• AYAPPAN G
• Anila S

: Human diseases can be assessed from the basic symptoms like cough, sneeze and snore. The evaluation of its intensity and frequency of occurrence could provide valuable clinical information in the assessment of patients with chronic diseases. The digital audio recordings of these signals are spectrally analyzed using Discrete Wavelet Transform (DWT) in Feature Selection process. Occasionally the noise that may produce from the environmental disturbances could also automatically eliminate with the help of Median Filter. It disclose the use of Hidden Markov Model (HMM) to automatically detect the sample signal from continuous ambulatory recordings . In former experiments they have extracted and differentiated various emotions of subject’s sounds such as Feature Extraction for emotion recognition, abnormal sound detection and classification for surveillance applications. This system have improvised in extracting the subject’s sound using Gray Level Co-occurrence Matrix (GLCM) in detecting the type of human diseases which are processed with the help of MATLAB and are trained with the Probabilistic Neural Network (PNN) for classification

Acoustic nonspeech signals, Harr wavelet transform, probabilistic neural network, Obstructive Sleep Apnea, discrete wavelet

"HUMAN DISEASE ASSESSMENT FROM AMBULATORY RECORDINGS OF NON-SPEECH HUMAN ACOUSTICS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.344-350, June 2019, Available :http://www.jetir.org/papers/JETIR1908207.pdf

"HUMAN DISEASE ASSESSMENT FROM AMBULATORY RECORDINGS OF NON-SPEECH HUMAN ACOUSTICS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp344-350, June 2019, Available at : http://www.jetir.org/papers/JETIR1908207.pdf