A new approach to signal filtering method using K-means clustering and distance-based Kalman filtering
Human axillary odours taken by an electronic nose (e-nose) device that uses a Metal Oxide Semiconductor (MOS) sensor not only contains a gas signal from the pure source of the axillary odour but also has the potential to contain other substances such as perfume and deodorant. This situation requires...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-12-01
|
Series: | Sensing and Bio-Sensing Research |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S221418042200068X |
_version_ | 1811178550009528320 |
---|---|
author | M. Syauqi Hanif Ardani Riyanarto Sarno Malikhah Malikhah Doni Putra Purbawa Shoffi Izza Sabilla Kelly Rossa Sungkono Chastine Fatichah Dwi Sunaryono Rahadian Indarto Susilo |
author_facet | M. Syauqi Hanif Ardani Riyanarto Sarno Malikhah Malikhah Doni Putra Purbawa Shoffi Izza Sabilla Kelly Rossa Sungkono Chastine Fatichah Dwi Sunaryono Rahadian Indarto Susilo |
author_sort | M. Syauqi Hanif Ardani |
collection | DOAJ |
description | Human axillary odours taken by an electronic nose (e-nose) device that uses a Metal Oxide Semiconductor (MOS) sensor not only contains a gas signal from the pure source of the axillary odour but also has the potential to contain other substances such as perfume and deodorant. This situation requires noise reduction so that dirty data can be cleaned and produce better predictions without wasting a lot of data. The approach taken in this study is to detect data clusters and data centroids from each reference data. Dimensional reduction using Linear Discriminant Analysis (LDA) on the reference data is carried out, then look for the centroid of each data using K-Means Clustering and use it to be a good signal estimate and process using Kalman Filtering so that it can be used to process axillary odour data containing deodorant. The proposed method was tested by a stacked Deep Neural Network (DNN) approach and can increase accuracy by 18.95% and balanced accuracy by 11.865% compared to original invalid data before filtering. The proposed method is also tested by other classification methods and able to produce the highest accuracy with 79.29% in Support Vector Classifier (SVC) and Multi-Layer Perception (MLP), while other filtering methods only get the highest accuracy with 69.03% also in SVC and MLP. We also analysed the execution time of each tested methods. |
first_indexed | 2024-04-11T06:20:15Z |
format | Article |
id | doaj.art-06be41632ecd4114a67b703076fc7a56 |
institution | Directory Open Access Journal |
issn | 2214-1804 |
language | English |
last_indexed | 2024-04-11T06:20:15Z |
publishDate | 2022-12-01 |
publisher | Elsevier |
record_format | Article |
series | Sensing and Bio-Sensing Research |
spelling | doaj.art-06be41632ecd4114a67b703076fc7a562022-12-22T04:40:36ZengElsevierSensing and Bio-Sensing Research2214-18042022-12-0138100539A new approach to signal filtering method using K-means clustering and distance-based Kalman filteringM. Syauqi Hanif Ardani0Riyanarto Sarno1Malikhah Malikhah2Doni Putra Purbawa3Shoffi Izza Sabilla4Kelly Rossa Sungkono5Chastine Fatichah6Dwi Sunaryono7Rahadian Indarto Susilo8Department of Informatics, Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember (ITS) Sukolilo, Surabaya, Indonesia.Department of Informatics, Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember (ITS) Sukolilo, Surabaya, Indonesia.; Corresponding author.Department of Engineering, Data Science Technology Study Program, Faculty of Advanced Technology and Multidiscipline, Airlangga University, Surabaya, Indonesia.Department of Informatics, Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember (ITS) Sukolilo, Surabaya, Indonesia.Department of Informatics, Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember (ITS) Sukolilo, Surabaya, Indonesia.Department of Informatics, Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember (ITS) Sukolilo, Surabaya, Indonesia.Department of Informatics, Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember (ITS) Sukolilo, Surabaya, Indonesia.Department of Informatics, Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember (ITS) Sukolilo, Surabaya, Indonesia.Department of Neurosurgery, Faculty of Medicine, Airlangga University, Surabaya, Indonesia.Human axillary odours taken by an electronic nose (e-nose) device that uses a Metal Oxide Semiconductor (MOS) sensor not only contains a gas signal from the pure source of the axillary odour but also has the potential to contain other substances such as perfume and deodorant. This situation requires noise reduction so that dirty data can be cleaned and produce better predictions without wasting a lot of data. The approach taken in this study is to detect data clusters and data centroids from each reference data. Dimensional reduction using Linear Discriminant Analysis (LDA) on the reference data is carried out, then look for the centroid of each data using K-Means Clustering and use it to be a good signal estimate and process using Kalman Filtering so that it can be used to process axillary odour data containing deodorant. The proposed method was tested by a stacked Deep Neural Network (DNN) approach and can increase accuracy by 18.95% and balanced accuracy by 11.865% compared to original invalid data before filtering. The proposed method is also tested by other classification methods and able to produce the highest accuracy with 79.29% in Support Vector Classifier (SVC) and Multi-Layer Perception (MLP), while other filtering methods only get the highest accuracy with 69.03% also in SVC and MLP. We also analysed the execution time of each tested methods.http://www.sciencedirect.com/science/article/pii/S221418042200068XElectronic noseK-means clusteringKalman filteringNoise reductionSignal processing |
spellingShingle | M. Syauqi Hanif Ardani Riyanarto Sarno Malikhah Malikhah Doni Putra Purbawa Shoffi Izza Sabilla Kelly Rossa Sungkono Chastine Fatichah Dwi Sunaryono Rahadian Indarto Susilo A new approach to signal filtering method using K-means clustering and distance-based Kalman filtering Sensing and Bio-Sensing Research Electronic nose K-means clustering Kalman filtering Noise reduction Signal processing |
title | A new approach to signal filtering method using K-means clustering and distance-based Kalman filtering |
title_full | A new approach to signal filtering method using K-means clustering and distance-based Kalman filtering |
title_fullStr | A new approach to signal filtering method using K-means clustering and distance-based Kalman filtering |
title_full_unstemmed | A new approach to signal filtering method using K-means clustering and distance-based Kalman filtering |
title_short | A new approach to signal filtering method using K-means clustering and distance-based Kalman filtering |
title_sort | new approach to signal filtering method using k means clustering and distance based kalman filtering |
topic | Electronic nose K-means clustering Kalman filtering Noise reduction Signal processing |
url | http://www.sciencedirect.com/science/article/pii/S221418042200068X |
work_keys_str_mv | AT msyauqihanifardani anewapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT riyanartosarno anewapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT malikhahmalikhah anewapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT doniputrapurbawa anewapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT shoffiizzasabilla anewapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT kellyrossasungkono anewapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT chastinefatichah anewapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT dwisunaryono anewapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT rahadianindartosusilo anewapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT msyauqihanifardani newapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT riyanartosarno newapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT malikhahmalikhah newapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT doniputrapurbawa newapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT shoffiizzasabilla newapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT kellyrossasungkono newapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT chastinefatichah newapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT dwisunaryono newapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering AT rahadianindartosusilo newapproachtosignalfilteringmethodusingkmeansclusteringanddistancebasedkalmanfiltering |