(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 13, No. 4, 2022 562 | Page www.ijacsa.thesai.org An Intelligent Approach based on the Combination of the Discrete Wavelet Transform, Delta Delta MFCC for Parkinson's Disease Diagnosis BOUALOULOU Nouhaila 1 , BELHOUSSINE DRISSI Taoufiq 2 Laboratory Electrical and Industrial Engineering, Information Processing, Informatics, and Logistics (GEITIIL), Faculty of Science Ain Chock. University Hassan II, Casablanca, Morocco NSIRI Benayad 3 Research Center STIS, M2CS, National Higher School of Arts and Craft, Rabat (ENSAM) Mohammed V University in Rabat Morocco Highlights  Collection of several types of speech recordings of the vowels /a/, /e/, /i/, /o/ and /u/.  The decomposition of each voice signal by DWT using the different types of wavelets.  Extraction of the delta delta MFCC from all voice samples.  Classification using decision tree classifier along with holdout scheme Graphical Abstract: Abstract—To diagnose Parkinson’s disease (PD), it is necessary to monitor the progression of symptoms. Unfortunately, diagnosis is often confirmed years after the onset of the disease. Communication problems are often the first symptoms that appear earlier in people with Parkinson’s disease. In this study, we focus on the signal of speech to discriminate between people with and without PD, for this, we used a Spanish database that contains 50 records of which 28 are patients with Parkinson’s disease and 22 are healthy people, these records contain five types of supported vowels (/a/, /e/, /i/, /o/ and /u/), The proposed treatment is based on the decomposition of each sample using Discrete Wavelet Transform (DWT) by testing several kinds of wavelets, then extracting the delta delta Mel Frequency Cepstral Coefficients (delta delta MFCC) from the decomposed signals, finally we apply the decision tree as a classifier, the purpose of this process is to determine which is the appropriate wavelet analyzer for each type of vowel to diagnose Parkinson’s disease. Keywords—Parkinson’s disease; discrete wavelet transform; delta delta MFCC; decision tree classifier I. INTRODUCTION Parkinson's disease is a severe health problem. According to the American Parkinson's Disease Association (APDA) [1], more than 10 million people worldwide are affected by Parkinson's disease. Due to the loss of certain groups of brain cells that produce neurotransmitters, including dopamine, causes symptoms such as impaired speech, movement, and sleep, as well as panic and anxiety attacks. Speech disorders include reduced speech intensity, fluctuating fundamental frequency, and irregular speech articulation which are signs that appear early in people with Parkinson's disease, allowing many studies to use the speech signal for the identification of Parkinson's disease [2-5]. However, the speech signal is one of the most complex signals to characterize, which makes it difficult to develop a system to understand different diseases such as Parkinson's disease [6-8], Alzheimer's disease [9-11], and COVID 19 [12- 15], etc. This complexity of the speech signal comes from a combination of several factors, the redundancy of the acoustic signal, the high inter-and intra-speaker variability, the effects Speech data Recording of sustained vowels /a/, /e/, /i/, /o/ & /u/ Pre-processing Down sampled to 16 kHz Discrete wavelet transform Signal decomposition Feature extraction Delta delta Mel frequency cepstral coefficients Classification Decision tree classifier