A Detailed Literature Survey Of Asthma Disease Detection With Various Classifiers

Abstract

Asthma is chronic airways disease characterized by recurrent attacks of breathlessness and wheezing. Adherence to medication regimes is a common failing for asthmatic patients and there exists a requirement to monitor such patients’ adherence. The detection of inhalations from recordings of inhaler use can provide empirical evidence about patients’ adherence to their asthma medication regime. A classification technique deals with classifying each pattern in one of the distinct classes.  A classification is a technique where asthma is classified based on its different morphological features. This paper explores about various feature methods and different classifiers for asthma disease classification. There are so many classification  techniques  such  as  k-Nearest  Neighbor (K-NN)Classifier, Support vector machine (SVM), Gaussian mixture model (GMM) and Discrete wavelet transform (DWT) etc,..By using unique combination feature asthma disease are classified. The process of Feature extraction is that, in which the speaker is represented by the small amount of data from the voice signal. This system converts a speech waveform to type of parametric representation for further analysis and processing. Classification model were selected always with difficult method, because the result may differ with various input data. Finally, we compared chaotic convolutional neural networks (CCNNs) with previous classifiers to recognize respiratory sounds with artifacts highly reliable. And CCNNs may gives better result for asthma detection, when compare to all classifiers. For real time detection of asthma disease, we took survey on different classifiers models and each techniques were declared in this paper elaborately.