Artificial Neural Networks (ANNs) can be applied for the diagnosis and treatment of muscular problems, providing a comprehensive customized service. Neuroscientists focused on muscular disorders operate neurological clinics that provide patients with specialized medical advice. This work seeks to develop and execute a system for identifying muscular disorders utilizing real-time electromyography (EMG) information. The suggested system comprises three primary components. The initial phase involves measuring the electrical activity of human arm muscles by EMG. The EMGLAB program is used to record and organize the acquired data. During the third stage, surface electrodes are utilized to assess real-time EMG signals, from which pertinent signal features are retrieved. MATLAB is used for signal processing activities, including filtering, amplification, and normalization. ANNs are utilized through a graphical user interface to diagnose muscle problems by analyzing essential EMG parameters, such as signal amplitude and duration. The study additionally investigates the creation of a MATLAB-based graphical user interface for the classification of real-world electromyography signals. The system has undergone testing across many cases involving distinct human arm muscles, producing encouraging results that illustrate the design's potential for practical application in medical institutions or private clinics.

Engineering and applied programs have difficulties in incorporating e-learning and blended learning into modern academic frameworks because of their dependence on laboratories and workshops for hands-on training. Due to advances in computer and communication technologies, students can use real lab equipment on their smartphones or desktop computers from anywhere. This paper examines the utilization of artificial intelligence (AI), the Internet of Things (IoT), and mixed reality technologies in the design of experiments for remote laboratories and the management of the educational process. In an interactive environment, students gain skills by constructing experiments with real and simulated components. This paper describes a mechatronics lab experiment that remotely regulates DC motor velocity using a virtual intelligent controller. This laboratory allows students to conduct experiments online by choosing from available real and simulated components essential for their experiments. The incorporation of mixed reality in remote laboratory design creates an interactive environment that increases skill development and enhances learning quality. These laboratories provide educational institutions with possibilities to participate in the creation of high-quality, cost-effective new programs.

Computer and communication technologies' use in healthcare was accelerated by the COVID-19 outbreak, which aimed to control respiratory illnesses such as asthma. Asthma diagnosis is typically based on air quality assessments and peak expiratory flow rate (PEFR). This study presents a smart home healthcare system that utilizes an adaptive neuro-fuzzy inference system (ANFIS) to predict asthma attacks, taking into account the AQI and PEFR. This technology is developed for respiratory monitoring systems. An NN-based controller is used to adjust a mechanical ventilator or CPAP device based on the severity of asthma. Real-time sensor data on various gases, humidity, temperature, and particulate matter is utilized to calculate AQI. The system transmits emergency data to healthcare centers and delivers personalized alerts via a mobile app. The proposed method was highly accurate, with RMSE values of 0.05 for AQI and 0.0045 for predicting asthma severity.

This work examines the design and implementation of an electromyography (EMG)-based user interface suitable for human-machine interaction in a structured and rapidly changing environment. It offers complicated learning routes for EMG-based user interfaces that classify the problem domain using different classifiers and estimate human motion more accurately using a specialized model. EMG-based systems aim to enhance robotic performance by distinguishing among various metric definitions and existing functional metrics that represent human motion in robotic simulations. This work introduces a robotic control system utilizing electrical signals from the user's arm. EMG signals are obtained from hand muscles by sensors positioned on the arm, measuring the voltage produced during muscular contraction and relaxation, with the maximum value recorded during contraction and the minimum value during relaxation. A completely synchronized connection between a human arm and a servo motor has been developed and implemented, with results calibrated and verified. Tests performed on healthy individuals and disabled individuals demonstrated the system's capacity for continuous EMG signal monitoring and real-time motor control, validating its efficacy and prospective uses.

Humanoid systems must manage model uncertainty and sensor noise safely, smoothly, and accurately. Conventional sliding-mode control is robust, but high-frequency switching causes chattering, force spikes upon contact onset, and actuator stress. Impedance and admittance control improve comfort but challenge with modeling errors and tracking precision. Higher-order sliding modes and extensive filtering can reduce chattering, but with increased complexity and computation. This study provides a Hybrid Sliding-Mode Controller that reduces chattering using forceaware sliding and boundary layer saturation. It has an admittance/force estimator for stable contact transitions and a fuzzy gain scheduler that only increases switching gain when motion and force errors grow. The proposed approach provides the robustness of conventional sliding control while offering direct contact force control. Lyapunov-based analysis in an adjustable region confirms ultimate boundedness. In contact simulations, the proposed controller reduces (Root Mean Square) RMS tracking error by 88.0%, steady-state mean absolute error by 89.7%, and total variation of the control signal, which indicates chattering, by 86.1%. Results suggest improved human-robot collaboration with smoother interaction, reduced force overshoot, and realistic real-time applications.

The COVID-19 pandemic has significantly accelerated the adoption of computer and communication technologies in disease diagnosis and healthcare, particularly in the study of respiratory conditions. Diagnosis of many respiratory diseases, including asthma, often relies on assessing indoor and outdoor air quality around the patient, along with specific tests related to the patient’s condition. This study aims to predict asthma attacks using Adaptive Neuro-Fuzzy Inference System (ANFIS) technology based on Air Quality Index (AQI) and Peak Expiratory Flow Rate (PEFR) data. The system integrates an embedded microcontroller and IoT sensor technology to monitor levels of crucial gases such as ammonia, hydrogen sulfide, carbon dioxide, acetone, formaldehyde, humidity, temperature as well as PM2.5, PM10. This comprehensive approach utilizes both AQI and PEFR data to predict asthma attacks, issue alerts, offer medical advice through a mobile application to asthma patients, and transmit patient conditions and related data to medical centers in critical cases. Test results indicate high accuracy in predicting both air quality index and asthma severity, with minimal errors of 0.05 RMSE for AQI and 0.0045 RMSE for asthma severity.

The COVID-19 pandemic has significantly accelerated the adoption of computer and communication technologies in disease diagnosis and healthcare, particularly in the study of respiratory conditions. Diagnosis of many respiratory diseases, including asthma, often relies on assessing indoor and outdoor air quality around the patient, along with specific tests related to the patient’s condition. This study aims to predict asthma attacks using Adaptive Neuro-Fuzzy Inference System (ANFIS) technology based on Air Quality Index (AQI) and Peak Expiratory Flow Rate (PEFR) data. The system integrates an embedded microcontroller and IoT sensor technology to monitor levels of crucial gases such as ammonia, hydrogen sulfide, carbon dioxide, acetone, formaldehyde, humidity, temperature as well as PM2.5, PM10. This comprehensive approach utilizes both AQI and PEFR data to predict asthma attacks, issue alerts, offer medical advice through a mobile application to asthma patients, and transmit patient conditions and related data to medical centers in critical cases. Test results indicate high accuracy in predicting both air quality index and asthma severity, with minimal errors of 0.05 RMSE for AQI and 0.0045 RMSE for asthma severity.

Photovoltaic installations are growing rapidly around the world as part of a global effort to obtain renewable energy and reduce global warming. Faults will also increase and become more difficult to identify and locate as PV plants become larger and more grid connected. In this paper, a deep learning approach has been used to detect and quantify defects in PV chains. Three types of defects are tested: open circuit, short circuit, and shading by applying three types of deep learning algorithms. The results showed that the accuracy of the proposed technique when using ResNet-50 to classify and identify defects was 98.22%. Through fault detection and classification, the system can be repaired quickly and efficiently, which enhances the stability and reliability of the photovoltaic system.

The design and implementation of a real-time computer control of an electric wheelchair for physically disabled people is presented. This design is based on brain-computer interface that receives and processes the electroencephalographic (EEG) signals to classify the required commands to drive the wheelchair. Neuro-Fuzzy technique has been used in the controller design for actuating motors of the wheelchair. This controller depends on real data received from obstacle avoidance sensors and brain computer interface. By combining the concepts of soft-computing and mechatronics, the implemented wheelchair has become more sophisticated and gives people more mobility.