Penerapan Algoritma Naïve Bayes untuk Klasifikasi Kelayakan Donor Darah Berbasis Web (Studi Kasus: Palang Merah Indonesia Kota Kebumen)

Rudiantoro, Arif (2019) Penerapan Algoritma Naïve Bayes untuk Klasifikasi Kelayakan Donor Darah Berbasis Web (Studi Kasus: Palang Merah Indonesia Kota Kebumen). Tugas Akhir thesis, University of Technology Yogyakarta.

Naskah Publikasi-Arif Rudiantoro-5130411059.pdf

Download (754kB) | Preview


There are six criterias used to determine the feasibility of blood donor candidates in Palang Merah Indonesia (PMI) namely haemoglobin level, systolic blood pressure, diastolic, body weight, age, sex, and other criteria. The purpose of this research is to develop a blood donor feasibility detection system using Naïve Bayes Classifier method which will produce likelihood value which is feasible or not for blood donor candidates. Blood donor candidate feasibility determination method in this system is Naïve Bayes. Naïve Bayes Classifier is a simple probabilistic-based prediction technique according to the implementation of Bayes theory under the assumption of strong independence. This algorithm performs a relatively time-consuming training process but its predictive process runs quickly and can be implemented in categorical or continuous feature data. Naïve Bayes Classifier method can be used to determine blood donor candidates whose opportunity and criteria are taken from the obtained data and result of calculation based on the formulation of basic theorem of Naïve Bayes’ Classifier. The category contained in Naïve Bayes Classifier method is valid data so its use also generates exact result as its example. Blood donors intending to donate their bloods have to meet specific requirements, for example they must be 17 to 60 years old, and other requirements. Donor’s criteria such as hemoglobin level, systolic blood pressure, diastolic, body weight, sex, and age can be made as supporting variables. Calculation process in Naïve Bayes Classifier is conducted by finding out required probability value from continuous feature in a class which is used as the difference of cumulative opportunity with certain intervals. After that, classification result uses normal density approach compared with the result of classification using cumulative opportunity difference approach. The result of accuracy testing in the system indicates analysis approximation with actual result and discovers whether the system is good or not. Testing process in PMI of Kebumen City the percentage of accuracy using confusion matrix resulting in 75% accuracy, 80% precision, and 72% recall of 20 test data. Keywords: Naïve Bayes Classifier, Classification of Donor Criteria, PMI, Accuracy Result

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Teknologi Informasi dan Elektro > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 05 Apr 2019 06:53
Last Modified: 05 Apr 2019 06:53

Actions (login required)

View Item View Item