TY - GEN
T1 - Health Level Classification of Motor Stroke Patients Based on Flex Sensor Using Fuzzy Logic Method
AU - Habibi, Anang
AU - Nugroho, Supeno Mardi Susiki
AU - Purnama, I. Ketut Eddy
AU - Prawitri, Yudith Dian
AU - Subadi, Imam
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - The wrist monitoring system, especially in stroke patients, has been developed in several countries using two types of sensors, IMU, Leap Motion, flex sensors and force sensors. However in a monitoring system that was developed to only detect changes in data, no classification of stages/stages of recovery has been found. By combining the flex sensor and force sensor with fuzzy classification into a monitoring system, it is able to determine the stage/level/level of recovery that has been achieved. The healing level/level displayed will motivate the stroke patients to be more active in their recovery and become a diagnosis that helps the medical team, especially doctors, in evaluating and determining the next stage of the exercise. The data set for each flex sensor and force sensor is known to be based on 50 experiments on each different user and in each flex dataset and force sensor it varies. The kilogram sensor force unit is converted to Newton by adding the earth's gravity coefficient 9,80665 m/s2. The stage of fertility is divided into 3 stages, weak, medium and normal. The results of the fuzzy system test on the user's right hand who have never had a stroke show good data readings, and the percent error obtained is 0%. The force sensor is able to read but not sensitive enough as some data still not readable and need additional sponges to increase ease in reading data. In conclusion from testing running programs, KNN is better than fuzzy.
AB - The wrist monitoring system, especially in stroke patients, has been developed in several countries using two types of sensors, IMU, Leap Motion, flex sensors and force sensors. However in a monitoring system that was developed to only detect changes in data, no classification of stages/stages of recovery has been found. By combining the flex sensor and force sensor with fuzzy classification into a monitoring system, it is able to determine the stage/level/level of recovery that has been achieved. The healing level/level displayed will motivate the stroke patients to be more active in their recovery and become a diagnosis that helps the medical team, especially doctors, in evaluating and determining the next stage of the exercise. The data set for each flex sensor and force sensor is known to be based on 50 experiments on each different user and in each flex dataset and force sensor it varies. The kilogram sensor force unit is converted to Newton by adding the earth's gravity coefficient 9,80665 m/s2. The stage of fertility is divided into 3 stages, weak, medium and normal. The results of the fuzzy system test on the user's right hand who have never had a stroke show good data readings, and the percent error obtained is 0%. The force sensor is able to read but not sensitive enough as some data still not readable and need additional sponges to increase ease in reading data. In conclusion from testing running programs, KNN is better than fuzzy.
KW - Flex sensor
KW - Force sensor
KW - Fuzzy Logic
KW - Health Level
KW - Motor Stroke
UR - http://www.scopus.com/inward/record.url?scp=85084430659&partnerID=8YFLogxK
U2 - 10.1109/CENIM48368.2019.8973257
DO - 10.1109/CENIM48368.2019.8973257
M3 - Conference contribution
AN - SCOPUS:85084430659
T3 - 2019 International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019 - Proceeding
BT - 2019 International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019 - Proceeding
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019
Y2 - 19 November 2019 through 20 November 2019
ER -