Means Clustering Research Articles

Abstract 7508: Distribution prophecy of circulating tumor cell clusters in CTC populace patients of epithelial cancers

Abstract Background: Role of CTCs in metastatic cancers to predict the % prediction of overall survival has been well-established. The effectiveness of three- or six-months adjuvant therapy in colorectal cancer estimation showed association of CTCs with the emergence of resistant cell clones. The presence of CTCs with clusters indicates an aggressiveness of the epithelial cancers. However, the presence of CTC clusters has not been evaluated in large populations. Here, we demonstrate the distribution prophecy of CTCs and CTC clusters in epithelial cancer patients. Methods: Retrospectively, 3458 patients' blood sample was analyzed for the presence and distribution of CTCs and CTC clusters using DCGI approved OncoDiscover platform having immunomagnetic multicomponent system mediated by anti EpCAM antibody. 1.5 mL of peripheral blood was analyzed to capture cells and clusters from Head & Neck, breast, and lung cancer patients. Earlier the sensitivity, specificity and accuracy of OncoDiscover assay was presented. CTCs and clusters were identified with CK 18 +ve, DAPI + ve and CD45 -ve staining using automated motorized fluorescence microscopy. CTCs clusters were defined by the presence of two or more CTCs bound together. Results: Out of 3458 epithelial cancer patients, 65.52 % patients showed the distribution of CTCs ~ 2262 (CTC numbers varied from 1-9/1.5 mL), while 7.54% patients showed CTC clusters (261 clusters). Total number of captured CTCs and clusters were 19345 (mean CTCs and cluster distribution was 5.59), while CTC were predominantly in 19037 numbers (98.41%) and clusters were 308 (1.59 %). Highest number of CTS were observed in HNC (52.98%) and breast cancers (22.75%), followed by lung cancer (5.65%). While, prophecy clusters were observed in breast cancers (26.95%), followed by lung (16.23%). Conclusions: The frequency and distribution of CTCs and CTC clusters was evaluated in epithelial cancers. Patients with CTC alone and patients having CTCs as well CTC clusters represent more aggressive disease and the progression of disease. The effectiveness of adjuvant therapy in epithelial cancers can be estimated with CTC and cluster for association of treatment outmoded with an emergence of resistant cell clones. Citation Format: Jayant Khandare, Gourishankar Aland, Ganesh Khutale, Saloni Andhari, Prathamesh Patil, Meghna Garbhe, Manoj Dongare, Tanvi Deshpande, Vikas Jadhav, Nirmal Raut, Gowhar Shafi, Atul Bharde, Aravindan Vasudevan, Sreeja Jayant. Distribution prophecy of circulating tumor cell clusters in CTC populace patients of epithelial cancers [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7508.

Abstract 3556: A pan-cancer ex vivo drug screen database for next-generation pharmacogenomics and functional precision oncology

Abstract Large-scale drug screens across thousands of drugs and biological models enable pan-cancer analyses that can reveal novel insights into therapeutic response and resistance. Existing databases, such as the Cancer Dependency Map only screen established 2D cell lines, which are known to poorly translate to patients. Ex vivo models such as patient-derived cells, spheroids, and organoids, have consistently demonstrated superior translatability from drug screening responses as they better replicate the original tumor. However, the cost, complexity, and difficulty of developing and screening ex vivo models has thus far prevented the establishment of any large-scale database comparable to existing cell line databases. We present the pan-preclinical (PPC) project, a large pan-cancer database of ex vivo drug responses comprising 2.1M raw dose-response measurements with curve-level summary statistics and metadata. The PPC database is assembled from over 30 previously published ex vivo studies and contains 2,880 ex vivo models spanning 106 cancer subtypes tested against subsets of 3,023 drugs. Compounds are harmonized across studies and paired with detailed chemoinformatics derived from PubChem. Each ex vivo sample is matched to an underlying patient and paired, where available, with genomics, transcriptomics, and clinical information such as sex, treatment history, and overall survival. Two thirds of the underlying studies did not originally make the underlying drug screening data available at publication time, making the PPC database a novel resource beyond data integration. Results: To investigate the power of the PPC database, we developed a preliminary computational modeling and statistical analysis pipeline. A hierarchical Bayesian factor model was developed to estimate dose-response curves, remove batch effects across studies, and impute missing drugs. Low-dimensional projections of ex vivo drug responses show biologically meaningful clustering. Statistical analyses of both observed and imputed drug responses recapitulate standard of care drugs as significantly effective across several cancer types. Overall, we envision the PPC project laying the foundation for the next generation of large-scale pharmacogenomic analyses and aiding in the coming era of functional precision oncology. Citation Format: Anneliese Markus, Karl Pichotta, Jeffrey Quinn, Jessica White, Christopher Tosh, Jinrui Liu, Erin Coyne, Wesley Tansey. A pan-cancer ex vivo drug screen database for next-generation pharmacogenomics and functional precision oncology [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3556.

Genetic Divergence Analysis of Wheat (Triticum aestivum L.) Genotypes

A laboratory experiment was carried out with 30 indigenous genotypes of bread wheat along with three checks in a complete randomized design for divergence analysis. The trial was conducted at Seed Technology laboratory of Acharya Narendra Deva University of Agriculture and Technology Kumarganj, Ayodhya during 2020-21. The observations were recorded on thirteen-character Test weight (1000-grain weight), seed width (mm), seed length (mm), shoot length, root length, seedling length, seedling dry weight, germination (%), first count, final count, vigour index-I, vigour index-II. The 30 genotypes grouped into 5 clusters resulted in cluster I and V emerging with highest number of entries as both were constituted by 9 entries followed by Cluster III having 6 genotypes and cluster II and VI having 4 genotypes respectively. The maximum intra cluster distance was estimated in the case of Cluster II (2.630) followed by cluster I (2.618), Cluster III (2.545), cluster IV (2.512), and cluster V (2.148). The highest inter-cluster distance was observed between clusters III and IV (6.062) Followed by clusters III and V (4.632), II and IV (4.489), cluster II and V ( 4.304). The minimum inter cluster was observed between II and III (3.317) followed by cluster IV and V ( 3.337) and cluster I and V (3.404). The cluster mean of 13 different characters for most of the character's highest cluster mean was observed in clusters IV and V and lowest cluster mean observed in cluster III and II.

DeepFore: A Deep Reinforcement Learning Approach for Power Forecasting in Renewable Energy Systems

An open network known as the “energy internet” links every component of the whole energy supply chains, from the generations. Due to their ability to mimic regional flow dynamics that have an impact on wind farm production, regional meteorological models are increasingly being used as a general tool for wind resource forecasting. In this study, higher vertical and horizontal resolutions WRF (weather research and forecasting) paradigm simulation are used to anticipate and validate production for a genuine onshore wind farm. This paper proposed a DeepFore which is a power forecasting system for hybrid renewable energy systems. Initially, the dataset is generated by the hybrid system. This data is preprocessed to improve the quality of the data by incorporating, filtering and outlier detection techniques. Then, this enriched data is fed into K++ means clustering algorithm to separate the normal data from faulty data. With the normal and original data, Teaching-Learning based optimization algorithm attempts to realize the optimal features which are important for forecasting. Finally, Deep SARSA which is deep reinforcement learning algorithm is incorporated to determine the power generated by the hybrid system. Better winds energy prediction estimations enable more efficient utilization of the produced electricity, according to computational models.

A subtype of schizophrenia patients with altered methylation level of genes related to immune cell activity.

Epigenetic changes are plausible molecular sources of clinical heterogeneity in schizophrenia. A subgroup of schizophrenia patients with elevated inflammatory or immune-dysregulation has been reported by previous studies. However, little is known about epigenetic changes in genes related to immune activation in never-treated first-episode patients with schizophrenia (FES) and its consistency with that in treated long-term ill (LTS) patients. In this study, epigenome-wide profiling with a DNA methylation array was applied using blood samples of both FES and LTS patients, as well as their corresponding healthy controls. Non-negative matrix factorization (NMF) and k -means clustering were performed to parse heterogeneity of schizophrenia, and the consistency of subtyping results from two cohorts. was tested. This study identified a subtype of patients in FES participants (47.5%) that exhibited widespread methylation level alterations of genes enriched in immune cell activity and a significantly higher proportion of neutrophils. This clustering of FES patients was validated in LTS patients, with high correspondence in epigenetic and clinical features across two cohorts. In summary, this study demonstrated a subtype of schizophrenia patients across both FES and LTS cohorts, defined by widespread alterations in methylation profile of genes related to immune function and distinguishing clinical features. This finding illustrates the promise of novel treatment strategies targeting immune dysregulation for a subpopulation of schizophrenia patients.

A high-fidelity digital twin predictive modeling of air-source heat pump using FCPM-SBLS algorithm

This paper proposes an innovative Digital Twin (DT) model to predict air-source heat pumps' (ASHP) coefficient of performance (COP) using a combination of fuzzy (c + p) means clustering (FCPM) and the stacked broad learning system (SBLS) algorithm (FCPM-SBLS). The SBLS algorithm is adopted to establish the structure of the DT model, considering the imperative of tracking real-time performance changes in ASHP applications. To enhance the fitting and generalization ability of the DT model, FCPM is employed to partition the dataset into subclasses, allowing for the creation of sub-models specifically tailored to each subclass. Moreover, an incremental-full evolution strategy of the DT model is proposed to track changes in ASHP performance. The DT model's validation is conducted using data collected at a railway passenger station. Results demonstrate that the FCPM-SBLS method has commendable predictive performance, with respective mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) values of 0.045, 0.012, and 0.252. Additionally, the proposed evolution strategy ensures timely updates for tracking ASHP performance changes. Through analysis of the evolution performance of DT model straddling over years, the updated model shows a 63.1% decrease in MAPE compared to the non-updated model. This study is not only conducive to advancing DT modeling in the field of HVAC systems, but also has practical significance for improving the energy efficiency and performance monitoring of ASHP.

The illusion of the Holy Grail of decoupling: Are there countries with relatively high SDGI and moderately low ecological footprint?

The development of sustainability indicators at the national level emerged due to the limitations of using GDP as a measure of well-being, sustainability, and resilience. Over time, various indicators and rankings have been formulated, with a shift in focus from solely economic growth to a more encompassing perspective. The objective of this study was to create a new ranking, based on the integration of two methodologies, namely UN Sustainable Development Goals Index (SDGI), and the Global Footprint Network's Ecological Footprint (EF), in order to identify meaningful clusters of countries based on both measures. Hierarchical clustering was utilized to group countries, while the Nearest Neighbour method was employed to filter out outliers, and the Ward method determined the final clusters. Additionally, the Pearson's correlation coefficient was calculated to assess the relationship between the 17 SDGIs and the EF. The clustering outcomes revealed that a three-cluster solution can be considered satisfactory. The results obtained with the new method demonstrate that the environmental dimension of SDGI is a sufficient metric for environmental sustainability in terms of ranking countries.

Shape-induced clusters of ellipsoids during triaxial compression: A multiscale analysis using LS-DEM

In this work, we numerically investigate the quasi-static shear behavior of ellipsoids under triaxial compression using the level set discrete element method (LS-DEM). Assemblies composed of ellipsoids with various aspect ratios are prepared at the densest states and then sheared to the critical state. Macroscopically, the stress and dilation behaviors are strongly affected by the particle shape, with the spheres having the least shear strength and dilatancy. At the particle scale, more ellipsoidal particles are more resistant to particle rotations and can effectively increase friction mobilizations.We identify the clusters in assemblies via the three-dimensional cluster labeling algorithm and then analyze the structural and mechanical properties of clusters. Based on our analysis, we find that the clusters exhibit the power-law decay in the cluster size distribution and have fractal structures. Upon shearing, the clusters tend to self-organize to gain mechanical stability, indicated by the increasing cluster stress ratio, and mainly support the deviatoric stresses in the assemblies. The mean cluster stress ratio is found to be linearly related to the macroscopic shear strength at the critical state, where more ellipsoidal shapes can gain higher cluster stress ratios, contributing to higher shear strength for the granular assembly. Microscopically, the cluster contributes more significantly to geometrical anisotropy terms while comparably to mechanical ones compared to the non-cluster.

AI-Assisted Enhanced Composite Metric-Based Intrusion Detection System for Secured Cyber Internet Security for Next-Generation Wireless Networks

The prevalence of distributed denial of service (DDoS) flooding assaults is one of the most serious risks to cloud computing security. These types of assaults have as their primary objective the exhaustion of the system’s available resources, that is, the target of the attack, in order to make the system in question unavailable to authorized users. Internet thieves often conduct flooding assaults of the kind known as DDoS, focusing primarily on the application and network levels. When the computer infrastructure is multi-mesh-geo distributed, includes multi-parallel services, and a high number of domains, it may be difficult to detect assaults. This is particularly true when a substantial number of domains are present. When there are a big number of independent administrative users using the services, the situation gets more complicated. The purpose of this body of research is to identify signs that may be utilized to detect DDoS flooding assaults; this is its main objective. As a result, throughout the course of our study, we established a composite metric that considers application, system, network, and infrastructure elements as possible indicators of the incidence of DDoS assaults. According to our research, DDoS assaults may be triggered by a combination of variables. Investigations of simulated traffic are being conducted in the cloud. High traffic may be the result of flooding assaults. The composite metric-based intrusion detection system will be the name of a one-of-a-kind intrusion detection system (IDS) that has been agreed upon ICMIDS. This system will use [Formula: see text]-Means clustering and the Genetic Algorithm (GA) to detect whether an effort has been made to flood the cloud environment. CMIDS employs a multi-threshold algorithmic strategy in order to identify malicious traffic occurring on a cloud-based network. Cisco has created this technology. This strategy necessitates a comprehensive investigation of all factors, which is crucial for assuring the continuation of cloud-based computing-based activities. This monitoring system involves the development, administration, and storage of a profile database, denoted as Profile DB. This database is used for recording and using the composite metric for each virtual machine. The results of a series of tests are compared to the ISCX benchmark dataset and statistical settings. The results indicate that ICMIDS has a reasonably high detection rate and the lowest false alarm rate in the majority of situations examined during the series of tests done to validate and verify its efficacy. This was shown by the fact that ICMIDS had the lowest false alarm rate among all examined conditions.

Brain connectivity in status epilepticus as a predictor of outcome: A diffusion tensor imaging study.

We aimed to explore structural connectivity in status epilepticus. We enrolled participants who underwent diffusion tensor imaging. We applied graph theory to investigate structural connectivity. We compared the structural connectivity measures between patients and healthy controls and between patients with poor (modified Rankin Scale [mRS] >3) and good (mRS ≤3) admissionoutcomes. We enrolled 28 patients and 31 healthy controls (age 65.5 vs.62.0 years, p=.438). Of these patients, 16 and 12 showed poor and good admissionoutcome (age 65.5vs.62.0 years, p=.438). The assortative coefficient (-0.113vs. -0.121, p=.021), mean clustering coefficient (0.007vs.0.006, p=.009), global efficiency (0.023vs.0.020, p=.009), transitivity (0.007vs.0.006, p=.009), and small-worldness index (0.006vs.0.005, p=.021) were higher in patients with status epilepticus than in healthy controls. The assortative coefficient (-0.108vs. -0.119, p=.042), mean clustering coefficient (0.007vs.0.006, p=.042), and transitivity (0.008vs.0.007, p=.042) were higher in patients with poor admissionoutcome than in those with good admissionoutcome. MRS score was positively correlated with structural connectivity measures, including the assortative coefficient (r=0.615, p=.003), mean clustering coefficient (r=0.544, p=.005), global efficiency (r=0.515, p=.007), transitivity (r=0.547, p=.007), and small-worldness index (r=0.435, p=.024). We revealed alterations in structural connectivity, showing increased integration and segregation in status epilepticus, which might be related with neuronal synchronization. This effect was more pronounced in patients with a poor admissionoutcome, potentially reshaping our understanding for comprehension of status epilepticus mechanisms and the development of more targeted treatments.

Academic Librarian Search Committee Members Identify Inclusivity Concerns with On-Campus Interview Practices

A Review of: Houk, K. & Neilson, J. (2023). Inclusive hiring in academic libraries: A qualitative analysis of attitudes and reflections of search committee members. College and Research Libraries, 84(4), 568-588. https://doi.org/10.5860/crl.84.4.568 Objective – To understand how academic librarian search committee members’ perceptions and attitudes affect the equitability and inclusiveness of the on-campus interview process. Design – Thematic text analysis of open-ended responses to short-answer questions from an online survey. Setting – Online survey conducted between February and March of 2021. Subjects – 166 academic librarians who had served on hiring committees for academic librarians in North America between 2016 and 2020. Methods – Participants for the 33-question survey were recruited through several academic library listservs and social media postings on Facebook, LinkedIn, and Twitter. The researchers first individually reviewed and coded all responses for short answer survey questions, then reviewed the codes together. Finally, a thematic map was developed after the researchers reached a consensus on their shared approach to coding and generating clusters of meanings. Main Results – Six major clusters were identified through thematic coding of participants’ text responses concerning their experiences of on-campus interview practices as hiring committee members. These themes represented challenges to the inclusiveness of academic librarian searches, and included search committees’ treatment of the interview process as either intentional or situational tests (1), reliance on the ambiguously defined selection criteria of fit (2), experience with varying levels of commitment to diversity, equity, inclusion, antiracism, and accessibility (DEIAA) values (3), frustration with prevalence of institutional bureaucracy throughout the hiring process (4), and uneven adoptions of inclusive hiring (5) or reflective practices (6). The researchers also noted a common respondent mistake of misinterpreting equal (i.e., identical) treatment of candidates as evidence of equitable interview practices. Conclusion – Findings from this study highlighted the importance of academic institutions and hiring committees adopting reflective practices to critically and intentionally incorporate DEIAA-informed practices in planning and conducting academic librarian searches. The authors also stressed the need to reduce possible biases in hiring practices favoring candidates who conforms to White, ableist, and heteronormative culture and values. Examples of these efforts included considering the necessity of each interview element for assessing candidate performances, proactively ensuring full accessibility of the interview itinerary, and operationalizing the definition of “fit” in assessing candidates’ abilities.

A Performance Prediction Method Utilizing Time-Dependent Subsystem Transfers between Family Systems

Based on cluster system theory and the Markov process, a performance prediction method utilizing time-dependent subsystem transfers between family systems is proposed in this paper. The family system is divided via the mean clustering method, with the key performance parameters of subsystems utilized as identification parameters. According to the transition quantity of subsystems in the family systems, the transition probability of subsystems between family systems is described via the Markov process. The transition matrix between subsystems is established by dividing multiple intervals of key performance states. The inter-family transfer matrix and the current family system label of the subsystem are updated in real time. Thus, the transition probability of any subsystem and the total number of subsystems to be transferred to the failure-state family system can be judged, and the remaining life can be further determined. Using the real-world monitoring dataset from the FAST Telescope, the effectiveness and accuracy of the method are verified. Due to the representativeness of family systems to subsystems and the powerful transfer-describing ability of Markov processes, the proposed method shows superiority in online prediction and performance evaluation compared to the fault data-based method, such as improvements in rapidity and accuracy. In addition, the proposed method can be used to evaluate overall reliability without reference samples, thus making the prediction method more practical in complex, large systems with small or even zero sample conditions.

Efficient Algorithm for K-Multiple-Means

K-Multiple-Means is an extension of K-means for the clustering of multiple means used in many applications, such as image segmentation, load balancing, and blind-source separation. Since K-means uses only one mean to represent each cluster, it fails to capture non-spherical cluster structures of data points. However, since K-Multiple-Means represents the cluster by computing multiple means and grouping them into specified c clusters, it can effectively capture the non-spherical clusters of the data points. To obtain the clusters, K-Multiple-Means updates a similarity matrix of a bipartite graph between the data points and the multiple means by iteratively computing the leading c singular vectors of the matrix. K-Multiple-Means, however, incurs a high computation cost for large-scale data due to the iterative SVD computations. Our proposal, F-KMM, increases the efficiency of K-Multiple-Means by computing the singular vectors from a smaller similarity matrix between the multiple means obtained from the similarity matrix of the bipartite graph. To compute the similarity matrix of the bipartite graph efficiently, we skip unnecessary distance computations and estimate lower bounding distances between the data points and the multiple means. Theoretically, the proposed approach guarantees the same clustering results as K-Multiple-Means since it can exactly compute the singular vectors from the similarity matrix between the multiple means. Experiments show that our approach is several orders of magnitude faster than previous clustering approaches that use multiple means.

Using k means clustering and integrated 2 DULV'S topsis method for geolocational data

Using k means clustering and integrated 2 DULV'S topsis method for geolocational data

A Lightweight Mutual Privacy Preserving $k$-Means Clustering in Industrial IoT

A Lightweight Mutual Privacy Preserving $k$-Means Clustering in Industrial IoT

Phenotypic clusters of type 2 diabetes mellitus among North Indians reveal higher levels of insulin deficiency along with insulin resistance

BackgroundType 2 diabetes is now considered a heterogenous disease. Distinct clusters have been identified with patterns varying between Europeans and South Asians as well as between South Indians who have described a novel cluster; Combined Insulin-Resistant and Deficient Diabetes, and individuals from West and East India who have reported that insulin deficiency is the primary driver of heterogeneity. Therefore, North Indian patients may also have a distinct, novel clustering pattern due to unique genetic, epigenetic, and environmental factors. We aim to identify clusters of type 2 diabetes in North Indians and to describe the different characteristics of these clusters. MethodsThe K value for the optimal number of clusters was obtained from two-step clustering. K means clustering was done with this K value using SPSS 29.0 software. Variables used for clustering were age, BMI, HbA1c, HOMA-beta, HOMA-IR, and waist circumference. ResultsFour phenotypically different clusters were identified in 469 individuals with type 2 diabetes. Cluster 1 was severe insulin deficient diabetes (15%), Cluster 2 was severe insulin resistant diabetes (22%), Cluster 3 was moderate obesity-related diabetes (35%), and Cluster 4 was moderate age-related diabetes (27%). Clusters 1 and 2 were similar to earlier studies but in different proportions. Clusters 3 and 4 characteristics were different from earlier studies, with greater impairment in beta cell function and higher HbA1c levels. Significant insulin resistance was noted in all clusters. ConclusionThe phenotypic clusters of type 2 diabetes identified in the present study were characterized by high levels of insulin deficiency along with important contributions from insulin resistance.

Multi-view Subspace Clustering Based on Weighted Tensor Schatten-P Norm

In the era of advancing technology and continuous societal evolution, an abundance of voluminous data from various domains has become prevalent in the public domain. Managing this wealth of data necessitates a series of preprocessing procedures, encompassing tasks such as data storage, computation, and analysis, with the aim of unveiling intrinsic features and patterns contained within. Among these procedures, clustering stands out as a crucial step, with the primary goal of unveiling the hidden structures within the data and organizing data samples into meaningful clusters based on specific criteria. Early clustering efforts were based on a singleview. Real world data, however, often contains interrelated information, leading to the emergence of multi-view clustering. Multiview subspace clustering (T-SVD) has been widely used in recent years. However, the equal treatment of each singular value in this approach lacks relevance when the data is noisy or contaminated. In order to improve the robustness and clustering performance, this paper presents a T-SVD weighted tensor norm. In order to improve the robustness, a Schatten-P norm was proposed. This paper explores multi-view subspace clustering is based on the Schatten-P norm weighted tensor. Experiments are carried out on 6 benchmark data sets, and the results are compared with 4 existing ones. Experiments show that the proposed approach is better than the most advanced multi-view subspace clustering methods.

Study of the Impact of Prosopis juliflora on Soil moisture and Humidity

This paper aims to present the impact of invasive alien species on soil moisture over the other native species. Prosopis juliflora is a majestic, non-native species that grows abundantly over the arid and semi-arid regions especially over the southern part of Indian sub-continent. These non-native, invasive species are modifying the native bio diversity, natural irrigation and local ecosystem by alternating the soil fertility measures such as soil moisture and relative humidity of the soil. In this study, the impact of the non-native species and native species on soil moisture and atmospheric humidity are considered for the analysis of the effect of the Prosopis juliflora and the variation in the conditions are visualized using the k- means clustering technique. The soil moisture at a depth of 2 meters and 1 meter and the air humidity is compared for regions in the presence of the nonnative species and in the absence of nonnative species. The results indicate that the non-native species has a negative impact on the cultivating land, spoiling its fertility measures by reducing its soil moisture content. The study provides evidence for the need to take necessary actions to eradicate species such as Prosopis juliflora and in turn to protect the native vegetation and develop management strategies to control the spread of the species.

High-density cluster core-based [formula omitted]-means clustering with an unknown number of clusters

The k-means algorithm, known for its simplicity and adaptability, faces challenges related to manual cluster number selection and sensitivity to initial centroid placement. This paper introduces an innovative framework aimed at overcoming these challenges. By proposing a data-driven cluster number estimation method and a robust initialization strategy based on high-density cluster cores, our approach revolutionizes k-means, unlocking its full unsupervised potential and ensuring superior performance, even in scenarios involving overlapping clusters. The method employs a novel density-based technique to accurately identify cluster cores, resulting in substantial improvements over existing methods. Rigorous experimentation on synthetic and real-world datasets demonstrates an average performance enhancement of 15% in terms of the Adjusted Rand Index for datasets with overlapping clusters, surpassing the capabilities of state-of-the-art density-based clustering methods and traditional k-means. Moreover, our method autonomously determines the optimal number of clusters, facilitating true unsupervised learning and eliminating the impact of initial centroid placement on clustering outcomes. This leads to stable and consistent results, addressing key limitations of the conventional k-means algorithm. The practical applicability of our approach is exemplified in image segmentation tasks, showcasing its versatility and reliability in real-world scenarios.

Invariance properties of limiting point processes and applications to clusters of extremes

Abstract Motivated by examples from extreme value theory, but without using the theory of regularly varying time series or any assumptions about the marginal distribution, we introduce the general notion of a cluster process as a limiting point process of returns of a certain event in a time series. We explore general invariance properties of cluster processes that are implied by stationarity of the underlying time series. Of particular interest in applications are the cluster size distributions, and we derive general properties and interconnections between the size of an inspected and a typical cluster. While the extremal index commonly used in extreme value theory is often interpreted as the inverse of a “mean cluster size”, we point out that this only holds true for the expected value of the typical cluster size, caused by an effect very similar to the inspection paradox in renewal theory.