Treffer: Investigating an Efficient Filter to Implement Automated Nadi Pariksha by Analysing Time and Frequency Domain Features with Machine Learning Approach.

In the realm of traditional Ayurveda practices, Nadi Pariksha (Pulse Diagnosis) stands out as a highly convenient and non-invasive method for examining the health of the human body. Rooted in ancient literature, Nadi Pariksha utilizes the radial artery pulse to assess the physiological condition. Recognizing the variability of pulses among individuals, influenced by factors such as age and time of day, mastering Nadi Pariksha has traditionally required personalized instruction from experts. Unfortunately, this specialized knowledge is at risk of fading away. To address this challenge, a sensor-based apparatus leveraging photoplethysmography is introduced which is designed to capture human pulse signals, facilitating the standardization and analysis of human Nadi. This innovative equipment comprises three pulse sensors, each dedicated to Vata, Pitta, and Kapha, alongside a microcontroller with an Analog-to-Digital converter connected to a laptop/PC via a COM port. In this study, pulse data from 250 volunteers, spanning ages 18 to 75 and representing a diverse mix of healthy and non-healthy individuals of both genders, underwent comprehensive analysis. A total of six pre-processing techniques, two types of features extraction methods to extract 60 features, and 3 classifiers were employed to distinguish healthy and non-healthy subjects. The comparison revealed that moving average and Butterworth filters exhibit higher accuracy in analyzing Nadi signals. The DT and KNN classifiers outshone others, achieving an impressive accuracy rate of 92%. This pioneering work holds significance for the analysis of Nadi signals and may pave the way for a new era of digitalization in Nadi Pariksha. [ABSTRACT FROM AUTHOR]

Copyright of International Research Journal of Multidisciplinary Technovation (IRJMT) is the property of Asian Research Association and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)