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.
The Machine learning methods, which are one of the most important branches of promising artificial intelligence, have great importance in all sciences such as engineering, medical, and also recently involved widely in statistical sciences and its various branches, including analysis of survival, as it can be considered a new branch used to estimate the survival and was parallel with parametric, nonparametric and semi-parametric methods that are widely used to estimate survival in statistical research. In this paper, the estimate of survival based on medical images of patients with breast cancer who receive their treatment in Iraqi hospitals was discussed. Three algorithms for feature extraction were explained: The first principal compone
... Show MoreThe paper investigates the impact of role-playing as a classroom technique on Iraqi EFL students’ speaking skill on Iraqi EFL students at the college level. The students are 40 college language students in University of Baghdad, College of Education Ibn-Rushd randomly chosen. Then, they were divided into two groups, experimental and control groups. Thirty questions were applied to both groups as a pre-test of speaking and the students asked to answer them orally. The experimental group was taught speaking skill of the targeted role-play technique while the control group was taught in traditional method. After 20 lessons of the teaching, the post-test of speaking was conducted in which the students in both groups were asked to answ
... Show MoreThe Sebkha is considered the evaporative geomorphological features, where climate plays an active role. It forms part of the surface features in Mesopotamia plain of Iraqi, which is the most fertile lands, and because of complimentary natural and human factors turned most of the arable land to the territory of Sebkha lands. The use satellite image (Raw Data), Landsat 30M Mss for the year 1976 Landsat 7 ETM, and the Landsat 8 for year 2013 (LDCM) for the summer Landsat Data Continuity Mission and perform geometric correction, enhancements, and Subset image And a visual analysis Space visuals based on the analysis of spectral fingerprints earth's This study has shown that the best in the discrimination of Sebkha Remote sensing techniques a
... Show MoreBackground Solar irradiance is a nonlinear and intermittent function, which makes accurate forecasting of solar power generation a challenge. The high variability of meteorological conditions is not well represented by conventional atmospheric models, thus hampering forecasting skill and model robustness. In this work, an advanced hybridization of multi-population cuckoo search (HMPCS) algorithm with machine learning (ML) methods is developed to enhance the prediction performance of photovoltaic (PV) power forecasting with more reliability. Methods In this study, a hybrid modeling framework is proposed, called HMPCS–ML framework which captures the global search capacity of HMPCS and predictive power of sophisti
... Show MorePrediction of penetration rate (ROP) is important process in optimization of drilling due to its crucial role in lowering drilling operation costs. This process has complex nature due to too many interrelated factors that affected the rate of penetration, which make difficult predicting process. This paper shows a new technique of rate of penetration prediction by using artificial neural network technique. A three layers model composed of two hidden layers and output layer has built by using drilling parameters data extracted from mud logging and wire line log for Alhalfaya oil field. These drilling parameters includes mechanical (WOB, RPM), hydraulic (HIS), and travel transit time (DT). Five data set represented five formations gathered
... Show MoreThin films of Magnetite have been deposited on Galvanized Steel (G-S) alloy using RF-reactive magnetron sputtering technique and protection efficiency of the corrosion of G-S. A Three-Electrodes Cell was used in saline water (3.5 % NaCl) solution at different temperatures (298, 308, 318 & 328K) using potentiostatic techniques with. Electrochemical Impedance Spectroscopy (EIS) and fitting impedance data via Frequency Response Analysis (FRA) were applied to G-S alloy with Fe3O4 and tested in 3.5 % NaCl solution at 298K.Results taken from Nyquist and Bode plots were analyzed using software provided with the instrument. The results obtained show that the rate of corrosion of G.S alloy increased with increasing the temperatures from 298 t
... Show More