Search

Objective: This study aimed to identify osteoporosis-related core genes using bioinformatics analysis and machine learning algorithms. Methods: mRNA expression profiles of osteoporosis patients were obtained from the Gene Expression Profiles (GEO) database, with GEO35958 and GEO84500 used as training sets, and GEO35957 and GSE56116 as validation sets. Differential gene expression analysis was performed using the R software "limma" package. A weighted gene co-expression network analysis (WGCNA) was conducted to identify key modules and modular genes of osteoporosis. Kyoto Gene and Genome Encyclopedia (KEGG), Gene Ontology (GO), and gene set enrichment analysis (GSEA) were performed on the differentially expressed genes. LASSO, SVM-RFE, and RF machine learning algorithms were used to screen for core genes, which were subsequently validated in the validation set. Predicted microRNAs (miRNAs) from the core genes were also analyzed, and differential miRNAs were validated using quantitative real-time PCR (qPCR) experiments. Results: A total of 1280 differentially expressed genes were identified. A disease key module and 215 module key genes were identified by WGCNA. Three core genes (ADAMTS5, COL10A1, KIAA0040) were screened by machine learning algorithms, and COL10A1 had high diagnostic value for osteoporosis. Four core miRNAs (has-miR-148a-3p, has-miR-195-3p, has-miR-148b-3p, has-miR-4531) were found by intersecting predicted miRNAs with differential miRNAs from the dataset (GSE64433, GSE74209). The qPCR experiments validated that the expression of has-miR-195-3p, has-miR-148b-3p, and has-miR-4531 was significantly increased in osteoporosis patients. Conclusion: This study demonstrated the utility of bioinformatics analysis and machine learning algorithms in identifying core genes associated with osteoporosis. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is the second most common neurological disorder caused by damage to dopaminergic neurons. Therefore, it is important to develop systems for early and automatic diagnosis of PD. For this purpose, a study that will contribute to the development of systems for the automatic diagnosis of PD is presented. The Electroencephalography (EEG) signals were decomposed into sub-bands using adaptive decomposition methods, such as empirical mode decomposition, variational mode decomposition, and Vold-Kalman order filtering (VKF). Various features were extracted from the sub-band decomposed signals, and the significant ones were determined by Chi-squared test. These important features were applied as input to support vector machine (SVM), fitch neural network (FNN), k-nearest neighbours (KNN), and decision trees (DT), machine learning (ML) models and classification was performed. We analysed the performance of ML models by obtaining accuracy, sensitivity, specificity, positive predictive value, negative predictive values, F1-score, false-positive rate, kappa statistics, and area under the curve. The classification process was performed for two cases: PD ON-HC and PD OFF-HC groups. The most successful method in this study was the VKF method, which was applied for the first time in this field with the approach specified for both cases. In both instances, the SVM algorithm was employed as the ML model, with classifier performance criterion values close to 100%. The results obtained in this study seem to be successful compared to the results of recent research on the diagnosis of PD. [ABSTRACT FROM AUTHOR]

The leaf area index (LAI), a crucial biophysical indicator, is used to assess and monitor crop growth for effective agricultural management. This study assessed the LAI at the seedling stage after conducting a field experiment with rainfed groundnut. The study tests the performance of multiple machine learning regression algorithms (MLRAs) and empirical vegetation indices (VIs) in retrieving groundnut's LAI using freely available Sentinel-2 data. The bands at 665 nm, 705 nm, 842 nm, and 2190 nm are the most sensitive for retrieving groundnut's LAI, according to an analysis of its band spectrum. Results suggest that VIs computed with wavebands centered at red (665 nm), red edge (705 nm), and near-infrared (842 nm) exhibited optimal R2 with Sentinel-2 data. Normalized difference vegetation index (NDVI), red edge normalized difference vegetation index (NDVIre), simple ratio (SR), red edge simple ratio (SRre), and green normalized difference vegetation index (gNDVI) were utilized as predictors for LAI. Regarding the results of the validation between estimated and measured LAI, SR demonstrated the highest accuracy for groundnut LAI prediction (r2 = 0.67, RMSE = 0.89). Ten MLRAs were tested, and results indicate from the perspective of the accuracy of models, the Gaussian processes regression, GPR (r2 = 0.73 and RMSE = 0.81), Kernel ridge regression, KRR (r2 = 0.72 and RMSE = 0.82) and Support vector regression, SVR (r2 = 0.70 and RMSE = 0.85) demonstrated to be the most suitable for LAI estimation for rainfed groundnut at the seedling stage. The systematic analysis based on the regression approaches tested here revealed that the GPR outperformed other models combined, therefore, most suitable for estimating rainfed groundnut LAI at the seedling stage. These findings serve as a benchmark for obtaining crop biophysical parameters in the framework of groundnut traits monitoring in a tropical West Africa. [ABSTRACT FROM AUTHOR]

The estimation of postmortem interval (PMI) is a complex and challenging problem in forensic medicine. In recent years, many studies have begun to use machine learning methods to estimate PMI. However, research combining postmortem computed tomography (PMCT) with machine learning models for PMI estimation is still in early stages. This study aims to establish a multi-tissue machine learning model for PMI estimation using PMCT data from various tissues. We collected PMCT data of seven tissues, including brain, eyeballs, myocardium, liver, kidneys, erector spinae, and quadriceps femoris from 10 rabbits after death. CT images were taken every 12 h until 192 h after death, and HU values were extracted from the CT images of each tissue as a dataset. Support vector machine, random forest, and K-nearest neighbors were performed to establish PMI estimation models, and after adjusting the parameters of each model, they were used as first-level classification to build a stacking model to further improve the PMI estimation accuracy. The accuracy and generalized area under the receiver operating characteristic curve of the multi-tissue stacking model were able to reach 93% and 0.96, respectively. Results indicated that PMCT detection could be used to obtain postmortem change of different tissue densities, and the stacking model demonstrated strong predictive and generalization abilities. This approach provides new research methods and ideas for the study of PMI estimation. [ABSTRACT FROM AUTHOR]

This study investigates the effectiveness of six prominent machine learning models—random forest, decision trees, K-nearest neighbor, logistic regression, support vector machines, and Naïve Bayes—for intrusion detection systems in industrial Internet of Things environments. The evaluation encompasses the effects of data preprocessing techniques, including feature engineering, data normalization, recoding, and missing data mitigation. Furthermore, the research delves into dataset balancing, examining the effects of six different techniques on model performance. The investigations are conducted using the domain-specific WUSTL-IIOT-2021 dataset, which captures the unique characteristics of IIoT data. The study also investigates multi-class attack identification utilizing an innovative SMOTE-based multi-class balancing approach to tackle dataset imbalances. The results indicate that data preprocessing and intelligent dataset balancing produce consistent enhancements in the classification performance of the selected models across binary and multi-classification tasks. Random forest emerges as the standout algorithm, delivering consistently high performance with computational efficiency. [ABSTRACT FROM AUTHOR]

In this study, we present a two-step method for predicting price bubbles in precious metals, which combines a widely recognized right-tailed unit root test to detect bubbles with various machine learning algorithms to pinpoint the potential predictors of bubble formation and their relative significance. We utilize logistic regression, support vector machines, CART, random forests, extreme gradient boosting, and neural networks algorithms, which are more precise than traditional methods in making predictions and can handle binary classification and regression issues. Our analysis covers monthly prices for gold, silver, palladium, and platinum from 1990M1-2022M10. The study extends the literature by utilizing the Generalized Supremum Augmented Dickey-Fuller test to identify potential price bubbles and analyzing the effect of macroeconomic, financial, and uncertainty factors on the likelihood of bubbles using machine learning algorithms. The findings indicate that macroeconomic factors play a significant role in the formation of price bubbles in precious metals; specifically the consumer confidence index in the USA was a common factor that had a positive impact on the likelihood of bubbles in gold, platinum, and silver. However, the leading factors in the formation of bubbles in palladium were found to be financial variables and uncertainty variables. As predicting bubbles is crucial for regulators and policymakers to take preventive measures against future crises, identifying the key predictors of bubble formation and forecasting them in the early stages is essential. [ABSTRACT FROM AUTHOR]

The problem of recognition and classification of loads at the output of generating and transmitting distributed parameter lines (DPL) in devices of high-power pulse technology (HPPT) by the amplitude and shape of the output signal using mathematical models based on machine learning methods and neural networks has been considered. A web application that recognizes parasitic parameters occurring in the devices based on DPL has been developed. [ABSTRACT FROM AUTHOR]

The rapid development of infinite networks and information technology has promoted the wide deployment and rapid growth of intelligent interactive devices. However, at the same time, touch interaction technology also faces many challenges such as lack of precision. This study combines federated learning with LayerGesture technology to optimize and design a touch interaction system with higher interaction accuracy and applies it to practice. The analysis results show that with the increase in the number of iterations of the federated model, the accuracy of the human–computer recognition interaction and the amount of information contained in it increases, and the accuracy curve reaches stability at about 2800 times and is at the optimal interaction adaptation. At this point, the loss function also decreases gradually, while the loss factor tends to 0, which verifies the stability of the optimized model. According to the participants' interaction experience and experimental results, the optimized LayerGesture technique of the federated learning model has an average correctness rate of 90.4% and the lowest average selection time, while the average selection time of LayerGesture in the interaction area at the edge of the screen is 2510 ms and the average correctness rate is 93.60%, which is better than the Shift technique. In addition, the subjective survey results indicated that more participants favored the optimized LayerGesture technique. In summary, this paper's joint learning algorithm contributes to the recognition effectiveness and efficiency of intelligent interactive systems. [ABSTRACT FROM AUTHOR]

Landslides are considered one of the most frequent natural disasters that cause human loss and damage property, affecting the sustainability of communities worldwide. Mapping landslide susceptibility has gained a lot of interest from researchers. Using machine learning methods to yield landslide susceptibility maps (LSMs) has been extensively studied in the last decade. However, the problems of sampling non-landslides and weighting classes of conditioning factors are not thoroughly investigated in landslide susceptibility models. Moreover, the process of zoning LSMs for different susceptible areas is often overlooked. To address this gap, we present a study on sampling non-landslides and computing appropriate weights, which are used to train machine learning models to obtain accurate outputs. The outputs are clustered into different susceptible levels by K-means clustering method. Our study was conducted in Nam Pam area, Vietnam. A landslide inventory of 71 landslide points and 44 delineated landslide polygons, and 13 conditioning factors were selected in this study area. Furthermore, three regression methods, i.e., Bayesian, K-Nearest Neighbors, and Support vector machine (SVM), were taken to generate LSMs. We assessed three models based on various metrics, including 5 statistical metrics and AUC. The reliability of LSMs was evaluated by MFR value. Empirical results have shown that SVM method and the 2:1 ratio of non-landslides to landslides are recommended to build landslide susceptibility models. [ABSTRACT FROM AUTHOR]

Escalation in flash floods and the enhanced devastations, especially in the arid and semiarid regions of the world has required precise mapping of the flash flood susceptible zones. In this study, we applied six novel credal decision tree (CDT)-based ensemble models—1. CDT, 2. CDT Alternative Decision Tree (ADTree), 3. CDT- Reduced Error Pruning Tree (REPT), 4. CDT- Rotational Forest (RF), 5. CDT-FT, 6. CDT- Naïve Bias Tree (NBTree). For preparing the flash flood susceptibility maps (FFSM), 206 flood locations were selected in the Neka-roud watershed of Iran with 70% as training data and 30% as testing data. Moreover, 18 flood conditing factors were considered for FFSM and a multi-colinearity test was performed for determining the role of the factors. Our results show that the distance from the stream plays a vital role in flash floods. The CDT-FT is the best-fit model out of the six novel algorithms employed in this study as demonstrated by the highest values of the area under the curve (AUC) of the receiver operating curve (ROC) (AUROC 0.986 for training data and 0.981 for testing data). Our study provides a novel approach and useful tool for flood management. [ABSTRACT FROM AUTHOR]

The objective of this study was to distinguish leek seeds belonging to the Starozagorski kamush variety and two breeding lines based on the selected fluorescence spectroscopic data. The classification models were developed for three classes of Starozagorski kamush vs. breeding line 4 vs. breeding line 39 and pairs of classes of Starozagorski kamush vs. breeding line 4, Starozagorski kamush vs. breeding line 39, and breeding line 4 vs. breeding line 39. The traditional machine learning algorithms, such as PART, Logistic, Naive Bayes, Random Forest, IBk, and Filtered Classifier were applied. All three classes were distinguished with an average accuracy of up to 93.33% for models built using IBk and Filtered Classifier. In the case of each model, Starozagorski kamush variety was completely different (accuracy of 100%, precision, and F-measure, MCC (Matthews correlation coefficient), and ROC (receiver operating characteristic) area of 1.000) from breeding lines, and the mixing of cases was observed between breeding line 4 and breeding line 39. The models built for pairs of leek seed classes distinguished Starozagorski kamush and breeding line 4 with an average accuracy reaching 100% (Logistic, Naive Bayes, Random Forest, IBk). The classification accuracy of Starozagorski kamush and breeding line 39 also reached 100% (Logistic, Naive Bayes, Random Forest, IBk), whereas breeding line 4 and breeding line 39 were classified with an average accuracy of up to 80% (Logistic, Naive Bayes, Random Forest, Filtered Classifier). The proposed approach combining fluorescence spectroscopy and machine learning may be used in practice to distinguish leek seed varieties and breeding lines. [ABSTRACT FROM AUTHOR]

The application of interdisciplinary non-invasive diagnostic methods combining fluorescence spectroscopy with multiple machine learning algorithms as tools for rapid application in tomato breeding programs is essential when crossing specific genotypes or parental samples to obtain representatives with better performance. Non-destructive distinguishing tomato species is of great importance for the preservation of product quality. This study aimed at combining fluorescence spectroscopic data and machine learning algorithms for distinguishing greenhouse tomatoes. The models for the discrimination of greenhouse tomato samples were built based on selected spectroscopic data using different machine learning algorithms from the groups of Meta, Functions, Bayes, Trees, Rules, and Lazy. The confusion matrices with accuracy for each sample, average accuracy, time taken to build the model, Kappa statistic, mean absolute error, root mean squared error and relative absolute error were determined. The greenhouse tomato samples were discriminated with an accuracy reaching 100% for the models built using Multi-Class Classifier (Meta), Logistic (Function), Bayes Net (Bayes), PART (Rules), and J48 (Trees). In the case of these algorithms, Kappa statistic was 1.0 and mean absolute error, root mean squared error and relative absolute error were equal to 0. [ABSTRACT FROM AUTHOR]

This study presents a new model to predict the static formation temperature in multiple geothermal fields using multiple machine learning algorithms. Both artificial intelligence and non-artificial intelligent algorithms were used for this prediction. The model developed in this study predicts static formation temperature using several machine learning algorithms, including artificial neural networks, fuzzy logic, k-nearest neighbors, and random forest algorithms. Results are compared with the real temperatures obtained from two geothermal wells. The random forest, fuzzy logic, and k-nearest neighbors algorithms outperformed the artificial neural network, with the random forest algorithm achieving higher accuracy. The MAE of the random forest algorithm was 0.7% and the RMSE was 0.9%. The MAE values for the other machine learning algorithms ranging from 1.5 to 8.4%, and the RMSE values ranged from 2 to 20.8%. Artificial intelligence methods were found to be more accurate than non-artificial intelligence (mathematical) methods, with varying percentages. The results generated by the unique new model computation and the measured test data are substantially matched when compared to computed data and observed temperature data. The novelty of this newly developed artificial intelligence model is that it serves as a practical and inexpensive tool for static formation temperature determination in geothermal and petroleum wells. [ABSTRACT FROM AUTHOR]

Sex estimation from skeletal remains is one of the crucial issues in forensic anthropology. Long bones can be a valid alternative to skeletal remains for sex estimation when more dimorphic bones are absent or degraded, preventing any estimation from the first intention methods. The purpose of this study was to generate and compare classification models for sex estimation based on combined measurement of long bones using machine learning classifiers. Eighteen measurements from four long bones (radius, humerus, femur, and tibia) were taken from a total of 2141 individuals. Five machine learning methods were employed to predict the sex: a linear discriminant analysis (LDA), penalized logistic regression (PLR), random forest (RF), support vector machine (SVM), and artificial neural network (ANN). The different classification algorithms using all bones generated highly accuracy models with cross-validation, ranging from 90 to 92% on the validation sample. The classification with isolated bones ranked between 83.3 and 90.3% on the validation sample. In both cases, random forest stands out with the highest accuracy and seems to be the best model for our investigation. This study upholds the value of combined long bones for sex estimation and provides models that can be applied with high accuracy to different populations. [ABSTRACT FROM AUTHOR]

The photoelectric factor (PEF) is an important well-logging tool to distinguish between different types of reservoir rocks because PEF measurement is sensitive to elements with high atomic numbers. Furthermore, the ratio of rock minerals could be determined by combining PEF log with other well logs. However, PEF logs could be missing in some cases such as in old well logs and wells drilled with barite-based mud. Therefore, developing models for estimating missing PEF logs is essential in those circumstances. In this work, we developed various machine learning models to predict PEF values using the following well logs as inputs: bulk density (RHOB), neutron porosity (NPHI), gamma ray (GR), compressional and shear velocity. The predictions of PEF values using adaptive-network-fuzzy inference system (ANFIS) and artificial neural network (ANN) models have errors of about 16% and 14% average absolute percentage error (AAPE) in the testing dataset, respectively. Thus, a different approach was proposed that is based on the concept of automated machine learning. It works by automatically searching for the optimal model type and optimizes its hyperparameters for the dataset under investigation. This approach selected a Gaussian process regression (GPR) model for the accurate estimation of PEF values. The developed GPR model decreases the AAPE of the predicted PEF values in the testing dataset to about 10% AAPE. This error could be further decreased to about 2% by modeling the potential noise in the measurements using the GPR model. [ABSTRACT FROM AUTHOR]

The interest in artificial intelligence (AI) predictive models in the domains of petrophysics and well logs has been rapidly growing as it prevails as a powerful tool, given the relative data abundance. Formation resistivity prediction, despite its existing necessity, remains a challenge. The objectives of this study are to provide a framework of considerations and limitations of resistivity prediction and to introduce AI models to predict resistivity in horizontal low formation quality well. Logging while drilling data were obtained for the study from a 12″ section of a horizontal low formation quality well. Statistical analyses were carried out to identify and remove insignificant features. RHOB, DTC, DTS, NPHI, and GR logs were used as input to build and train the model. Data scaling and transformation techniques were applied to improve the model's accuracy and accelerate the rate of convergence. Four models were built and trained using artificial neural network (ANN), adaptive neuro-fuzzy inference system types 1 and 2 (ANFIS 1 & ANFIS 2), and Support vector machine. Cross plots, coefficient of determination (R2) and mean absolute percentage error (MAPE) were used to evaluate the effectiveness of the prediction. All of the four predictive models yielded comparable results, where R2 values ranged between 0.90 and 0.95 for the training data set, and 0.89, to 0.91 for testing dataset. ANN model had an inherent complexity with two hidden layers, 30 neurons each. The main applications of resistivity predicted values are to be used qualitatively for geo-steering applications and to estimate the saturation profile of logged intervals. For those two applications, the resistivity prediction accuracy is subject to the relative significance of the value magnitude. [ABSTRACT FROM AUTHOR]

Sex estimation of skeletal remains is one of the most important tasks in forensic anthropology. The radius bone is useful to develop standard guidelines for sex estimation across various populations and is an alternative when coxal or femoral bones are not available. The aim of the present study was to assess the sexual dimorphism from radius measurements in a French sample and compare the predictive accuracy of several modelling techniques, using both classical statistical methods and machine learning algorithms. A total of 78 left radii (36 males and 42 females) were used in this study. Sixteen measurements were made. The modelling techniques included a linear discriminant analysis (LDA), flexible discriminant analysis (FDA), regularised discriminant analysis (RDA), penalised logistic regression (PLR), random forests (RF) and support vector machines (SVM). The different statistical models showed an accuracy of classification that is greater than 94%. After selection of variables, the accuracies increased to 97%. The measurements made at the proximal part of the radius (sagittal and transversal diameters of the head, and sagittal diameter of the neck), at distal part (maximum width of the distal epiphysis) and of the entire bone (maximum length) stand out among the various models. The present study suggests that the radius bone constitutes a valid alternative for sex estimation of skeletal remains with comparable classification accuracies to the pelvis or femur and that the non-classical statistical models may provide a novel approach to sex estimation from the radius bone. However, the extrapolation of the current results cannot be made without caution because our sample was composed of very aged individuals. [ABSTRACT FROM AUTHOR]

Path finding is used to solve the problem of finding a traversable path through an environment with obstacles. This problem can be seen in many different fields of study and these areas rely on fast and efficient path finding algorithms. This paper aims to describe and review state of the art optimization techniques that are used on optimized path finding and compare their performances. Moreover, a special attention is paid on the proposed approaches to identify how they are tested on different test cases; whether the test cases are automatically generated or benchmark instances. The review opens avenues about the importance of automatic test case generation to test the different path finding algorithms. [ABSTRACT FROM AUTHOR]

Purpose: Can the risk factors that cause first trimester pregnancy loss in good-quality frozen-thawed embryo transfer (FET) cycles be predicted using machine learning algorithms? Methods: This is a retrospective cohort study conducted at Sisli Memorial Hospital, ART and Reproductive Genetics Center, between January 2011 and May 2021. A total of 3805 good-quality FET cycles were included in the study. First trimester pregnancy loss rates were evaluated according to female age, paternal age, body mass index (BMI), diagnosis of infertility, endometrial preparation protocols (natural/artificial), embryo quality (top/good), presence of polycystic ovarian syndrome (PCOS), history of recurrent pregnancy loss (RPL), recurrent implantation failure (RIF), severe male infertility, adenomyosis and endometriosis. Results: The first trimester pregnancy loss rate was 18.2% (693/ 3805). The presence of RPL increased first trimester pregnancy loss (OR = 7.729, 95%CI = 5.908–10.142, P = 0.000). BMI, which is > 30, increased first trimester pregnancy loss compared to < 25 (OR = 1.418, 95%CI = 1.025–1.950, P = 0.033). Endometrial preparation with artificial cycle increased first trimester pregnancy loss compared to natural cycle (OR = 2.101, 95%CI = 1.630–2.723, P = 0.000). Female age, which is 35–37, increased first trimester pregnancy loss compared to < 30 (OR = 1.617, 95%CI = 1.120–2.316, P = 0.018), and female age, which is > 37, increased first trimester pregnancy loss compared to < 30 (OR = 2.286, 95%CI = 1.146–4,38, P = 0.016). The presence of PCOS increased first trimester pregnancy loss (OR = 1.693, 95%CI = 1.198–2.390, P = 0.002). The number of previous IVF cycles, which is > 3, increased first trimester pregnancy loss compared to < 3 (OR = 2.182, 95%CI = 1.708–2.790, P = 0.000). Conclusions: History of RPL, RIF, advanced female age, presence of PCOS, and high BMI (> 30 kg/m2) were the factors that increased first trimester pregnancy loss. [ABSTRACT FROM AUTHOR]

Acute myocardial ischemia (AMI) remains the leading cause of death worldwide, and the post-mortem diagnosis of AMI represents a current challenge for both clinical and forensic pathologists. In the present study, the untargeted metabolomics based on ultra-performance liquid chromatography combined with high-resolution mass spectrometry was applied to analyze serum metabolic signatures from AMI in a rat model (n = 10 per group). A total of 28 endogenous metabolites in serum were significantly altered in AMI group relative to control and sham groups. A set of machine learning algorithms, namely gradient tree boosting (GTB), support vector machine (SVM), random forest (RF), logistic regression (LR), and multilayer perceptron (MLP) models, was used to screen the more valuable metabolites from 28 metabolites to optimize the biomarker panel. The results showed that classification accuracy and performance of MLP model were better than other algorithms when the metabolites consisting of L-threonic acid, N-acetyl-L-cysteine, CMPF, glycocholic acid, L-tyrosine, cholic acid, and glycoursodeoxycholic acid. Finally, 17 blood samples from autopsy cases were applied to validate the classification model's value in human samples. The MLP model constructed based on rat dataset achieved accuracy of 88.23%, and ROC of 0.89 for predicting AMI type II in autopsy cases of sudden cardiac death. The results demonstrated that MLP model based on 7 molecular biomarkers had a good diagnostic performance for both AMI rats and autopsy-based blood samples. Thus, the combination of metabolomics and machine learning algorithms provides a novel strategy for AMI diagnosis. [ABSTRACT FROM AUTHOR]

Unsupervised clustering (e.g., K-means) and supervised machine learning [e.g., support vector machines (SVMs)] methods can be used in data-driven classification and predictive mapping of mineral prospectivity. In this study, the conceptual model of porphyry-type Cu deposits in Varzaghan district, Northwest Iran, was utilized to translate mineralization-related processes into mappable targeting criteria, resulting in six evidence layers derived from geochemical, geological, structural and remote sensing data. Then, traditional K-means clustering (KMC) method and a supervised SVM were employed to construct GIS-based mineral prospectivity maps. One of the challenging issues for generation of mineral prospectivity maps using clustering algorithms is to select suitable cluster centers (called centroids) in order to circumscribe the similar spatial features into meaningful clusters. Machine learning methods are strongly sensitive to hyperparameter values that contribute to prediction, as the prediction accuracy can significantly enhance when the optimized hyperparameters are calibrated to training procedure. To reach these goals, a genetic algorithm was incorporated into K-means and SVM in order to automatically select the optimized cluster centroids and tuned hyperparameters, respectively, and two new prospectivity models namely GKMC and genetic-based SVM were then generated. To evaluate the performance accuracy in training procedures of SVM and genetic-based SVM, K-fold cross-validation and confusion matrix were employed. Moreover, success-rate curves were plotted to compare the overall performance of unsupervised clustering models comprising KMC and GKMC and also supervised machine learning models comprising SVM and genetic-based SVM for detection of favorable areas associated with porphyry-type Cu mineralization. The results suggested the superiority of genetic-based SVM model over other models. [ABSTRACT FROM AUTHOR]

The recent advances in the application of machine learning to drug discovery have made it a 'hot topic' for research, with hundreds of academic groups and companies integrating machine learning into their drug discovery projects. Nevertheless, there remains great uncertainty regarding the most appropriate ways to evaluate the relative performance of these powerful methods against more traditional cheminformatics approaches, and many pitfalls remain for the unwary. In 2020, researchers at MIT (Stokes et al., Cell 180(4), 688–702, 2020) reported the discovery of a new compound with antibacterial activity, halicin, through the use of a neural network machine learning method. A robust ability to identify new active chemotypes through computational methods would be very useful. In this study, we have used the Stokes et al. dataset to compare the performance of this method to two other approaches, Mapping of Activity Through Dichotomic Scores (MADS) by Todeschini et al. (J Chemom 32(4):e2994, 2018) and Random Matrix Theory (RMT) by Lee et al. (Proc Natl Acad Sci 116(9):3373–3378, 2019). Our results demonstrate that all three methods are capable of predicting halicin as an active antibacterial compound, but that this result is dependent on the dataset composition, pre-processing and the molecular fingerprint used. We have further assessed overall performance as determined by several performance metrics. We also investigated the scaffold hopping potential of the methods by modifying the dataset by removal of the β-lactam and fluoroquinolone chemotypes. MADS and RMT are able to identify actives in the test set that contained these substructures. This ability arises because of high scoring fragments of the withheld chemotypes that are in common with other active antibiotic classes. Interestingly, MADS is relatively better compared to the other two methods based on general predictive performance. [ABSTRACT FROM AUTHOR]

A common theme emerging from nutrient omission trials conducted extensively across sub-Saharan Africa has been the large variability in yield response to applied nutrients. Yet, little is known about the factors associated with this variability. Therefore, the objectives of this review were to (1) synthesize the available data from nutrient omission trials of maize and rice and quantify spatial variability in yield responses and the probability of attaining specified yield targets; (2) identify the genotypic, environmental, and nutrient management factors associated with yield responses; and (3) provide insights and actionable information for setting priorities for future nutrient management research and development. Here, we provide distributions and expected values of yield response and agronomic efficiencies of nitrogen (N), phosphorus (P), and potassium (K) to serve as benchmarks for improving fertilizer recommendations. We also show that with the combined application of NPK fertilizer, rain-fed maize and rice yields can be raised from the current yields of ~2 Mg ha−1 to 4 Mg ha−1. Yield responses to N, P, and K were in the ratio of 11:6:1 in maize and 13:7:5 in rice, probably arising from differences in uptake requirements and growing environments. K yield responses were 2–3 times higher in rice than in maize. Explorative analysis using machine learning algorithms provided further insights into the possible interaction of agroecology, soil type, and exchangeable cations on the spatial variability in yield responses to N, P, and K in maize and rice. We recommend future research to address site-specific interactions between the applied and indigenous soil nutrients, focusing on optimizing application rates of K, other macronutrients and micronutrients for sustainable intensification of maize and rice production. This study highlights the critical need for balanced fertilization to optimize the productivity and nutrient use efficiencies in rice and maize production in smallholder farming systems in SSA. [ABSTRACT FROM AUTHOR]

This study was aimed at evaluating the effect of spontaneous lacto-fermentation of carrot slices on flesh structure using different machine learning approaches. The textures computed from digital images of lacto-fermented and fresh carrot slices were compared using neural networks and other algorithms from different groups. In the case of Multilayer Perceptron, accuracies for training, testing and validation were considered. For some of the networks, lacto-fermented and fresh samples were completely distinguished. The accuracies for training, testing and validation were equal to 100%. For models built using other algorithms (LDA (Linear Discriminant Analysis), Multi Class Classifier, LMT (Logistic Model Tree), KStar, Naive Bayes, PART), the following metrics were used for the evaluation of model effectiveness: accuracies, time taken to build model, Kappa statistic, mean absolute error, root mean squared error, PRC (Precision-Recall) Area, ROC (Receiver Operating Characteristic) Area, MCC (Matthews Correlation Coefficient), F-Measure, Recall, Precision, FP (False Positive) Rate and TP (True Positive) Rate. The most satisfactory results were obtained for the LDA. The lacto-fermented and fresh carrot slices were distinguished with an average accuracy of 99%, low values of errors (mean absolute error: 0.0117, root mean squared error: 0.1014) and FP Rate (0.010). The weighted averages of other metrics were greater than or equal to 0.98 (Kappa statistic: 0.98, PRC Area: 0.987, ROC Area: 0.991, MCC: 0.980, F-Measure: 0.990, Recall: 0.990, Precision: 0.990, TP Rate: 0.990). The obtained results demonstrated the usefulness of different machine learning approaches to the evaluation of the effect of fermentation on changes in the carrot flesh structure. [ABSTRACT FROM AUTHOR]

Objective: Diabetes is a chronic fatal disease that has affected millions of people all over the globe. Type 2 Diabetes Mellitus (T2DM) accounts for 90% of the affected population among all types of diabetes. Millions of T2DM patients remain undiagnosed due to lack of awareness and under resourced healthcare system. So, there is a dire need for a diagnostic and prognostic tool that shall help the healthcare providers, clinicians and practitioners with early prediction and hence can recommend the lifestyle changes required to stop the progression of diabetes. The main objective of this research is to develop a framework based on machine learning techniques using only lifestyle indicators for prediction of T2DM disease. Moreover, prediction model can be used without visiting clinical labs and hospital readmissions. Method: A proposed framework is presented and implemented based on machine learning paradigms using lifestyle indicators for better prediction of T2DM disease. The current research has involved different experts like Diabetologists, Endocrinologists, Dieticians, Nutritionists, etc. for selecting the contributing 1552 instances and 11 attributes lifestyle biological features to promote health and manage complications towards T2DM disease. The dataset has been collected through survey and google forms from different geographical regions. Results: Seven machine learning classifiers were employed namely K-Nearest Neighbour (KNN), Linear Regression (LR), Support Vector Machine (SVM), Naive Bayes (NB), Decision Tree (DT), Random Forest (RF) and Gradient Boosting (GB). Gradient Boosting classifier outperformed best with an accuracy rate of 97.24% for training and 96.90% for testing separately followed by RF, DT, NB, SVM, LR, and KNN as 95.36%, 92.52%, 90.72%, 90.20%, 90.20% and 77.06% respectively. However, in terms of precision, RF achieved high performance (0.980%) and KNN performed the lowest (0.793%). As far as recall is being concerned, GB achieved the highest rate of 0.975% and KNN showed the worst rate of 0.774%. Also, GB is top performed in terms of f1-score. According to the ROCs, GB and NB had a better area under the curve compared to the others. Conclusion: The research developed a realistic health management system for T2DM disease based on machine learning techniques using only lifestyle data for prediction of T2DM. To extend the current study, these models shall be used for different, large and real-time datasets which share the commonality of data with T2DM disease to establish the efficacy of the proposed system. [ABSTRACT FROM AUTHOR]

Cyberbullying is a menace in today's socially networked world. It can have damaging physical and mental effects on the victims and hence, it needs to be tackled efficiently—several detection approaches are proposed in literature but those are mostly standalone. In this paper, we revisit the distributed and collaborative approach for detecting cyberbullying behavior using machine learning algorithms—a comprehensive enhancement of our past work—that uses many local and cloud-based collaborative configurations and different datasets. It contains a set of nodes, called detection nodes, which can identify cyberbullying employing Machine Learning classification algorithms and collaborate with each other as needed. Several experiments, consisting of various collaborative patterns, different scales, and failure scenarios, have been carried out using different Twitter © datasets in this study. The empirical results obtained from the experimentation show that the proposed approach is generic (i.e., allows the incorporation of different learning and collaborative techniques), and achieves better recall and precision values when compared with the stand-alone paradigm. [ABSTRACT FROM AUTHOR]

Solutions in geotechnics have been optimizing with the aid of machine learning methods. The aim of this paper is to apply different machine learning algorithms in order to achieve rock mass classification. It is demonstrated that RMR classification system can be obtained using only variables which are closely related to rock mass quality, instead of all RMR variables, without missing significant accuracy. The different machine learning algorithms used are the naïve Bayes, random forest, artificial neural networks and support vector machines. The variables to calculate RMR, selected by factor analysis, are: rock strength, rock weathering, spacing, persistence and aperture of discontinuities and presence of water. The machine learning models were trained and tested thirty times, with random subsampling, using two-thirds of the total database for training sample. The models presented average accuracy greater than 0.81, which was calculated from the confusion matrix, using the proportion of true positives and true negatives in the test sample. Significant values of efficiency, precision and reproducibility rates were achieved. The study shows the application of machine learning algorithms allows obtaining the RMR classes, even with a small number of variables. In addition, the results of the evaluation metrics of the developed algorithms show that the methodology can be applied to new database, working as a valuable way to achieve rock mass classification. [ABSTRACT FROM AUTHOR]

Nondestructive experiments are widely employed for determining mechanical properties. In this work, a spherical impact test is virtually performed to determine the plastic properties of a thick aluminum plate. The finite element model is validated experimentally, and several simulations are then performed in accordance with the design of the experiment program. Several algorithms, including support vector machine, Gaussian process regression (GPR), and nonlinear regressions (second- and third-order polynomials) as machine learning techniques, are employed to estimate the material plastic properties. The indentation depth and indentation radius are considered as input variables to predict the tangent modulus (TM) and yield stress (YS). Results reveal that the second-order polynomial and GPR methods realize better performance in terms of determination coefficient and root mean square error criteria in assessing YS. [ABSTRACT FROM AUTHOR]

Increasing understanding of human genome variability allows for better use of the predictive potential of DNA. An obvious direct application is the prediction of the physical phenotypes. Significant success has been achieved, especially in predicting pigmentation characteristics, but the inference of some phenotypes is still challenging. In search of further improvements in predicting human eye colour, we conducted whole-exome (enriched in regulome) sequencing of 150 Polish samples to discover new markers. For this, we adopted quantitative characterization of eye colour phenotypes using high-resolution photographic images of the iris in combination with DIAT software analysis. An independent set of 849 samples was used for subsequent predictive modelling. Newly identified candidates and 114 additional literature-based selected SNPs, previously associated with pigmentation, and advanced machine learning algorithms were used. Whole-exome sequencing analysis found 27 previously unreported candidate SNP markers for eye colour. The highest overall prediction accuracies were achieved with LASSO-regularized and BIC-based selected regression models. A new candidate variant, rs2253104, located in the ARFIP2 gene and identified with the HyperLasso method, revealed predictive potential and was included in the best-performing regression models. Advanced machine learning approaches showed a significant increase in sensitivity of intermediate eye colour prediction (up to 39%) compared to 0% obtained for the original IrisPlex model. We identified a new potential predictor of eye colour and evaluated several widely used advanced machine learning algorithms in predictive analysis of this trait. Our results provide useful hints for developing future predictive models for eye colour in forensic and anthropological studies. [ABSTRACT FROM AUTHOR]

For a better future in machine learning (ML), it is necessary to modify our current concepts to get the fastest ML. Many designers had attempted to find the optimal learning rates in their applications through many algorithms over the past decades, but they have not yet achieved their target of highest speed of back-propagation (BP). This research proposes a novel BP rule called the Instant Learning Ratios-Machine Learning (ILR-ML) or (ILRML). Unlike the traditional BP algorithms, the ILR-ML offers its learning without the concepts of the learning rate(s). The ILR-ML has a new concept called the "Learning Ratio" and indicated by a sign (Δℓ). The ILR-ML performs the full BP algorithm with 100% accuracy per each learning iteration. The ILR-ML is more suitable for the online machine learning. [ABSTRACT FROM AUTHOR]

Accurate prediction of the water level will help prevent overexploiting groundwater and help control water resources. On the other hand, water level predicting is a highly dynamic and non-linear process dependent on complex factors. Therefore, developing models to predict water levels to optimize water resources management in the reservoir is essential. Thus, this work recommends various supervised machine learning algorithms for predicting water levels with groundwater level correlation. The predicting models have Linear Regression (LR), Support Vector Machines (SVM), Gaussian Processes Regression (GPR), and Neural Network (NN). This study includes four scenarios; The first scenario (SC1) uses lag 1; second scenario (SC2) uses lag 1 and lag 2; third scenario (SC3) uses lag 1, lag 2, and lag 11 and the fourth scenario (SC4) uses lag 1, lag 2, lag 11 and lag 12. These scenarios have been determined using the autocorrelation function (ACF), and these lags represent the month. The results showed that for SC1, SC2, and SC4, all model performance in GPR gave good results where the highest R equal to 0.71 in SC1, 0.78 in SC2, and 0.73 in SC4 using the Matern 5/2 GPR model. For SC3, the Stepwise LR model gave a better result with an R of 0.79. It can be concluded that Matern 5/2 of Gaussian Processes Regression Models is a reliable model to predict water level as the method gave a high performance in each scenario (except SC3) with a relatively fastest training time. The NN model had the worst performance to the other three models since it has the highest MAE values, RMSE, and lowest value of R in almost all four scenarios of input combinations. These results obtained in this study serves as an excellent benchmark for future water level prediction using the GPR and LR with four scenarios created. [ABSTRACT FROM AUTHOR]

The rapid spread of coronavirus disease (COVID-19) has become a worldwide pandemic and affected more than 15 million patients reported in 27 countries. Therefore, the computational biology carrying this virus that correlates with the human population urgently needs to be understood. In this paper, the classification of the human protein sequences of COVID-19, according to the country, is presented based on machine learning algorithms. The proposed model is based on distinguishing 9238 sequences using three stages, including data preprocessing, data labeling, and classification. In the first stage, data preprocessing's function converts the amino acids of COVID-19 protein sequences into eight groups of numbers based on the amino acids' volume and dipole. It is based on the conjoint triad (CT) method. In the second stage, there are two methods for labeling data from 27 countries from 0 to 26. The first method is based on selecting one number for each country according to the code numbers of countries, while the second method is based on binary elements for each country. According to their countries, machine learning algorithms are used to discover different COVID-19 protein sequences in the last stage. The obtained results demonstrate 100% accuracy, 100% sensitivity, and 90% specificity via the country-based binary labeling method with a linear support vector machine (SVM) classifier. Furthermore, with significant infection data, the USA is more prone to correct classification compared to other countries with fewer data. The unbalanced data for COVID-19 protein sequences is considered a major issue, especially as the US's available data represents 76% of a total of 9238 sequences. The proposed model will act as a prediction tool for the COVID-19 protein sequences in different countries. [ABSTRACT FROM AUTHOR]

Software testing process is a crucial part in software development. Generally the errors made by developers get fixed at a later stage of the software development process. This increases the impact of the defect. To prevent this, defects need to be predicted during the initial days of the software development, which in turn helps in efficient utilization of the testing resources. Defect prediction process involves classification of software modules into defect prone and non-defect prone. This paper aims to reduce the impact of two major issues faced during defect prediction, i.e., data imbalance and high dimensionality of the defect datasets. In this research work, various software metrics are evaluated using feature selection techniques such as Recursive Feature Elimination (RFE), Correlation-based feature selection, Lasso, Ridge, ElasticNet and Boruta. Logistic Regression, Decision Trees, K-nearest neighbor, Support Vector Machines and Ensemble Learning are some of the algorithms in machine learning that have been used in combination with the feature extraction and feature selection techniques for classifying the modules in software as defect prone and non-defect prone. The proposed model uses combination of Partial Least Square (PLS) Regression and RFE for dimension reduction which is further combined with Synthetic Minority Oversampling Technique due to the imbalanced nature of the used datasets. It has been observed that XGBoost and Stacking Ensemble technique gave best results for all the datasets with defect prediction accuracy more than 0.9 as compared to algorithms used in the research work. [ABSTRACT FROM AUTHOR]

Changes in precipitation as a result of climate change are becoming a widespread issue all around the world. A lack of rainfall causes a meteorological drought. The short-term Standardized Precipitation Index (SPI-6) index was used to estimate meteorological drought conditions in Saudi Arabia's Asir region from 1970 to 2017. Innovative trend analysis (ITA), the Modified Mann–Kendall test (MMK), the Sequential Mann–Kendall test, and Morlet wavelet transformation were used to detect trend and periodicity in meteorological drought conditions in the Asir region. In addition, the meteorological drought conditions were forecasted by integrating Particle Swarm Optimization (PSO) ensemble machine learning algorithm and an artificial neural network (ANN). Droughts of varying severity have become more frequent in Asir, according to the findings. In most stations, ITA and MMK tests have revealed a significant increase in drought. In all stations, the SQMK test revealed a big sudden year-over-year drought trend. With the exception of one station, all stations experienced extreme drought frequency discovered using Morlet Wavelet Transformation over a long period of time (10 years or more) (station 34). The PSO-ANN hybrid learning algorithm predicted SPI-6 values that had a strong correlation with actual SPI-6 values and also had lower error values, indicating that this model performed well. The PSO-ANN model predicts that the Asir region of Saudi Arabia will experience major moderate to extreme drought events in the coming years (2018–2025). The findings of this analysis will assist planners and policymakers in planning for the acquisition of sustainable agriculture in the study area. [ABSTRACT FROM AUTHOR]

A method that has recently been mentioned as information encoding brain is cross-frequency coupling (CFC). It is generally assumed that CFC can play a crucial role in perception, memory, and attention. In this study, two new indices for evaluating frequency–amplitude coupling (FAC) through generalized linear model (GLM) and linear regression method were introduced and investigated along with other CFC indices. Electroencephalogram (EEG) signals were recorded during covert visual attention tasks to find out the CFC index capability so as to distinguish different states in the mentioned tasks. To this end, machine learning algorithms were used and four various types of CFC, phase–amplitude coupling (PAC), phase–phase coupling (PPC), amplitude–amplitude coupling (AAC), and frequency–amplitude coupling (FAC) in recorded signals were considered as inputs for classifiers. The results demonstrated that the proposed method used for evaluating FAC through linear regression can provide more information about the different states in two covert attention tasks using quadratic discriminant analysis (QDA) by classification performance of 94.21% and 90.54% in color and direction tasks, respectively. Also, FAC that used a GLM model and PAC had a higher performance compared with PPC and AAC in color task (90.74 and 92.24% against 83.21 and 86.22). We can conclude that CFC can encompass useful information about semantic category of stimuli in covert attention tasks and can be used as an acceptable alternative for the time–frequency features of brain signals. [ABSTRACT FROM AUTHOR]

In the recent years, the volume of text documents in the form of digital way has grown up extremely in size. As significance, there is a need to be competent to automatically bring together and classify the documents based on their content. The main goal of text classification is to partition the unstructured set of documents into their respective categories based on its content. The main aim of this research work is to automatically classify the documents which are stored in the personal computer into their relevant categories. This work has two significant phases. In the first phase, the important features are selected for classification and the second phase is the classification of text documents. For selecting the optimal features, this research work proposes a new algorithm, optimization technique for feature selection (OTFS) algorithm. To estimate the proficiency of proposed feature selection algorithm, the OTFS algorithm was compared with the existing approaches artificial bee colony, firefly algorithm, ant colony optimization and particle swarm optimization. In the second phase, this research work proposed machine learning-based automatic text classification (MLearn-ATC) algorithm for text classification. In classification, the MLearn-ATC algorithm was compared with widely used classification techniques probabilistic neural network, support vector machine, K-nearest neighbor and Naïve Bayes. From this, the output of first phase is used as the input for classification phase. The decisive results establish that the proposed algorithms achieve the better accuracy for optimizing the features and classifying the text documents based on their content. [ABSTRACT FROM AUTHOR]

In recent years, it became possible to use different methods for the analysis of mechanical systems with the help of computers to learn like humans and by increasing their interaction with the world by observing autonomously. One of these mechanical analyzes is the fracture mechanics in which the behavior of the laminated composites having a crack is examined. In this study, experimental methods, finite element analysis (FEA) and machine learning algorithms (MLA) were used to analyze the fracture behavior of polymer composites in Mode I, Mode I/II and Mode II loading situations. For the experimental study, the fracture behaviors of the laminated composites reinforced with pure glass, pure carbon and glass/carbon hybrid knitted fabrics were tested with the help of Arcan test apparatus. In the finite element method, the linear elastic fracture behavior at the crack tip was analyzed by using the J-integral method. In the field of MLA, there is no single learning algorithm that provides good learning on all real-world problem data. Therefore, algorithm selection is done experimentally so various machine algorithms were used in the study. The analysis result showed that the finite element analysis and machine learning results were in good agreement with experimental measurements. This study is particularly important for the comparison of machine learning techniques with FEA in regression applications. [ABSTRACT FROM AUTHOR]

To improve the prediction of the individual risk of conversion to psychosis in UHR subjects, by considering all CAARMS' symptoms at first presentation and using a multivariate machine learning method known as logistic regression with Elastic-net shrinkage. 46 young individuals who sought help from the specialized outpatient unit at Sainte-Anne hospital and who met CAARMS criteria for UHR were assessed, among whom 27 were reassessed at follow-up (22.4 ± 6.54 months) and included in the analysis. Elastic net logistic regression was trained, using CAARMS items at baseline to predict individual evolution between converters (UHR-P) and non-converters (UHR-NP). Elastic-net was used to select the few CAARMS items that best predict the clinical evolution. All validations and significances of predictive models were computed with non-parametric re-sampling strategies that provide robust estimators even when the distributional assumption cannot be guaranteed. Among the 25 CAARMS items, the Elastic net selected 'obsessive–compulsive symptoms' and 'aggression/dangerous behavior' as risk factors for conversion while 'anhedonia' and 'mood swings/lability' were associated with non-conversion at follow-up. In the ten-fold stratified cross-validation, the classification achieved 81.8% of sensitivity (P = 0.035) and 93.7% of specificity (P = 0.0016). Non-psychotic prodromal symptoms bring valuable information to improve the prediction of conversion to psychosis. Elastic net logistic regression applied to clinical data is a promising way to switch from group prediction to an individualized prediction. [ABSTRACT FROM AUTHOR]

Reference evapotranspiration (ETo) is considered as an essential component in hydrological and agro meteorological processes. Its accurate estimation becomes an imperative in the planning and management of irrigation practices. ETo estimation also plays a vital role in improving the irrigation efficiency, water reuse and irrigation scheduling. The conventional physical model of Penmen Montieth (PM56) developed by Food and agriculture organization (FAO) has been recommended worldwide for ETo estimation. This model was firstly used in this study to determine ETo by using required meteorological data and obtained results used as referenced values. Afterward, five data machine learning algorithms/data driven models, support vector machine (SVM), multilayer perceptron (MLP), group method of data handling (GMDH), general regression neural network (GRNN) and cascade correlation neural network (CCNN), were applied to estimate ETo values. The climatic data of maximum and minimum temperatures, wind speed, average relative humidity and sunshine hours of six stations from Pakistan was used to train and test data driven model. Data driven models were also applied on other climatic stations without training data which lie in China, New Zealand and USA to further validate and investigate their performance. Comparison results indicated that model efficiency (ME) and correlation coefficient (r) of SVM were obtained (ranges: ME = 95–99%; r = 0.96–1) maximum for all the selected stations. Alternatively, model errors (RMSE = 0.016, MSE = 0.0001 & MAE = 0.08) for SVM were found minimum in comparison to GMDH, MLP, CCNN and GRNN. In addition, all data driven models show enough divergence from hyper arid to high humid climate except SVM which shows almost identical results for all the climatic zones in comparison to standard FAO-PM56 method. Finally, it can be concluded that SVM could be considered as a reliable alternative method for ETo estimation among data driven models. [ABSTRACT FROM AUTHOR]

Mobile phone touch screen devices are equipped with high processing power and high memory. This led to users not only storing photos or videos but stored sensitive application such as banking applications. As a result of that the security system of the mobile phone touch screen devices becomes sacrosanct. The application of machine learning algorithms in enhancing security on mobile phone touch screen devices is gaining a tremendous popularity in both academia and the industry. However, notwithstanding the growing popularity, up to date no comprehensive survey has been conducted on machine learning algorithms solutions to improve the security of mobile phone touch screen devices. This survey aims to connect this gap by conducting a comprehensive survey on the solutions of machine learning algorithms to improve the security of mobile phone touch screen devices including the analysis and synthesis of the algorithms and methodologies provided for those solutions. This article presents a comprehensive survey and a new taxonomy of the state-of-the-art literature on machine learning algorithms in improving the security of mobile phone touch screen devices. The limitation of the methodology in each article reviewed is pointed out. Challenges of the existing approaches and new perspective of future research directions for developing more accurate and robust solutions to mobile phone touch screen security are discussed. In particular, the survey found that exploring of different aspects of deep learning solutions to improve the security of mobile phone touch screen devices is under-explored. [ABSTRACT FROM AUTHOR]

In the industry, large- and small-scale manufacturers and even original equipment manufacturers are facing a major problem in monitoring large data. Because the amount of data is increasing daily, detecting faults and the methodology of detecting faults are becoming increasingly complex, such that there are insufficient intelligent data-driven mechanisms for achieving a short response time and high accuracy. Intelligent systems utilizing the advantages of Internet of Things (IoT) are emerging; however, they still require innovation. To design an intelligent system for a fault detection system, we propose a new fog-based IoT framework called cognitive Fog of Things framework, for achieving improved industrial fault detection and correction. The proposed framework comprises fog area networks including sensor nodes, fogs, and machine learning algorithms for detection and prediction. The proposed network operates on message queue transportation telemetry and cognitive learning fogs. The proposed concept is developed in a real-time scenario using Raspberry Pi with different case studies for implementation and using various parameters such as different types of faults, time of computation, detection time, and accuracy. [ABSTRACT FROM AUTHOR]

Phishing is a cyber-attack which targets naive online users tricking into revealing sensitive information such as username, password, social security number or credit card number etc. Attackers fool the Internet users by masking webpage as a trustworthy or legitimate page to retrieve personal information. There are many anti-phishing solutions such as blacklist or whitelist, heuristic and visual similarity-based methods proposed to date, but online users are still getting trapped into revealing sensitive information in phishing websites. In this paper, we propose a novel classification model, based on heuristic features that are extracted from URL, source code, and third-party services to overcome the disadvantages of existing anti-phishing techniques. Our model has been evaluated using eight different machine learning algorithms and out of which, the Random Forest (RF) algorithm performed the best with an accuracy of 99.31%. The experiments were repeated with different (orthogonal and oblique) random forest classifiers to find the best classifier for the phishing website detection. Principal component analysis Random Forest (PCA-RF) performed the best out of all oblique Random Forests (oRFs) with an accuracy of 99.55%. We have also tested our model with the third-party-based features and without third-party-based features to determine the effectiveness of third-party services in the classification of suspicious websites. We also compared our results with the baseline models (CANTINA and CANTINA+). Our proposed technique outperformed these methods and also detected zero-day phishing attacks. [ABSTRACT FROM AUTHOR]

Aiming to aid Electric-Power Industry to accurately understand users, hybrid learning model based ensemble learning algorithms for recognizing user to be sensitive to electric charge is proposed in this paper. On the basis of big data presented by CCF competition sponsor in China, with some excellent technology or algorithm such as JieBa, SFFS, etc., we extract many key features from data set and successfully draw a portrait for users who pay close attention to electric charge. Furthermore, machine learning algorithms and the strategy selection model related to them are investigated. The feasibility that hybrid learning model combining several ensemble learning algorithms can substantially improve classification accuracy are proved from theoretical level. Then the details of implementing hybrid learning model are described in the paper. Lastly, the hybrid learning model named Stacking is achieved, which yields better performance in contrast to the state-of-the-art competitors. The experimental results indicate that Stacking has both high precision and recall with 0.8 and 0.85 respectively. Furthermore the F1 score of Stacking evaluation is 0.823. [ABSTRACT FROM AUTHOR]

Health care systems are merely designed to meet the needs of increasing population globally. People around the globe are affected with different types of deadliest diseases. Among the different types of commonly existing diseases, diabetes is a major cause of blindness, kidney failure, heart attacks, etc. Health care monitoring systems for different diseases and symptoms are available all around the world. The rapid development in the fields of Information and Communication Technologies made remarkable improvements in health care systems. Various Machine Learning algorithms are proposed which automates the working model of health care systems and enhances the accuracy of disease prediction. Hadoop cluster based distributed computing framework supports in efficient processing and storing of extremely large datasets in cloud environment. This work proposes the novel implementation of machine learning algorithms in hadoop based clusters for diabetes prediction. The results show that the machine learning algorithms can able to produce highly accurate diabetes predictive healthcare systems. Pima Indians Diabetes Database from National Institute of Diabetes and Digestive Diseases is used to evaluate the working of algorithm. [ABSTRACT FROM AUTHOR]

Higher-order spectra (HOS) is an efficient feature extraction method used in various biomedical applications such as stages of sleep, epilepsy detection, cardiac abnormalities, and affective computing. The motive of this work was to explore the application of HOS for an automated diagnosis of Parkinson’s disease (PD) using electroencephalography (EEG) signals. Resting-state EEG signals collected from 20 PD patients with medication and 20 age-matched normal subjects were used in this study. HOS bispectrum features were extracted from the EEG signals. The obtained features were ranked using t value, and highly ranked features were used in order to develop the PD Diagnosis Index (PDDI). The PDDI is a single value, which can discriminate the two classes. Also, the ranked features were fed one by one to the various classifiers, namely decision tree (DT), fuzzy K-nearest neighbor (FKNN), K-nearest neighbor (KNN), naive bayes (NB), probabilistic neural network (PNN), and support vector machine (SVM), to choose the best classifier using minimum number of features. We have obtained an optimum mean classification accuracy of 99.62%, mean sensitivity and specificity of 100.00 and 99.25%, respectively, using the SVM classifier. The proposed PDDI can aid the clinicians in their diagnosis and help to test the efficacy of drugs. [ABSTRACT FROM AUTHOR]

This work is a hybrid architecture design furnished successfully using artificial intelligence techniques, rough data sets theory and machine learning algorithms. The purpose of this work is to bring the spotless and smart approach in identifying the thyroid disease in a human. There are several mechanisms implemented on thyroid data sets which produced astonished outcomes, but the data considered for the thyroid disease diagnoses (TDD) is inconsistent, redundant and consists of missing attribute values as per my literature survey. The proposed work is to construct an expert advisory system of hybrid architecture, which is to determine the optimistic disease growth because of the thyroid gland. A string matching system (SMS) was at the outset developed, which can predict the actual TDD based on the knowledge available. If the SMS fails, an individual approaches using artificial bee colony optimization and particle swarm optimization are developed to achieve the accuracy of results appreciating the measure values as 65 and 93 %, but the results obtained using the above said approaches are calculated using some missed attribute values which are not included in the knowledge likewise left blank and hence the proposed work continues to first generate the missing attribute value in the knowledge by using rough data sets theory and the obtained data (missed attribute values) is given to predict optimistic disease along with its prevention and its curing methods. However, the data generated cannot predict the optimal disease and hence it is proposed to use a machine learning algorithm so that, obtained result is hygienic. The knowledge for implementation of this work is gathered from Intelligent System Laboratory of K.N. Toosi University of Technology, Imam Khomeini Hospital. A questionnaire form is developed for providing an interface for user so they can contribute the data. [ABSTRACT FROM AUTHOR]

This paper presents a particular problem dealing with the apparition of burr during the drilling process in the aeronautic industry. This burr cannot exceed a height limit of 127 μm as set out by the aeronautical guidelines and must be eliminated before riveting. If this is not performed, it can cause structural damage which would constitute a danger due to the lack of safety. Moreover, the industry needs to find an automated and optimised process in which the drilling and deburring can be carried out in real time, eliminating those other unnecessary tasks, in order to obtain high-quality pieces. The work presents the applicability of data mining and machine learning techniques so as to obtain a real time burr detection model. This model could be implanted in the computer numerical control of the machine allowing the whole process to be automated and optimised. These techniques can be applied to other types of processes. [ABSTRACT FROM AUTHOR]