Healthcare Technology

Visually impaired people face several challenges to accomplish everyday tasks, especially when attempting to have safe and independent mobility. Improving the mobility skills of visually impaired people may improve their ability to participate in society, enhancing their productivity, self-maintenance, leisure, and overall quality of life A smart jacket is designed by embedding the sensor on the jacket, that enables the user to detect an obstacle and safely navigate. The prototype model has an accuracy of 98% for obstacle with in 200cm. The smart jacket requires low power hence can be used for real time navigation for visually impaired people. These results have important implications for developing wearable devices for the safe mobility of visually impaired people.

According to global driving statistics 21% of the road accidents occurring in the world are due to driver fatigue and drowsiness. This includes over 328,000 crashes per year including over 6,400 fatal crashes. The work aim of this project is to reduce the accidents occurring in the world due to driver fatigue and drowsiness. One of the most effective methods to reduce this risk is by monitoring the driver’s brainwaves and sending alerts. Brainwaves provide information about the state of mind of a person such as awake, alert, relaxation, sleep and so on. This can be done using a portable brainwave monitor. When sleep pattern is recognized by the brainwave monitoring system it immediately sends a signal that alerts the driver and helps mitigate crashes. The brainwave monitoring system was proposed to reduce the total number of fatal accidents due to drowsiness and fatigue. This system is intended to determine the different states of mind and frequencies associated with brain activity. These will be in the form of signals. The signals where then connected to a wireless transmitter, in order to transfer the data wirelessly. Our aim is to make this system cost effective and reliable.

The goal of our project is to make ventilators readily available, compact and cost effective to support the overstretched healthcare system and reduce the impact of the pandemic. Assessing the readiness of promising technologies, the design of the ventilator is less complicated with fewer valve controls. The reduction on costly sensors and valves makes it effective at mitigating the budgetary needs, making it best suited for helping patients from secluded / remote areas. The Control unit of the pneumatic system uses a buck (DC-DC) converter, driven by PWM pulses with a set duty cycle in the micro controller (Aurdino). The I:E ratios are to be set before administering the ventilator. Doctors usually after assessing the patients set these parameters as per requirements.

The present pandemic COVID-19 major impact is on the lungs of the human being which reduces the breathing rate and oxygen intake, CT scan are best preferred by doctor to assist and identify COVID-19 stage or pneumonia in the people. In this paper a novel approach has been proposed to identify the lung abnormality through the sounds generated by the air when it travels through the respiratory organ of the human. To assess the condition of the lungs in this method sound wave analysis is done by evaluating the audio diagnostics of the lungs which is recorded through sensors and modified stethoscope chest pieces. Hence the process used is a non-invasive one which would be cost effective and can be easily used by any layman. In this paper a sound wave analysis is done on the sound captured through stethoscope. Stethoscope captures the sound of the lungs, heart beat and the external noise. Random forest supervised machine learning algorithm is used to classify normal and abnormal lungs. Trained and tested the model with the help of Kaggle data set.

Challenges faced by the people with the disabilities or problems of not having a limb are either birth anomaly or a very unfortunate accident which the person faced. The primary motivation for doing this project was to understand and realize the challenges faced by the people with these problems. This project aims to develop a prosthetic-arm which should be same as human hand that is with five fingers which is done using foam. Aurdino Uno is used along with SG-90 servo motor. The fingers are controlled by the servo motors using a thin metallic string whose one end is connected to the finger and the other end to the motor. NRF24L01 module is used to make a wireless communication between two Arduino boards. This component is then connected to Arduino Uno using jumper wires and a battery is used to run this setup. Now a module is made to control the Prosthetic arm. A glove is used on which flex sensors are placed. These flex sensors are connected to another Arduino Uno. Another NRF24L01 module is used which acts as a transmitter in this case to communicate with the one present in the prosthetic arm. Arduino IDE with necessary supporting files is used. The code developed is used to program the microcontroller on the Aurdino board for controlling the motors based on sensors’ input. When fingers are bent on the transmitter glove, the resistance of the flex sensor increases and this information is sent to the Aurdino which is transmitted to the receiving end using NRF24L01. The Aurdino of the prosthetic arm receives the information and the signal drives the corresponding servo motor to rotate to desired angle resulting in the movement of the fingers of the prosthetic arm.

Brain-Computer Interfaces (BCI) are tools that open a new channel of communication between humans and machines. BCI helped in the evolution of a new world where man and computer had never been so close. Advancements in cognitive neuro-sciences facilitated us with better brain imaging techniques and thus interfaces between machines and the human brain became a reality. In the case of severe motor disabilities, like amyotrophic lateral sclerosis (ALS) or spinal cord injury (SCI), these pathways are blocked and cannot be used for communication. Since the brain functions of these people are not affected by the disease, BCI can provide an effective way to translate thought into machine readable commands. Electroencephalography (EEG), can be used for applications like prosthetic devices, applications in warfare, gaming, virtual reality and robotics upon signal conditioning and processing. This project is entirely based on Brain-Computer Interface with an objective of actuating a robotic arm with the help of device commands derived from EEG signals. This system unlike any other existing technology is purely non-invasive in nature, cost effective and is one of its kinds that can serve various requirements such as prosthesis. This suggests a low-cost system implementation that can even serve as a reliable substitute for the existing technologies of prosthesis like BIONICS.

In the field of orthopedic surgery, 3D printing implants and instrumentation can be used to address a variety of pathologies that would otherwise be challenging to manage with products made from traditional subtractive manufacturing. Furthermore, 3D bio printing has significantly impacted bone and cartilage restoration procedures and has the potential to completely transform how we treat patients with debilitating musculoskeletal injuries. This review outlines the basics of 3D printing technology and its current applications in orthopedic surgery and ends with a brief summary of 3D bio printing and its potential future impact. With compatible software and appropriate materials, consumers can witness the transformation from starting material to finished product of their own designs. Three-dimensional printed anatomic models are commonly used in preoperative planning and have become a useful educational tool for patient instruction and trainee teaching. For many orthopedic procedures, including arthroplasty and complex reconstructions, the use of 3D-printed patient-specific instrumentation (PSI) has become commonplace. The excitement around 3D printing continues to build as the fusion of 3D printing and biomedical science has shown early promise.

In world of wireless technology, the number of devices accessing the internet is growing every second. Most of the devices use wireless communication for sharing data between devices through internet, this has unfortunately led to an increase in network complexity, shortage of wireless radio bandwidth and an increased risk of interference of radio frequencies put limitation on radio frequency which is used in WiFi (Wireless Fidelity). Li-Fi is a new technology which uses visible light for communication instead of radio waves. It refers to 5G Visible Light Communication systems using Light Emitting Diodes as a medium to high speed communication in a similar manner as Wi-Fi. It can help to conserve a large amount of electricity by transmitting data through light bulbs and other such lighting equipment’s. Li-Fi uses light as a carrier as opposed to traditional use of radio waves as in Wi-Fi and this means that it cannot penetrate walls, which the radio waves are able to. It is typically implemented using white LED bulbs at the downlink transmitter. By varying the current through the LED at a very high speed, we can vary the output at very high speeds. This is the principle of the Li-Fi. The working of the LiFi is itself very simple if the LED is ON, the signal transmitted is a digital 1 whereas if it is OFF, the signal transmitted is a digital 0. By varying the rate at which the LEDs flicker, we can encode various data and transmit it.

The novel coronavirus (COVID-19) has raised world concern since it emerged in Wuhan, China in December 2019. It rapidly spread, resulting in an epidemic throughout China, followed by an increasing number of cases in other countries throughout the world. This project makes use of face mask detection system to make sure if a person is wearing a mask. Another feature of this project is to make sure social distancing in a public place. This is achieved by video tracking. The first step we use object tracking to find the number of people present in a place, by allowing limited people maintaining social distance is easier. The second step is to make sure the people inside are maintaining a safe distance, this is done by checking if the distance between people is six feet (about two arms’ length). This project uses Tiny-YOLO algorithm (You Only Look Once) on raspberry pi for real-time object detection. The YOLO object detector is often cited as being one of the fastest deep learning-based object detectors, achieving a high Fame Per Second (FPS), but YOLO is still not fast enough to run on embedded devices such as the Raspberry Pi. So, in this project makes use of tiny YOLO which has a small model size (< 50MB) and fast inference speed, making it suited for embedded deep learning devices such as the Raspberry Pi, Google Coral, and NVIDIA Jetson Nano. Overall, this project helps to reduce the number of COVID-19 patients and makes public places safer.

The preictal state is very useful for seizure prediction, as it starts few minutes before the seizure. The aim of this project is to predict epileptic seizure by detecting the start of preictal state’s sufficient time before the ictal state or onset of seizure starts. Early prediction helps patients, as medication can be done by the doctors to prevent the seizure. This project aims at providing cost-effective solution for predicting and monitoring Seizure Onset with Electroencephalogram data. The concept of Machine Learning is implemented fore predicting the onset of seizure before in hand. A neural network is implemented to predict the EEG signals received by the sensors. It has two hidden layers for prediction. This neural network has an accuracy up to 97%, which is good, effective neural network to predict an occurring seizure. The Arduino Mega 2560 is used for process the signals received by the sensors. EEG sensors, pulse sensor, and temperature sensor are used to measure EEG signals, heart rate and the body temperature of the patient. Analog signals are received by the sensors and given to Arduino Mega 2560 for digitization using built-in A-D converter. These digital signals are recorded for future use. They are now given to the neural network for prediction of the seizure of the patient. If there is a prediction of seizure, the patient can refrain themselves from doing any work that might cause harm to them such as swimming or driving. This system gives almost accurate results in predicting seizures and is patient specific results based on their history. The reports are analyzed to keep the patient safe and healthy.