Disabled persons usually require an assistant to help them in their daily routines especially for their mobility. The limitation of being physically impaired affects the quality of life in executing their daily routine especially the ones with a wheelchair. Pushing a wheelchair has its own side effects for the user especially the person with hands and arms impairments. This paper aims to develop a smart wheelchair system integrated with home automation. With the advent of the Internet of Things (IoT), a smart wheelchair can be operated using voice command through the Google assistant Software Development Kit (SDK). The smart wheelchair system and the home automation of this study were powered by Raspberry Pi 3 B+ and NodeMCU, respectively. Voice input commands were processed by the Google assistant Artificial Intelligence Yourself (AIY) to steer the movement of wheelchair. Users were able to speak to Google to discover any information from the website. For the safety of the user, a streaming camera was added on the wheelchair. An improvement to the wheelchair system that was added on the wheelchair is its combination with the home automation to help the impaired person to control their home appliances through Blynk application.
Observations on three voice tones (low, medium and high) of voice command show that the minimum voice intensity for this smart wheelchair system is 68.2 dB. Besides, the user is also required to produce a clear voice command to increase the system accuracy.
This study presented the implementation of a small-scale (50 W) solar energy harvesting system coupled with an electrolyzer and proton exchange membrane (PEM) fuel cell. The energy from the solar panel would be utilized by the electrolyzer to produce hydrogen gas. The hydrogen gas would be used, in turn, by the PEM fuel cell to generate electricity which supports both DC and AC load. Excess energy from the solar panel is also used to charge the lead-acid backup battery. Analysis of the system showed that 400 mL of hydrogen gas could be produced within every 17 minutes in optimal conditions; between 11 am until 4 pm with bright sunlight. For every 400 mL of hydrogen gas, the PEM fuel cell could sustain continuous operation of a 5V 500 mA DC load for 95 seconds. Theoretically, more than 7000 mL of hydrogen gas could be produced within 5 hours in strong sunlight, which could power up a 50 mA and 500 mA load for 4.7 hours and 28 minutes respectively, during evening or night operations. The proposed system could complement the traditional battery-based storage system while remaining as a clean source of energy production.
Most of the hospitals in Malaysia still utilise manual inspection by medical
personnel to determine the health conditions of the patients. The data
collected from the medical equipment would have to be analysed and verified
by the hospital. Frequently, many patients need medical inspections.
However, to provide a precise diagnosis, medical personnel requires more
time. This limitation can be addressed by the development of automated and
wireless health monitoring systems with health diagnostic feature supported
by artificial intelligence (AI). In this project, the objective is to develop a
prototype of a wireless (non-invasive) heartbeat monitoring system with
supervised learning. This system monitors the heartbeat activity and predicts
the condition of the user's heartbeat. Technically, a photoplethysmographybased (PPG-based) heartbeat sensor is used to build a heartbeat sensing
device with a Bluetooth feature that communicates with an Android
application. The Android application is developed to receive heartbeat data
from the device and feed the data into an AI classification model to predict
the heartbeat condition of the user. This AI classifier was built from
heartbeat data collected from 10 healthy people. The additional heartbeat
dataset was generated based on a sound source of heartbeat information to
increase the volume of the training dataset. The completion of this project
implementation results in a wireless heartbeat monitoring system that can be
applied regardless of location and time. The accuracy of the AI prediction is
99 % when evaluated with a testing dataset. The empirical accuracy obtained
by testing the system with actual implementation is 90 %.