Semi-Supervised Discriminative Classification Robust to Sample-Outliers and Feature-Noises

Generalized and Robust Least Squares Regression

As a simple yet effective method, least squares regression (LSR) is extensively applied for data regression and classification. Combined with sparse representation, LSR can be extended to feature selection (FS) as well, in which l1 regularization is often applied in embedded FS algorithms. However, because the loss function is in the form of squared error, LSR and its variants are sensitive to noises, which significantly degrades the effectiveness and performance of classification and FS. To cope with the problem, we propose a generalized and robust LSR (GRLSR) for classification and FS, which is made up of arbitrary concave loss function and the l2,p -norm regularization term. Meanwhile, an iterative algorithm is applied to efficiently deal with the nonconvex minimization problem, in which an additional weight to suppress the effect of noises is added to each data point. The weights can be automatically assigned according to the error of the samples. When the error is large, the value of the corresponding weight is small. It is this mechanism that allows GRLSR to reduce the impact of noises and outliers. According to the different formulations of the concave loss function, four specific methods are proposed to clarify the essence of the framework. Comprehensive experiments on corrupted datasets have proven the advantage of the proposed method.

Brain connectivity for subtypes of parkinson's disease using structural MRI

Objective. Delineating Parkinson's disease (PD) into distinct subtypes is a major challenge. Most studies use clinical symptoms to label PD subtypes while our work uses an imaging-based data-mining approach to subtype PD. Our study comprises two major objectives - firstly, subtyping Parkinson's patients based on grey matter information from structural magnetic resonance imaging scans of human brains; secondly, comparative structural brain connectivity analysis of PD subtypes derived from the former step.Approach. Source-based-morphometry decomposition was performed on 131 Parkinson's patients and 78 healthy controls from PPMI dataset, to derive at components (regions) with significance in disease and high effect size. The loading coefficients of significant components were thresholded for arriving at subtypes. Further, regional grey matter maps of subtype-specific subjects were separately parcellated and employed for construction of subtype-specific association matrices using Pearson correlation. These association matrices were binarized using sparsity threshold and leveraged for structural brain connectivity analysis using network metrics.Main results. Two distinct Parkinson's subtypes (namely A and B) were detected employing loadings of two components satisfying the selection criteria, and a third subtype (AB) was detected, common to these two components. Subtype A subjects were highly weighted in inferior, middle and superior frontal gyri while subtype B subjects in inferior, middle and superior temporal gyri. Network metrics analyses through permutation test revealed significant inter-subtype differences (p < 0.05) in clustering coefficient, local efficiency, participation coefficient and betweenness centrality. Moreover, hubs were obtained using betweenness centrality and mean network degree.Significance. MRI-based data-driven subtypes show frontal and temporal lobes playing a key role in PD. Graph theory-driven brain network analyses could untangle subtype-specific differences in structural brain connections showing differential network architecture. Replication of these initial results in other Parkinson's datasets may be explored in future. Clinical Relevance- Investigating structural brain connections in Parkinson's disease may provide subtype-specific treatment.

Robust Supervised and Semisupervised Least Squares Regression Using ℓ2,p-Norm Minimization

Least squares regression (LSR) is widely applied in statistics theory due to its theoretical solution, which can be used in supervised, semisupervised, and multiclass learning. However, LSR begins to fail and its discriminative ability cannot be guaranteed when the original data have been corrupted and noised. In reality, the noises are unavoidable and could greatly affect the error construction in LSR. To cope with this problem, a robust supervised LSR (RSLSR) is proposed to eliminate the effect of noises and outliers. The loss function adopts l2,p -norm ( ) instead of square loss. In addition, the probability weight is added to each sample to determine whether the sample is a normal point or not. Its physical meaning is very clear, in which if the point is normal, the probability value is 1; otherwise, the weight is 0. To effectively solve the concave problem, an iterative algorithm is introduced, in which additional weights are added to penalize normal samples with large errors. We also extend RSLSR to robust semisupervised LSR (RSSLSR) to fully utilize the limited labeled samples. A large number of classification performances on corrupted data illustrate the robustness of the proposed methods.

Machine learning models for diagnosis and prognosis of Parkinson's disease using brain imaging: general overview, main challenges, and future directions

Parkinson's disease (PD) is a progressive and complex neurodegenerative disorder associated with age that affects motor and cognitive functions. As there is currently no cure, early diagnosis and accurate prognosis are essential to increase the effectiveness of treatment and control its symptoms. Medical imaging, specifically magnetic resonance imaging (MRI), has emerged as a valuable tool for developing support systems to assist in diagnosis and prognosis. The current literature aims to improve understanding of the disease's structural and functional manifestations in the brain. By applying artificial intelligence to neuroimaging, such as deep learning (DL) and other machine learning (ML) techniques, previously unknown relationships and patterns can be revealed in this high-dimensional data. However, several issues must be addressed before these solutions can be safely integrated into clinical practice. This review provides a comprehensive overview of recent ML techniques analyzed for the automatic diagnosis and prognosis of PD in brain MRI. The main challenges in applying ML to medical diagnosis and its implications for PD are also addressed, including current limitations for safe translation into hospitals. These challenges are analyzed at three levels: disease-specific, task-specific, and technology-specific. Finally, potential future directions for each challenge and future perspectives are discussed.

Unsupervised Feature Selection With Weighted and Projected Adaptive Neighbors

In the field of data mining, how to deal with high-dimensional data is a fundamental problem. If they are used directly, it is not only computationally expensive but also difficult to obtain satisfactory results. Unsupervised feature selection is designed to reduce the dimension of data by finding a subset of features in the absence of labels. Many unsupervised methods perform feature selection by exploring spectral analysis and manifold learning, such that the intrinsic structure of data can be preserved. However, most of these methods ignore a fact: due to the existence of noise features, the intrinsic structure directly built from original data may be unreliable. To solve this problem, a new unsupervised feature selection model is proposed. The graph structure, feature weights, and projection matrix are learned simultaneously, such that the intrinsic structure is constructed by the data that have been feature weighted and projected. For each data point, its nearest neighbors are acquired in the process of graph construction. Therefore, we call them adaptive neighbors. Besides, an additional constraint is added to the proposed model. It requires that a graph, corresponding to a similarity matrix, should contain exactly c connected components. Then, we present an optimization algorithm to solve the proposed model. Next, we discuss the method of determining the regularization parameter γ in our proposed method and analyze the computational complexity of the optimization algorithm. Finally, experiments are implemented on both synthetic and real-world datasets to demonstrate the effectiveness of the proposed method.

Voiceprint and machine learning models for early detection of bulbar dysfunction in ALS

BACKGROUND AND OBJECTIVE

Bulbar dysfunction is a term used in amyotrophic lateral sclerosis (ALS). It refers to motor neuron disability in the corticobulbar area of the brainstem which leads to a dysfunction of speech and swallowing. One of the earliest symptoms of bulbar dysfunction is voice deterioration characterized by grossly defective articulation, extremely slow laborious speech, marked hypernasality and severe harshness. Recently, research efforts have focused on voice analysis to capture this dysfunction. The main aim of this paper is to provide a new methodology to diagnose this dysfunction automatically at early stages of the disease, earlier than clinicians can do.

METHODS

The study focused on the creation of a voiceprint consisting of a pattern generated from the quasi-periodic components of a steady portion of the five Spanish vowels and the computation of the five principal and independent components of this pattern. Then, a set of statistically significant features was obtained using multivariate analysis of variance and the outcomes of the most common supervised classification models were obtained.

RESULTS

The best model (random forest) obtained an accuracy, sensitivity and specificity of 88.3%, 85.0% and 95.0% respectively when classifying bulbar vs. control participants but the results worsened when classifying bulbar vs. no-bulbar patients (accuracy, sensitivity and specificity of 78.7%, 80.0% and 77.5% respectively for support vector machines). Due to the great uncertainty found in the annotated corpus of the ALS patients without bulbar involvement, we used a safe semi-supervised support vector machine to relabel the ALS participants diagnosed without bulbar involvement as bulbar and no-bulbar. The performance of the results obtained increased, especially when classifying bulbar and no-bulbar patients obtaining an accuracy, sensitivity and specificity of 91.0%, 83.3% and 100.0% respectively for support vector machines. This demonstrates that our model can improve the diagnosis of bulbar dysfunction compared not only with clinicians, but also the methods published to date.

CONCLUSIONS

The results obtained demonstrate the efficiency and applicability of the methodology presented in this paper. It may lead to the development of a cheap and easy-to-use tool to identify this dysfunction in early stages of the disease and monitor progress.

Orthogonal latent space learning with feature weighting and graph learning for multimodal Alzheimer's disease diagnosis

Recent studies have shown that multimodal neuroimaging data provide complementary information of the brain and latent space-based methods have achieved promising results in fusing multimodal data for Alzheimer's disease (AD) diagnosis. However, most existing methods treat all features equally and adopt nonorthogonal projections to learn the latent space, which cannot retain enough discriminative information in the latent space. Besides, they usually preserve the relationships among subjects in the latent space based on the similarity graph constructed on original features for performance boosting. However, the noises and redundant features significantly corrupt the graph. To address these limitations, we propose an Orthogonal Latent space learning with Feature weighting and Graph learning (OLFG) model for multimodal AD diagnosis. Specifically, we map multiple modalities into a common latent space by orthogonal constrained projection to capture the discriminative information for AD diagnosis. Then, a feature weighting matrix is utilized to sort the importance of features in AD diagnosis adaptively. Besides, we devise a regularization term with learned graph to preserve the local structure of the data in the latent space and integrate the graph construction into the learning processing for accurately encoding the relationships among samples. Instead of constructing a similarity graph for each modality, we learn a joint graph for multiple modalities to capture the correlations among modalities. Finally, the representations in the latent space are projected into the target space to perform AD diagnosis. An alternating optimization algorithm with proved convergence is developed to solve the optimization objective. Extensive experimental results show the effectiveness of the proposed method.

A Computerized Analysis with Machine Learning Techniques for the Diagnosis of Parkinson's Disease: Past Studies and Future Perspectives

According to the World Health Organization (WHO), Parkinson's disease (PD) is a neurodegenerative disease of the brain that causes motor symptoms including slower movement, rigidity, tremor, and imbalance in addition to other problems like Alzheimer's disease (AD), psychiatric problems, insomnia, anxiety, and sensory abnormalities. Techniques including artificial intelligence (AI), machine learning (ML), and deep learning (DL) have been established for the classification of PD and normal controls (NC) with similar therapeutic appearances in order to address these problems and improve the diagnostic procedure for PD. In this article, we examine a literature survey of research articles published up to September 2022 in order to present an in-depth analysis of the use of datasets, various modalities, experimental setups, and architectures that have been applied in the diagnosis of subjective disease. This analysis includes a total of 217 research publications with a list of the various datasets, methodologies, and features. These findings suggest that ML/DL methods and novel biomarkers hold promising results for application in medical decision-making, leading to a more methodical and thorough detection of PD. Finally, we highlight the challenges and provide appropriate recommendations on selecting approaches that might be used for subgrouping and connection analysis with structural magnetic resonance imaging (sMRI), DaTSCAN, and single-photon emission computerized tomography (SPECT) data for future Parkinson's research.

Adaptive Data Structure Regularized Multiclass Discriminative Feature Selection

Feature selection (FS), which aims to identify the most informative subset of input features, is an important approach to dimensionality reduction. In this article, a novel FS framework is proposed for both unsupervised and semisupervised scenarios. To make efficient use of data distribution to evaluate features, the framework combines data structure learning (as referred to as data distribution modeling) and FS in a unified formulation such that the data structure learning improves the results of FS and vice versa. Moreover, two types of data structures, namely the soft and hard data structures, are learned and used in the proposed FS framework. The soft data structure refers to the pairwise weights among data samples, and the hard data structure refers to the estimated labels obtained from clustering or semisupervised classification. Both of these data structures are naturally formulated as regularization terms in the proposed framework. In the optimization process, the soft and hard data structures are learned from data represented by the selected features, and then, the most informative features are reselected by referring to the data structures. In this way, the framework uses the interactions between data structure learning and FS to select the most discriminative and informative features. Following the proposed framework, a new semisupervised FS (SSFS) method is derived and studied in depth. Experiments on real-world data sets demonstrate the effectiveness of the proposed method.

Deep Feature Space: A Geometrical Perspective

One of the most prominent attributes of Neural Networks (NNs) constitutes their capability of learning to extract robust and descriptive features from high dimensional data, like images. Hence, such an ability renders their exploitation as feature extractors particularly frequent in an abundance of modern reasoning systems. Their application scope mainly includes complex cascade tasks, like multi-modal recognition and deep Reinforcement Learning (RL). However, NNs induce implicit biases that are difficult to avoid or to deal with and are not met in traditional image descriptors. Moreover, the lack of knowledge for describing the intra-layer properties -and thus their general behavior- restricts the further applicability of the extracted features. With the paper at hand, a novel way of visualizing and understanding the vector space before the NNs' output layer is presented, aiming to enlighten the deep feature vectors' properties under classification tasks. Main attention is paid to the nature of overfitting in the feature space and its adverse effect on further exploitation. We present the findings that can be derived from our model's formulation and we evaluate them on realistic recognition scenarios, proving its prominence by improving the obtained results.

Advanced Dropout: A Model-Free Methodology for Bayesian Dropout Optimization

Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural networks (DNNs). We propose advanced dropout, a model-free methodology, to mitigate overfitting and improve the performance of DNNs. The advanced dropout technique applies a model-free and easily implemented distribution with parametric prior, and adaptively adjusts dropout rate. Specifically, the distribution parameters are optimized by stochastic gradient variational Bayes in order to carry out an end-to-end training. We evaluate the effectiveness of the advanced dropout against nine dropout techniques on seven computer vision datasets (five small-scale datasets and two large-scale datasets) with various base models. The advanced dropout outperforms all the referred techniques on all the datasets. We further compare the effectiveness ratios and find that advanced dropout achieves the highest one on most cases. Next, we conduct a set of analysis of dropout rate characteristics, including convergence of the adaptive dropout rate, the learned distributions of dropout masks, and a comparison with dropout rate generation without an explicit distribution. In addition, the ability of overfitting prevention is evaluated and confirmed. Finally, we extend the application of the advanced dropout to uncertainty inference, network pruning, text classification, and regression. The proposed advanced dropout is also superior to the corresponding referred methods. Codes are available at https://github.com/PRIS-CV/AdvancedDropout.

Parkinson's Disease Classification and Clinical Score Regression via United Embedding and Sparse Learning From Longitudinal Data

Parkinson's disease (PD) is known as an irreversible neurodegenerative disease that mainly affects the patient's motor system. Early classification and regression of PD are essential to slow down this degenerative process from its onset. In this article, a novel adaptive unsupervised feature selection approach is proposed by exploiting manifold learning from longitudinal multimodal data. Classification and clinical score prediction are performed jointly to facilitate early PD diagnosis. Specifically, the proposed approach performs united embedding and sparse regression, which can determine the similarity matrices and discriminative features adaptively. Meanwhile, we constrain the similarity matrix among subjects and exploit the l_2,p norm to conduct sparse adaptive control for obtaining the intrinsic information of the multimodal data structure. An effective iterative optimization algorithm is proposed to solve this problem. We perform abundant experiments on the Parkinson's Progression Markers Initiative (PPMI) data set to verify the validity of the proposed approach. The results show that our approach boosts the performance on the classification and clinical score regression of longitudinal data and surpasses the state-of-the-art approaches.

Low-rank sparse feature selection with incomplete labels for Alzheimer's disease progression prediction

BACKGROUND

How to predict the cognitive performance of Alzheimer's disease (AD) and identify the informative neuroimaging markers is essential for timely treatment and possible delay of the disease. However, incomplete labeled samples and noises in neuroimaging data pose challenges to building reliable and robust prediction models. In this paper, we present a model named Low-rank Sparse Feature Selection with Incomplete Labels (LSFSIL) for predicting cognitive performance and identifying informative neuroimaging markers with MRI data and incomplete cognitive scores.

METHOD

We propose a sparse matrix decomposition method to decompose the incomplete cognitive score matrix into two parts for recovering missing scores and utilizing incomplete labeled data. The former is the recovered cognitive score matrix without missing values. To make the recovered scores close to the real ones, a manifold regularizer is devised to fit the label distribution for capturing the label correlations locally. The latter is a ℓ₁-norm regularized matrix which represents the associated errors. Next, a low-rank regression model that regards the recovered matrix as the target is developed to increase the robustness to noises and outliers. Besides, ℓ_2,1-norm is introduced into the objective function as a sparse regularization to identify the important features.

RESULTS

Experimental results demonstrate that LSFSIL achieves higher performance and outperforms several state-of-the-art feature selection approaches. Moreover, the neuroimaging markers selected by LSFSIL are consistent with the previous AD studies.

CONCLUSIONS

LSFSIL is effective in informative neuroimaging marker identification for cognitive performance prediction with incomplete labeled data.

Adversarial concept drift detection under poisoning attacks for robust data stream mining

Continuous learning from streaming data is among the most challenging topics in the contemporary machine learning. In this domain, learning algorithms must not only be able to handle massive volume of rapidly arriving data, but also adapt themselves to potential emerging changes. The phenomenon of evolving nature of data streams is known as concept drift. While there is a plethora of methods designed for detecting its occurrence, all of them assume that the drift is connected with underlying changes in the source of data. However, one must consider the possibility of a malicious injection of false data that simulates a concept drift. This adversarial setting assumes a poisoning attack that may be conducted in order to damage the underlying classification system by forcing an adaptation to false data. Existing drift detectors are not capable of differentiating between real and adversarial concept drift. In this paper, we propose a framework for robust concept drift detection in the presence of adversarial and poisoning attacks. We introduce the taxonomy for two types of adversarial concept drifts, as well as a robust trainable drift detector. It is based on the augmented restricted Boltzmann machine with improved gradient computation and energy function. We also introduce Relative Loss of Robustness-a novel measure for evaluating the performance of concept drift detectors under poisoning attacks. Extensive computational experiments, conducted on both fully and sparsely labeled data streams, prove the high robustness and efficacy of the proposed drift detection framework in adversarial scenarios.

On the Suitability of Bagging-Based Ensembles with Borderline Label Noise

Real-world classification data usually contain noise, which can affect the accuracy of the models and their complexity. In this context, an interesting approach to reduce the effects of noise is building ensembles of classifiers, which traditionally have been credited with the ability to tackle difficult problems. Among the alternatives to build ensembles with noisy data, bagging has shown some potential in the specialized literature. However, existing works in this field are limited and only focus on the study of noise based on a random mislabeling, which is unlikely to occur in real-world applications. Recent research shows that other types of noise, such as that occurring at class boundaries, are more common and challenging for classification algorithms. This paper delves into the analysis of the usage of bagging techniques in these complex problems, in which noise affects the decision boundaries among classes. In order to investigate whether bagging is able to reduce the impact of borderline noise, an experimental study is carried out considering a large number of datasets with different noise levels, and several noise models and classification algorithms. The results obtained reflect that bagging obtains a better accuracy and robustness than the individual models with this complex type of noise. The highest improvements in average accuracy are around 2–4% and are generally found at medium-high noise levels (from 15–20% onwards). The partial consideration of noisy samples when creating the subsamples from the original training set in bagging can make it so that only some parts of the decision boundaries among classes are impaired when building each model, reducing the impact of noise in the global system.

Multi-center sparse learning and decision fusion for automatic COVID-19 diagnosis

The coronavirus disease 2019 (COVID-19) pandemic caused by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to a sharp increase in hospitalized patients with multi-organ disease pneumonia. Early and automatic diagnosis of COVID-19 is essential to slow down the spread of this epidemic and reduce the mortality of patients infected with SARS-CoV-2. In this paper, we propose a joint multi-center sparse learning (MCSL) and decision fusion scheme exploiting chest CT images for automatic COVID-19 diagnosis. Specifically, considering the inconsistency of data in multiple centers, we first convert CT images into histogram of oriented gradient (HOG) images to reduce the structural differences between multi-center data and enhance the generalization performance. We then exploit a 3-dimensional convolutional neural network (3D-CNN) model to learn the useful information between and within 3D HOG image slices and extract multi-center features. Furthermore, we employ the proposed MCSL method that learns the intrinsic structure between multiple centers and within each center, which selects discriminative features to jointly train multi-center classifiers. Finally, we fuse these decisions made by these classifiers. Extensive experiments are performed on chest CT images from five centers to validate the effectiveness of the proposed method. The results demonstrate that the proposed method can improve COVID-19 diagnosis performance and outperform the state-of-the-art methods.

Classification of Initial Stages of Alzheimer’s Disease through Pet Neuroimaging Modality and Deep Learning: Quantifying the Impact of Image Filtering Approaches

Alzheimer’s disease (AD) is a leading health concern affecting the elderly population worldwide. It is defined by amyloid plaques, neurofibrillary tangles, and neuronal loss. Neuroimaging modalities such as positron emission tomography (PET) and magnetic resonance imaging are routinely used in clinical settings to monitor the alterations in the brain during the course of progression of AD. Deep learning techniques such as convolutional neural networks (CNNs) have found numerous applications in healthcare and other technologies. Together with neuroimaging modalities, they can be deployed in clinical settings to learn effective representations of data for different tasks such as classification, segmentation, detection, etc. Image filtering methods are instrumental in making images viable for image processing operations and have found numerous applications in image-processing-related tasks. In this work, we deployed 3D-CNNs to learn effective representations of PET modality data to quantify the impact of different image filtering approaches. We used box filtering, median filtering, Gaussian filtering, and modified Gaussian filtering approaches to preprocess the images and use them for classification using 3D-CNN architecture. Our findings suggest that these approaches are nearly equivalent and have no distinct advantage over one another. For the multiclass classification task between normal control (NC), mild cognitive impairment (MCI), and AD classes, the 3D-CNN architecture trained using Gaussian-filtered data performed the best. For binary classification between NC and MCI classes, the 3D-CNN architecture trained using median-filtered data performed the best, while, for binary classification between AD and MCI classes, the 3D-CNN architecture trained using modified Gaussian-filtered data performed the best. Finally, for binary classification between AD and NC classes, the 3D-CNN architecture trained using box-filtered data performed the best.

A Deep-Learning Based Visual Sensing Concept for a Robust Classification of Document Images under Real-World Hard Conditions

This paper’s core objective is to develop and validate a new neurocomputing model to classify document images in particularly demanding hard conditions such as image distortions, image size variance and scale, a huge number of classes, etc. Document classification is a special machine vision task in which document images are categorized according to their likelihood. Document classification is by itself an important topic for the digital office and it has several usages. Additionally, different methods for solving this problem have been presented in various studies; their respectively reached performance is however not yet good enough. This task is very tough and challenging. Thus, a novel, more accurate and precise model is needed. Although the related works do reach acceptable accuracy values for less hard conditions, they generally fully fail in the face of those above-mentioned hard, real-world conditions, including, amongst others, distortions such as noise, blur, low contrast, and shadows. In this paper, a novel deep CNN model is developed, validated and benchmarked with a selection of the most relevant recent document classification models. Additionally, the model’s sensitivity was significantly improved by injecting different artifacts during the training process. In the benchmarking, it does clearly outperform all others by at least 4%, thus reaching more than 96% accuracy.

Single and Combined Neuroimaging Techniques for Alzheimer's Disease Detection

Alzheimer's disease (AD) consists of the gradual process of decreasing volume and quality of neuron connection in the brain, which consists of gradual synaptic integrity and loss of cognitive functions. In recent years, there has been significant attention in AD classification and early detection with machine learning algorithms. There are different neuroimaging techniques for capturing data and using it for the classification task. Input data as images will help machine learning models to detect different biomarkers for AD classification. This marker has a more critical role for AD detection than other diseases because beta-amyloid can extract complex structures with some metal ions. Most researchers have focused on using 3D and 4D convolutional neural networks for AD classification due to reasonable amounts of data. Also, combination neuroimaging techniques like functional magnetic resonance imaging and positron emission tomography for AD detection have recently gathered much attention. However, gathering a combination of data can be expensive, complex, and tedious. For time consumption reasons, most patients prefer to throw one of the neuroimaging techniques. So, in this review article, we have surveyed different research studies with various neuroimaging techniques and ML methods to see the effect of using combined data as input. The result has shown that the use of the combination method would increase the accuracy of AD detection. Also, according to the sensitivity metrics from different machine learning methods, MRI and fMRI showed promising results.

Half-Quadratic Minimization for Unsupervised Feature Selection on Incomplete Data

Unsupervised feature selection (UFS) is a popular technique of reducing the dimensions of high-dimensional data. Previous UFS methods were often designed with the assumption that the whole information in the data set is observed. However, incomplete data sets that contain unobserved information can be often found in real applications, especially in industry. Thus, these existing UFS methods have a limitation on conducting feature selection on incomplete data. On the other hand, most existing UFS methods did not consider the sample importance for feature selection, i.e., different samples have various importance. As a result, the constructed UFS models easily suffer from the influence of outliers. This article investigates a new UFS method for conducting UFS on incomplete data sets to investigate the abovementioned issues. Specifically, the proposed method deals with unobserved information by using an indicator matrix to filter it out the process of feature selection and reduces the influence of outliers by employing the half-quadratic minimization technique to automatically assigning outliers with small or even zero weights and important samples with large weights. This article further designs an alternative optimization strategy to optimize the proposed objective function as well as theoretically and experimentally prove the convergence of the proposed optimization strategy. Experimental results on both real and synthetic incomplete data sets verified the effectiveness of the proposed method compared with previous methods, in terms of clustering performance on the low-dimensional space of the high-dimensional data.

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.

Machine Learning Methods with Decision Forests for Parkinson’s Detection

Biomedical engineers prefer decision forests over traditional decision trees to design state-of-the-art Parkinson’s Detection Systems (PDS) on massive acoustic signal data. However, the challenges that the researchers are facing with decision forests is identifying the minimum number of decision trees required to achieve maximum detection accuracy with the lowest error rate. This article examines two recent decision forest algorithms Systematically Developed Forest (SysFor), and Decision Forest by Penalizing Attributes (ForestPA) along with the popular Random Forest to design three distinct Parkinson’s detection schemes with optimum number of decision trees. The proposed approach undertakes minimum number of decision trees to achieve maximum detection accuracy. The training and testing samples and the density of trees in the forest are kept dynamic and incremental to achieve the decision forests with maximum capability for detecting Parkinson’s Disease (PD). The incremental tree densities with dynamic training and testing of decision forests proved to be a better approach for detection of PD. The proposed approaches are examined along with other state-of-the-art classifiers including the modern deep learning techniques to observe the detection capability. The article also provides a guideline to generate ideal training and testing split of two modern acoustic datasets of Parkinson’s and control subjects donated by the Department of Neurology in Cerrahpaşa, Istanbul and Departamento de Matemáticas, Universidad de Extremadura, Cáceres, Spain. Among the three proposed detection schemes the Forest by Penalizing Attributes (ForestPA) proved to be a promising Parkinson’s disease detector with a little number of decision trees in the forest to score the highest detection accuracy of 94.12% to 95.00%.

A Survey on Deep Learning for Neuroimaging-Based Brain Disorder Analysis

Deep learning has recently been used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET), and it has achieved significant performance improvements over traditional machine learning in computer-aided diagnosis of brain disorders. This paper reviews the applications of deep learning methods for neuroimaging-based brain disorder analysis. We first provide a comprehensive overview of deep learning techniques and popular network architectures by introducing various types of deep neural networks and recent developments. We then review deep learning methods for computer-aided analysis of four typical brain disorders, including Alzheimer's disease, Parkinson's disease, Autism spectrum disorder, and Schizophrenia, where the first two diseases are neurodegenerative disorders and the last two are neurodevelopmental and psychiatric disorders, respectively. More importantly, we discuss the limitations of existing studies and present possible future directions.

Actuator and Sensor Fault Classification for Wind Turbine Systems Based on Fast Fourier Transform and Uncorrelated Multi-Linear Principal Component Analysis Techniques

In response to the high demand of the operation reliability and predictive maintenance, health monitoring and fault diagnosis and classification have been paramount for complex industrial systems (e.g., wind turbine energy systems). In this study, data-driven fault diagnosis and fault classification strategies are addressed for wind turbine energy systems under various faulty scenarios. A novel algorithm is addressed by integrating fast Fourier transform and uncorrelated multi-linear principal component analysis techniques in order to achieve effective three-dimensional space visualization for fault diagnosis and classification under a variety of actuator and sensor faulty scenarios in 4.8 MW wind turbine benchmark systems. Moreover, comparison studies are implemented by using multi-linear principal component analysis with and without fast Fourier transform, and uncorrelated multi-linear principal component analysis with and without fast Fourier transformation data pre-processing, respectively. The effectiveness of the proposed algorithm is demonstrated and validated via the wind turbine benchmark.

Logistic Regression Confined by Cardinality-Constrained Sample and Feature Selection

Many vision-based applications rely on logistic regression for embedding classification within a probabilistic context, such as recognition in images and videos or identifying disease-specific image phenotypes from neuroimages. Logistic regression, however, often performs poorly when trained on data that is noisy, has irrelevant features, or when the samples are distributed across the classes in an imbalanced setting; a common occurrence in visual recognition tasks. To deal with those issues, researchers generally rely on ad-hoc regularization techniques or model a subset of these issues. We instead propose a mathematically sound logistic regression model that selects a subset of (relevant) features and (informative and balanced) set of samples during the training process. The model does so by applying cardinality constraints (via l₀-'norm' sparsity) on the features and samples. l₀ defines sparsity in mathematical settings but in practice has mostly been approximated (e.g., via l₁ or its variations) for computational simplicity. We prove that a local minimum to the non-convex optimization problems induced by cardinality constraints can be computed by combining block coordinate descent with penalty decomposition. On synthetic, image recognition, and neuroimaging datasets, we show that the accuracy of the method is higher than alternative methods and classifiers commonly used in the literature.

Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI

Structural magnetic resonance imaging (sMRI) has been widely used for computer-aided diagnosis of neurodegenerative disorders, e.g., Alzheimer's disease (AD), due to its sensitivity to morphological changes caused by brain atrophy. Recently, a few deep learning methods (e.g., convolutional neural networks, CNNs) have been proposed to learn task-oriented features from sMRI for AD diagnosis, and achieved superior performance than the conventional learning-based methods using hand-crafted features. However, these existing CNN-based methods still require the pre-determination of informative locations in sMRI. That is, the stage of discriminative atrophy localization is isolated to the latter stages of feature extraction and classifier construction. In this paper, we propose a hierarchical fully convolutional network (H-FCN) to automatically identify discriminative local patches and regions in the whole brain sMRI, upon which multi-scale feature representations are then jointly learned and fused to construct hierarchical classification models for AD diagnosis. Our proposed H-FCN method was evaluated on a large cohort of subjects from two independent datasets (i.e., ADNI-1 and ADNI-2), demonstrating good performance on joint discriminative atrophy localization and brain disease diagnosis.

Robust adaptation regularization based on within-class scatter for domain adaptation

In many practical applications, the assumption that the distributions of the data employed for training and test are identical is rarely valid, which would result in a rapid decline in performance. To address this problem, the domain adaptation strategy has been developed in recent years. In this paper, we propose a novel unsupervised domain adaptation method, referred to as Robust Adaptation Regularization based on Within-Class Scatter (WCS-RAR), to simultaneously optimize the regularized loss, the within-class scatter, the joint distribution between domains, and the manifold consistency. On the one hand, to make the model robust against outliers, we adopt an l_2,1-norm based loss function in virtue of its row sparsity, instead of the widely-used l₂-norm based squared loss or hinge loss function to determine the residual. On the other hand, to well preserve the structure knowledge of the source data within the same class and strengthen the discriminant ability of the classifier, we incorporate the minimum within-class scatter into the process of domain adaptation. Lastly, to efficiently solve the resulting optimization problem, we extend the form of the Representer Theorem through the kernel trick, and thus derive an elegant solution for the proposed model. The extensive comparison experiments with the state-of-the-art methods on multiple benchmark data sets demonstrate the superiority of the proposed method.

Illuminating the Black Box: Interpreting Deep Neural Network Models for Psychiatric Research

Psychiatric research is often confronted with complex abstractions and dynamics that are not readily accessible or well-defined to our perception and measurements, making data-driven methods an appealing approach. Deep neural networks (DNNs) are capable of automatically learning abstractions in the data that can be entirely novel and have demonstrated superior performance over classical machine learning models across a range of tasks and, therefore, serve as a promising tool for making new discoveries in psychiatry. A key concern for the wider application of DNNs is their reputation as a "black box" approach-i.e., they are said to lack transparency or interpretability of how input data are transformed to model outputs. In fact, several existing and emerging tools are providing improvements in interpretability. However, most reviews of interpretability for DNNs focus on theoretical and/or engineering perspectives. This article reviews approaches to DNN interpretability issues that may be relevant to their application in psychiatric research and practice. It describes a framework for understanding these methods, reviews the conceptual basis of specific methods and their potential limitations, and discusses prospects for their implementation and future directions.

Quantitative Trait Module-Based Genetic Analysis of Alzheimer's Disease

The pathological features of Alzheimer's Disease (AD) first appear in the medial temporal lobe and then in other brain structures with the development of the disease. In this work, we investigated the association between genetic loci and subcortical structure volumes of AD on 393 samples in the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Brain subcortical structures were clustered into modules using Pearson's correlation coefficient of volumes across all samples. Module volumes were used as quantitative traits to identify not only the main effect loci but also the interactive effect loci for each module. Thirty-five subcortical structures were clustered into five modules, each corresponding to a particular brain structure/area, including the limbic system (module I), the corpus callosum (module II), thalamus-cerebellum-brainstem-pallidum (module III), the basal ganglia neostriatum (module IV), and the ventricular system (module V). Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment results indicate that the gene annotations of the five modules were distinct, with few overlaps between different modules. We identified several main effect loci and interactive effect loci for each module. All these loci are related to the function of module structures and basic biological processes such as material transport and signal transduction.

Tannic acid modified MoS2 nanosheet membranes with superior water flux and ion/dye rejection

Energy-efficient membranes are urgently needed for water desalination and separation due to ever-increasing demand for fresh water. However, it is extremely challenging to increase membrane water flux and simultaneously achieve high rejection rates of cations or organic dyes. Herein, we report a tannic acid (TA) assisted exfoliation method to fabricate TA-modified MoS₂ (TAMoS₂) nanosheets with high production yield (90 ± 5%). The TAMoS₂ nanosheets membranes show excellent non-swelling stability in water. It is found that a hybrid membrane with 1 wt% of TAMoS₂ in MoS₂ nanosheets demonstrates overall better performance than pure MoS₂ and TAMoS₂ membrane. Such a hybrid membrane with a thickness of 5 µm shows fast water flux at around 32 L m^-2 h^-1 (LMH) and >97% rejection of various cations under static diffusion mode. Under vacuum-driven filtration condition, the as-prepared hybrid membrane demonstrates ultrafast water flux of 15,000 ± 100 L/(m² h bar) and 99.87 ± 0.1% rejection of multiple model organic dyes. To the best of our knowledge, the above performances are superior to those of all MoS₂-based membranes reported previously in terms of water flux and ion/dye rejection. This work represents a leap forward towards the practical applications of 2D TAMoS₂ membranes in various engineering and environmental areas.

Supervised Discriminative Sparse PCA for Com-Characteristic Gene Selection and Tumor Classification on Multiview Biological Data

Principal component analysis (PCA) has been used to study the pathogenesis of diseases. To enhance the interpretability of classical PCA, various improved PCA methods have been proposed to date. Among these, a typical method is the so-called sparse PCA, which focuses on seeking sparse loadings. However, the performance of these methods is still far from satisfactory due to their limitation of using unsupervised learning methods; moreover, the class ambiguity within the sample is high. To overcome this problem, this paper developed a new PCA method, which is named the supervised discriminative sparse PCA (SDSPCA). The main innovation of this method is the incorporation of discriminative information and sparsity into the PCA model. Specifically, in contrast to the traditional sparse PCA, which imposes sparsity on the loadings, here, sparse components are obtained to represent the data. Furthermore, via the linear transformation, the sparse components approximate the given label information. On the one hand, sparse components improve interpretability over the traditional PCA, while on the other hand, they are have discriminative abilities suitable for classification purposes. A simple algorithm is developed, and its convergence proof is provided. SDSPCA has been applied to the common-characteristic gene selection and tumor classification on multiview biological data. The sparsity and classification performance of SDSPCA are empirically verified via abundant, reasonable, and effective experiments, and the obtained results demonstrate that SDSPCA outperforms other state-of-the-art methods.

Sparse Principal Component Analysis With Preserved Sparsity Pattern

Principal component analysis (PCA) is widely used for feature extraction and dimension reduction in pattern recognition and data analysis. Despite its popularity, the reduced dimension obtained from the PCA is difficult to interpret due to the dense structure of principal loading vectors. To address this issue, several methods have been proposed for sparse PCA, all of which estimate loading vectors with few non-zero elements. However, when more than one principal component is estimated, the associated loading vectors do not possess the same sparsity pattern. Therefore, it becomes difficult to determine a small subset of variables from the original feature space that have the highest contribution in the principal components. To address this issue, an adaptive block sparse PCA method is proposed. The proposed method is guaranteed to obtain the same sparsity pattern across all principal components. Experiments show that applying the proposed sparse PCA method can help improve the performance of feature selection for image processing applications. We further demonstrate that our proposed sparse PCA method can be used to improve the performance of blind source separation for functional magnetic resonance imaging data.

Parkinson's Disease Diagnosis via Joint Learning From Multiple Modalities and Relations

Parkinson's disease (PD) is a neurodegenerative progressive disease that mainly affects the motor systems of patients. To slow this disease deterioration, early and accurate diagnosis of PD is an effective way, which alleviates mental and physical sufferings by clinical intervention. In this paper, we propose a joint regression and classification framework for PD diagnosis via magnetic resonance and diffusion tensor imaging data. Specifically, we devise a unified multitask feature selection model to explore multiple relationships among features, samples, and clinical scores. We regress four clinical variables of depression, sleep, olfaction, cognition scores, as well as perform the classification of PD disease from the multimodal data. The multitask model explores the relationships at the level of clinical scores, image features, and subjects, to select the most informative and diseased-related features for diagnosis. The proposed method is evaluated on the public Parkinson's progression markers initiative dataset. The extensive experimental results show that the multitask framework can effectively boost the performance of regression and classification and outperforms other state-of-the-art methods. The computerized predictions of clinical scores and label for PD diagnosis may offer quantitative reference for decision support as well.