Search

A b s t r a c t. The potential use of optimized support vector machines with simulated annealing algorithm in developing prediction functions for estimating soil aggregate stability and soil shear strength was evaluated. The predictive capabilities of support vector machines in comparison with traditional regression prediction functions were also studied. In results, the support vector machines achieved greater accuracy in predicting both soil shear strength and soil aggregate stability properties comparing to traditional multiple-linear regression. The coefficient of correlation (R) between the measured and predicted soil shear strength values using the support vector machine model was 0.98 while it was 0.52 using the multiple-linear regression model. Furthermore, a lower mean square error value of 0.06 obtained using the support vector machine model in prediction of soil shear strength as compared to the multiple-linear regression model. The ERROR% value for soil aggregate stability prediction using the multiple-linear regression model was 14.59% while a lower ERROR% value of 4.29% was observed for the support vector machine model. The mean square error values for soil aggregate stability prediction using the multiplelinear regression and support vector machine models were 0.001 and 0.012, respectively. It appears that utilization of optimized support vector machine approach with simulated annealing algorithm in developing soil property prediction functions could be a suitable alternative to commonly used regression methods. K e y w o r d s: soft computing, support vector machines, simulated annealing algorithm, soil shear strength, aggregate stability

Recent large-scale genome-wide association studies have identified common genetic variations that may contribute to the risk of amyotrophic lateral sclerosis (ALS). However, pinpointing the risk variants in noncoding regions and underlying biological mechanisms remains a major challenge. Here, we constructed a convolutional neural network model with a large-scale GWAS meta-analysis dataset to unravel functional noncoding variants associated with ALS based on their epigenetic features. After filtering and prioritizing of candidates, we fine-mapped two new risk variants, rs2370964 and rs3093720, on chromosome 3 and 17, respectively. Further analysis revealed that these polymorphisms are associated with the expression level of CX3CR1 and TNFAIP1, and affect the transcription factor binding sites for CTCF, NFATc1 and NR3C1. Our results may provide new insights for ALS pathogenesis, and the proposed research methodology can be applied for other complex diseases as well.

Huntington’s disease (HD) is a rare neurodegenerative disorder caused by an expansion of CAG trinucleotide repeat located in the exon 1 of Huntingtin (HTT) gene in human chromosome 4. The HTT protein is ubiquitously expressed in the brain. Specifically, mutant HTT (mHTT) protein-mediated toxicity leads to a dramatic degeneration of the striatum among many regions of the brain. HD symptoms exhibit a major involuntary movement followed by cognitive and psychiatric dysfunctions. In this review, we address the conventional role of wild type HTT (wtHTT) and how mHTT protein disrupts the function of medium spiny neurons (MSNs). We also discuss how mHTT modulates epigenetic modifications and transcriptional pathways in MSNs. In addition, we define how non-cell autonomous pathways lead to damage and death of MSNs under HD pathological conditions. Lastly, we overview therapeutic approaches for HD. Together, understanding of precise neuropathological mechanisms of HD may improve therapeutic approaches to treat the onset and progression of HD.

The identification of transcription factor binding sites (TFBSs) is a problem for which computational methods offer great hope. Thus far, the expectation maximization (EM) technique has been successfully utilized in finding TFBSs in DNA sequences, but inappropriate initialization of EM has yielded poor performance or running time scalability under a given data set. In this study, we used a sequential integration approach that defined the final solution as the set of solutions acquired from solving objectives in a cascade manner to integrate the fuzzy C-means and the EM approaches to DNA motif discovery. The new method is explained in detail and tested on the chromatin immunoprecipitation sequencing (ChIP-seq) data sets for different transcription factors (TFs) with various motif patterns. The proposed algorithm also suggests an efficient process for analyzing motif similarity to known motifs as well as finding a target motif. A comparison of results with those of the well-known motif-finding tool, MEME-ChIP, shows the advantages of our proposed framework over this existing tool. Experimental results show that we were able to find the true motifs for all TFs, and that the motifs found by our proposed algorithm were more similar to JASPAR-known motifs for the STAT1, GATA1, and JUN TFs than those found by MEME-ChIP.

The brain needs more energy than other organs in the body. Mitochondria are the generator of vital power in the living organism. Not only do mitochondria sense signals from the outside of a cell, but they also orchestrate the cascade of subcellular events by supplying adenosine-5′-triphosphate (ATP), the biochemical energy. It is known that impaired mitochondrial function and oxidative stress contribute or lead to neuronal damage and degeneration of the brain. This mini-review focuses on addressing how mitochondrial dysfunction and oxidative stress are associated with the pathogenesis of neurodegenerative disorders including Alzheimer’s disease, amyotrophic lateral sclerosis, Huntington’s disease, and Parkinson’s disease. In addition, we discuss state-of-the-art computational models of mitochondrial functions in relation to oxidative stress and neurodegeneration. Together, a better understanding of brain disease-specific mitochondrial dysfunction and oxidative stress can pave the way to developing antioxidant therapeutic strategies to ameliorate neuronal activity and prevent neurodegeneration.

Numerous industrial applications of machine learning feature critical issues that need to be addressed. This work proposes a framework to deal with these issues, such as competing objectives and class imbalance in designing a machine vision system for the in-line detection of surface defects on glass substrates of thin-film transistor liquid crystal displays (TFT-LCDs). The developed inspection system composes of (i) feature engineering: extraction of only the defect-relevant features from images using two-dimensional wavelet decomposition and (ii) training ensemble classifiers (proof of concept with a C5.0 ensemble, random forests (RF), and adaptive boosting (AdaBoost)). The focus is on cost sensitivity, increased generalization, and robustness to handle class imbalance and address multiple competing manufacturing objectives. Comprehensive performance evaluation was conducted in terms of accuracy, sensitivity, specificity, and the Matthews correlation coefficient (MCC) by calculating their 12, 000 bootstrapped estimates. Results revealed significant differences (p < 0.05) between the three developed diagnostic algorithms. RFR (accuracy of 83.37%, sensitivity of 60.62%, specificity of 89.72%, and MCC of 0.51) outperformed both AdaBoost (accuracy of 81.14%, sensitivity of 69.23%, specificity of 84.48%, and MCC of 0.50) and the C5.0 ensemble (accuracy of 78.35%, sensitivity of 65.35%, specificity of 82.03%, and MCC of 0.44) in all the metrics except sensitivity. AdaBoost exhibited stronger performance in detecting defective TFT-LCD glass substrates. These promising results demonstrated that the proposed ensemble approach is a viable alternative to manual inspections when applied to an industrial case study with issues such as competing objectives and class imbalance.

Interpretation of noncoding disease variants, which comprise the vast majority of Genome-wide association studies (GWAS) hits, remains a momentous challenge due to haplotype structure and our limited understanding of the mechanisms and physiological contexts of noncoding elements. GWAS have identified loci underlying human diseases, but assigning the causal nucleotide changes still remain a controversial issue. Here we addressed these issues through the combination of high-density genotyping and epigenomic data using a random forest model to discover the noncoding causal variants. Focusing on autoimmune diseases, we triaged putative causal variants for atopic dermatitis and inflammatory bowel diseases. Making a filtering pipeline, we found three interesting single nucleotide polymorphisms (rs1800630, rs1799964 and rs4796793) in the upstream site of TNF and STAT3 genes, two frequent genes shared in some autoimmune diseases, and show how those variants affect on TNF and STAT3 expression levels. All data and source codes related to this manuscript are available at https://github.com/jieunjung511/Autoimmune-research.

A large number of real-world machine learning and data mining problems have several crucial issues that need to be solved, such as class imbalance and multiple objectives; these issues cannot be easily overcome with many learning methods. This study proposes an efficient approach to address the issues and applies the approach in the design of a machine vision system for a real-world problem: inline inspection of surface defects on glass substrates of thin-film transistor liquid crystal displays (TFT-LCDs). The three major steps in the machine vision system are: (1) selective extraction of defect features from images using 2-dimemnsional wavelet decomposition, (2) training cost-sensitive classifiers to handle class imbalance, and (3) use of ensemble techniques to achieve multiple manufacturing objectives. When applied to an industrial case study, the achieved performance shows that using the proposed approach in defect inspection of TFT-LCD glass substrates is a viable alternative to manual inspection.

This study addresses classification methodology for the automatic inspection of a range of defects on the surface of glass substrates in thin film transistor liquid crystal display glass substrate manufacturing. The proposed methodology consisted of four stages: (1) feature extraction by calculating the wavelet co-occurrence signature from the substrate images, (2) handling of imbalanced dataset using the Synthetic Minority Over-sampling TEchnique (SMOTE), (3) reduction of the feature's dimension by principal component analysis, and (4) finally choosing the best classifier between three different methods: Classification And Regression Tree (CART), Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM). In training the SVM and MLP classifiers, the simulated annealing algorithm was used to obtain the optimal tuning parameters for the classifiers. From the industrial case study, the proposed feature extraction algorithm could remove the defect-irrelevant image features and SMOTE increased the accuracy of all three methods. Furthermore, the optimized SVM and MLP models were more accurate than the CART model whereas a higher accuracy of 89.5% was observed for the proposed SVM model.

The visual appearance of manufactured products is often one of the major quality attributes for certain types of products, which are used mainly for display purposes or used as the exterior part of other products. TFT―LCD (thin film transistor―liquid crystal display) glass substrates can serve as a representative case. In such cases, visual quality (i.e., visual appearance), as well as the physical or mechanical quality attributes, has to be controlled or maintained. This paper presents an industrial case study of a machine vision methodology for the automatic grading of TFT―LCD glass substrates. In this case study, a classification model was developed using support vector machine (SVM), optimized via the simulated annealing (SA) algorithm. Parallel genetic algorithm (PGA) was also used to reduce the number of features for classification. The results show that utilization of an optimized SVM approach with SA in classification of TFT―LCD glass defects could be a viable alternative to manual classification in the TFT―LCD glass substrate industry.

The visual appearance of manufactured products is often one of the important quality attributes for certain types of products, which are mainly used for display purposes or used as the exterior part of other products. TFT-LCD (thin film transistor – liquid crystal display) glass substrates can be one of the representative cases. In such cases, visual quality (i.e., visual appearance) as well as the physical or mechanical quality attributes has to be controlled or maintained. This paper presents an industrial case study of a new machine vision methodology to manufacturing of TFT-LCD glass substrates. In this case study, we developed a classification model using support vector machine (SVM), optimized via the simulated annealing (SA) algorithm. We also used parallel genetic algorithm to reduce the number of features for classification. The results show that utilization of optimized SVM approach with SA in classification of TFT-LCD glass defects could be a viable alternative to manual classification in the TFT-LCD glass substrate industry.

Complex systems are complex, evolutionary, and dynamical system. One general method to predict such systems is use the previous and most recently behavior of a system to predict its future changes. The main advantage of this method is the ability to predict the behavior of systems without analytical prediction rules. In this situation, decision makers are often presented with several competing forecasts produced by different forecasting methods. A decision maker who needs a predict could choose a combined forecast that is generally more precise than any of the individual forecasts, for the combined forecast gets more information into consideration and the preciseness of the combined forecast improves as more methods are included in the combination. This article proposes a new forecast combination strategy, by using support vector machines that improve the forecasting capability of the model. Finally the results of using this method on two sample datasets are presented and the superiority of this method is demonstrated.