Text

PERBANDINGAN METODE PERHITUNGAN JARAK DALAM ALGORITMA K-NEAREST NEIGHBOUR UNTUK KLASIFIKASI DATA PENYAKIT PADA MANUSIA

---

Penilaian

---

One of the algorithms in Machine Learning principles that can be used to classify large amounts of data by producing clear and effective results is the K-Nearest Neighbour Algorithm. This research aims to prove which of the distance calculation formulas in the K-Nearest Neighbour Algorithm has an accuracy value with good performance in classifying human disease datasets. The proof is done by comparing the existing distance calculation formulas, namely Euclidean distance, Manhattan distance, Minkowsky distance and Chebyshev distance. The dataset uses data on diseases that are often experienced by humans such as Heart Attack, Breast Cancer, Diabetes and Stroke. The results show that Euclidean distance is the distance calculation formula that gets the most accuracy values with good performance compared to other distance calculation formulas. Even the highest accuracy results obtained can reach 90% with performance values namely Precision of 0.921053, Recall of 0.833333 and F-Measure of 0.875 with a K value of 3 for the classification of breast cancer datasets. So it is concluded that Euclidean distance is a distance calculation formula that is able to produce high accuracy values with good performance for classifying human disease datasets.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207002279	T74442	T744422022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T744422022

Publisher

Inderalaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2022

Collation

xxvii, 140 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.740 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Informatika
Data File-file dan Database

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment