Biomedical Engineering

Abstract

This research presents the designing and evaluation of an IoT-based physiotherapy device designed to improve the accuracy of hand function assessments for rehabilitation. Traditional physiotherapy practices largely depend on subjective clinician evaluations, leading to inconsistencies and limiting personalized patient progress tracking. To address this, the proposed device uses force-sensitive resistors (FSR), flex sensors, and a gyroscope-accelerometer combination to measure hand grip strength, flexion, and rotation in real-time. The device transmits data wirelessly to a mobile application, providing a continuous, objective, and quantitative approach to monitoring hand functionality. The methodology involved designing and assembling the device components, 3D printing a flexible TPU casing, and developing custom algorithms for processing sensor data via an ESP32 microcontroller. Clinical testing was conducted with diverse participants performing controlled hand exercises, capturing a range of data on grip strength and movement patterns. This data was analyzed for flexion, rotation, and variability across different age and gender groups, providing a basis for assessing individual progress and comparative insights. Results indicated that the device could accurately track rehabilitation metrics, with participants showing measurable improvements in grip strength, flexion, and control across therapy sessions. On average, an 8% increase in flexion and a 12% increase in gyroscopic readings were observed per session. The data revealed distinct performance patterns among participants, supporting the device’s potential to personalize therapy plans and enhance rehabilitation outcomes.

Abstract

In this paper, a wearable device is presented which is designed to monitor the vital signs of young children and detect the possibility of a seizure before it occurs. Epilepsy and seizure disorders affect millions of people worldwide, and young children are particularly vulnerable to these conditions. However, it can be challenging for young children to communicate or recognize the symptoms of a seizure, which can lead to under-diagnosis and delayed treatment. The Seizure Tracker device includes an array of sensors - a biometric sensor hub for heart rate, blood pressure, and oxygen saturation, a temperature sensor, and an IMU sensor for jerk detection. The device uses a machine learning algorithm based on support vector machines to analyze the sequential data of a person both under normal and seizure conditions and classify the possibility of a seizure with an accuracy of 84%. The macro F1 score of the model on the test set was 0.8191. The misclassification rate of the model was 0.16.

Abstract

This study describes the construction and testing of a ball with built-in sensors that is intended to evaluate muscular strength and promote exercise in autistic youngsters. To measure the throwing force and the squeezing strength, the ball has inbuilt accelerometers and force sensors. This research highlights how technology-assisted therapy can benefit autistic children's physical health and development. The data collected by the stress ball included force data by the FSR sensor, timestamps and the acceleration data from the MPU6050 sensor. The stress ball uses the Bluetooth module to transmit data wirelessly to a remote device running a python script which stores the data for later analysis. The pressure data and the acceleration data generated during the squeezing action and the throwing action were collected across 6 weeks. The average of the peak force and the acceleration data were plotted for multiple weeks. The results showed that there was a 26% increase in the squeezing force exerted by the child in the duration of 6 weeks. Whereas the acceleration caused during the throwing action did not show any significant trend as the values kept fluctuating without any identifiable pattern.