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, me

Summary The paper proposes a small custom CNN for classifying solid waste into four classes: aluminum, cardboard, plastic, and glass. It is designed for real-time use on limited hardware such as a Raspberry Pi or Jetson.

Correct grading of apple slices can help ensure quality and improve the marketability of the final product, which can impact the overall development of the apple slice industry post-harvest. The study intends to employ the convolutional neural network (CNN) architectures of ResNet-18 and DenseNet-201 and classical machine learning (ML) classifiers such as Wide Neural Networks (WNN), Naïve Bayes (NB), and two kernels of support vector machines (SVM) to classify apple slices into different hardness classes based on their RGB values. Our research data showed that the DenseNet-201 features classified by the SVM-Cubic kernel had the highest accuracy and lowest standard deviation (SD) among all the methods we tested, at 89.51 %  1.66 %. This

Physicians are likely to expend significant labor and time while manually calculating blood smears. Automatic computer-based methods for classifying acute lymphoblastic leukemia have trouble correctly lighting stained white blood cell microscopy images and accurately separating cells that touch or overlap. Additionally, incorporating machine learning techniques into medical services is very hard because doctors can deal with rough guesses as long as the results aren't too bad, but they can't use these calculations for actual medical care. Enabling a A deep network having knowledge of the accuracy of its own predictions is a fascinating and crucial issue. Most instances segmentation frameworks weigh the mask quality during the instance

Olfactory impairment and abnormal frontal EEG oscillations are recognized as early markers of Alzheimer’s disease (AD). Using a publicly available olfactory EEG dataset of 35 subjects spanning normal cognition, amnestic mild cognitive impairment (aMCI), and AD, each with MMSE scores and demographics, stimulus-locked epochs from four electrodes (Fp1, Fz, Cz, Pz) were processed with wavelet-based time–frequency analysis. Band-limited power ratios (delta, theta, alpha, beta) were computed as log-transformed post-odor/baseline values and aggregated to subject-level features. Statistical analyses revealed graded attenuation of odor-evoked frontal (Fp1) band-power ratios across groups, with significant differences in several band–od

The acidity of spent lubricant was treated using sodium hydroxide solution. The effect of three variables on the treatment have been studied . These are mixing time rangingfrom 5-35 minutes, NaOH to lubricant weight ratio ranging from  0.25-1.25 and weight percentage  of NaOH ranging from  2-6 % .

The experimental design of Box-Wilson method is adopted to find a useful relationship between the three controllable variables and the lowering in the acidity of the spent lubricant. Then the effective variables and interactions are identified using the statistical analysis(F-test) of  three variable fractional design. The mathematical model is well represented  by a second order polynomial.

By

This work aims to analyze and study the bit performance in directional oil wells which leads to get experience about the drilled area by monitoring bit performance and analyzing its work. This study is concerned with Rumaila Oil Field by studying directional hole of one oil well with different angles of inclination. Drilling program was used in order to compare with used parameters (WOB, RPM and FR).in those holes. The effect of the drilling hydraulic system on the bit performance was studied as well as the hydraulic calculation can be done by using Excel program. This study suggests method which is used to predict the value of penetration rate by studying different formation type to choose the best drilling parameters t

Shaky Baghdad heavy crude oil 22 API is processed by distillation and solvent extraction. The purpose of distillation is to separate the light distillates    (light fractions) which represent 35% of heavy crude oil, and to obtain the reduced crude oil. The heavy residue (9 API) is  extracted with Iraqi light naphtha to get the deasphaltened oil (DAO), the extraction carried out with temperature range of 20-75 ^oC, solvent to oil ratio 5-15:1(ml:g) and a mixing time of 15 minutes. In general, results show that API of DAO increased twice the API of reduced crude oil while sulfur and metals content decreased 20% and 50% respectively. Deasphaltened oil produced from various operating conditions blended with the

A field experiment was carried out during two winter season 2013, 2014 at the field of the Department of Field Crops, College of Agriculture, University of Baghdad, to study the effect of seeds soaking with Gibberellic acid and foliar with Abscisic Acid on the growth, yield, and content of Anise oil seeds using factorial experiment within RCBD design with three replicates. The seeds was treated within GA3 were soaked with two concentrations of  30, and 60 mg. litter-1 in addition to without soaking and the code has been B0 , B1 , B2 overlapped these transactions with two concentrations of Abscisic Acid  3, and 6 mg. litter-1 in addition to without foliar A0 , A1 , A2The seeds to be treated  with GA3 are soaked for 24 hours prior

With the increasing reliance on microgrids as flexible and sustainable solutions for energy distribution, securing decentralized electricity grids requires robust cybersecurity strategies tailored to microgrid-specific vulnerabilities. The research paper focuses on enhancing detection capabilities and response times in the face of coordinated cyber threats in microgrid systems by implementing advanced technologies, thereby supporting decentralized operations while maintaining robust system performance in the presence of attacks. It utilizes advanced power engineering techniques to strengthen cybersecurity in modern power grids. A real-world CPS testbed was utilized to simulate the smart grid environment and analyze the impact of cyberattack