Precise and interpretable classification of autism-related behaviors is important for initial diagnosis, personalized intervention, and support arrangements. This study proposes an interpretable machine learning (ML) model using Light Gradient Boosting Machine (LightGBM) and Categorical Boosting (CatBoost) to classify behavioral patterns into four categories (normal, mild, moderate, and severe) associated with Autism Spectrum Disorder (ASD) based on a custom 377-instance survey dataset from Iraqi parents and teachers of children aged 6-12. The model observes 16 key features across communication and social interaction, repetitive behaviors, language, and adaptive skills, preprocessed via interquartile range (IQR) outlier removal, mean imputation, and K-nearest neighbors (KNN) balancing. Shapley Additive Explanations (SHAP) provide instance-level explanations, and Permutation Feature Importance (PFI) quantifies global feature importance. CatBoost had better accuracy (99. 53%) precision recall, and F1-scores (even reaching 1. 00 for some classes), completely outshining LightGBM (97. 65%). This combination of two XAI tools improves clinicians' trust and the practicality of insights, taking ASD assessment that is both accessible and transparent a step further beyond the use of black-box sensor-based models.
Abstract
The following research is marked by "social intelligence and its role in demonstration the potential abilities for individuals." The discussion dealt with the concepts of contemporary is very important because of their significant role in influencing the work of the Organization, as adopted link between the concepts of social intelligence and the potential role of the first to show the second .The research hypotheses tested in three health institutions in the city of Mosul, the research community is represented (Al-Salam Hospital and General Hospital and the son of ether), while the sample were the leaders of these institutio
... Show MoreIntroduction: The introduction of analytics tools in sports indicates that artificial neural networks can be one of the intelligent approaches to process complex data and identify patterns that help players move according to their most suitable positions. Objective: The purpose of this research is to investigate the possibility of using artificial neural networks to determine the physical and motor abilities of football players and determine their suitable playing positions based on exact quantitative indicators. Method: The study sample consists of 45 youth players aged (15–16) years from the Espanyol Football Academy in Baghdad. The results are analyzed using a multilayer perceptron (MLP) artificial neural network model to ident
... Show MoreDeep learning has recently received a lot of attention as a feasible solution to a variety of artificial intelligence difficulties. Convolutional neural networks (CNNs) outperform other deep learning architectures in the application of object identification and recognition when compared to other machine learning methods. Speech recognition, pattern analysis, and image identification, all benefit from deep neural networks. When performing image operations on noisy images, such as fog removal or low light enhancement, image processing methods such as filtering or image enhancement are required. The study shows the effect of using Multi-scale deep learning Context Aggregation Network CAN on Bilateral Filtering Approximation (BFA) for d
... Show MoreIn this research, the problem of multi- objective modal transport was formulated with mixed constraints to find the optimal solution. The foggy approach of the Multi-objective Transfer Model (MOTP) was applied. There are three objectives to reduce costs to the minimum cost of transportation, administrative cost and cost of the goods. The linear membership function, the Exponential membership function, and the Hyperbolic membership function. Where the proposed model was used in the General Company for the manufacture of grain to reduce the cost of transport to the minimum and to find the best plan to transfer the product according to the restrictions imposed on the model.
Early detection of eye diseases can forestall visual deficiency and vision loss. There are several types of human eye diseases, for example, diabetic retinopathy, glaucoma, arteriosclerosis, and hypertension. Diabetic retinopathy (DR) which is brought about by diabetes causes the retinal vessels harmed and blood leakage in the retina. Retinal blood vessels have a huge job in the detection and treatment of different retinal diseases. Thus, retinal vasculature extraction is significant to help experts for the finding and treatment of systematic diseases. Accordingly, early detection and consequent treatment are fundamental for influenced patients to protect their vision. The aim of this paper is to detect blood vessels from
... Show MoreBackground: The study aimed to investigate the effect of different techniques of en masse retraction on the vertical and sagittal position, axial inclination, rate of space closure, and type of movement of maxillary central incisor. Materials and methods: A typodont simulation system was used (CL II division 2 malocclusion). Three groups were used group 1(N=10, T-loop), group 2(N=10, Time-Saving loop), and group 3(N=10, Microimplant). Photographs were taken before and after retraction and measurements were made using Autodesk AutoCAD© software 2010. Kruskal-Wallis one-way analyses of variance and Mann-Whitney U test (p?0.05) were used. Results: The rate of space closure showed no significant difference among the three groups (p?0.05), whi
... Show MoreThe prepared nanostructure SiO2 thin films were densified by two techniques (conventional and Diode Pumped Solid State Laser (DPSS) (532 nm). X-ray diffraction (XRD), Field Emission Scanning electron microscopy (FESEM), and Atomic Force Microscope (AFM) technique were used to analyze the samples. XRD results showed that the structure of SiO2 thin films was amorphous for both Oven and Laser densification. FESEM and AFM images revealed that the shape of nano silica is spherical and the particle size is in nano range. The small particle size of SiO2 thin film densified by DPSS Laser was (26 nm) , while the smallest particle size of SiO2 thin film densified by Oven was (111 nm).