In this paper, a practical machine learning based fault diagnosis method is proposed for induction motors using experimental data. Various single- and multi- electrical and/or mechanical faults are applied to two identical induction motors in lab experiments. Stator currents and vibration signals of the motors are measured simultaneously during experiments and are used in developing the fault diagnosis method. Two signal processing techniques, Matching Pursuit (MP) and Discrete Wavelet Transform (DWT), are chosen for feature extraction. Three classification algorithms, support vector machine (SVM), K-nearest neighbors (KNN), and Ensemble, with 17 different classifiers offered in MATLAB Classification Learner toolbox are used in the study to evaluate the performance and suitability of different classifiers for induction motor fault diagnosis. It is found that five classifiers (Fine Gaussian SVM, Fine KNN, Weighted KNN, Bagged trees, and Subspace KNN) can provide near 100% classification accuracy for all faults applied to each motor, but the remaining 12 classifiers do not perform well. A novel curve fitting technique is developed to calculate features for the motors that stator currents or vibration signals under certain loadings are not tested for a particular fault. The proposed fault diagnosis method can accurately detect single- or multi- electrical and mechanical faults in induction motors.

Artificial intelligence methods are being increasingly applied across various domains, but their often opaque nature has raised concerns about accountability and trust. In response, the field of explainable AI (XAI) has emerged to address the need for human-understandable AI systems. Evolutionary computation (EC), a family of powerful optimization and learning algorithms, offers significant potential to contribute to XAI, and vice versa. This paper provides an introduction to XAI and reviews current techniques for explaining machine learning models. We then explore how EC can be leveraged in XAI and examine existing XAI approaches that incorporate EC techniques. Furthermore, we discuss the application of XAI principles within EC itself, investigating how these principles can illuminate the behavior and outcomes of EC algorithms, their (automatic) configuration, and the underlying problem landscapes they optimize. Finally, we discuss open challenges in XAI and highlight opportunities for future research at the intersection of XAI and EC. Our goal is to demonstrate EC’s suitability for addressing current explainability challenges and to encourage further exploration of these methods, ultimately contributing to the development of more understandable and trustworthy ML models and EC algorithms.

Metabolomics uses quantitative analyses of metabolites from tissues or bodily fluids to acquire a functional readout of the physiological state. Complex diseases arise from the influence of multiple factors, such as genetics, environment and lifestyle. Since genes, RNAs and proteins converge onto the terminal downstream metabolome, metabolomics datasets offer a rich source of information in a complex and convoluted presentation. Thus, powerful computational methods capable of deciphering the effects of many upstream influences have become increasingly necessary. In this review, the workflow of metabolic marker discovery is outlined from metabolite extraction to model interpretation and validation. Additionally, current metabolomics research in various complex disease areas is examined to identify gaps and trends in the use of several statistical and computational algorithms. Then, we highlight and discuss three advanced machine-learning algorithms, specifically ensemble learning, artificial neural networks, and genetic programming, that are currently less visible, but are budding with high potential for utility in metabolomics research. With an upward trend in the use of highly-accurate, multivariate models in the metabolomics literature, diagnostic biomarker panels of complex diseases are more recently achieving accuracies approaching or exceeding traditional diagnostic procedures. This review aims to provide an overview of computational methods in metabolomics and promote the use of up-to-date machine-learning and computational methods by metabolomics researchers.

Metabolomics studies use quantitative analyses of metabolites from body fluids or tissues in order to investigate a sequence of cellular processes and biological systems in response to genetic and environmental influences. This promises an immense potential for a better understanding of the pathogenesis of complex diseases. Most conventional metabolomics analysis methods exam one metabolite at a time and may overlook the synergistic effect of combining multiple metabolites. In this article, we proposed a new bioinformatics framework that infers the non-linear synergy among multiple metabolites using a symbolic model and subsequently, identify key metabolites using network analysis. Such a symbolic model is able to represent a complex non-linear relationship among a set of metabolites associated with osteoarthritis (OA) and is automatically learned using an evolutionary algorithm. Applied to the Newfoundland Osteoarthritis Study (NFOAS) dataset, our methodology was able to identify nine key metabolites including some known osteoarthritis-associated metabolites and some novel metabolic markers that have never been reported before. The results demonstrate the effectiveness of our methodology and more importantly, with further investigations, propose new hypotheses that can help better understand the OA disease. Biomedical research has entered a new era where a large number of molecules and different components in biological systems can be quantitatively examined to investigate the causes of common human diseases. However, given the complexity of biological systems, those causes may not contribute to diseases individually but through interactions. The identification of those interactions, or the synergy of multiple factors, is a very challenging task due to the computational limitation, as well as the lack of effective methodologies for investigating multiple factors simultaneously. In this study, we proposed to model such an interaction effect through a self-learning algorithm using mechanisms inspired by natural evolution. Moreover, by constructing a synergy network using those evolved models, we were able to identify a set of interacting factors associated with a particular disease.

Rational: Myelin loss is a characteristic feature of both ischemic white matter disease and its associated vascular dementia, and is a hallmark of chronic cerebral hypoperfusion due to carotid artery stenosis. Yet the cellular mechanisms involved in ischemic dysmyelination are not well-understood, and no effective treatment has emerged to prevent or slow hypoperfusion-related demyelination. In a study employing the bilateral common carotid artery stenosis (BCAS) mouse model, we found reduced cerebral blood flow velocity and arteriolar pulsatility, and confirmed that prolonged BCAS provoked myelin disruption. These pathological features were associated with marked cognitive decline, in the absence of evident damage to axons.

Colorectal cancer (CRC) has a high incident rate in both men and women and is affecting millions of people every year. Genome-wide association studies (GWAS) on CRC have successfully revealed common single-nucleotide polymorphisms (SNPs) associated with CRC risk. However, they can only explain a very limited fraction of the disease heritability. One reason may be the common uni-variable analyses in GWAS where genetic variants are examined one at a time. Given the complexity of cancers, the non-additive interaction effects among multiple genetic variants have a potential of explaining the missing heritability. In this study, we employed two powerful ensemble learning algorithms, random forests and gradient boosting machine (GBM), to search for SNPs that contribute to the disease risk through non-additive gene-gene interactions. We were able to find 44 possible susceptibility SNPs that were ranked most significant by both algorithms. Out of those 44 SNPs, 29 are in coding regions. The 29 genes include ARRDC5, DCC, ALK, and ITGA1, which have been found previously associated with CRC, and E2F3 and NID2, which are potentially related to CRC since they have known associations with other types of cancer. We performed pairwise and three-way interaction analysis on the 44 SNPs using information theoretical techniques and found 17 pairwise (p < 0.02) and 16 three-way (p ≤ 0.001) interactions among them. Moreover, functional enrichment analysis suggested 16 functional terms or biological pathways that may help us better understand the etiology of the disease.