Identification of Diabetes through Urine Using Gas Sensor and Convolutional Neural Network

Abstract

Currently, blood glucose disease detection devices are administered invasively by inserting a needle into a finger or a blood vessel. This can cause trauma to the patient, especially if the frequency of examinations is very frequent. Therefore, we need a more comfortable and effective device for early recognition of the signs of diabetes mellitus. Blood sugar monitoring can also be done by smelling the patient's urine. Electronic nose is a system that can be used to identify someone with diseases including diabetes. The electronic nose system used in this study consists of several semiconductor gas sensors. The pattern recognition algorithms utilize convolutional neural network (CNN), learning vector quantization (LVQ), multilayer Perceptron (MLP), Naïve Bayes, k-Nearest Neighbors (k-NN), SVM, PCA-Logistic Regression (PCA-LR), PCA -LVQ, and PCA-MLP. The experimental results show that the CNN has the highest accuracy of 100% in the identification of two classes, namely healthy, and diabetic.

Reducing the Electronic Nose Sensor Array for Asthma Detection Using Firefly Algorithm

“…1D-CNN is organized to process one-dimensional sequential data, such as gas sensor response signals [12]. This model uses convolution layers, called conv, which provide filters or kernels to extract and analyze features from the sensor response curve more accurately.…”

“…PCA is usually used as a dimensionality reduction technique, converting the original dataset into PCA coordinates that characterize the location of the data in PCA space using an orthogonal linear transformation [12]. The converted data is ranked based on the amount of variance in the data.…”

“…An electronic nose is a device that employs an array of chemical gas sensors to recognize the characteristics of various types of gas. This approach has been applied to detect diseases in the human body, such as lung disease [6,9,10], and diabetes [11,12].…”

Identification of chronic obstructive pulmonary disease using graph convolutional network in electronic nose

“…1D CNN is specialized for sequential data due to its mechanism involving convolutional layers called conv. This layer contains filters and kernels to extract patterns or features from the input dataset [11]. This model presents feed-forward and backpropagation approaches similar to ANN [27].…”

“…An electronic nose comprises chemical gas sensors, offering an odor-Indonesian J Elec Eng & Comp Sci ISSN: 2502-4752  Identification of chronic obstructive pulmonary disease using graph convolutional network … (Dava Aulia) 265 detection means inspired by the human nose function. This approach is an alternative way to detect human body abnormalities [8]- [11].…”