Supervised Machine Learning Classification Research Articles

Classification of e-waste using machine learning-assisted laser-induced breakdown spectroscopy.

Waste management and the economy are intertwined in various ways. Adopting sustainable waste management techniques can contribute to economic growth and resource conservation. Artificial intelligence (AI)-based classification is very crucial for rapid and contactless classification of metals in electronic waste (e-waste) management. In the present research work, five types of aluminium alloys, because of their extensive use in structural, electrical and thermotechnical functions in the electronics industry, were taken. Laser-induced breakdown spectroscopy (LIBS), a spectral identifier technique, was employed in conjunction with machine learning (ML) classification models of AI. Principal component analysis (PCA), an unsupervised ML classifier, was found incapable to differentiate LIBS data of alloys. Supervised ML classifier was then trained (for 10-fold cross-validation) on randomly selected 80% and tested on 20% spectral data of each alloy to assess classification capacity of each. In most of the tested variants of K nearest neighbour (kNN) the resulting accuracy was lower than 30% but kNN ensembled with random subspace method showed improved accuracy up to 98%. This study revealed that an AI-based LIBS system can classify e-waste alloys rather effectively in a non-contactless mode and could potentially be connected with robotic systems, hence, minimizing manual labour.

-wave-based exploration of sensitive EEG features and classification of situation awareness

Abstract The purpose of this study was to explore the electroencephalogram (EEG) features sensitive to situation awareness (SA) and then classify SA levels. Forty-eight participants were recruited to complete an SA standard test based on the multi-attribute task battery (MATB) II, and the corresponding EEG data and situation awareness global assessment technology (SAGAT) scores were recorded. The population with the top 25% of SAGAT scores was selected as the high-SA level (HSL) group, and the bottom 25% was the low-SA level (LSL) group. The results showed that (1) for the relative power of $\beta$ 1 (16–20Hz), $\beta$ 2 (20–24Hz) and $\beta$ 3 (24–30Hz), repeated measures analysis of variance (ANOVA) in three brain regions (Central Central-Parietal, and Parietal) × three brain lateralities (left, midline, and right) × two SA groups (HSL and LSL) showed a significant main effect for SA groups; post hoc comparisons revealed that compared with LSL, the above features of HSL were higher. (2) for most ratio features associated with $\beta$ 1 ∼ $\beta$ 3, ANOVA also revealed a main effect for SA groups. (3) EEG features sensitive to SA were selected to classify SA levels with small-sample data based on the general supervised machine learning classifiers. Five-fold cross-validation results showed that among the models with easy interpretability, logistic regression (LR) and decision tree (DT) presented the highest accuracy (both 92%), while among the models with hard interpretability, the accuracy of random forest (RF) was 88.8%, followed by an artificial neural network (ANN) of 84%. The above results suggested that (1) the relative power of $\beta$ 1 ∼ $\beta$ 3 and their associated ratios were sensitive to changes in SA levels; (2) the general supervised machine learning models all exhibited good accuracy (greater than 75%); and (3) furthermore, LR and DT are recommended by combining the interpretability and accuracy of the models.

Abstract PO4-05-05: Immune Activation Signatures for predicting CDKi primary response in advanced breast cancer patients

Abstract Background Cyclin Dependent Kinase inhibitors (CDKi’s) in combination with Endocrine Therapy (ET) have changed the first line management of patients with the most common subtype (HR+, HER2-) of metastatic breast cancer (MBC), improving progression-free survival (PFS) and overall survival. However, in approved indications for advanced breast cancer, approximately 20% of patients have been observed to have no response to CDKi’s and ET, and to progress after starting these therapies. Unlike other targeted therapeutics, there is no companion diagnostic or other clinically reliable biomarker for clinical decision support to indicate which patients will and will not benefit from CDKi therapy. Methods We have developed a novel platform that measures the Immune Activation Signature of patient plasma samples. Via simple measurements of the total concentration of protein-incorporated amino acid residues within patient plasma samples, the platform is designed to reveal changes in the proportion of immunoglobulins and albumin, and class-switching among immunoglobulins. For that purpose, we use Bioorthogonal chemical labelling reactions to label the protein-incorporated amino acids residues within the plasma. We measured the plasma samples of N=30 HR+, HER2- MBC patients, median age 54 years old, who were baseline naïve for CDKi’s treatment (16 on palbociclib, 11 on ribociclib, and 3 on abemaciclib) and ET. Eighteen patients had metastatic visceral disease and 12 patients had bone-only MBC. All patients were prospectively followed, and response assessed according to RECIST criteria on a CT scan every 3-months. Results Non-responding patients developed objective progressive disease during the first 6 months after starting CDKis and ET. In this cohort, 4 patients (13%) were classified as non-responders. The median PFS in non-responding patients was 4.5 months (4.03-5.02) and the median PFS in the cohort of responding patients was 16.6 months (6.8 – 40.9). The Immune Activation Signatures of the Responding and Non-Responding patients are shown in table 1. We analyzed the results with classical statistics and machine learning. A multivariate analysis of variance (MANOVA) test of the null hypothesis that the Immune Activation Signatures of Non-Responders and Responders are the same gave p = 0.00388. We analyzed the measured Immune Activation Signatures using a supervised machine learning classifier and observed in a held-back validation set correct prediction of 100% of non-responding patients and 95% accurate predictions overall. Conclusions According to these results, this platform may provide a clinically helpful biomarker for clinical decision support in the advanced or aggressive breast cancer context (patients with visceral metastasis bordering on visceral crisis), or for patient stratification in new indications. Table. Immune Activation Signature measurements (mean values in Clinical Outcome) Citation Format: Luis Costa, Cong Tang, Emma Yates, Qi Shi, Wesley Sukdao, Patricia Corredeira, Gonçalo Costa, Helena Pais, Catarina Abreu, Leonor Ribeiro, Rita Teixeira de Sousa, Sofia Torres, André Mansinho, Sandra Casimiro, Ana Cavaco, Patricia Alves, Angela Rodrigues, Lisiana Szeneszi, Gonçalo Bernardes. Immune Activation Signatures for predicting CDKi primary response in advanced breast cancer patients [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO4-05-05.

Abstract PO5-26-05: Machine learning-based risk prediction for late distant recurrence in young women with estrogen receptor-positive/human epidermal growth factor 2-negative breast cancer

Abstract Background There is a clinical unmet need to predict the risk of late recurrence in premenopausal women with estrogen receptor (ER)-positive/human epidermal growth factor 2 (HER2)-negative breast cancer (BC) who completed endocrine treatment (ET). Previous studies suggest that the CTS5 model, developed using data from cohorts with postmenopausal women and predicts a likelihood of late recurrence after five years of ET, is not highly predictive in premenopausal women. We developed a machine learning-based model predicting the chance of late distant recurrence (DR) using multi-institutional cohorts of premenopausal women with ER-positive/HER2-negative BC who have had no DR for five years from the surgery. Methods The study conducted a retrospective review of patients who underwent primary surgery between 2000 and 2011 at Samsung Medical Center, Gangnam Severance Hospital, and Seoul National University Hospital. The study included premenopausal women with ER-positive/HER2-negative BC aged 45 years or younger, who were treated over two years of ET with or without ovarian function suppression and had not experienced distant recurrence for at least five years following the surgery. Patients who had received neoadjuvant chemotherapy were excluded from the study. The primary endpoint is the area under the curve (AUC) and sensitivity (Recall) of the model predicting late DR after five years from primary operation. A total of nine clinical features, including age, tumor size, the number of positive lymph nodes, nuclear grade (NG), histologic grade (HG), progesterone receptor (PR) status, chemotherapy, extension of ET, and addition of OFS, were utilized for supervised machine learning classification. Results A total of 2,555 patients were included in this study. The median age was 41 (range, 21-45) years. During a median follow-up duration of 130.3 (range, 60.0-257.6) months, 157 women (6.1%) had late DR after five years of breast cancer surgery. Age, NG, HG, tumor size, and the number of positive LNs were important clinicopathologic variables for late recurrence. The treatment variables included chemotherapy, extension of ET, and the addition of OFS. There were 1,951 patients (76.4%) who had adjuvant chemotherapy, 650 patients (25.4%) with extension of ET over 5 years, and 529 patients (20.7%) who underwent addition of OFS. To develop the model, we performed repeated 5-fold cross-validation using a Balanced Random Forest classifier. The AUC and sensitivity of the model with six features, including age, tumor size, the number of positive lymph nodes, NG, HG, and PR status, were 0.705 and 0.768, respectively. When chemotherapy was added to this model, the AUC and sensitivity of the model increased to 0.713 and 0.771, respectively. When two more treatment features, such as ET extension and addition of OFS, were added to the model, the AUC and sensitivity were 0.714 and 0.752, respectively. Conclusions Demographic and clinical characteristics of the patients in this study Table. Citation Format: Dong Seung Shin, Janghee Lee, Jong-Ho Cheun, Jun-Hee Lee, Yewon Shin, Soong June Bae, Eunhye Kang, Sunyoung Kwon, Han-Byoel Lee, Jai Min Ryu, Sung Gwe Ahn. Machine learning-based risk prediction for late distant recurrence in young women with estrogen receptor-positive/human epidermal growth factor 2-negative breast cancer [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO5-26-05.

CHRONIC KIDNEY DISEASE PREDICTION USING MACHINE LEARNING

The term ―chronic kidney disease‖ means lasting damage to the kidneys that can get worse over time. If the damage is very bad, your kidneys may stop working. This is called kidney failure, or end-stage Kidney disease (ESRD). Kidney disease patients have the potential to get into the chronic phase and chronic kidney disease (CKD) is a decrease in kidney function gradually. So, doctors can diagnose kidney disease patients. So, predicting whether patients with Kidney disease have entered a phase of chronic kidney disease or not by showing the best accuracy result of comparing supervised classification machine learning algorithms. The aim is to investigate machine learning- based techniques for CKD forecasting by predicting results in the best accuracy. The analysis of the dataset by supervised machine learning technique (SMLT) to capture several information like, variable identification, univariate analysis, bi-variate and multi-variate analysis, missing value treatments and analyze the data validation, data cleaning/preparation, and data visualization will be done on the entire given dataset. Additionally, to compare and discuss the performance of various machine learning algorithms from the given hospital dataset with an evaluation classification report, identify the confusion matrix and to categorizing data from priority and the result shows that the effectiveness of the proposed machine learning algorithm technique can be compared with the best accuracy with precision, Recall and F1 Score. Key Words: Chronic kidney, Damage, Univariate, bi-variate, Multi-variate.

Vehicle-to-Cyclist Collision Prediction Models by Applying Machine Learning Techniques to Virtual Reality Bicycle Simulator Data

The study of vulnerable road users (VRUs) behavior is key to designing and optimizing driving assistance systems, such as the autonomous emergency braking (AEB) system. These kinds of devices could help lower the VRU accident rate, which is of particular interest to cyclists, who are the subject of this research. To better understand cyclists’ reaction patterns in frequently occurring collision scenarios in urban environments, this paper focuses on developing a virtual reality (VR) simulator for cyclists (VRBikeSim) that incorporates eye-tracking functionality. The braking and steering systems were calibrated by means of on-track tests with a sensorized bicycle in order to improve the accuracy of the bicycle virtual model. From the data obtained in the virtual tests, a battery of predictive models was built using supervised machine learning classifiers. All of them exhibited an accuracy higher than 85%, especially the K-Nearest Neighbors model. This model allowed us to obtain the best balance between the prediction of avoidance and collision cases, as well as enabling computationally lower times to be incorporated into the decision-making algorithm of an AEB system.

Measuring interpersonal firearm violence: natural language processing methods to address limitations in criminal charge data.

Firearm violence constitutes a public health crisis in the United States, but comprehensive data infrastructure is lacking to study this problem. To address this challenge, we used natural language processing (NLP) to classify court record documents from alleged violent crimes as firearm-related or non-firearm-related. We accessed and digitized court records from the state of Washington (n = 1472). Human review established a gold standard label for firearm involvement (yes/no). We developed a key term search and trained supervised machine learning classifiers for this labeling task. Results were evaluated in a held-out test set. The decision tree performed best (F1 score: 0.82). The key term list had perfect recall (1.0) and a modest F1 score (0.65). This case report highlights the accuracy, feasibility, and potential time-saved by using NLP to identify firearm involvement in alleged violent crimes based on digitized narratives from court documents.

Feature-specific quantile normalization and feature-specific mean–variance normalization deliver robust bi-directional classification and feature selection performance between microarray and RNAseq data

BackgroundCross-platform normalization seeks to minimize technological bias between microarray and RNAseq whole-transcriptome data. Incorporating multiple gene expression platforms permits external validation of experimental findings, and augments training sets for machine learning models. Here, we compare the performance of Feature Specific Quantile Normalization (FSQN) to a previously used but unvalidated and uncharacterized method we label as Feature Specific Mean Variance Normalization (FSMVN). We evaluate the performance of these methods for bidirectional normalization in the context of nested feature selection.ResultsFSQN and FSMVN provided clinically equivalent bidirectional model performance with and without feature selection for colon CMS and breast PAM50 classification. Using principal component analysis, we determine that these methods eliminate batch effects related to technological platforms. Without feature selection, no statistical difference was identified between the performance of FSQN and FSMVN of cross-platform data compared to within-platform distributions. Under optimal feature selection conditions, balanced accuracy was FSQN and FSMVN were statistically equivalent to the within-platform distribution performance in multivariable linear regression analysis. FSQN and FSMVN also provided similar performance to within-platform distributions as the number of selected genes used to create models decreases.ConclusionsIn the context of generating supervised machine learning classifiers for molecular subtypes, FSQN and FSMVN are equally effective. Under optimal modeling conditions, FSQN and FSMVN provide equivalent model accuracy performance on cross-platform normalization data compared to within-platform data. Using cross-platform data should still be approached with caution as subtle performance differences may exist depending on the classification problem, training, and testing distributions.

Brain Tumor Detection Using Neural Classification in Machine Learning

Brain cancer classification is a difficult task due to the variety and complexity of tumors shown in magnetic resonance imaging (MRI) pictures. This research presents two neural network approaches for categorizing MRI brain images. The proposed neural network method consists of three steps: feature extraction, dimensionality reduction, and classification. First, we extracted features from MRI images using discrete wavelet transformation (DWT). In this second stage, we reduce the salient features of MRIs using principal component analysis (PCA). For the classification step, two supervised machine learning classifiers have been developed. Artificial neural networks are used by both classifiers; however, the second one employs back propagation (BPN) while the first one uses feed-forward (FF-ANN). Using the classifiers, MRI brain images of the subjects were classified as normal or abnormal. Artificial neural networks have numerous applications, including function approximation, feature extraction, optimization, and classification (ANNs). They are specifically intended to enhance photos, distinguish and categorize items, separate and register objects, and extract features. Among these, object and picture recognition is the most important for complex processing tasks such as classifying brain tumors. Radial basis function (RBF), cellular, multi-layer perceptron (MLP), hop field, and pulse-coupled neural networks have all been used in image segmentation. These networks can be categorized as feed-forward (associative) or feedback (auto-associative).

Race/Ethnicity and Other Predictors of Early-Onset Type 2 Diabetes Mellitus in the US Population.

Among US adults aged 20 + years in the USA with previously diagnosed type 2 diabetes mellitus (T2DM), we aimed to estimate the prevalence of early-onset T2DM (onset at age < 50.5years) and to test associations between early-onset T2DM and race/ethnicity, and other hypothesized predictors. We pooled data from the annual National Health and Nutrition Examination Surveys (NHANES) over the years 2001 through 2018. We tested hypotheses of association and identified predictors using stepwise logistic regression analysis, and 11 supervised machine learning classification algorithms. After appropriate weighting, we estimated that among adults in the USA aged 20 + years with previously diagnosed T2DM, the prevalence of early-onset was 52.9% (95% confidence intervals, 49.6 to 56.2%). Among Non-Hispanic Whites (NHW) the prevalence was 48.6% (95% CI, 44.6 to 52.6%), among Non-Hispanic Blacks: 56.9% (95% CI, 51.8 to 62.0%), among Hispanics: 62.7% (95% CI, 53.2 to 72.3%). In the final multivariable logistic regression model, the top-3 markers predicting early-onset T2DM in males were NHB ethnicity (OR = 2.97; 95% CI: 2.24-3.95) > tobacco smoking (OR = 2.79; 95% CI: 2.18-3.58) > high education level (OR = 1.65; 95% CI: 1.27-2.14) in males. In females, the ranking was tobacco smoking (OR = 2.59; 95% CI: 1.90-3.53) > Hispanic ethnicity (OR = 1.49; 95% CI: 1.08-2.05) > obesity (OR = 1.30; 95% CI: 0.91-1.86) in females. The acculturation score emerged from the machine learning approach as the dominant marker explaining the race disparity in early-onset T2DM. The prevalence of early-onset T2DM was higher among NHB and Hispanic people, than among NHW people. Independently of race/ethnicity, acculturation, tobacco smoking, education level, marital status, obesity, and hypertension were also predictive.

The impact of comorbidities and economic inequality on COVID-19 mortality in Mexico: a machine learning approach.

Studies from different parts of the world have shown that some comorbidities are associated with fatal cases of COVID-19. However, the prevalence rates of comorbidities are different around the world, therefore, their contribution to COVID-19 mortality is different. Socioeconomic factors may influence the prevalence of comorbidities; therefore, they may also influence COVID-19 mortality. This study conducted feature analysis using two supervised machine learning classification algorithms, Random Forest and XGBoost, to examine the comorbidities and level of economic inequalities associated with fatal cases of COVID-19 in Mexico. The dataset used was collected by the National Epidemiology Center from February 2020 to November 2022, and includes more than 20 million observations and 40 variables describing the characteristics of the individuals who underwent COVID-19 testing or treatment. In addition, socioeconomic inequalities were measured using the normalized marginalization index calculated by the National Population Council and the deprivation index calculated by NASA. The analysis shows that diabetes and hypertension were the main comorbidities defining the mortality of COVID-19, furthermore, socioeconomic inequalities were also important characteristics defining the mortality. Similar features were found with Random Forest and XGBoost. It is imperative to implement programs aimed at reducing inequalities as well as preventable comorbidities to make the population more resilient to future pandemics. The results apply to regions or countries with similar levels of inequality or comorbidity prevalence.

Integration of machine learning models with microsatellite markers: New avenue in world grapevine germplasm characterization

Development of efficient analytical techniques is required for effective interpretation of biological data to take novel hypotheses and finding the critical predictive patterns. Machine Learning algorithms provide a novel opportunity for development of low-cost and practical solutions in biology. In this study, we proposed a new integrated analytical approach using supervised machine learning algorithms and microsatellites data of worldwide vitis populations. A total of 1378 wild (V. vinifera spp. sylvestris) and cultivated (V. vinifera spp. sativa) accessions of grapevine were investigated using 20 microsatellite markers. Data cleaning, feature selection, and supervised machine learning classification models vis, Naive Bayes, Support Vector Machine (SVM) and Tree Induction methods were implied to find most indicative and diagnostic alleles to represent wild/cultivated and originated geography of each population. Our combined approaches showed microsatellite markers with the highest differentiating capacity and proved efficiency for our pipeline of classification and prediction of vitis accessions. Moreover, our study proposed the best combination of markers for better distinguishing of populations, which can be exploited in future germplasm conservation and breeding programs.

Machine learning classifiers for signal detection in ambient backscatter communication under time-selective fading

In the world of the Internet of Things (IoT), ambient backscatter communication, or AmBaC, is a cutting-edge technology that has attracted a lot of interest. It meets the requirement for low-power communication in IoT devices, which are often located in a multitude of settings and scenarios where power efficiency is essential. In the literature, most signal detection is carried out using an energy detector or Minimum Mean Square Error (MMSE) detector under static conditions. In this work, we perform signal detection using multiple supervised machine learning (ML) classifiers, namely random forest, K-nearest neighbors (KNN), and support vector machine (SVM), and we examine the system performance in terms of bit error rate (BER) for both stationary and moving radio-frequency (RF) source. The simulation findings demonstrate that the proposed supervised ML classifiers surpass the conventional signal detector. In particular, the performance of the SVM classifier is best among all the other ML classifiers. Additionally, we examined the performance of different kernels of the SVM classifier and discovered that the Gaussian kernel offers the highest performance when it comes to SVM classifier performance.

Development of a Fault Detection and Localization Model for a Water Distribution Network

Water distribution networks are complex systems that aid in the delivery of water to residential and non-residential areas. However, the networks can be affected by different types of faults, which could lead to the wastage of treated water. As such, there is a need to develop a reliable leakage detection and localization system that can detect leak occurrences in the network. This study, using a simulated dataset from EPANET, presents the application of supervised machine learning classifiers for leak detection and localization in the water distribution network of the University of Port Harcourt Choba campus. The study compared three machine learning classification tools that are used in pattern recognition analysis: the support vector machine, k-nearest neighbor, and artificial neural network. The robustness and effectiveness of the proposed approach are compared with those of the performance of the classifiers for leakage detection in the network of the case study. The results show that the support vector machine performs the best, with 79% accuracy, while the respective accuracies for the remaining classifiers are 70% for the k-nearest neighbor and 61% for the artificial neural networks. The high accuracy demonstrated by the models shows that they are able to detect and address issues relating to fault detection in a water distribution network. This model could provide a leakage detection system to be applied to buildings for the efficient management of water in their networks.

A fault detection strategy for an ePump during EOL tests based on a knowledge-based vibroacoustic tool and supervised machine learning classifiers

This paper presents a methodology for identifying faulty components in an electric pump during the end-of-line test based on accelerations and pressure pulsation data used to train an ensemble learning algorithm based on supervised machine learning classifiers. Despite various quality control measures in pump manufacturing, some out-of-tolerance components can pass through and end up on the assembly line, potentially leading to premature failure or abnormal noise during real-field operation. Because of the high impact, it is very important to put in place actions to mitigate the risk of delivering non-conform units, even if properly working in terms of pressure-flow rate performances. In this paper, an innovative knowledge-based vibroacoustic tool together with a machine learning built-in Python® library have been used to post-process acceleration and pressure pulsations data to generate features, which are then used to train, and test several supervised machine learning algorithms. The ensemble learning algorithm combines the best classifiers to identify healthy electric pump units with high accuracy, achieving above 95% accuracy in an experimental test campaign carried out on eighty electric pumps. Results are compared using principal component analysis for dimensionality reduction, and a sensor sensitivity study is conducted.

CLASSIFYING THE SUPERVISED MACHINE LEARNING AND COMPARING THE PERFORMANCES OF THE ALGORITHMS

Supervised Learning (SL), also recognized as SML, means Supervised Machine Learning. Its a subclass of AI (Artificial Intelligence) and Machine Learning (ML). Its defined by the conduct of entitled datasets for training algorithms that predict outcomes precisely or classify data. The input dataset is faded into the supervised Machine Learning model, which synthesizes its weights until the model has been fitted properly, which happens as a segment of the cross-validation process. Supervised learning machine assists organizations in solving different kinds of real-world problems. SML is searching for algorithms that externally outfitted the instances to produce common hypotheses, preparing predictions for future cases.The supervised Machine Learning (SML) classifications are frequently completed tasks by effective intelligent systems. This paper discusses different categories of Supervised Machine Learning classification technology, compares different categories of supervised learning algorithms and identifies the best effective classification algorithm based on some instances, data set and variables or features. This paper discusses eight different types of SML algorithms. Those were envisaging: Artificial Neural Network (ANN), Bayesian Networks, K-nearest Neighbor (KNN), Random Forest, Decision Tree (DT), Linear Regression, Support Vector Machine (SVM), and Logistic Regression.These eight algorithms develop in the python language. Using a sample dataset for every algorithm and justify the algorithm performance. Here, justify the algorithms based on three different outcomes: throughput, response time, and accuracy. The supervised learning method depends on pre-defined parameters. The performance metric has an important role in identifying the ability and capacity of any kind of machine learning algorithm. The outcomes show that Decision Tree is the best prediction performance in this paper and gives the best accuracy, response time and throughput. The next accurate algorithms in SML algorithms are Logistic Regression and SVM after the DT algorithm.

Application of machine learning to assess the influence of microstructure on twin nucleation in Mg alloys

Twin nucleation in textured Mg alloys was studied by means of electron back-scattered diffraction in samples deformed in tension along different orientations in more than 3000 grains. In addition, 28 relevant parameters, categorized in four different groups (loading condition, grain shape, apparent Schmid factors, and grain boundary features) were also recorded for each grain. This information was used to train supervised machine learning classification models to analyze the influence of the microstructural features on the nucleation of extension twins in Mg alloys. It was found twin nucleation is favored in larger grains and in grains with high twinning Schmid factors, but also that twins may form in the grains with very low or even negative Schmid factors for twinning if they have at least one smaller neighboring grain and another one (or the same) that is more rigid. Moreover, twinning of small grains with high twinning Schmid factors is favored if they have low basal slip Schmid factors and have at least one neighboring grain with a high basal slip Schmid factor that will deform easily. These results reveal the role of many-body relationships, such as differences in stiffness and size between a given grain and its neighbors, to assess extension twin nucleation in grains unfavorably oriented for twinning.

Next generation phenotyping for diagnosis and phenotype–genotype correlations in Kabuki syndrome

The field of dysmorphology has been changed by the use Artificial Intelligence (AI) and the development of Next Generation Phenotyping (NGP). The aim of this study was to propose a new NGP model for predicting KS (Kabuki Syndrome) on 2D facial photographs and distinguish KS1 (KS type 1, KMT2D-related) from KS2 (KS type 2, KDM6A-related). We included retrospectively and prospectively, from 1998 to 2023, all frontal and lateral pictures of patients with a molecular confirmation of KS. After automatic preprocessing, we extracted geometric and textural features. After incorporation of age, gender, and ethnicity, we used XGboost (eXtreme Gradient Boosting), a supervised machine learning classifier. The model was tested on an independent validation set. Finally, we compared the performances of our model with DeepGestalt (Face2Gene). The study included 1448 frontal and lateral facial photographs from 6 centers, corresponding to 634 patients (527 controls, 107 KS); 82 (78%) of KS patients had a variation in the KMT2D gene (KS1) and 23 (22%) in the KDM6A gene (KS2). We were able to distinguish KS from controls in the independent validation group with an accuracy of 95.8% (78.9–99.9%, p < 0.001) and distinguish KS1 from KS2 with an empirical Area Under the Curve (AUC) of 0.805 (0.729–0.880, p < 0.001). We report an automatic detection model for KS with high performances (AUC 0.993 and accuracy 95.8%). We were able to distinguish patients with KS1 from KS2, with an AUC of 0.805. These results outperform the current commercial AI-based solutions and expert clinicians.

Identifying the Learning Style of Students Using Machine Learning Techniques: An Approach of Felder Silverman Learning Style Model (FSLSM)

Identification of the learning style of the students in the teaching and learning environment plays a significant importance in improving both teaching and learning perspectives. The intension of the research was to investigate about applying the Machine Learning Techniques for identification of the Learning style of the students in online learning environment based on the Felder Silverman Learning Style (FSLSM) identification model. The significance of this experiment is that the proposed methodology considers the combination of access frequency (f) of course materials and total time (T) students spent on each course activity. For data collection process, it was designed reusable plugin for the Moodle for time tracking. Real-time dataset was prepared using three course modules designed according to the features of FSLSM model and the features for analyzing the students according to the FSLSM, it was selected seven criteria, and the features were validated using Pearson Correlation Coefficient method. These course modules were enrolled 150 students per each module. Once the data set was prepared, the data set was preprocessed and applied Five Supervised Classification Machine learning algorithms as Decision Tree, Logistic Regression, Random Forest, Support Vector Machine and K-Nearest Neighbors algorithm. The models were evaluated using Accuracy, Precision, Recall and F1 values. Over the five algorithms the Decision Tree classifier algorithm performed with best average accuracy with 93.5% for Input, 86% for Perception, 89.5 for Processing and 94% for Understanding dimension. The models were validated using the K-fold Cross validation and Standard Deviation values. Mean Squared Error, Bias and Variance values were considered the evaluation of underfitting or overfitting context of the model. To parameter optimization, the Grid Search Methodology was applied to find the best combination of criterion for the model. Finally, an application was developed for Identifying the Learning Style of the Students using the designed Machine learning model. The Consistency of the ML Model based on the Decision Tree classifier algorithm were evaluated using the results generated through developed application and the results suggested that consistency for taught machine learning algorithms is often between 85% to 95%, which is an acceptable range. The results generated by the application for identification of the learning style suggested the combination of learning style for particular students sample as Global-Mild, Visual- Strong, Sensing- Moderate and Reflective-Strong. Identification of these combination of learning style assist for teachers by giving an insight which components of the learning contents should be improved in course designing process.

Assessment of Random Forest and Neural Network for Improving Land Use/ Land Cover Mapping from LIDAR Data and RGB Image: A Case Study of Magaga-El-Menia Governorate, Egypt

The goals of this article are to improve classification of land use/land cover information using LIDAR data and RGB images, as well as to compare the performance of various supervised machine learning classifiers (random forest and neural network) for extracting land use/land cover information. The 3D coordinates are first transferred to a high-resolution raster via interpolation. Height and intensity raster grids are formed. Second, various raster maps - a normalized digital surface model (nDSM), the difference of returns, and the LiDAR intensity image -are combined to create a multi-channel image. Five scenarios with different combinations were created. Finally, on the five separate datasets, several classifications based on random forest and neural network classifiers were performed. The classification findings were subjected to a quantitative accuracy check. A comparison of these five methodologies has been conducted. Following that, morphological operations were used to eliminate noise. The results revealed also that the fourth approach is the best followed by the third approach then the last approach then the second approach followed by the first approach. It was discovered that random forest classification outperforms neural network classification in terms of classification accuracy.