Automatic Detection of Paroxysms in EEG Signals using Morphological Descriptors and Artificial Neural Networks 1 Crore Projects

Automatic Detection of Paroxysms in EEG Signals using Morphological Descriptors and Artificial Neural Networks Free Projects download

ABSTRACT:

The electroencephalogram (EEG) signal plays an important role in the diagnosis of epilepsy. The EEG recordings of the ambulatory recording systems generate very lengthy data and the detection of the epileptic activity requires a time-consuming analysis of the entire length of the EEG data by an expert. The traditional methods of analysis being tedious, many automated diagnostic systems for epilepsy has emerged in recent years. 

This paper proposes a neural-network-based automated epileptic EEG detection system that uses approximate entropy (ApEn) as the input feature. ApEn is a statistical parameter that measures the predictability of the current amplitude values of a physiological signal based on its previous amplitude values. It is known that the value of the ApEn drops sharply during an epileptic seizure and this fact is used in the proposed system. 

Two different types of neural networks, namely, Elman and probabilistic neural networks are considered. ApEn is used for the first time in the proposed system for the detection of epilepsy using neural networks. It is shown that the overall accuracy values as high as 100% can be achieved by using the proposed system.

EXISTING SYSTEM:

1. The existing system was done only by manual to detect the epilepsy.
2. The existing system of artificial neural network based detection systems for epileptic diagnosis has been proposed by several researchers.
3. The method proposed by Weng and Khorasani uses the features proposed by Gotman and Wang, namely, average EEG amplitude, average EEG duration, coefficient of variation, dominant frequency, and average power spectrum as inputs to an adaptive structured neural network.
4. The method proposed by Pradhan et al. uses a raw EEG signal as an input to a learning vector quantization network.
5. In 2004, Nigam and Graupe proposed a new neural network model called LAMSTAR network, and two time-domain attributes of EEG, namely, relative spike amplitude and spike rhythmicity have been used as inputs for the purpose of the detection of epilepsy.
6. Themethod proposed by Kiymik et al. uses a back propagation neural network with periodogram and autoregressive features as the input for the automated detection of epilepsy.

PROPOSED SYSTEM:

1. Though the use of Artificial Neural Networks increases the computational complexity, the high overall detection accuracies achieved with this system surpasses its disadvantage as in any automated seizure detection system; the detection of the seizure with high accuracy is of primary importance. Approximate Entropy shows clear discrimination between the normal and epileptic EEG signals.
2. The optimum Approximate Entropy obtained based on this data may not hold good for a general case. Hence, using a linear separator with known Approximate Entropy parameter values may not give good results in situations where a large number of different subjects are involved. This problem will not arise in the proposed ANN-based method as it has performed well irrespective of the Approximate Entropy used.
3. It is known that Approximate Entropy possesses good characteristics such as robustness in the characterization of the epileptic patterns and low computational burden. Hence, an automated system using Approximate Entropy as the input feature is best suited for the real-time detection of the epileptic seizures.
4. The proposed system is based on two types of EEG, namely, EEG signals of awake and epileptic subjects. It can be made more robust by acclimatizing it to the other manifestations of EEG like sleep EEG.

Modules:

1. Pre processing module
2. Approximate Entropy
3. Training Signals
4. Classification module
5. Output Module.

Pre processing module:

            This is our first module. This module used to get the amplitude from the neural files which we are getting from EEG machine. We can give the details of patient and disease details here. This is our input module.

Approximate Entropy module:

            ApEn is the time series module. There is a lots of signals will come from the EEG machine. This will make more time analyze. So our ApEn Helps us to get the different signal from the frequent amplitude.

Training Signals Module:

            This module is used to train the signal into our project. This is nothing but, storage of signals. We have to store only the epilepsy data into this module. This module only used to help us to find epilepsy.

Classification Module:

            This is the important module. This is to do the compare with the file which are trained in the previous module (Training) and detect the epilepsy with the use of neural network concepts.

Output Module:

            In our output module, we can get the details of patient and that patient affected by epilepsy or not. This is our report module of our project.

SOFTWARE REQUIREMENTS:

ENVIRONMENT                         :     Visual Studio .NET 2008

.NET FRAMEWORK                  :     Version 3.5

BACK END                                 :      SQL SERVER 2005

Automatic Detection of Paroxysms in EEG Signals using Morphological Descriptors and Artificial Neural Networks 1 Crore Projects , Automatic Detection of Paroxysms in EEG Signals using Morphological Descriptors and Artificial Neural Networks free download ,Automatic Detection of Paroxysms in EEG Signals using Morphological Descriptors and Artificial Neural Networks abstract , Automatic Detection of Paroxysms in EEG Signals using Morphological Descriptors and Artificial Neural Networks mca projects , Automatic Detection of Paroxysms in EEG Signals using Morphological Descriptors and Artificial Neural Networks source code , Automatic Detection of Paroxysms in EEG Signals using Morphological Descriptors and Artificial Neural Networks asp.net free download , Automatic Detection of Paroxysms in EEG Signals using Morphological Descriptors and Artificial Neural Networks source code free download