Healthcare Technology

The project IKSHANA mainly deals with helping the children who need to be monitored continuously. This real time monitoring system will monitor the mental health of children and elderly and also determine their vitals and provide them the necessary help. It is mainly designed to help the specially abled kids who should be under constant watch. If they are left alone, they can damage things and harm themselves to seek attention of their guardians. Hence, if they are continuously monitored by use of camera and AI when they start to act aggressively. Parents can look after their kids or even elder people who require continuous monitoring. Their health report will be automatically sent to concerned doctor so that they can track their health. There is also provision of video monitoring so that parents or care givers can talk and calm them down. Cloud storage involves stashing data on hardware in a remote physical location, which can be accessed from any device. Cloud storage systems generally encompass hundreds of data servers linked together by a master control server, but the simplest system might involve just one. The AI-enabled device in this can measure movements, sleep patterns, and vital signs of the patient. What is unique about the device is that it radiates about a thousand times less radiation than from a mobile phone thus can be extremely user and health friendly.

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.

We all encounter small accidents and injuries in our daily lives. Often, people fall sick with the change in season, particularly elderly people. Is it feasible and necessary to run to a doctor every time for a simple flu or an injury? We would say ‘NO’. But some measures have to be taken to treat these basic injuries and flu and identify its severity. To deal with this problem, we have come up with an innovative solution of a bot which will help people to get all the first aid help they need and also get information about the probability of the diseases they might have. In this era, health monitoring devices are the need of the hour as there is an increase in diseases of different kinds. For certain diseases people have to visit the doctor as soon as possible and take treatment to stop it or slowdown from making more severe damage. Conventionally when people fall sick, they try to be the doctor themselves and ignore their issue by swallowing few tablets to get rid of the ailment for the time being. To help people to get timely and proper diagnosis and help them to take more care about their health, we propose the idea of a health aid device.

There are 3 stages of our project: POSE DETECTION: In this stage of the project, we confirm if the user is performing the pose or not using a deep learning model which is 95% accurate. The model treats pose detection as a classification problem and has two outputs i.e., the user is performing a selected pose and the user is not performing the selected pose. If the output is negative, the program does not proceed further and it has to start from the beginning. POSE ESTIMATION: A computer vision technique that predicts and tracks the location of a person or object. This is done by looking at the orientation and combination of the pose. Pose estimation for our project is done by using MediaPipe which outputs a set of 33 keypoints on the user. This is typically done by identifying, locating, and tracking a number of key points on a given person, these key points represent important joints like an elbow or knee. POSE CORRECTION : In this stage of the project we find the angles of the various joints involved by using keypoints and compare it with standard angles for the given pose. The accuracy before correction is calculated using the two i.e, deviation and standard angles. The area of correction is then identified and conveyed to the user and also corrections to be made to the pose is given quantitatively to the user. This system can be implemented on any embedded device or an android app to guide a person to go through the positions of a yoga exercise by estimating the position of limbs, compare it with a reference model and voice assistant tells the user about the correctness of the asana.

Alzheimer’s disease is one of the most common neurodegenerative diseases and is considered to be the main cause of cognitive impairment in elderly people. The major symptom of Alzheimer’s disease is progressive dementia that eventually results in dysfunction of daily life. Memory problems are typically one of the first signs of Alzheimer’s, though initial symptoms may vary from person to person. A decline in other aspects of thinking, such as finding the right words, vision/spatial issues, and impaired reasoning or judgment, may also signal the very early stages of Alzheimer’s disease. As the person moves through the stages of Alzheimer’s, he or she will need more care. One reason is that medicines used to treat Alzheimer’s disease can only control symptoms; they cannot cure the disease. Symptoms, such as memory loss and confusion, will get worse over time. Due to this, generally these patients will need more help. A popular technology-Internet of Things (IoT) is used in this project to build an assistive device for Alzheimer patients. The device continuously monitors Alzheimer patient’s behavior at home and abroad and inform the geographical location and occurrence of the accident and critical conditions to family members and healthcare personnel. The IoT device is also capable of reminding the Alzheimer patients to take the medicines and food at designated times of the day. The proposed system aims to achieve higher accuracy towards sending emergency alerts and current health condition of patients such as heartbeat, blood pressure and sugar level, to the caretakers or family members and doctors likewise. This IoT based device helps reduce extra expenses and provides timely response to these patients.

Motor Neuron Disease is a medical condition where the motor neurons of the patient are paralyzed, due to which none of the voluntary actions can be performed. The main problem faced by these patients is that they cannot communicate. Thus in order to help these patients to communicate, this project develops an algorithm for the real time video Oculography system. The camera focuses on the eye of the patient and records the eye blink. The algorithm is written for the same and to convert eye blink to speech. The algorithm for converting eye blink to sentences is implemented in python software. The code is then fed to a Raspberry pi 3 microprocessor. The eye blink is detected using the web cam and the respective output is obtained as speech. Thus, the patient is able to communicate his basic needs with the outside world. The reason for using Raspberry Pi 3 is because of the WiFi /Bluetooth facility, CPU/GPU pair. This enables the implementation of the wireless Bluetooth speaker which can be placed anywhere around the patient. The caretaker need not be with the patient throughout. The use of currently trending components and coding makes it portable and user friendly. The future scope of this prototype is to implement in IOT. Along with the speech output, the operation will be performed in real time. This reduces the effort of the caretaker to assist the patient as he can perform the activities that he intends to on his own.

This project discusses various issues and challenges related to disability in India and emphasizes to strengthen health care and service to the disabled community. In a world where we have Google Assistant, Siri, Cortana, Alexa and other voice assistive technologies, making the lives of normal people easier, we do not have any sort of such technology for people who are physically challenged or the temporary hospital inmates. Census report of 2011 (2016 updated) reveal that, 2.21% of the total Indian population are disabled. Putting that in numbers, 2.68 Crore people fall into the category. Hospital inmates too do not have an assistance device to inform their needs to the nurse in charge. Here, we present an assistive technology in the form of an embedded system solely focused to help physically challenged people and hospital patients communicate with their assistant for assistance, with just a push of a button. Upon pressing, the message is wirelessly transmitted to outside the room and is displayed on the TV. The same message will also be sent to the assistant in the form of a SMS in case he/she is not present in the vicinity of the TV, thereby ensuring that the services are not missed at any cost. The system uses ARM controller at the transmitter/user end and a Raspberry Pi at the receiver/assistant end. The wireless communication is achieved using zig-bee protocol.

Foot plantar pressure is the pressure field that acts between the foot and the support surface during every day loco motor activities. Information derived from such pressure measures is important in gait and posture research for diagnosing lower limb problems, footwear designs, sport biomechanics, injury prevention and other applications. The project system is based on highly linear pressure sensors with no hysteresis. The development of miniature, lightweight, and energy efficient circuit solutions for healthcare sensor applications is an increasingly important research focus given the rapid technological advances in healthcare monitoring equipment, micro fabrication processes and wireless communication. Feet provide the primary surface of interaction with the environment during locomotion. Thus, it is important to diagnose the foot problems at an early stage for injury prevention, risk management and general well-being. One approach to measuring foot health, widely used in various applications, is examining foot plantar pressure characteristics. It is therefore, important that accurate and reliable foot plantar pressure measurement systems are developed.

The conventional methods that perform object recognition use image processing to detect edges and for pruning the image to remove the unwanted background. When object recognition is performed using image processing technique, the images in the database needs pre-processing. However, these are not dynamic and there is no learning or training involved. Convolutional Neural Networks are known for their image processing capabilities, in that no pre-processing is required before giving an image as input to them. Use of 2D images in object recognition may sometimes result in wrong classification. Since 3D images possess more information, use of such images will result in more reliable classification. In stereoscopic images, the depth information will separate the foreground from the background. his depth information is used as the 3rd dimension. Neural networks can analyze information the way human brain does. The main object of the invention is to provide a system for real time object recognition using stereoscopic images. It is another object of the invention to provide a system for real time object recognition using convolutional neural network, the said network utilizes three dimensional information obtained from stereoscopic image of the object.