Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
David Isura
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Analisa Akurasi dari Pendeteksian Berjalan pada Variasi Peletakan Sensor IMU, Filter Kalman dan FIR, serta Klasifikasi KNN dan Naive Bayes David Isura; Hurriyatul Fitriyah; Rakhmadhany Primananda
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 1 (2022): Januari 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Development of research in footsteps has been carried out, especially by using IMU sensor. IMU sensor is a system that can detect changes in speed, orientation of the gravitational force. However, the accuracy in measuring "footsteps" using IMU sensor is not yet accurate, due to inconsistent human footsteps, different body shapes, stepping models and so on. In this research, researchers used MPU6050 sensor where the sensor produces two types of sensors, namely accelerometer sensors and gyroscope sensors. Sensor placement points are located on the wrist, calf and thigh. Sensor used will produce three axis, where each axis is filtered using a Kalman Filter and a Finite Impulse Response (FIR) Filter. After the data is filtered, then data will be classified with the data has been sorted (training data). The classification used is K-NN and Naive Bayes. The use of the best filter is owned by the Kalman filter, which has the lowest average ratio compared to the FIR filter, which is 0.378. Accuracy results obtained from research that has been carried out are 92.5%, where the accuracy has a combination of the use of gyroscope sensors, sensor placement in the calves, the use of Kalman filters and the Naive Bayes classification algorithm. The resulting computation time is 0.23 seconds.
Co-Authors Fitriyah, Hurriyatul Rakhmadhany Primananda