Search

This study introduces a novel multi-modal dataset that has been meticulously curated to significantly improve diagnostic capabilities for Autism Spectrum Disorder (ASD). The dataset is intended to exploit the inherent diagnostic potential of facial images by emphasizing their systematic analysis. It is comprised of video excerpts from the Self- Stimulatory Behavior Dataset (SSBD) demonstrating behaviors such as hand flapping, head banging, and spinning, as well as 50 videos from ASD therapists and specialized educational institutions. In order to establish a comparative baseline, 100 videos from traditional educational contexts were collected for the Normal control group. Face Recognition (FR) pipeline with MTCNN is used for facial recognition, followed by precision-driven cropping, alignment, and scaling stages, resulting in RGB (2D) facial representations. Moreover, the incorporation of 3DDFA-V2 facilitates the transformation of 2D RGB images into a comprehensive 3D dataset by means of depth maps. The dataset contains 173 individuals aged 1 to 11 years in the Normal control group and 123 individuals, including 93 males and 30 females, in the ASD group. The data was divided into training and testing sets, with 1068 training samples and 100 testing samples, respectively. Open access to this dataset for researchers, medical professionals, and technologists will foster collaborative efforts in the development of automated ASD diagnostic methods, leveraging multi-modal data and deep learning to improve diagnostic precision and efficiency. [ABSTRACT FROM AUTHOR]

The conventional buck-boost converter may increase or decrease voltage and offers the advantages of cost- effectiveness and simplicity in construction. The power conversion efficiency of the typical buck-boost converter is limited by the negative effects of the device's parasitic features. We provide a high voltage conversion gain low-voltage-stress buck-boost converter based on a coat circuit in this work. Integrating a microcontroller into the conventional buck-boost converter expands the voltage conversion range and decreases the voltage strains on the semiconductor components. Buck- boost converters may maintain a consistent output voltage by changing it to be greater or less than the voltage at the input. A microcontroller application regulates the pulse durations of PWM signals to manipulate the output voltage. The buck- boost converter for solar panels in this research operates within an input voltage range of 5 to 10 V. [ABSTRACT FROM AUTHOR]

A flywheel with a changeable moment of inertia is known as variable Inertia flywheel (VIF) can be proposed to overcome complexity on moment of inertia that causes difficulty during rotating machine start-up. While there is an extensive amount of literature on VIF control strategies, very little addresses practical considerations. Depending on the parameters of the application system, a VIF system may be designed and built using a relatively simple control approach. To determine how a semi-active VIF control system and the input parameters of a rotating electrical machine relate to one another in minimizing energy losses, this study collects data from a VIF linked motor system. The last step in developing an intelligent semi active control for the rotating machine linked with VIF is to utilize a machine learning method to predict the parameters of the control application system. [ABSTRACT FROM AUTHOR]

The rotary cranes (tower crane) main purpose in finding a proper control strategy to transport the loads from one location to another. The controlling approach should consider two main factors which are minimizing the moving time of the payload from the primary pick up point to the destination point and second, the oscillation of the payload must be reduced to prevent hazards for people and equipment in the workplace. These days, instead of skillful crane operator, a lot of controllers have designed for the purpose of minimizing angle of swing as well as obtaining precise positioning. However, still each of them has some limitations and an enhanced controller is necessary with the aim of increasing the efficiency of the rotary crane system. In this research, input shaping technique, a technique of convolving the impulse sequences, an input shaper, with the command signal of the system is implemented into the rotary crane system. The outcome of the convolution is then being used as the reference command to drive the system. The inputs for the system are the position and the angle of swing that are being detected by the encoder and potentiometer. These inputs are converted into digital signal by the means of DAQ card. Then, after they are being manipulated with the design input shaper in the MATLAB simulation software, the simulation model will then be connected to the real system by using the XPC Target. The execution of the MATLAB simulation on the target PC will result in reduced angle of swing of the rotary crane system. This project is very significant due to fact that it brings an improvement in controlling the angle of swing of the rotary crane and minimizes the time needed to move the payload. [ABSTRACT FROM PUBLISHER]