogenic Cooling Circuits (SMCCC). To guarantee cooling, Loss-of-Flow Accidents (LOFAs) in the SMCCC are to be avoided. In this work, we develop a three-step methodology for the prompt detection of LOFA precursors (i.e., those combinations of component failures causing a LOFA). First, we randomly generate accident scenarios by Monte Carlo sampling of the failures of typical SMCCC components and simulate the corresponding transient system response by a deterministic thermal-hydraulic code. In this phase, we also employ quick-running Proper Orthogonal Decomposition (POD)-based Kriging metamodels, adaptively trained to reproduce the output of the long-running code, to decrease the computational time. Second, we group the generated scenarios by a Spectral Clustering (SC) employing the Fuzzy C-Means (FCM), in order to identify the main patterns of system evolution towards abnormal states (e.g., a LOFA). Third, we develop an On-line Supervised Spectral Clustering (OSSC) technique to associate time-varying parameters measured during plant functioning to one of the prototypical groups obtained, which may highlight the related LOFA precursors (in terms of SMCCC components failures). We apply the proposed technique to the simplified model of a cryogenic cooling circuit of a single module of the ITER Central Solenoid Magnet (CSM). The framework developed promptly detects 95% of LOFA events and around 80% of the related precursors.