Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Jurnal Sistem dan In...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Jurnal Sistem dan Informatika (JSI)
Article . 2024 . Peer-reviewed
License: CC BY SA
Data sources: Crossref
addClaim

Pengenalan Aktivitas Manusia dengan Seleksi Fitur Analysis of Variance (ANOVA) dan Mutual Information (MI) pada Data Sensor Accelerometer Berbasis Machine Learning

Authors: null Made Liandana; null I Made Darma Susila; null Yohanes Priyo Atmojo;

Pengenalan Aktivitas Manusia dengan Seleksi Fitur Analysis of Variance (ANOVA) dan Mutual Information (MI) pada Data Sensor Accelerometer Berbasis Machine Learning

Abstract

Pengenalan aktivitas manusia telah banyak dikembangkan untuk berbagai keperluan, seperti kesehatan, olahraga, hingga pengawasan lanjut usia. Penggunaan perangkat sensor menjadi salah satu pilihan dalam melakukan pengenalan aktivitas manusia. Sensor accelerometer adalah salah satu perangkat yang umum digunakan dalam pengenalan aktivitas. Data sensor ini memerlukan teknik dan algoritma yang tepat sehingga menghasilkan hasil pengenalan aktivitas yang sesuai. Penggunaan tradisional machine learning menjadi salah satu teknik yang dapat digunakan, teknik ini memerlukan proses ekstraksi fitur, dan seleksi fitur. Teknik seleksi fitur mana dan berapa jumlah fitur yang tepat untuk mendapatkan performa machine learning yang optimal perlu dilakukan investigasi lebih lanjut. Pada penelitian ini, dilakukan evaluasi terhadap kombinasi sejumlah fitur menggunakan algoritma machine learning: Extreme Gradient Boosting (XGB), Gradient Boosting (GBoost), Random Forest (RF), Decision Tree (DT), dan Support Vector Machine (SVM. Dataset publik yang digunakan yaitu FORTH-TRACE. Sensor yang digunakan adalah sensor accelerometer. Fitur yang digunakan meliputi nilai minimum, nilai maksimum, nilai rata-rata, nilai tengah, standar deviasi, dan nilai interkuartil. Sedangkan seleksi fitur yang digunakan adalah Analysis of Variance (ANOVA) dan Mutual Information (MI). Performa machine learning yang paling optimal ketika jumlah fitur 17 sampai dengan 18 fitur dengan akurasi 0,875, sedangkan performa machine learning paling optimal dicapai dengan menggunakan Extreme Gradient Boosting (XGB).

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
gold