Loading...
Please wait, while we are loading the content...
Similar Documents
Investigation of Digestive System Disorders with Cutaneous Electrogastrogram ( EGG ) Signal-An Engineering Approach
| Content Provider | Semantic Scholar |
|---|---|
| Copyright Year | 2011 |
| Abstract | The aim of this study is to develop an Electrogastrogram [EGG] acquisition procedure and different engineering methods for EGG signal analysis and comparing the different methods for the classification of normal subjects and abnormal subjects in order to guide the physician in the investigation digestive system disorders in fair amount of accuracy before the unwanted endoscopy procedure. Digestive system plays a vital role in human body because it helps to regulate the metabolic activity based on the food intake. However, the normal function of the digestive system is affected by many disorders such as nausea, dyspepsia gastritis, ulcer, vomiting, etc. Currently the physician for investigation of digestive disorders adopts the endoscope procedure, which is invasive and costly. This paper discusses the EGG acquisition procedure for collecting the EGG database about more than 150 subjects and the EGG analysis by three phases. In phase 1, EGG signal is analyzed using Fast Fourier Transform [FFT]. It classifies the signal for a normal subject or abnormal subject based on the frequency. In phase 2, EGG signal is analyzed with wavelet transform. It classifies the signal for a normal subject or abnormal subject based on the error. In phase 3, EGG signal is analyzed with Neural Network algorithms. It classifies the signal for a normal subject or abnormal subject based on the Mean Square Error [MSE] and Epochs.In the FFT analysis, the normal subject will have the frequency range 0.048 Hz < f <0.051 Hz and for the abnormal subject it have frequency f< 0.048 Hz and f >0.051 Hz. From the wavelet analysis, the normal subjects have the percentage of error value at 22.21% whereas the abnormal subjects have the percentage of error value at 15.45% for frequency below 0.048 Hz and the percentage of error value range from 25% to 41% for frequency above 0.051 Hz depending on disorders. In the Neural network analysis, different Back Propagation Network [BPN] training algorithm included but out of these three algorithm namely trainrp, traincgf and trainoss satisfies the condition but trainrp is more suitable for the classifications of normal subjects and abnormal subjects.From the Investigation of Digestive System Disorders with Cutaneous Electrogastrogram (EGG) Signal An Engineering Approach 211 above three phases of analysis of EGG signal, it is found that the methodologies adopted here able to analysis the EGG signal with a fair amount of accuracy to assist the physician either individually or combination of all in the investigation of digestive system disorders. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://3cpm.com/wp-content/uploads/2018/05/Canine-Tachygastria.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
