Smart Sensor Calibration with Auto-Rotating Perceptrons

Daniel Saromo; Leonardo Bravo; Elizabeth R. Villota

Smart Sensor Calibration with Auto-Rotating Perceptrons

Daniel Saromo, Leonardo Bravo, Elizabeth R. Villota

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Sensor calibration is vital to have valid measure-ments of physical activities. Herein we deal withadjusting the signal from a wearable force sensoragainst a reference scale. By using a few samplesand data augmentation, we trained a neural-basedregression model to correct the wearable output.For this task, we tested the novel Auto-RotatingPerceptrons (ARP). We found that a neural ARPmodel with sigmoid activations can outperforman identical neural network based on classic per-ceptrons with sigmoid and even ReLU activation.

Original language	Spanish
Title of host publication	International Conference on Machine Learning: LatinX in AI (LXAI) Research Workshop 2020
State	Published - 1 Jan 2020

Cite this

@inproceedings{03d05102762045d39557502d99e4aa24,

title = "Smart Sensor Calibration with Auto-Rotating Perceptrons",

abstract = "Sensor calibration is vital to have valid measure-ments of physical activities. Herein we deal withadjusting the signal from a wearable force sensoragainst a reference scale. By using a few samplesand data augmentation, we trained a neural-basedregression model to correct the wearable output.For this task, we tested the novel Auto-RotatingPerceptrons (ARP). We found that a neural ARPmodel with sigmoid activations can outperforman identical neural network based on classic per-ceptrons with sigmoid and even ReLU activation.",

author = "Daniel Saromo and Leonardo Bravo and Villota, {Elizabeth R.}",

year = "2020",

month = jan,

day = "1",

language = "Espa{\~n}ol",

booktitle = "International Conference on Machine Learning: LatinX in AI (LXAI) Research Workshop 2020",

}

TY - GEN

T1 - Smart Sensor Calibration with Auto-Rotating Perceptrons

AU - Saromo, Daniel

AU - Bravo, Leonardo

AU - Villota, Elizabeth R.

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Sensor calibration is vital to have valid measure-ments of physical activities. Herein we deal withadjusting the signal from a wearable force sensoragainst a reference scale. By using a few samplesand data augmentation, we trained a neural-basedregression model to correct the wearable output.For this task, we tested the novel Auto-RotatingPerceptrons (ARP). We found that a neural ARPmodel with sigmoid activations can outperforman identical neural network based on classic per-ceptrons with sigmoid and even ReLU activation.

AB - Sensor calibration is vital to have valid measure-ments of physical activities. Herein we deal withadjusting the signal from a wearable force sensoragainst a reference scale. By using a few samplesand data augmentation, we trained a neural-basedregression model to correct the wearable output.For this task, we tested the novel Auto-RotatingPerceptrons (ARP). We found that a neural ARPmodel with sigmoid activations can outperforman identical neural network based on classic per-ceptrons with sigmoid and even ReLU activation.

UR - https://research.latinxinai.org/papers/icml/2020/pdf/Oral_Daniel_Saromo.pdf

M3 - Contribución a la conferencia

BT - International Conference on Machine Learning: LatinX in AI (LXAI) Research Workshop 2020

ER -

Smart Sensor Calibration with Auto-Rotating Perceptrons

Abstract

Other files and links

Cite this