Search Results (15)

This study presents an integrated and reproducible framework for within-tier screening of potential healthcare accessibility in Bangkok. Facilities in three service tiers (primary 294 units, regular 75, referral 29) are analyzed using point-pattern diagnostics, Voronoi geometric partitions, population-weighted allocation from subdistrict controls, and cumulative network travel-time isochrones. Spatial diagnostics indicate clustering among primary care units, a near-random configuration for regular units, and modest dispersion for referral hospitals, summarized by observed-to-expected nearest-neighbor ratios of approximately 0.77, 1.05, and 1.19, respectively. Voronoi partitions translate these distributions into geometric units that enlarge with increasing inter-facility spacing, while population-weighted assignments reveal higher population-per-partition-area burdens in the outer east and southwest. Isochrone maps (5–60 min rings) show central corridors with short travel times and peripheral areas where potential access declines. Interpreted against statutory planning intent, the maps indicate broad consistency of siting with high-intensity zones, alongside residual gaps at residential fringes. Framed as repeatable indicators of access and coverage, the workflow contributes to measuring and monitoring urban health sustainability under universal health coverage and routine planning cycles. The framework yields transparent indicators that support monitoring, priority setting, and incremental adjustments within each tier. Limitations include planar proximity assumptions, uniform areal weighting, single-mode modeled travel times without temporal variation, and the absence of capacity measures, motivating future work on capacity-weighted partitions, minimal dasymetric refinements, and time-dependent multimodal scenarios. Full article

Federated learning (FL) for skeleton-based action recognition remains underexplored, particularly under strong client heterogeneity where regular FedAvg tends to cause client drift and unstable convergence. We introduce Clustered Federated Spatio-Temporal Graph Attention Networks (CF-STGAT), a clustered FL framework that leverages attention-derived spatio-temporal statistics from local STGAT models to dynamically group clients and perform attention-weighted inter-cluster fusion that gently align cluster models. Concretely, the server periodically extracts multi-head parameter-based attention descriptors, normalizes and projects them via PCA, and applies K-means to form clusters; a global reference is then computed by attention–similarity weighting and used to regularize each cluster model with a lightweight fusion step. On NTU RGB+D 60/120(NTU 60/120), CF-STGAT consistently outperforms strong FL baselines with the STGAT backbone, yielding absolute top-1 gains of +0.84/+4.09 (NTU 60, X-Sub/X-Setup) and +7.98/+4.18 (NTU 120, X-Sub/X-Setup) over FedAvg, alongside smoother per-client trajectories and lower terminal test loss. Ablations indicate that attention-guided clustering and inter-cluster fusion are complementary: clustering reduces within-group variance whereas fusion limits cross-cluster divergence. The approach keeps local training unchanged and adds only server-side statistics and clustering. Full article

Deep clustering aims to discover meaningful data groups by jointly learning representations and cluster probability distributions. Yet existing methods rarely consider the underlying information characteristics of these distributions, causing ambiguity and redundancy in cluster assignments, particularly when different augmented views are used. To address this issue, this paper proposes a novel information-principled deep clustering framework for learning invariant, redundancy-reduced, and discriminative cluster probability distributions, termed ICIRD. Specifically, ICIRD is built upon three complementary modules for cluster probability distributions: (i) conditional entropy minimization, which increases assignment certainty and discriminability; (ii) inter-cluster mutual information minimization, which reduces redundancy among cluster distributions and sharpens separability; and (iii) cross-view mutual information maximization, which enforces semantic consistency across augmented views. Additionally, a contrastive representation mechanism is incorporated to provide stable and reliable feature inputs for the cluster probability distributions. Together, these components enable ICIRD to jointly optimize both representations and cluster probability distributions in an information-regularized manner. Extensive experiments on five image benchmark datasets demonstrate that ICIRD outperforms most existing deep clustering methods, particularly on fine-grained datasets such as CIFAR-100 and ImageNet-Dogs. Full article

To address the challenges of small-sample rock fine classification—such as overfitting caused by limited sample size and the increased complexity resulting from high inter-class similarity—this study proposes a Stacking ensemble method tailored for small-sample rock image classification. Using a dataset of seven rock categories provided by the BdRace platform, 38 features were extracted across three dimensions—color, texture, and grain size—through grayscale thresholding, HSV color space analysis, gray-level co-occurrence matrix computation, and morphological analysis. The interrelationships among features were evaluated using Spearman correlation analysis and hierarchical clustering, while a voting-based fusion strategy integrated Lasso regularization, gray correlation analysis, and variance filtering for feature dimensionality reduction. The Whale Optimization Algorithm (WOA) was employed to perform global optimization on the base learners, including Random Forest (RF), K-Nearest Neighbors (KNN), Naive Bayes (NBM), and Support Vector Machine (SVM), with Logistic Regression serving as the meta-classifier to construct the final Stacking ensemble model. Experimental results demonstrate that the Stacking method achieves an average classification accuracy of 85.41%, with the highest accuracy for black coal identification (97.16%). Compared to the single models RF, KNN, NBM, and SVM, it improves accuracy by 7.27%, 8.64%, 6.79%, and 6.94%, respectively. Evidently, the Stacking model integrates the strengths of individual models, significantly enhancing recognition accuracy. This research not only improves rock identification accuracy and reduces exploration costs but also advances the intelligent transformation of geological exploration, demonstrating considerable engineering application value. Full article

Recently, a growing number of researchers have focused on multi-view subspace clustering (MSC) due to its potential for integrating heterogeneous data. However, current MSC methods remain challenged by limited robustness and insufficient exploitation of cross-view high-order latent information for clustering advancement. To address these challenges, we develop a novel MSC framework termed TMSC-TNNBDR, a tensorized MSC framework that leverages t-SVD based tensor nuclear norm (TNN) regularization and block diagonal representation (BDR) learning to unify view consistency and structural sparsity. Specifically, each subspace representation matrix is constrained by a block diagonal regularizer to enforce cluster structure, while all matrices are aggregated into a tensor to capture high-order interactions. To efficiently optimize the model, we developed an optimization algorithm based on the inexact augmented Lagrange multiplier (ALM). The TMSC-TNNBDR exhibits both optimized block-diagonal structure and low-rank properties, thereby enabling enhanced mining of latent higher-order inter-view correlations while demonstrating greater resilience to noise. To investigate the capability of TMSC-TNNBDR, we conducted several experiments on certain datasets. Benchmarking on circumscribed datasets demonstrates our method’s superior clustering performance over comparative algorithms while maintaining competitive computational overhead. Full article

Federated learning (FL) has emerged as a powerful framework for decentralized model training, preserving data privacy by keeping datasets localized on distributed devices. However, data heterogeneity, characterized by significant variations in size, statistical distribution, and composition across client datasets, presents a persistent challenge that impairs model performance, compromises generalization, and delays convergence. To address these issues, we propose FedDPA, a novel framework that utilizes dynamic prototypical alignment. FedDPA operates in three stages. First, it computes class-specific prototypes for each client to capture local data distributions, integrating them into an adaptive regularization mechanism. Next, a hierarchical aggregation strategy clusters and combines prototypes from similar clients, which reduces communication overhead and stabilizes model updates. Finally, a contrastive alignment process refines the global model by enforcing intra-class compactness and inter-class separation in the feature space. These mechanisms work in concert to mitigate client drift and enhance global model performance. We conducted extensive evaluations on standard classification benchmarks—EMNIST, FEMNIST, CIFAR-10, CIFAR-100, and Tiny-ImageNet 200—under various non-identically and independently distributed (non-IID) scenarios. The results demonstrate the superiority of FedDPA over state-of-the-art methods, including FedAvg, FedNH, and FedROD. Our findings highlight FedDPA’s enhanced effectiveness, stability, and adaptability, establishing it as a scalable and efficient solution to the critical problem of data heterogeneity in federated learning. Full article

Molecular network conformations in the over-stoichiometric arsenoselenides of canonical As_xSe_100−x system (40 ≤ x ≤ 100) covering a full row of thioarsenide-type As₄Se_n entities (0 ≤ n ≤ 6) are analyzed with ab initio quantum-chemical modeling employing cluster-simulation code CINCA. Native (melt-quenching-derived) and nanostructurization-driven (activated by nanomilling) polymorphic and polyamorphic transitions initiated by decomposition of the thioarsenide-type As₄Se_n cage molecules and incorporation of their remnants into a newly polymerized arsenoselenide network are identified on the developed map of molecular network clustering in a binary As-Se system. Within this map, compositional counter lines corresponding to preferential molecular or network-forming tendencies in the examined arsenoselenides are determined, explaining that network-crystalline conformations prevail in the boundary compositions corresponding to n = 6 and n = 0, while molecular-crystalline ones dominate inside the rows corresponding to n = 4 and n = 3. A set of primary and secondary equilibrium lines is introduced in the developed clustering map to account for inter-phase equilibria between the most favorable (regular) and competitive (irregular) thioarsenide phases. Straightforward interpretation of decomposition reactions accompanying induced crystallization and amorphization (reamorphization) in the arsenoselenides is achieved, employing disproportionality analysis of thioarsenide-type molecular network conformations within the reconstructed clustering map. The preference of network clustering at the boundaries of the As₄Se_n row (at n = 6 and n = 0) disturbs inter-phase equilibria inside this row, leading to unexpected anomalies, such as absence of stable tetra-arsenic triselenide As₄Se₅ molecular-crystalline species; polyamorphism in mechanoactivated As₄Se_n alloys (2 ≤ n ≤ 6); breakdown in the glass-forming ability of melt-quenching-derived arsenoselenides in the vicinity of tetra-arsenic biselenide As₄Se₂ composition; plastically and normally crystalline polymorphism in tetra-arsenic triselenide As₄Se₃-based thioarsenides, and so on. Full article

Aiming at the problems of existing time series data clustering methods, such as the lack of similarity metric universality, the influence of dimensional catastrophe, and the limitation of feature expression ability, a time series data clustering method based on unsupervised contrasting learning (UCL-TSC) is proposed. The method first utilizes Residual, TCN, and CNN-TCN to construct multi-view representations of spatial, temporal, and spatial–temporal features of time series data, and adaptively fuses complementary information to enhance feature extraction capabilities. Subsequently, positive and negative sample pairs are constructed based on nearest neighbor and pseudo-clustering label information. Finally, a contrast loss function consisting of feature loss, clustering loss, and a regularization term is designed to facilitate the model in achieving compact intra-cluster and sparse inter-cluster clustering effects in the clustering process. The experimental results on the UCR dataset show that UCL-TSC performs well with respect to several evaluation indexes, such as clustering accuracy, normalized information degree, and purity, and is more effective in learning time series data features and achieving accurate clustering compared to traditional clustering and deep clustering methods. Full article

Networks offer a compact representation of complex systems such as social, communication, and biological systems. Traditional network models are often inadequate to capture the diverse nature of contemporary networks, which may exhibit temporal variation and multiple types of interactions between entities. Multilayer networks (MLNs) provide a more comprehensive representation by allowing interactions between nodes to be represented by different types of links, each reflecting a distinct type of interaction. Community detection reveals meaningful structure and provides a better understanding of the overall functioning of networks. Current approaches to multilayer community detection are either limited to community detection over the aggregated network or are extensions of single-layer community detection methods with simplifying assumptions such as a common community structure across layers. Moreover, most of the existing methods are limited to multiplex networks with no inter-layer edges. In this paper, we introduce a spectral-clustering-based community detection method for two-layer MLNs. The problem of detecting the community structure is formulated as an optimization problem where the normalized cut for each layer is minimized simultaneously with the normalized cut for the bipartite network along with regularization terms that ensure the consistency of the within- and across-layer community structures. The proposed method is evaluated on both synthetic and real networks and compared to state-of-the-art methods. MLNs. The problem of detecting the community structure is formulated as an optimization problem where the normalized cut for each layer is minimized simultaneously with the normalized cut for the bipartite network along with regularization terms that ensure the consistency of the intra- and inter-layer community structures. The proposed method is evaluated on both synthetic and real networks and compared to state-of-the-art methods. Full article

Diabetic retinopathy (DR) is a leading cause of blindness in middle-aged diabetic patients. Regular screening for DR using fundus imaging aids in detecting complications and delays the progression of the disease. Because manual screening takes time and is subjective, deep learning has been used to help graders. Pre-trained or brute force CNN models are used in existing DR grading CNN-based approaches that are not suited to fundus image complexity. To solve this problem, we present a method for automatically customizing CNN models based on fundus image lesions. It uses k-medoid clustering, principal component analysis (PCA), and inter-class and intra-class variations to determine the CNN model’s depth and width. The designed models are lightweight, adapted to the internal structures of fundus images, and encode the discriminative patterns of DR lesions. The technique is validated on a local dataset from King Saud University Medical City, Saudi Arabia, and two challenging Kaggle datasets: EyePACS and APTOS2019. The auto-designed models outperform well-known pre-trained CNN models such as ResNet152, DenseNet121, and ResNeSt50, as well as Google’s AutoML and Auto-Keras models based on neural architecture search (NAS). The proposed method outperforms current CNN-based DR screening methods. The proposed method can be used in various clinical settings to screen for DR and refer patients to ophthalmologists for further evaluation and treatment. Full article

We investigated a comprehensive analysis of the mutual exciting mechanism for the dynamic of stock price trends. A multi-dimensional Hawkes-model-based approach was proposed to capture the mutual exciting activities, which take the form of point processes induced by dual moving average crossovers. We first performed statistical measurements for the crossover event sequence, introducing the distribution of the inter-event times of dual moving average crossovers and the correlations of local variation (LV), which is often used in spike train analysis. It was demonstrated that the crossover dynamics in most stock sectors are generally more regular than a standard Poisson process, and the correlation between variations is ubiquitous. In this sense, the proposed model allowed us to identify some asymmetric cross-excitations, and a mutually exciting structure of stock sectors could be characterized by mutual excitation correlations obtained from the kernel matrix of our model. Using simulations, we were able to substantiate that a burst of the dual moving average crossovers in one sector increases the intensity of burst both in the same sector (self-excitation) as well as in other sectors (cross-excitation), generating episodes of highly clustered burst across the market. Furthermore, based on our finding, an algorithmic pair trading strategy was developed and backtesting results on real market data showed that the mutual excitation mechanism might be profitable for stock trading. Full article

Superpixels group perceptually similar pixels into homogeneous sub-regions that act as meaningful features for advanced tasks. However, there is still a contradiction between color homogeneity and shape regularity in existing algorithms, which hinders their performance in further processing. In this work, a novel Contour Optimized Non-Iterative Clustering (CONIC) method is presented. It incorporates contour prior into the non-iterative clustering framework, aiming to provide a balanced trade-off between segmentation accuracy and visual uniformity. After the conventional grid sampling initialization, a regional inter-seed correlation is first established by the joint color-spatial-contour distance. It then guides a global redistribution of all seeds to modify the number and positions iteratively. This is done to avoid clustering falling into the local optimum and achieve the exact number of user-expectation. During the clustering process, an improved feature distance is elaborated to measure the color similarity that considers contour constraint and prevents the boundary pixels from being wrongly assigned. Consequently, superpixels acquire better visual quality and their boundaries are more consistent with the object contours. Experimental results show that CONIC performs as well as or even better than the state-of-the-art superpixel segmentation algorithms, in terms of both efficiency and segmentation effects. Full article

Single-cell RNA-seq (scRNA-seq) is a powerful tool to measure the expression patterns of individual cells and discover heterogeneity and functional diversity among cell populations. Due to variability, it is challenging to analyze such data efficiently. Many clustering methods have been developed using at least one free parameter. Different choices for free parameters may lead to substantially different visualizations and clusters. Tuning free parameters is also time consuming. Thus there is need for a simple, robust, and efficient clustering method. In this paper, we propose a new regularized Gaussian graphical clustering (RGGC) method for scRNA-seq data. RGGC is based on high-order (partial) correlations and subspace learning, and is robust over a wide-range of a regularized parameter $\lambda$. Therefore, we can simply set $\lambda =2$ or $\lambda =log\left(p\right)$ for AIC (Akaike information criterion) or BIC (Bayesian information criterion) without cross-validation. Cell subpopulations are discovered by the Louvain community detection algorithm that determines the number of clusters automatically. There is no free parameter to be tuned with RGGC. When evaluated with simulated and benchmark scRNA-seq data sets against widely used methods, RGGC is computationally efficient and one of the top performers. It can detect inter-sample cell heterogeneity, when applied to glioblastoma scRNA-seq data. Full article

With the rapid development in sensing technology, data mining, and machine learning fields for human health monitoring, it became possible to enable monitoring of personal motion and vital signs in a manner that minimizes the disruption of an individual’s daily routine and assist individuals with difficulties to live independently at home. A primary difficulty that researchers confront is acquiring an adequate amount of labeled data for model training and validation purposes. Therefore, activity discovery handles the problem that activity labels are not available using approaches based on sequence mining and clustering. In this paper, we introduce an unsupervised method for discovering activities from a network of motion detectors in a smart home setting. First, we present an intra-day clustering algorithm to find frequent sequential patterns within a day. As a second step, we present an inter-day clustering algorithm to find the common frequent patterns between days. Furthermore, we refine the patterns to have more compressed and defined cluster characterizations. Finally, we track the occurrences of various regular routines to monitor the functional health in an individual’s patterns and lifestyle. We evaluate our methods on two public data sets captured in real-life settings from two apartments during seven-month and three-month periods. Full article

Brain tumor detection and its analysis are essential in medical diagnosis. The proposed work focuses on segmenting abnormality of axial brain MR DICOM slices, as this format holds the advantage of conserving extensive metadata. The axial slices presume the left and right part of the brain is symmetric by a Line of Symmetry (LOS). A semi-automated system is designed to mine normal and abnormal structures from each brain MR slice in a DICOM study. In this work, Fuzzy clustering (FC) is applied to the DICOM slices to extract various clusters for different k. Then, the best-segmented image that has high inter-class rigidity is obtained using the silhouette fitness function. The clustered boundaries of the tissue classes further enhanced by morphological operations. The FC technique is hybridized with the standard image post-processing techniques such as marker controlled watershed segmentation (MCW), region growing (RG), and distance regularized level sets (DRLS). This procedure is implemented on renowned BRATS challenge dataset of different modalities and a clinical dataset containing axial T2 weighted MR images of a patient. The sequential analysis of the slices is performed using the metadata information present in the DICOM header. The validation of the segmentation procedures against the ground truth images authorizes that the segmented objects of DRLS through FC enhanced brain images attain maximum scores of Jaccard and Dice similarity coefficients. The average Jaccard and dice scores for segmenting tumor part for ten patient studies of the BRATS dataset are 0.79 and 0.88, also for the clinical study 0.78 and 0.86, respectively. Finally, 3D visualization and tumor volume estimation are done using accessible DICOM information. Full article