Semi-supervised Clustering Method Research Articles

Semi-supervised deep learning for molecular clump verification

Context. A reliable molecular clump detection algorithm is essential for studying these clumps. Existing detection algorithms for molecular clumps still require that detected candidates be verified manually, which is impractical for large-scale data. Semi-supervised learning methods, especially those based on deep features, have the potential to accomplish the task of molecular clump verification thanks to the powerful feature extraction capability of deep networks. Aims. Our main objective is to develop an automated method for the verification of molecular clump candidates. This method utilises a 3D convolutional neural network (3D CNN) to extract features of molecular clumps and employs semi-supervised learning to train the model, with the aim being to improve its generalisation ability and data utilisation. It addresses the issue of insufficient labelled samples in traditional supervised learning and enables the model to better adapt to new, unlabelled samples, achieving high accuracy in the verification of molecular clumps. Methods. We propose SS-3D-Clump, a semi-supervised deep clustering method that jointly learns the parameters of a 3D CNN and the cluster assignments of the generated features for automatic verification of molecular clumps. SS-3D-Clump iteratively classifies the features with the Constrained-KMeans and uses these class labels as supervision to update the weights of the entire network. Results. We used CO data from the Milky Way Imaging Scroll Painting project covering 350 square degrees in the Milky Way’s first, second, and third quadrants. The ClumpFind algorithm was applied to extract molecular clump candidates in these regions, which were subsequently verified using SS-3D-Clump. The SS-3D-Clump model, trained on a dataset comprising three different density regions, achieved an accuracy of 0.933, a recall rate of 0.955, a precision rate of 0.945, and an F1 score of 0.950 on the corresponding test dataset. These results closely align with those obtained through manual verification. Conclusions. Our experiments demonstrate that the SS-3D-Clump model achieves high accuracy in the automated verification of molecular clumps. It effectively captures the essential features of the molecular clumps and overcomes the challenge of limited labelled samples in supervised learning by using unlabelled samples through semi-supervised learning. This enhancement significantly improves the generalisation capability of the SS-3D-Clump model, allowing it to adapt effectively to new and unlabelled samples. Consequently, SS-3D-Clump can be integrated with any detection algorithm to create a comprehensive framework for the automated detection and verification of molecular clumps.

Graph-Based Semi-Supervised Deep Image Clustering With Adaptive Adjacency Matrix.

Image clustering is a research hotspot in machine learning and computer vision. Existing graph-based semi-supervised deep clustering methods suffer from three problems: 1) because clustering uses only high-level features, the detailed information contained in shallow-level features is ignored; 2) most feature extraction networks employ the step odd convolutional kernel, which results in an uneven distribution of receptive field intensity; and 3) because the adjacency matrix is precomputed and fixed, it cannot adapt to changes in the relationship between samples. To solve the above problems, we propose a novel graph-based semi-supervised deep clustering method for image clustering. First, the parity cross-convolutional feature extraction and fusion module is used to extract high-quality image features. Then, the clustering constraint layer is designed to improve the clustering efficiency. And, the output layer is customized to achieve unsupervised regularization training. Finally, the adjacency matrix is inferred by actual network prediction. A graph-based regularization method is adopted for unsupervised training networks. Experimental results show that our method significantly outperforms state-of-the-art methods on USPS, MNIST, street view house numbers (SVHN), and fashion MNIST (FMNIST) datasets in terms of ACC, normalized mutual information (NMI), and ARI.

Machine Learning-Facilitated Cross-Panel Automatic Classification at Both Sample and Cell Level in Acute Myeloid Leukemia

Introduction Flow cytometry (FC) immunophenotyping is essential for accurate and prompt diagnosis of acute myeloid leukemia (AML), with up to 95% of AML patients showing detectable aberrant immunophenotype (IP) by FC. Current manual and subjective analysis of clinical FC data, however, lacks reproducibility and leads to interpretation variation. In previous studies, we showed that supervised machine learning (ML) approaches can detect IP abnormalities and identify the acute leukemia subclassification accurately at the specimen level. We also found that comparable classification performance can be achieved using only a subset of markers of the reagent panel (Ko et al., 2018; Monaghan et al., 2022). To interpret the ML classification results, we have developed data clustering and discriminative learning methods to identify and visualize the diagnostic cell populations in a 2D space for hematopathology review (Ji et al., 2020; Lee et al., 2018). Built upon these approaches, this study reports our findings on developing an interpretable cross-panel ML classification model to support timely and accurate diagnosis and subclassification of AML. Materials and Method The AML diagnosis model at the sample level utilized FC data obtained from 53 bone marrow (BM) aspirate samples from Roswell Park Comprehensive Cancer Center (RPCCC) and 50 BM aspirate samples from UPMC. Data from RPCCC were acquired using a Beckman Coulter Navios EX and measured with the ClearLLab10C panel; while data from UPMC were acquired using a BD FACSCantoII and measured with a UPMC-developed diagnostic panel. We used only the common parameters collected within these 103 FC data sets and applied a previously published Gaussian Mixture Model-Support Vector Machine (GMM-SVM) based approach to train a cross panel sample-level classification model for AML diagnosis (Ko et al., 2018; Monaghan et al., 2022). Three-fold cross-validation was conducted to assess the model performance, using sensitivity, specificity, classification accuracy, and area under the receiver operating characteristic curve (AUC). For the cell-level visualization and analysis, all samples in the training set were pooled together, before a uniform manifold approximation and projection (UMAP) process was applied to transform and visualize the cell populations within the samples. Specifically, 26 non-neoplastic and 27 AML samples from the M2 panel of the ClearLLab10C from the RPCCC cohort were combined for the UMAP visualization. Then the FlowSOM unsupervised clustering method and the DAFI semi-supervised clustering method (Lee et al., 2018) were applied to identify all of the cell populations that have significant differences between the AML samples and the non-neoplastic controls. Results The cross-panel AML versus non-neoplastic classifier, combining FC data from UPMC and RPCCC achieved exceptional performance. The AML detection model using all parameters on the ClearLLab10C panel achieved an AUC of 100%. When using only the overlapping parameters between the ClearLLab10C and the UPMC panels, the classification model achieved an AUC of 99.5%, while the cross-panel classifier achieved an AUC of 99.1% (Table 1). Specimen-level visualization confirmed the separation of AML versus non-neoplastic controls. The UMAP plots, created by pooling non-neoplastic and AML samples, exhibited distinct patterns for different AML subtypes (M1 to M5) and a genetic mutation (e.g., AML IDH1), which were distinct from control samples. Using the automated gating analysis, cell populations identified as different between AML and control samples were characterized and visualized in 2D-by-2D scatter plots for straightforward interpretation and assessment based on their immunophenotype. Conclusion Our study demonstrated the feasibility to develop and assess a ML classification model for AML detection and diagnosis using overlapping markers in FC data across reagent panels and sites. Advanced visualization and automated gating analysis enabled the interpretation of the ML classification by identifying and characterizing the diagnostic cell populations and their phenotypic heterogeneity, providing insights into AML heterogeneity at both the specimen and the single cell level. These findings highlight the potential of ML capability for improving patient care by timely and accurate diagnosis and subclassification of AML.

Two neurosubtypes of ADHD different from the clinical phenotypes

Clinical and etiological variability of attention deficit hyperactivity disorder (ADHD) presents an obstacle to understand the disorder. The aim of this study was to disentangle the heterogeneity of ADHD using neuroimaging and a semi-supervised machine learning algorithm. We collected brain structural and functional magnetic resonance imaging (MRI) data and clinical profiles of 183 children with ADHD and 396 neurotypical controls from 7 independent sites. We also used an external validation set with 750 subjects. We adopted a semi-supervised clustering method to subtype ADHD by regional volumetric measures of gray matter, white matter, and fractional amplitude of low frequency fluctuation (fALFF). In addition, split sample test, leave-one-site-out test and external validation were applied to evaluate the reproducibility and stability of ADHD subtypes. Two stable and reproducible neurosubtypes of ADHD were disclosed, which were proved by the split-sample test and leave-one-site-out validation. The structural and functional patterns of ADHD subtypes were also stable in the external validation set. The current two neurosubtypes differed in clinical manifestations and volumetric gray matter, white matter volume and fALFF patterns. The current neurosubtypes of ADHD which were different from clinical phenotypes could facilitate understanding the underlying neuropathological and neurobiological mechanism of the disorder.

A combined deep neural network and semi-supervised clustering method for sports injury risk prediction

Sports injury risk prediction plays an important role in evaluating the stability of the body in the process of sports. Based on deep neural network and semi-supervised clustering theory, this paper constructs a sports injury risk prediction model, and designs a recognition algorithm based on feature sequence classification combined with Bayesian filtering, which solves the problems of false alarms and missed alarms caused by relying on local spatial attribute features. The FMS (functional movement screen) kit was used to test seven movements (squat, hurdle step, straight leg squat, shoulder flexibility, active straight leg lift, trunk stability push-up, and body rotation) of 29 athletes. In the simulation process, Pareto analysis method was used to evaluate the overall risk of athletes' after-school physical exercise, and the FMS score, receiver operating characteristic (ROC) curve and Youden index were calculated. The results showed that the best cut-off points of the total score of FMS for athletes as a whole, male athletes and female athletes were 15.5, 15.5 and 16.5, respectively, which effectively verified the generalization performance of the above sports prediction model.

Semi-Supervised Subspace Clustering via Tensor Low-Rank Representation

In this letter, we propose a novel semi-supervised subspace clustering method, which is able to simultaneously augment the initial supervisory information and construct a discriminative affinity matrix. By representing the limited amount of supervisory information as a pairwise constraint matrix, we observe that the ideal affinity matrix for clustering shares the same low-rank structure as the ideal pairwise constraint matrix. Thus, we stack the two matrices into a 3-D tensor, where a global low-rank constraint is imposed to promote the affinity matrix construction and augment the initial pairwise constraints synchronously. Besides, we use the local geometry structure of input samples to complement the global low-rank prior to achieve better affinity matrix learning. The proposed model is formulated as a Laplacian graph regularized convex low-rank tensor representation problem, which is further solved with an alternative iterative algorithm. In addition, we propose to refine the affinity matrix with the augmented pairwise constraints. Comprehensive experimental results on eight commonly-used benchmark datasets demonstrate the superiority of our method over state-of-the-art methods. The code is publicly available at https://github.com/GuanxingLu/Subspace-Clustering.

KISL: knowledge-injected semi-supervised learning for biological co-expression network modules.

The exploration of important biomarkers associated with cancer development is crucial for diagnosing cancer, designing therapeutic interventions, and predicting prognoses. The analysis of gene co-expression provides a systemic perspective on gene networks and can be a valuable tool for mining biomarkers. The main objective of co-expression network analysis is to discover highly synergistic sets of genes, and the most widely used method is weighted gene co-expression network analysis (WGCNA). With the Pearson correlation coefficient, WGCNA measures gene correlation, and uses hierarchical clustering to identify gene modules. The Pearson correlation coefficient reflects only the linear dependence between variables, and the main drawback of hierarchical clustering is that once two objects are clustered together, the process cannot be reversed. Hence, readjusting inappropriate cluster divisions is not possible. Existing co-expression network analysis methods rely on unsupervised methods that do not utilize prior biological knowledge for module delineation. Here we present a method for identification of outstanding modules in a co-expression network using a knowledge-injected semi-supervised learning approach (KISL), which utilizes apriori biological knowledge and a semi-supervised clustering method to address the issue existing in the current GCN-based clustering methods. To measure the linear and non-linear dependence between genes, we introduce a distance correlation due to the complexity of the gene-gene relationship. Eight RNA-seq datasets of cancer samples are used to validate its effectiveness. In all eight datasets, the KISL algorithm outperformed WGCNA when comparing the silhouette coefficient, Calinski-Harabasz index and Davies-Bouldin index evaluation metrics. According to the results, KISL clusters had better cluster evaluation values and better gene module aggregation. Enrichment analysis of the recognition modules demonstrated their effectiveness in discovering modular structures in biological co-expression networks. In addition, as a general method, KISL can be applied to various co-expression network analyses based on similarity metrics. Source codes for the KISL and the related scripts are available online at https://github.com/Mowonhoo/KISL.git.

Pairwise constraints-based semi-supervised fuzzy clustering with multi-manifold regularization

Introducing a handful of pairwise constraints into fuzzy clustering models to revise memberships has been proven beneficial to boosting clustering performance. However, current pairwise constraints-based semi-supervised fuzzy clustering methods suffer from common deficiencies, i.e., the insufficient and imprecise revisions of memberships, by which the further improvement of clustering performance may be encumbered. To yield more pleasurable results, this paper proposes a new pairwise constraints-based semi-supervised fuzzy clustering method with multi-manifold regularization (MMRFCM), which can overcome the above deficiencies simultaneously. Firstly, data are regarded as located in various manifolds, and the multi-manifold regularization is delicately designed to sufficiently revise memberships for all data objects to guarantee good overall clustering performance. Secondly, local structural information is incorporated into designed multi-manifold regularization to ensure the precision and stability of the revisions on memberships. Thirdly, the approximated non-linear similarities evolving from ensemble p-Laplacian are applied to discover implicit local structures more thoroughly to further strengthen the effect of the multi-manifold regularization. Based on these strategies, MMRFCM efficiently exploits pairwise constraints to sufficiently and precisely modify memberships during the clustering process and thus achieves excellent results. Like most fuzzy clustering methods, MMRFCM is solved by alternative updates and the solutions are locally optimal. In the comprehensive experiments conducted on different types of datasets, MMRFCM successfully outperforms several classical and state-of-the-art fuzzy clustering methods in terms of clustering accuracy (CA), normalized mutual information (NMI), and adjusted rand index (ARI). The excellent results demonstrate the superiority, stability, and reliability of the proposed method.

Risk prediction of chronic diseases with a two-stage semi-supervised clustering method

Early detection of chronic diseases such as cardiovascular disease (CVD) and diabetes can make the difference between life and death. Previous studies have demonstrated the feasibility of disease diagnosis and prediction using machine learning and disease-indicating biomarkers. The aim of this study is to develop a method to detect the risk of future disease even when disease-indicating biomarker readings are in the normal range. Data from the US Centers for Disease Control and Prevention (CDC) National Health and Nutrition Examination Surveys (NHANES) are used for this study. A two-stage semi-supervised K-Means (SSK-Means) clustering approach was developed to identify the underlying risk of each individual and categorize them into high or low-risk groups for CVD and diabetes. Our developed method of classification can identify groups as high risk or low risk, even if they would have been considered normal using traditional biomarker threshold criteria. For CVD, the SSK-Means clustering results showed that individuals over 30 years of age in the high-risk group were almost twice as likely to develop CVD as individuals in the low-risk group. For diabetes, the SSK-Means clustering results showed that individuals over 50 years in the high-risk group have at least two times the risk of developing diabetes compared with individuals in the low-risk group.

Application of big data adaptive semi-supervised clustering method based on deep learning

In order to solve the problems of high computational complexity, poor dimensionality reduction, and reduced clustering effect when the clustering task faces a large amount of big data, the application of a large data adaptive semi-supervised clustering method based on deep learning is proposed. Through the self-encoder of the deep clustering network, the analysis of the confrontation network is generated, and the semi-supervised deep clustering algorithm and algorithm of the adaptive strategy are optimized. Through the encoder layer structure of the deep coding network, different parameters are set for all data sets for algorithm experimental analysis. The results show that the data obtained by this method is faster, more accurate and more optimized than the traditional clustering method, which proves the effectiveness of the method.

ScCNC: a method based on capsule network for clustering scRNA-seq data.

A large number of studies have shown that clustering is a crucial step in scRNA-seq analysis. Most existing methods are based on unsupervised learning without the prior exploitation of any domain knowledge, which does not utilize available gold-standard labels. When confronted by the high dimensionality and general dropout events of scRNA-seq data, purely unsupervised clustering methods may not produce biologically interpretable clusters, which complicate cell type assignment. In this article, we propose a semi-supervised clustering method based on a capsule network named scCNC that integrates domain knowledge into the clustering step. Significantly, we also propose a Semi-supervised Greedy Iterative Training method used to train the whole network. Experiments on some real scRNA-seq datasets show that scCNC can significantly improve clustering performance and facilitate downstream analyses. The source code of scCNC is freely available at https://github.com/WHY-17/scCNC. Supplementary data are available at Bioinformatics online.

Deep multi-view semi-supervised clustering with sample pairwise constraints

Multi-view clustering has attracted much attention thanks to the capacity of multi-source information integration. Although numerous advanced methods have been proposed in past decades, most of them generally overlook the significance of weakly-supervised information and fail to preserve the feature properties of multiple views, thus resulting in unsatisfactory clustering performance. To address these issues, in this paper, we propose a novel Deep Multi-view Semi-supervised Clustering (DMSC) method, which jointly optimizes three kinds of losses during networks finetuning, including multi-view clustering loss, semi-supervised pairwise constraint loss and multiple autoencoders reconstruction loss. Specifically, a KL divergence based multi-view clustering loss is imposed on the common representation of multi-view data to perform heterogeneous feature optimization, multi-view weighting and clustering prediction simultaneously. Then, we innovatively propose to integrate pairwise constraints into the process of multi-view clustering by enforcing the learned multi-view representation of must-link samples (cannot-link samples) to be similar (dissimilar), such that the formed clustering architecture can be more credible. Moreover, unlike existing rivals that only preserve the encoders for each heterogeneous branch during networks finetuning, we further propose to tune the intact autoencoders frame that contains both encoders and decoders. In this way, the issue of serious corruption of view-specific and view-shared feature space could be alleviated, making the whole training procedure more stable. Through comprehensive experiments on eight popular image datasets, we demonstrate that our proposed approach performs better than the state-of-the-art multi-view and single-view competitors.

Self-boosted with dynamic semi-supervised clustering method for imbalanced big data classification

Self-boosted with dynamic semi-supervised clustering method for imbalanced big data classification

Self-Boosted With Dynamic Semi-Supervised Clustering Method for Imbalanced Big Data Classification

Big data plays a major role in the learning, manipulation, and forecasting of information intelligence. Due to the imbalance of data delivery, the learning and retrieval of information from such large datasets can result in limited classification outcomes and wrong decisions. Traditional machine learning classifiers successfully handling the imbalanced datasets still there is inadequacy in overfitting problems, training cost, and sample hardness in classification. In order to forecast a better classification, the research work proposed the novel “Self-Boosted with Dynamic Semi-Supervised Clustering Method”. The method is initially preprocessed by constructing sample blocks using Hybrid Associated Nearest Neighbor heuristic over-sampling to replicate the minority samples and merge each copy with every sub-set of majority samples to remove the overfitting issue thus slightly reduce noise with the imbalanced data. After preprocessing the data, massive data classification requires big data space which leads to large training costs.

Characterizing Heterogeneity in Neuroimaging, Cognition, Clinical Symptoms, and Genetics Among Patients With Late-Life Depression

Late-life depression (LLD) is characterized by considerable heterogeneity in clinical manifestation. Unraveling such heterogeneity might aid in elucidating etiological mechanisms and support precision and individualized medicine. To cross-sectionally and longitudinally delineate disease-related heterogeneity in LLD associated with neuroanatomy, cognitive functioning, clinical symptoms, and genetic profiles. The Imaging-Based Coordinate System for Aging and Neurodegenerative Diseases (iSTAGING) study is an international multicenter consortium investigating brain aging in pooled and harmonized data from 13 studies with more than 35 000 participants, including a subset of individuals with major depressive disorder. Multimodal data from a multicenter sample (N = 996), including neuroimaging, neurocognitive assessments, and genetics, were analyzed in this study. A semisupervised clustering method (heterogeneity through discriminative analysis) was applied to regional gray matter (GM) brain volumes to derive dimensional representations. Data were collected from July 2017 to July 2020 and analyzed from July 2020 to December 2021. Two dimensions were identified to delineate LLD-associated heterogeneity in voxelwise GM maps, white matter (WM) fractional anisotropy, neurocognitive functioning, clinical phenotype, and genetics. A total of 501 participants with LLD (mean [SD] age, 67.39 [5.56] years; 332 women) and 495 healthy control individuals (mean [SD] age, 66.53 [5.16] years; 333 women) were included. Patients in dimension 1 demonstrated relatively preserved brain anatomy without WM disruptions relative to healthy control individuals. In contrast, patients in dimension 2 showed widespread brain atrophy and WM integrity disruptions, along with cognitive impairment and higher depression severity. Moreover, 1 de novo independent genetic variant (rs13120336; chromosome: 4, 186387714; minor allele, G) was significantly associated with dimension 1 (odds ratio, 2.35; SE, 0.15; P = 3.14 ×108) but not with dimension 2. The 2 dimensions demonstrated significant single-nucleotide variant-based heritability of 18% to 27% within the general population (N = 12 518 in UK Biobank). In a subset of individuals having longitudinal measurements, those in dimension 2 experienced a more rapid longitudinal change in GM and brain age (Cohen f2 = 0.03; P = .02) and were more likely to progress to Alzheimer disease (Cohen f2 = 0.03; P = .03) compared with those in dimension 1 (N = 1431 participants and 7224 scans from the Alzheimer's Disease Neuroimaging Initiative [ADNI], Baltimore Longitudinal Study of Aging [BLSA], and Biomarkers for Older Controls at Risk for Dementia [BIOCARD] data sets). This study characterized heterogeneity in LLD into 2 dimensions with distinct neuroanatomical, cognitive, clinical, and genetic profiles. This dimensional approach provides a potential mechanism for investigating the heterogeneity of LLD and the relevance of the latent dimensions to possible disease mechanisms, clinical outcomes, and responses to interventions.

Two neuroanatomical subtypes of males with autism spectrum disorder revealed using semi-supervised machine learning

BackgroundClinical and etiological varieties remain major obstacles to decompose heterogeneity in autism spectrum disorders (ASD). Recently, neuroimaging raised new hope to identify neurosubtypes of ASD for further understanding the biological mechanisms behind the disorder.MethodsIn this study, brain structural MRI data and clinical measures of 221 male subjects with ASD and 257 healthy controls were selected from 7 independent sites from the Autism Brain Image Data Exchange database (ABIDE). Heterogeneity through discriminative analysis (HYDRA), a recently-proposed semi-supervised clustering method was utilized to divide individuals with ASD into several neurosubtypes by regional volumetric measures of gray matter, white matter, and cerebrospinal fluid. Voxel-wise volume, clinical measures, dynamic resting-state functional magnetic resonance imaging (R-fMRI) measures among different neurosubtypes of ASD were explored. In addition, support vector machine (SVM) model was applied to test whether the neurosubtyping of ASD could improve diagnostic accuracy of ASD.ResultsTwo neurosubtypes of ASD with different voxel-wise volumetric patterns were revealed. The full-scale intelligence quotient (IQ), verbal IQ, Autism Diagnostic Observation Schedule (ADOS) total scores and ADOS severity scores were significantly different between the two neurosubtypes, the total intracranial volume was correlated with performance IQ in Subtype 1 and was correlated with ADOS communication score and ADOS social score in Subtype 2. Compared with Subtype 2, Subtype 1 showed lower dynamic R-fMRI measures, lower dynamic functional architecture stability, higher mean and lower standard deviation (SD) of concordance among dynamic R-fMRI measures in cerebellum. In addition, classification accuracies between ASD neurosubtypes and healthy controls were significantly improved compared with classification accuracy between entire ASD group and healthy controls.LimitationsThe present study excluded female subjects and left-handed subjects, which limited the ability to investigate the associations between these factors and the heterogeneity of ASD.ConclusionsThe two distinct neuroanatomical subtypes of ASD validated by other data modalities not only adds reliability of the result, but also bridges from brain phenomenology to clinical behavior. The current neurosubtypes of ASD could facilitate understanding the neuropathology of this disorder and could be potentially used to improve clinical decision-making process and optimize treatment.

TS3FCM: trusted safe semi-supervised fuzzy clustering method for data partition with high confidence

TS3FCM: trusted safe semi-supervised fuzzy clustering method for data partition with high confidence

Multi-scale semi-supervised clustering of brain images: Deriving disease subtypes.

Disease heterogeneity is a significant obstacle to understanding pathological processes and delivering precision diagnostics and treatment. Clustering methods have gained popularity for stratifying patients into subpopulations (i.e., subtypes) of brain diseases using imaging data. However, unsupervised clustering approaches are often confounded by anatomical and functional variations not related to a disease or pathology of interest. Semi-supervised clustering techniques have been proposed to overcome this and, therefore, capture disease-specific patterns more effectively. An additional limitation of both unsupervised and semi-supervised conventional machine learning methods is that they typically model, learn and infer from data using a basis of feature sets pre-defined at a fixed anatomical or functional scale (e.g., atlas-based regions of interest). Herein we propose a novel method, "Multi-scAle heteroGeneity analysIs and Clustering" (MAGIC), to depict the multi-scale presentation of disease heterogeneity, which builds on a previously proposed semi-supervised clustering method, HYDRA. It derives multi-scale and clinically interpretable feature representations and exploits a double-cyclic optimization procedure to effectively drive identification of inter-scale-consistent disease subtypes. More importantly, to understand the conditions under which the clustering model can estimate true heterogeneity related to diseases, we conducted extensive and systematic semi-simulated experiments to evaluate the proposed method on a sizeable healthy control sample from the UK Biobank (N=4403). We then applied MAGIC to imaging data from Alzheimer's disease (ADNI, N=1728) and schizophrenia (PHENOM, N=1166) patients to demonstrate its potential and challenges in dissecting the neuroanatomical heterogeneity of common brain diseases. Taken together, we aim to provide guidance regarding when such analyses can succeed or should be taken with caution. The code of the proposed method is publicly available at https://github.com/anbai106/MAGIC.

Electricity consumption pattern analysis beyond traditional clustering methods: A novel self-adapting semi-supervised clustering method and application case study

The fast-paced informatization of power systems across the world provides an unprecedented amount of data, which greatly facilitates their study and offers in turn the possibility to assist in the transition towards truly smart, low-carbon energy systems. In this context, the use of clustering methods for the study of household Electricity Consumption Behaviour (ECB) proves highly beneficial as it facilitates, among other things, more effective deployment of distributed renewable energy assets, development of differentiated tariff policies and load forecasting. However, the similarity metrics used in traditional clustering methods have difficulties in accurately capturing the time variability of electrical load profiles. In order to address this problem, we developed a novel semi-supervised automatic clustering method based on a self-adapting metric learning process. The proposed method is a bespoke application to the analysis of electricity demand load patterns that combines the recently developed Deep Linear Discriminant Analysis algorithm for supervised learning with the data-adaptive Affinity Propagation clustering algorithm (DLDA + AP), and achieves high-quality automatic clustering with an accuracy that is 75 percentage points higher than traditional methods such as k-means, on average. Based on this bespoke method, a unified load dictionary which captures the mainstream daily electricity consumption patterns of 5566 households in London was produced. Through the analysis of the load dictionary and household daily electricity consumption, it’s possible to build a complete ECB profile for the households in the sample dataset. Furthermore, combining the 206 household properties which were found to be strongly correlated with the ECB, this method provides a practical approach to residential customer segmentation for the electricity market.

Identifying Groups of Fake Reviewers Using a Semisupervised Approach

Online product reviews have become increasingly important in digital consumer markets where they play a crucial role in making purchasing decisions by most consumers. Unfortunately, spammers often take advantage of online reviews by writing fake reviews to promote/demote certain products. Most of the previous studies have focused on detecting fake reviews and individual fake reviewer-ids. However, to target a particular product, fake reviewers work collaboratively in groups and/or create multiple fake ids to write reviews and control the sentiments of the product. This article addresses the problem of finding such fake reviewer groups. More specifically, we propose a top-down framework for candidate fake reviewer groups’ detection based on the DeepWalk approach on reviewers’ graph data and a (modified) semisupervised clustering method, which can incorporate partial background knowledge. We validate our proposed framework on a real review dataset from the Google Play Store, which has partial ground-truth information about 2207 fraud reviewer-ids out of all 38 123 reviewer-ids in the dataset. Our experimental results demonstrate that the proposed approach is able to identify the candidate spammer groups with reasonable accuracy. The proposed approach can also be extended to detect groups of opinion spammers in social media (e.g. fake comments or fake postings) with temporal affinity, semantic characteristics, and sentiment analysis.