AddThis

Bookmark and Share

Friday 31 May 2013

EEG BASED REAL TIME EPILEPSY PREDICTION AND ALERT SYSTEM WITH GPS AND GSM


Epilepsy is a general term used for a group of disorders that cause disturbances in electrical signaling in the brain. Like an office building or a computer, the brain is a highly complex electrical system, powered by roughly 80 pulses of energy per second. These pulses move back and forth between nerve cells to produce thoughts, feelings, and memories. An epileptic seizure occurs when these energy pulses come much more rapidly-as many as 500 per second for a short time-due to an electrical abnormality in the brain. This brief electrical surge can happen in just a small area of the brain, or it can affect the whole brain. Epilepsy affects about 50 million people worldwide, and while anticonvulsant medications can reduce the frequency of seizures, the drugs are ineffective for as many as one in three patients. The proposed project develops a device that can be fitted on the body of an epileptic patient. The system tracks the patient using satellites and also gives warnings about epilepsy much before its occurrence. 

            The project consists of a microcontroller based embedded system connected to EEG sensors and a satellite tracking module. The user has the option of fixing the threshold values. This data is compared with the threshold level. If the read value is above or below the threshold values, the system automatically sends notification messages to the doctor/hospital/relative. The panic button can be pressed by the user if any illness is felt.  The system also activates an alarm that informs the nearby people about the illness. Another important feature is the position data transfer. This system can also transfers the location data from the satellite to the hospital/relative using GSM.  Based on the position data the location of the patient can be indicated in an earth map like Google Maps.

        Electroencephalography (EEG) is the recording of electrical activity along the scalp produced by the firing of neurons within the brain. In clinical contexts, EEG refers to the recording of the brain's spontaneous electrical activity over a short period of time, usually 20–40 minutes, as recorded from multiple electrodes placed on the scalp. In neurology, the main diagnostic application of EEG is in the case of epilepsy, as epileptic activity can create clear abnormalities on a standard EEG study. A secondary clinical use of EEG is in the diagnosis of coma, encephalopathies, and brain death. EEG used to be a first-line method for the diagnosis of tumors, stroke and other focal brain disorders.

            The world’s communication market is witnessing a tremendous growth in the field of mobile communication and became the focus for the economic and industrial development of the society. Currently, while the telecommunications industries are deploying Third Generation (3G) systems worldwide, emerging nations postulate enabling technologies like implementation of position data transfer services. Position data transfer involves two steps. The first step is to determine the location of the User and the second step is to send the location information. Many technologies currently exist for locating the MU such as GPS based technologies. GPS has greater potential because of its accuracy and seamless navigation. Similarly, GSM technology is an extremely successful digital wireless cellular evolution and an exceptional story of global achievement. This project merges these two technologies in a very efficient way.

The GSM Terminal is an industrial GSM Modem for the transfer of data, SMS and faxes in the GSM networks. Industrial standard interface and an integrated SIM card mean it can be used rapidly, easily and universally as a dual band GSM Terminal. Its performance bandwidth and the robust housing make it easier to quickly implement new applications in areas such as telemetry, telematics and remote control.        

          Epilepsy is a very fatal condition which is caused as a result of imbalance in the nervous system. The very common symptoms of epilepsy includes sudden fluctuations in heart beat rate and involuntary muscular movements (seizures). The aura (practical symptom) of epilepsy includes fluctuations in heartbeat, nausea, dizziness etc.

The application software in the PC allows the doctor/hospital authorities to view the patient details and location. The PC side software can be developed using VB/HTML/.NET.

Saturday 25 May 2013

HUMAN INTERACTION CONTROLLED ROBOT WITH ARTIFICIAL INTELIGENCE


Human Interaction based interfaces are changing the way we interact with computers, giving us a more intuitive way to control devices. Taking into account certain motions and speech recognition are easy and intuitive to perform, allowing an unprecedented level of control over the surrounding devices. Cameras and sensors translate movements of our bodies without the need of remotes or hand held tracking tools. As the underlying technologies evolve, a variety of approaches to gesture-based input are being explored. The most common applications for gesture based computing are for computer games, file and media browsing, and simulation and training. Controlling a computer applications can to brought to new level using speech recognition. The robot is having artificial intelligence to a level that it can interact with speech response.
                                                The proposed embedded system consists of a robotic arm supported with a vehicle at the base. Our aim is to deliver a user interface (UI) that enables the user to interact with the computer using Hand Gestures and Speech Recognition. For this we track the colour rings placed on the user's fingers using Matlab. The gesture recognition enables the user to control the arm movements by getting the positions of the colour rings. The total system can be controlled through voice recognition system using matlab.
We perform Voice recognition, an extremely complex visual task, almost instantaneously and our own recognition ability is far more robust than any computer's software can hope to be. We are able to recognize the voice of several thousand individuals whom we have met during our lifetime.
This current research is focused towards developing a sort of unsupervised pattern recognition scheme that does not depend on excessive geometry and computations like deformable templates. Neural network approach seemed to be an adequate method to be used for recognition due to its simplicity, speed and learning capability, also it was chosen because it has proved to be highly robust in pattern recognition tasks and because it is relatively simple to implement.




Speaker recognition using Neural Network approach was developed in Matlab technical computing language on a Microsoft Windows personal computer. The Database library was created manually and recognition were done and displayed