Indonesian Journal of Electrical Engineering and Computer Science Vol. 28, No. 1, October 2022, pp. 174~182 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v28.i1.pp174-182  174 Journal homepage: http://ijeecs.iaescore.com Predicting the value of sperm analysis using an electronic nose Raden Aa Koesoema Wijaya 1 , Ahmad Kusumaatmaja 2 , Dicky Moch Rizal 3 1 Departement of Biomedical Engineering, Multidiciplinary Graduate School Faculty, University of Gadjah Mada, Yogyakarta, Indonesia 2 Department of Physics, Faculty of Math and Natural Sciences, University of Gadjah Mada, Yogyakarta, Indonesia 3 Department of Physiology, Faculty of Medicine, Public Health, and Nursing, University of Gadjah Mada, Yogyakarta, Indonesia Article Info ABSTRACT Article history: Received Dec 6, 2021 Revised Jun 14, 2022 Accepted Jul 17, 2022 Total motile sperm count and DNA fragmentation Index are two parameters in sperm analysis that have recently been used to determine the outcome of the management of cases of male infertility. Total Motile Sperm Count is one of the values considered better than the 2010 World Health Organization standard sperm analysis in terms of predictive value for the success of the spontaneous ongoing pregnancy rate. High DNA Fragmentation Index values were associated with lower pregnancy success and an increased risk of low fertilization rate or total fertilization failure. In this study, we developed a method to classify sperm analysis based on total motility sperm count and DNA Fragmentation Index values by using an electronic nose. In the total motility sperm count (TMSC) study, we use four algorithms with the result of accuracy values 95% and in the DNA fragmentation Index study, we get a fairly good accuracy value for two algorithms with the accuracy values 70%. Keywords: DNA fragmentation index Electronic nose Seminal fluid Total motile sperm count Volatile organic compound This is an open access article under the CC BY-SA license. Corresponding Author: Dicky Moch Rizal Department of Physiology, Faculty of Medicine, Public Health, and Nursing, University of Gadjah Mada Street of Farmako, North Sekip, Yogyakarta, Indonesia Email: drdickyandrologi@ugm.ac.id 1. INTRODUCTION Artificial intelligence has now developed in helping sperm morphology analysis through image processing. The computer-assisted sperm analysis (CASA) can be processed in real-time. However, this CASA examination is quite expensive, and it has not been included in the 2010 WHO guideline for sperm analysis. Another semen examination method that has utilized artificial intelligence technology is calculating sperm concentration using machine learning-based spectroscopy [1]. Semen analysis is the main procedure in infertility examination to classify sperm samples as having normal or abnormal values. Furthermore, the sperm analysis will be used to select, track and collect healthy sperm for in vitro processing. One study applied artificial intelligence to microscopic images of sperm analysis results to simplify and speed up the process of classifying sperm cells using the faster region convolutional neural network (FRCNN) with elliptic scanning algorithm (ESA). This new method can detect sperm and identify sperm motility within 1.12 seconds with an accuracy of 97.37% [2]. Sperm morphology is a very important factor in the assessment of sperm quality. Various artificial intelligence methods have been developed to help classify sperm deformities based on datasets of sperm morphology. One of these studies applies multi-stage cascade-connected preprocessing and machine learning based on a non-linear support vector machine (SVM) kernel. The results of this study provide an accuracy of 86.6% for the human sperm head morphology (HuSHeM) dataset and 85.7% for the Sperm Morphology image data set (SMIDS), respectively [3]. Another study developed an artificial intelligence algorithm using a network-based deep transfer learning approach and deep multi-task transfer learning (DMTL), to classify