Unsupervised Learning Method Research Articles

Decoupled learning for brain image registration.

Image registration is one of the important parts in medical image processing and intelligent analysis. The accuracy of image registration will greatly affect the subsequent image processing and analysis. This paper focuses on the problem of brain image registration based on deep learning, and proposes the unsupervised deep learning methods based on model decoupling and regularization learning. Specifically, we first decompose the highly ill-conditioned inverse problem of brain image registration into two simpler sub-problems, to reduce the model complexity. Further, two light neural networks are constructed to approximate the solution of the two sub-problems and the training strategy of alternating iteration is used to solve the problem. The performance of algorithms utilizing model decoupling is evaluated through experiments conducted on brain MRI images from the LPBA40 dataset. The obtained experimental results demonstrate the superiority of the proposed algorithm over conventional learning methods in the context of brain image registration tasks.

Bayesian Reconstruction Algorithms for Low-Dose Computed Tomography Are Not Yet Suitable in Clinical Context.

Computed tomography (CT) is a widely used examination technique that usually requires a compromise between image quality and radiation exposure. Reconstruction algorithms aim to reduce radiation exposure while maintaining comparable image quality. Recently, unsupervised deep learning methods have been proposed for this purpose. In this study, a promising sparse-view reconstruction method (posterior temperature optimized Bayesian inverse model; POTOBIM) is tested for its clinical applicability. For this study, 17 whole-body CTs of deceased were performed. In addition to POTOBIM, reconstruction was performed using filtered back projection (FBP). An evaluation was conducted by simulating sinograms and comparing the reconstruction with the original CT slice for each case. A quantitative analysis was performed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). The quality was assessed visually using a modified Ludewig's scale. In the qualitative evaluation, POTOBIM was rated worse than the reference images in most cases. A partially equivalent image quality could only be achieved with 80 projections per rotation. Quantitatively, POTOBIM does not seem to benefit from more than 60 projections. Although deep learning methods seem suitable to produce better image quality, the investigated algorithm (POTOBIM) is not yet suitable for clinical routine.

ETLD: an encoder-transformation layer-decoder architecture for protein contact and mutation effects prediction.

The latent features extracted from the multiple sequence alignments (MSAs) of homologous protein families are useful for identifying residue-residue contacts, predicting mutation effects, shaping protein evolution, etc. Over the past three decades, a growing body of supervised and unsupervised machine learning methods have been applied to this field, yielding fruitful results. Here, we propose a novel self-supervised model, called encoder-transformation layer-decoder (ETLD) architecture, capable of capturing protein sequence latent features directly from MSAs. Compared to the typical autoencoder model, ETLD introduces a transformation layer with the ability to learn inter-site couplings, which can be used to parse out the two-dimensional residue-residue contacts map after a simple mathematical derivation or an additional supervised neural network. ETLD retains the process of encoding and decoding sequences, and the predicted probabilities of amino acids at each site can be further used to construct the mutation landscapes for mutation effects prediction, outperforming advanced models such as GEMME, DeepSequence and EVmutation in general. Overall, ETLD is a highly interpretable unsupervised model with great potential for improvement and can be further combined with supervised methods for more extensive and accurate predictions.

Identification of clinical phenotypes associated with poor prognosis in patients with nonalcoholic fatty liver disease via unsupervised machine learning.

Both fibrosis status and body weight are important for assessing prognosis in nonalcoholic fatty liver disease (NAFLD). The aim of this study was to identify population clusters for specific clinical outcomes based on fibrosis-4 (FIB-4) index and body mass index (BMI) using an unsupervised machine learning method. We conducted a multicenter study of 1335 biopsy-proven NAFLD patients from Japan. Using the Gaussian mixture model to divide the cohort into clusters based on FIB-4 index and BMI, we investigated prognosis for these clusters. The cohort consisted of 223 cases (16.0%) with advanced fibrosis (F3-4) as assessed from liver biopsy. Median values of BMI and FIB-4 index were 27.3kg/m2 and 1.67. The patients were divided into four clusters by Bayesian information criterion, and all-cause mortality was highest in cluster d, followed by cluster b (P=0.001). Regarding the characteristics of each cluster, clusters d and b presented a high FIB-4 index (median 5.23 and 2.23), cluster a presented the lowest FIB-4 index (median 0.78), and cluster c was associated with moderate FIB-4 level (median 1.30) and highest BMI (median 34.3kg/m2 ). Clusters a and c had lower mortality rates than clusters b and d. However, all-cause of death in clusters a and c was unrelated to liver disease. Our clustering approach found that the FIB-4 index is an important predictor of mortality in NAFLD patients regardless of BMI. Additionally, non-liver-related diseases were identified as the causes of death in NAFLD patients with low FIB-4 index.

Unsupervised dual-domain disentangled network for removal of rigid motion artifacts in MRI

Motion artifacts in magnetic resonance imaging (MRI) have always been a serious issue because they can affect subsequent diagnosis and treatment. Supervised deep learning methods have been investigated for the removal of motion artifacts; however, they require paired data that are difficult to obtain in clinical settings. Although unsupervised methods are widely proposed to fully use clinical unpaired data, they generally focus on anatomical structures generated by the spatial domain while ignoring phase error (deviations or inaccuracies in phase information that are possibly caused by rigid motion artifacts during image acquisition) provided by the frequency domain. In this study, a 2D unsupervised deep learning method named unsupervised disentangled dual-domain network (UDDN) was proposed to effectively disentangle and remove unwanted rigid motion artifacts from images. In UDDN, a dual-domain encoding module was presented to capture different types of information from the spatial and frequency domains to enrich the information. Moreover, a cross-domain attention fusion module was proposed to effectively fuse information from different domains, reduce information redundancy, and improve the performance of motion artifact removal. UDDN was validated on a publicly available dataset and a clinical dataset. Qualitative and quantitative experimental results showed that our method could effectively remove motion artifacts and reconstruct image details. Moreover, the performance of UDDN surpasses that of several state-of-the-art unsupervised methods and is comparable with that of the supervised method. Therefore, our method has great potential for clinical application in MRI, such as real-time removal of rigid motion artifacts.

An unsupervised dual contrastive learning framework for scatter correction in cone-beam CT image

Purpose:Cone-beam computed tomography (CBCT) is widely utilized in modern radiotherapy; however, CBCT images exhibit increased scatter artifacts compared to planning CT (pCT), compromising image quality and limiting further applications. Scatter correction is thus crucial for improving CBCT image quality. Methods:In this study, we proposed an unsupervised contrastive learning method for CBCT scatter correction. Initially, we transformed low-quality CBCT into high-quality synthetic pCT (spCT) and generated forward projections of CBCT and spCT. By computing the difference between these projections, we obtained a residual image containing image details and scatter artifacts. Image details primarily comprise high-frequency signals, while scatter artifacts consist mainly of low-frequency signals. We extracted the scatter projection signal by applying a low-pass filter to remove image details. The corrected CBCT (cCBCT) projection signal was obtained by subtracting the scatter artifacts projection signal from the original CBCT projection. Finally, we employed the FDK reconstruction algorithm to generate the cCBCT image. Results:To evaluate cCBCT image quality, we aligned the CBCT and pCT of six patients. In comparison to CBCT, cCBCT maintains anatomical consistency and significantly enhances CT number, spatial homogeneity, and artifact suppression. The mean absolute error (MAE) of the test data decreased from 88.0623 ± 26.6700 HU to 17.5086 ± 3.1785 HU. The MAE of fat regions of interest (ROIs) declined from 370.2980 ± 64.9730 HU to 8.5149 ± 1.8265 HU, and the error between their maximum and minimum CT numbers decreased from 572.7528 HU to 132.4648 HU. The MAE of muscle ROIs reduced from 354.7689 ± 25.0139 HU to 16.4475 ± 3.6812 HU. We also compared our proposed method with several conventional unsupervised synthetic image generation techniques, demonstrating superior performance. Conclusions:Our approach effectively enhances CBCT image quality and shows promising potential for future clinical adoption.

Stability follows efficiency based on the analysis of a large perovskite solar cells ageing dataset

While perovskite solar cells have reached competitive efficiency values during the last decade, stability issues remain a critical challenge to be addressed for pushing this technology towards commercialisation. In this study, we analyse a large homogeneous dataset of Maximum Power Point Tracking (MPPT) operational ageing data that we collected with a custom-built High-throughput Ageing System in the past 3 years. In total, 2,245 MPPT ageing curves are analysed which were obtained under controlled conditions (continuous illumination, controlled temperature and atmosphere) from devices comprising various lead-halide perovskite absorbers, charge selective layers, contact layers, and architectures. In a high-level statistical analysis, we find a correlation between the maximum reached power conversion efficiency (PCE) and the relative PCE loss observed after 150-hours of ageing, with more efficient cells statistically also showing higher stability. Additionally, using the unsupervised machine learning method self-organising map, we cluster this dataset based on the degradation curve shapes. We find a correlation between the frequency of particular shapes of degradation curves and the maximum reached PCE.

Classification of Thyroid Tumors Based on DNA Methylation Patterns.

Background: Alterations in DNA methylation are stable epigenetic events that can serve as clinical biomarkers. The aim of this study was to analyze methylation patterns among various follicular cell-derived thyroid neoplasms to identify disease subtypes and help understand and classify thyroid tumors. Methods: We employed an unsupervised machine learning method for class discovery to search for distinct methylation patterns among various thyroid neoplasms. Our algorithm was not provided with any clinical or pathological information, relying exclusively on DNA methylation data to classify samples. We analyzed 810 thyroid samples (n = 256 for discovery and n = 554 for validation), including benign and malignant tumors, as well as normal thyroid tissue. Results: Our unsupervised algorithm identified that samples could be classified into three subtypes based solely on their methylation profile. These methylation subtypes were strongly associated with histological diagnosis (p < 0.001) and were therefore named normal-like, follicular-like, and papillary thyroid carcinoma (PTC)-like. Follicular adenomas, follicular carcinomas, oncocytic adenomas, and oncocytic carcinomas clustered together forming the follicular-like methylation subtype. Conversely, classic papillary thyroid carcinomas (cPTC) and tall cell PTC clustered together forming the PTC-like subtype. These methylation subtypes were also strongly associated with genomic drivers: 98.7% BRAFV600E-driven cancers were PTC like, whereas 96.0% RAS-driven cancers had a follicular-like methylation pattern. Interestingly, unlike other diagnoses, follicular variant PTC (FVPTC) samples were split into two methylation clusters (follicular like and PTC like), indicating a heterogeneous group likely to be formed by two distinct diseases. FVPTC samples with a follicular-like methylation pattern were enriched for RAS mutations (36.4% vs. 8.0%; p < 0.001), whereas FVPTC- with PTC-like methylation patterns were enriched for BRAFV600E mutations (52.0% vs. 0%, Fisher exact p = 0.004) and RET fusions (16.0% vs. 0%, Fisher exact p = 0.003). Conclusions: Our data provide novel insights into the epigenetic alterations of thyroid tumors. Since our classification method relies on a fully unsupervised machine learning approach for subtype discovery, our results offer a robust background to support the classification of thyroid neoplasms based on methylation patterns.

On-line tool wear monitoring under variable milling conditions based on a condition-adaptive hidden semi-Markov model (CAHSMM)

Since tool wear during machining process imposes a significant limitation on production quality as well as efficiency, on-line tool wear monitoring (TWM) is one of considerably crucial issues for intelligent manufacturing system. However, there is still a lack of universal on-line TWM techniques appropriate for the practical production process with variable machining parameters. Therefore, this study proposes a highly condition-adaptive method for tool wear state monitoring and remaining useful life (RUL) estimation under time-varying operation conditions. Multi-domain features are first extracted from vibration, acoustic emission and sound signals, and subsequently fused by the kernel principal component analysis (KPCA) to highlight discriminative information correlated to tool wear. A condition-adaptive hidden semi-Markov model (CAHSMM) is established to describe the evolution of tool wear, in which the accelerated failure time model (AFTM) embedded with Taylor tool life equation is utilized to determine the state transition probabilities that are strongly dependent on cutting parameters and duration time. Moreover, to extrapolate the Gaussian mixture models (GMMs) used to represent the observation probability beyond the range where they were trained, a Moment matching based on-line unsupervised transfer learning (OUTL) method is developed. After obtaining the state transition and observation probabilities, a modified forward algorithm is eventually implemented so as to assess tool wear online. Both the dataset from milling experiments of Ti6Al4V and PHM 2010 are employed for verifying the effectiveness of the proposed method. The results show that the presented method enables to reliably evaluate wear state and RUL of the cutter even under time-switching operation parameters, which demonstrates its promising potential for industrial applications.

Supervised categorized principal component analysis for imagined speech classification via applying singular value decomposition on a symmetry matrix

The dimension of the feature vectors for performing the imagined speech is large. Hence, it is required to reduce their dimension as well as perform the classification simultaneously. This is a categorized principal component analysis (CatPCA) problem. However, the conventional CatPCA methods are unsupervised learning methods and the design of the unitary matrix in the conventional principal component analysis (PCA) algorithms is only based on the PCA approach. Therefore, the classification performance is limited. This paper proposes a supervised CatPCA approach for performing the imagined speech classification. Also, the objective function of an optimization problem for designing the unitary matrix is formulated based on both the PCA algorithm and the k means algorithm. To find the analytical solution of the optimization problem, a property on computing the singular value decomposition (SVD) of a symmetric matrix is employed. Then, the design of the cluster centers in the k means algorithm is formulated as a quadratic programming. Finally, the above two procedures are iterated until the algorithm converges. Since the analytical solutions of these two optimization problems can be derived analytically, the required computational power for finding the solution of the optimization problem is low. To demonstrate the effectiveness of our proposed CatPCA algorithm, the Track 3 of the International brain computer interface (BCI) Competition Database is employed as the dataset for performing the performance evaluation. The computer numerical simulation results show that our proposed CatPCA algorithm yields the higher classification accuracy compared to PCA variants and the dimension reduction related algorithms. Also, the required execution time of our proposed method is lower than those of the states of the arts methods. This demonstrates the effectiveness and the efficiency of our proposed CatPCA algorithm.

A weakly supervised inpainting-based learning method for lung CT image segmentation

Recently, various fully supervised learning methods are successfully applied for lung CT image segmentation. However, pixel-wise annotations are extremely expert-demanding and labor-intensive, but the performance of unsupervised learning methods are failed to meet the demands of practical applications. To achieve a reasonable trade-off between the performance and label dependency, a novel weakly supervised inpainting-based learning method is introduced, in which only bounding box labels are required for accurate segmentation. Specifically, lesion regions are first detected by an object detection network, then we crop them out of the input image and recover the missing holes to normal regions using a progressive CT inpainting network (PCIN). Finally, a post-processing method is designed to get the accurate segmentation mask from the difference image of input and recovered images. In addition, real information (i.e., number, location and size) of the bounding boxes of lesions from the dataset guides us to make the training dataset for PCIN. We apply a multi-scale supervised strategy to train PCIN for a progressive and stable inpainting. Moreover, to remove the visual artifacts resulted from the invalid features of missing holes, an initial patch generation network (IPGN) is proposed for holes initialization with generated pseudo healthy image patches. Experiments on the public COVID-19 dataset demonstrate that PCIN is outstanding in lung CT images inpainting, and the performance of our proposed weakly supervised method is comparable to fully supervised methods.

Seismic Characterization of the Blue Mountain Geothermal Field

Subsurface characterization is crucial for geothermal energy exploration and production. Yet hydrothermal reservoirs usually reside in highly fractured and faulted zones where accurate characterization is very challenging because of low signal-to-noise ratios of land seismic data and lack of coherent reflection signals. We perform an active-source seismic characterization for the Blue Mountain geothermal field in Nevada using active seismic data to reveal the elastic medium property complexity and fault distribution at this field. We first employ an unsupervised machine learning method to attenuate groundroll and near-surface guided-wave noise and enhance coherent reflection and scattering signals from noisy seismic data. We then build a smooth initial P-wave velocity model based on an existing magnetotellurics survey result, and use 3D first-arrival traveltime tomography to refine the initial velocity model. We then derive a set of elastic wave velocities and anisotropic parameters using elastic full-waveform inversion, and obtain PP and PS images using elastic reverse-time migration. We identify major faults by analyzing the variations of seismic velocities and anisotropy parameters, and reveal mid- to small-scale faults by applying a supervised machine learning method to the seismic migration images. Our characterization reveals complex velocity heterogeneities and anisotropies, as well as faults, with a high spatial resolution. These results can provide valuable information for optimal placement of future injection and production wells to increase geothermal energy production at the Blue Mountain geothermal power plant.

Towards inverse microstructure-centered materials design using generative phase-field modeling and deep variational autoencoders

The field of Integrated Computational Materials Engineering (ICME) combines a broad range of methods to study materials’ responses over a spectrum of length scales. A relatively unexplored aspect of microstructure-sensitive materials design is uncertainty propagation and quantification (UP/UQ) of materials’ microstructure, as well as establishing process-structure–property (PSP) relationships for inverse material design. In this study, an efficient UP technique built on the idea of changing probability measures and a deep generative unsupervised representative machine learning method for microstructure-based design of thermal conductivity of materials is proposed. Probability measures are used to represent microstructure space, and Wasserstein metrics are used to test the efficiency of the UP method. By using deep Variational AutoEncoder (VAE), we identify the correlations between the material/process parameters and the thermal conductivity of heterogeneous dual-phase microstructures. Through high-throughput screening, UP, and the deep-generative VAE method, PSP relationships that are too complex can be revealed by exploiting the materials’ design space with an emphasis on microstructures. As a last point, we demonstrate generative machine learning serves as a useful tool for inverse microstructure-centered materials design, and we demonstrate this by examining the inverse design of thermal conductivity in nano-structured materials. The results reveal the effects of morphology, volume fraction, characteristic length scale, and the individual thermal diffusivity of phases on the thermal conductivity of dual-phase alloys. Our findings emphasize the advantages of high-throughput phase-field modeling and generative deep learning for linking PSP and inverse microstructure-centered materials design.

Construction of gene subgroups of Crohn disease based on transcriptome data.

The global prevalence of Crohn disease (CD), a chronic inflammatory disease of the intestine, has been increasing; however, the etiology and pathogenesis of this disease have not been fully elucidated. Therefore, in the present study, we aimed to better understand the molecular mechanisms underlying CD to aid the development of novel therapeutic strategies for this condition. Based on the transcriptome data from patients with CD, this study used an unsupervised learning method to construct gene co-expression molecular subgroups and the R and SPSS software to identify the biological, clinical, and genetic characteristics and signatures of each subgroup. Two subgroups were analyzed. Compared to subgroup II, subgroup I consisted of older patients with a more limited range of disease presentation and had a higher number of smokers. The specific genes associated with this subgroup, including CDKN2B, solute carrier family 22 member 5, and phytanoyl-CoA 2-hydroxylase, can be targeted for managing intestinal dysbacteriosis. The number of patients showing infiltrating lesions was higher, the number of smokers was lower, and CD severity was worse in patients in subgroup II than those in subgroup I. The specific genes relevant to subgroup II included cluster of differentiation 44, tryptophanyl-tRNA synthetase, and interleukin 10 receptor, alpha subunit, which may be related to viral infection. The present study segregated patients with CD into 2 subgroups; the findings reported herein provide a new theoretical basis for the diagnosis and treatment of CD and could aid a thorough identification of potential therapeutic targets for this disease.

The Experimentalist's Guide to Machine Learning for Small Molecule Design.

Initially part of the field of artificial intelligence, machine learning (ML) has become a booming research area since branching out into its own field in the 1990s. After three decades of refinement, ML algorithms have accelerated scientific developments across a variety of research topics. The field of small molecule design is no exception, and an increasing number of researchers are applying ML techniques in their pursuit of discovering, generating, and optimizing small molecule compounds. The goal of this review is to provide simple, yet descriptive, explanations of some of the most commonly utilized ML algorithms in the field of small molecule design along with those that are highly applicable to an experimentally focused audience. The algorithms discussed here span across three ML paradigms: supervised learning, unsupervised learning, and ensemble methods. Examples from the published literature will be provided for each algorithm. Some common pitfalls of applying ML to biological and chemical data sets will also be explained, alongside a brief summary of a few more advanced paradigms, including reinforcement learning and semi-supervised learning.

UPLC-QDA and machine learning for distinguishing different commodity specifications of Fritillariae Cirrhosae Bulbus and application of data augmentation technology

This study aimed to establish a method based on machine learning technology for accurately predicting the commodity specifications of Fritillariae Cirrhosae Bulbus and explore the application of data augmentation technology in the field of drug analysis. The correlation optimized warping(COW) algorithm was used to perform peak calibration on the UPLC-QDA multi-channel superimposed data of 30 batches of samples, and the data were normalized. Through unsupervised learning methods such as clustering analysis, principal component analysis(PCA), and correlation analysis, the general characteristics of the data were understood. Then, the logistic regression algorithm was used for supervised learning on the data, and the condition tabular generative adversarial networks(CTGAN) was used to generate a large amount of data. Logistic regression classification models were trained separately using the real data and the data generated by CTGAN, and these models were evaluated. The logistic regression model trained with real data achieved cross-validation and test set accuracies of 0.95 and 1.00, respectively, while the logistic regression model trained with both real and CTGAN-generated data achieved cross-validation and test set accuracies of 0.99 and 1.00, respectively. The results indicate that machine learning can accurately predict the classification of Songbei, Qingbei, and Lubeibased on UPLC-QDA detection data. CTGAN-generated data can partially compensate for the lack of data in drug analysis, improving the accuracy and predictive ability of machine learning models.

Graph Neural Networks for Intelligent Transportation Systems: A Survey

Graph neural networks (GNNs) have been extensively used in a wide variety of domains in recent years. Owing to their power in analyzing graph-structured data, they have become broadly popular in intelligent transportation systems (ITS) applications as well. Despite their widespread applications in different transportation domains, there is no comprehensive review of recent advancements and future research directions that covers all transportation areas. Accordingly, in this survey, for the first time, we provide an overview of GNN studies in the general domain of ITS. Unlike previous surveys, which have been limited to traffic forecasting problems, we explore how GNN frameworks have evolved for different ITS applications, including traffic forecasting, demand prediction, autonomous vehicles, intersection management, parking management, urban planning, and transportation safety. Also, we micro-categorize the studies based on their transportation application to identify domain-specific research directions, opportunities, and challenges, which have been missing in previous surveys. Moreover, we identify unique and undiscussed research opportunities and directions, which is the result of reviewing a wide range of transportation applications. The neglected role of edge and graph learning in ITS applications, developing multi-modal models, and exploiting the power of unsupervised and reinforcement learning methods for developing more powerful GNNs are some examples of such new discussions in this survey. Finally, we have identified popular baseline models and datasets in each transportation domain, which facilitate the development and evaluation of future GNN-based frameworks.

A decentralized, prospective, observational study to collect real-world data from patients with myasthenia gravis using smartphones.

We conducted a 3-month, prospective study in a population of patients with Myasthenia Gravis (MG), utilizing a fully decentralized approach for recruitment and monitoring (ClinicalTrials.gov Identifier: NCT04590716). The study objectives were to assess the feasibility of collecting real-world data through a smartphone-based research platform, in order to characterize symptom involvement during MG exacerbations. Primary data collection included daily electronically recorded patient-reported outcomes (ePROs) on the presence of MG symptoms, the level of symptom severity (using the MG-Activities of Daily Living assessment, MG-ADL), and exacerbation status. Participants were also given the option to contribute data on their physical activity levels from their own wearable devices. The study enrolled and onboarded 113 participants across 37 US states, and 73% (N= 82) completed the study. The mean age of participants was 53.6 years, 60% were female. Participants were representative of a moderate to severe MG phenotype, with frequent exacerbations, high symptom burden and multiple comorbidities. 55% of participants (N=45) reported MG exacerbations during the study, with an average of 6.3 exacerbation days per participant. Median average MG-ADL scores for participants during self-reported exacerbation and non-exacerbation periods were 7 (interquartile range 4-9, range 1-19) and 0.3 (interquartile range 0-0.8, range 0-9), respectively. Analyses examining relationships between patient-reported and patient-generated health data streams and exacerbation status demonstrated concordance between self-reported MG-ADL scores and exacerbation status, and identified features that may be used to understand and predict the onset of MG symptom exacerbations, including: 1.) dynamic changes in day-to-day symptom reporting and severity 2.) daily step counts as a measure of physical activity and 3.) clinical characteristics of the patient, including the amount of time since their initial diagnosis and their active medications related to MG treatment. Finally, application of unsupervised machine learning methods identified unique clusters of exacerbation subtypes, each with their own specific representation of symptoms and symptom severity. While these symptom signatures require further study and validation, our results suggest that digital phenotyping, characterized by increased multidimensionality and frequency of the data collection, holds promise for furthering our understanding of clinically significant exacerbations and reimagining the approach to treating MG as a heterogeneous condition.

FedUSC: Collaborative Unsupervised Representation Learning From Decentralized Data for Internet of Things

Federated Learning (FL) lately has shown much promise in improving the shared model and preserving data privacy. However, these existing methods are only of limited utility in the Internet of Things (IoT) scenarios, as they either heavily depend on high-quality labeled data or only perform well under idealized conditions, which typically cannot be found in practical applications. In this paper, we propose a novel federated unsupervised learning method for image classification without the use of any ground truth annotations. In IoT scenarios, a big challenge is that decentralized data among multiple clients is normally non-IID, leading to performance degradation. To address this issue, we further propose a dynamic update mechanism that can decide how to update the local model based on weights divergence. Extensive experiments show that our method outperforms all baseline methods by large margins, including +6.67% on CIFAR-10, +5.15% on STL-10, and +8.44% on SVHN in terms of classification accuracy. In particular, we obtain promising results on Mini-ImageNet and COVID-19 datasets and outperform several federated unsupervised learning methods under non-IID settings.

Optimized deep belief network and unsupervised deep learning methods for disease prediction

Due to the vast amount of patient health data, automated healthcare systems still struggle to classify and diagnose various ailments. Learning redundant data also reduces categorization accuracy. A Deep Belief Network (DBN) has been used to precisely extract the most important aspects from clinical data by ignoring irrelevant/redundant features. Due of many learning variables, training is complicated. Similarly, the hybrid model has been employed by ensemble Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) to categorize diseases. But, its efficiency depends on the proper choice of kernels and hyper-parameters. Therefore, this paper develops an efficient feature extraction and classification model for healthcare systems. First, several medical data related to the patient’s health are collected. Then, an Optimized DBN (ODBN) model is presented for maximizing the accurateness of DBN by optimizing the learning variables depends on the Ant Lion Optimization (ALO) algorithm. With learning ODBN, the most relevant features are extracted with reduced computational complexity. After that, the CNN-LSTM with Unsupervised Fine-tuned Deep Self-Organizing Map (UFDSOM)-based classifier model is designed to categorize the extracted features into categories of illnesses. In this novel classifier, dropout normalization and parameter tuning processes are applied to avoid overfitting and optimize the hyper-parameters, which results in a less training period. In the end, studies utilizing publically accessible datasets show that the ODBN with CNN-LSTM-UFDSOM system outperforms classical models by 98.23%.