TY - GEN
T1 - Optimization Based Random Forest Algorithm Modification for Detecting Monkeypox Disease
AU - Hapsari, Rinci Kembang
AU - Purwanti, Endah
AU - Widyanto, Wahyu
AU - Gunawan, Ricky
AU - Nurlaily, Firdausiyah
AU - Salim, Abdullah Harits
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Monkeypox is a zoonotic infectious disease caused by orthopoxvirus. Common symptoms that could indicate Monkeypox are fever, headache, muscle aches, back pain, tiredness or unwell, and swollen lymph nodes. In this research, we conducted a predictive study on Monkey Pox using the Random Forest algorithm optimized with Particle Swam Optimization, which we call PRFO. This algorithm can improve the performance of ordinary Random Forests by making a relatively fast running time and increasing the accuracy value of the algorithm. The results of tests that have been carried out on three datasets, namely: 1) The MonkeyPox dataset, which has 25 thousand data, shows an increase in the accuracy value of 2.08% from 67.80% to 69.88%, 2) The Health dataset with 20 thousand data increased by 0.89% from 92.79% to 93.67%, and 3) The PulsarStar dataset with 12 thousand data increased by 0.27%, From 97.89% to 98.16%. The increase in value is based on the PRFO parameter, which only uses 30 particles with a maximum of 50 iterations. From the tests that have been carried out, the application of the PRFO algorithm can find the best solution on a dataset with more than 10 thousand data in a relatively short time.
AB - Monkeypox is a zoonotic infectious disease caused by orthopoxvirus. Common symptoms that could indicate Monkeypox are fever, headache, muscle aches, back pain, tiredness or unwell, and swollen lymph nodes. In this research, we conducted a predictive study on Monkey Pox using the Random Forest algorithm optimized with Particle Swam Optimization, which we call PRFO. This algorithm can improve the performance of ordinary Random Forests by making a relatively fast running time and increasing the accuracy value of the algorithm. The results of tests that have been carried out on three datasets, namely: 1) The MonkeyPox dataset, which has 25 thousand data, shows an increase in the accuracy value of 2.08% from 67.80% to 69.88%, 2) The Health dataset with 20 thousand data increased by 0.89% from 92.79% to 93.67%, and 3) The PulsarStar dataset with 12 thousand data increased by 0.27%, From 97.89% to 98.16%. The increase in value is based on the PRFO parameter, which only uses 30 particles with a maximum of 50 iterations. From the tests that have been carried out, the application of the PRFO algorithm can find the best solution on a dataset with more than 10 thousand data in a relatively short time.
KW - Disease
KW - Monkeypox
KW - Particle Swam Optimization
KW - Random Forest
UR - http://www.scopus.com/inward/record.url?scp=85182019326&partnerID=8YFLogxK
U2 - 10.1109/ICVEE59738.2023.10348223
DO - 10.1109/ICVEE59738.2023.10348223
M3 - Conference contribution
AN - SCOPUS:85182019326
T3 - 2023 6th International Conference on Vocational Education and Electrical Engineering: Integrating Scalable Digital Connectivity, Intelligence Systems, and Green Technology for Education and Sustainable Community Development, ICVEE 2023 - Proceeding
SP - 340
EP - 346
BT - 2023 6th International Conference on Vocational Education and Electrical Engineering
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th International Conference on Vocational Education and Electrical Engineering, ICVEE 2023
Y2 - 14 October 2023 through 15 October 2023
ER -