PENGARUH SELEKSI FITUR PARTICLE SWARM OPTIMIZATION DALAM MEMPREDIKSI KLASIFIKASI KELAYAKAN PENDONOR DARAH PADA UTD KOTA BEKASI DENGAN DECISION TREE C4.5
Fulfilling blood needs is very important to improve the quality of health services by a country, there is one public health center in Indonesia that is dedicated to helping people with blood-related problems, such as making blood donations called the Blood Transfusion Unit (UTD). In carrying out blo...
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Published: |
2023-06-22.
|
| Subjects: | |
| Online Access: | Link Metadata |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Fulfilling blood needs is very important to improve the quality of health services by a country, there is one public health center in Indonesia that is dedicated to helping people with blood-related problems, such as making blood donations called the Blood Transfusion Unit (UTD). In carrying out blood donors, the problem that officers often face is when the demand for blood increases, or the number of donors is large, of course it creates long queues and takes a long time to check the eligibility of donors, makes donors sometimes bored and discourages them from donating for reasons of time and so on. Due to the limited number of officers involved and still using manual methods in determining prospective blood donors. For this reason, a model is needed for the efficiency of checking the eligibility of blood donors to maximize services. Therefore, in this study, utilizing data mining in determining the eligibility status of donors at UTD PMI Bekasi City, the algorithm used is Decision Tree C4.5 with PSO as an attribute selector. From the results of this study, that Hemoglobin has the highest Gain value, which is equal to 0.17. Therefore, hemoglobin is the most influential factor in determining the classification of blood donor status for UTD PMI Bekasi City. The results obtained in using the Decision Tree C4.5 method only in classification get an accuracy of 93.75%. Then testing using the Decision Tree C4.5 algorithm with the optimization of the PSO algorithm resulted in an increase in the best accuracy value of 97.02%. Therefore, using the PSO algorithm can improve the training performance results of the Decision Tree C4.5 classification model, resulting in better accuracy results with a difference of 3.27%. |
|---|---|
| Item Description: | http://repository.upnvj.ac.id/24982/1/ABSTRAK.pdf http://repository.upnvj.ac.id/24982/18/AWAL.pdf http://repository.upnvj.ac.id/24982/14/BAB%20I.pdf http://repository.upnvj.ac.id/24982/4/BAB%20II.pdf http://repository.upnvj.ac.id/24982/5/BAB%20III.pdf http://repository.upnvj.ac.id/24982/15/BAB%20IV.pdf http://repository.upnvj.ac.id/24982/7/BAB%20V.pdf http://repository.upnvj.ac.id/24982/8/DAFTAR%20PUSTAKA.pdf http://repository.upnvj.ac.id/24982/9/RIWAYAT%20HIDUP.pdf http://repository.upnvj.ac.id/24982/19/LAMPIRAN.pdf http://repository.upnvj.ac.id/24982/11/HASIL%20PLAGIARISME.pdf http://repository.upnvj.ac.id/24982/12/ARTIKEL%20KI.pdf |