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

The compressive residual stresses generated by shot peening, is increased in a direct proportional way with shot peening time (SPT). For each metal, there is an optimum shot peening time (O.S.T) which gives the optimum fatigue life. This paper experimentally studied to optimize shot peening time of aluminium alloy 6061-T651 as well as using of and analysis of variance (ANOVA).

Two types of fatigue test specimens’ configuration were used, one without notch (smooth) and the other with a notch radius (1,25mm), each type was shot peened at different time. The (O.S.T) was experimentally estimated  to be 8 minutes reaching the surface stresses at maximum peak of -184.94 MPa.

A response surface methodology (RSM) is presen

This work presents a canned-food defect-detection method using the EfficientDet model with four backbones (MobileNet, EfficientNet, Swin-T, and ConvNeXt). The dataset included 8046 images with a resolution of 512 × 512 pixels. The performance criteria in this study accuracy “mAP”, computational cost “FLOPs”, and Frames Per Second “FPS”. The lightweight backbone with EfficientDet achieves a mean Average Precision (mAP) of 90% with MobileNet, while EfficientNet achieves mAP accuracy of 92% and 94%. The heavy backbone for EfficientDet (Swin-T, and ConvNeXt) achieves mAP accuracy of 96% and 98%. The main contribution of this study is to optimize the speed of conveyor belts in industrial production lines to considers the

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.

Naturally carbonate reservoirs have very low oil recovery efficiency owing to their wettability and tightness of matrix. However, adding surfactant to brine solution can enhance oil recovery by changing the wettability of the carbonate rock surface from oil-wet to water-wet. In the present study, the effects of different brines in the presence of surfactant hexadecyltrimethylammonium bromide (CTAB), on the wettability of carbonate rock were investigated through different characteristics such as surface tension interfacial tension and contact angle. The best concentration of CTAB was investigated at 500 ppm in brine (NaCl) reduced surface tension and interfacial tensions to 42 mN/m and 15 mN/m respectively and prevented reservoir fro

As the demands of sixth-generation (6G) networks escalate towards achieving high speeds and improved energy efficiency, there is an increasing need for intelligent and real-time adaptive solutions within the physical processing layer. This study proposes an innovative engineering framework based on an encapsulated architecture utilising FBGA (micro-distributed spherical array) technology, integrated with an internal artificial intelligence module, to achieve adaptive beamforming with high efficiency in dense wireless environments. The primary objective of this research is to develop an intelligent communication architecture that determines the optimal transmission angles and regulates power consumption in real-time by integrating ar