Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

IMPLEMENTATION OF K-NEAREST NEIGHBOR ALGORITHM FOR CLASSIFICATION OF LUNG CANCER CAUSES

View through CrossRef
Abstract: Lung cancer is most deadly cancers in the world. Identification and classification of the causes of understanding lung cancer is essential for developing more effective prevention and treatment strategies. The issue is that a lot of individuals are unaware about the characteristics and causes of lung cancer. The purpose of this study is to apply the K-Nearest Neighbor (K-NN) algorithm in the classification of the causes of lung cancer and provide education to the public must be aware of the traits of lung cancer patients and, to stay away from the causes of lung cancer. The dataset used consists of 309 samples with 16 relevant attributes. The K-NN algorithm was trained and tested to assess its ability to classify the factors that cause lung cancer. The results showed an accuracy of 90.32%, with a precision for the "YES" class of 96% and the "NO" class of 67%. The recall value for the "YES" class was 92% and for the "NO" class was 80%. The implementation of this algorithm gives good results in classification and can help in early detection and prevention of lung cancer which can be used in the development of more effective prevention and early diagnosis strategies. Keywords: lung cancer; k-nearest neighbor; classification; machine learning  Abstrak: Kanker paru-paru tergolong jenis penyakit kanker yang memperoleh angka kematian paling tinggi di dunia. Identifikasi dan klasifikasi penyebab kanker paru-paru sangat penting untuk pengembangan strategi pencegahan dan pengobatan yang lebih efektif. Masalah yang terjadi adalah banyak orang yang belum mengetahui tentang ciri-ciri dan penyebab-penyebab dari kangker paru tersebut. Tujuan penelitian ini adalah mengimplementasikan algoritma K-Nearest Neighbor (K-NN) dalam klasifikasi penyebab kanker paru-paru serta memberikan edukasi kepada masyarakat banyak agar mengetahui ciri-ciri orang yang mengidap kangker paru-paru dan tentunya untuk menghindari penyebab-penyebab dari kangker paru-paru tersebut. Dataset yang digunakan terdiri dari 309 sampel dengan 16 atribut yang relevan. Algoritma K-NN kemudian dilatih dan diuji untuk menilai kemampuannya dalam mengklasifikasikan faktor-faktor penyebab kanker paru-paru. Hasil penelitian menunjukkan akurasi sebesar 90.32%, dengan skor precision untuk kelas "YES" sebesar 96% dan kelas "NO" sebesar 67%. Nilai recall untuk kelas "YES" adalah 92% dan untuk kelas "NO" sebesar 80%. Implementasi algoritma ini memberikan hasil yang baik dalam klasifikasi dan dapat membantu dalam deteksi dini serta pencegahan kanker paru-paru yang dapat digunakan dalam pengembangan strategi pencegahan dan diagnosis dini yang lebih efektif. Kata kunci: kanker paru-paru; k-nearest neighbor; klasifikasi; machine learning
Title: IMPLEMENTATION OF K-NEAREST NEIGHBOR ALGORITHM FOR CLASSIFICATION OF LUNG CANCER CAUSES
Description:
Abstract: Lung cancer is most deadly cancers in the world.
Identification and classification of the causes of understanding lung cancer is essential for developing more effective prevention and treatment strategies.
The issue is that a lot of individuals are unaware about the characteristics and causes of lung cancer.
The purpose of this study is to apply the K-Nearest Neighbor (K-NN) algorithm in the classification of the causes of lung cancer and provide education to the public must be aware of the traits of lung cancer patients and, to stay away from the causes of lung cancer.
The dataset used consists of 309 samples with 16 relevant attributes.
The K-NN algorithm was trained and tested to assess its ability to classify the factors that cause lung cancer.
The results showed an accuracy of 90.
32%, with a precision for the "YES" class of 96% and the "NO" class of 67%.
The recall value for the "YES" class was 92% and for the "NO" class was 80%.
The implementation of this algorithm gives good results in classification and can help in early detection and prevention of lung cancer which can be used in the development of more effective prevention and early diagnosis strategies.
Keywords: lung cancer; k-nearest neighbor; classification; machine learning  Abstrak: Kanker paru-paru tergolong jenis penyakit kanker yang memperoleh angka kematian paling tinggi di dunia.
Identifikasi dan klasifikasi penyebab kanker paru-paru sangat penting untuk pengembangan strategi pencegahan dan pengobatan yang lebih efektif.
Masalah yang terjadi adalah banyak orang yang belum mengetahui tentang ciri-ciri dan penyebab-penyebab dari kangker paru tersebut.
Tujuan penelitian ini adalah mengimplementasikan algoritma K-Nearest Neighbor (K-NN) dalam klasifikasi penyebab kanker paru-paru serta memberikan edukasi kepada masyarakat banyak agar mengetahui ciri-ciri orang yang mengidap kangker paru-paru dan tentunya untuk menghindari penyebab-penyebab dari kangker paru-paru tersebut.
Dataset yang digunakan terdiri dari 309 sampel dengan 16 atribut yang relevan.
Algoritma K-NN kemudian dilatih dan diuji untuk menilai kemampuannya dalam mengklasifikasikan faktor-faktor penyebab kanker paru-paru.
Hasil penelitian menunjukkan akurasi sebesar 90.
32%, dengan skor precision untuk kelas "YES" sebesar 96% dan kelas "NO" sebesar 67%.
Nilai recall untuk kelas "YES" adalah 92% dan untuk kelas "NO" sebesar 80%.
Implementasi algoritma ini memberikan hasil yang baik dalam klasifikasi dan dapat membantu dalam deteksi dini serta pencegahan kanker paru-paru yang dapat digunakan dalam pengembangan strategi pencegahan dan diagnosis dini yang lebih efektif.
 Kata kunci: kanker paru-paru; k-nearest neighbor; klasifikasi; machine learning.

Related Results

Abstract SY38-02: Clinical investigations of obesity in cancer: BMI and other confounders
Abstract SY38-02: Clinical investigations of obesity in cancer: BMI and other confounders
Abstract Obesity has been linked with increased incidence and worse outcomes of at least 13 human cancers. For other cancers, our understanding of their relationship...
Abstract 1345: Evidence for genetic mediation of lung cancer through hay fever.
Abstract 1345: Evidence for genetic mediation of lung cancer through hay fever.
Abstract Introduction: In the past decade, advances in genetics have led to the discovery of numerous lung cancer susceptibility variants. The majority of these vari...
Small Cell Lung Cancer and Tarlatamab: A Meta-Analysis of Clinical Trials
Small Cell Lung Cancer and Tarlatamab: A Meta-Analysis of Clinical Trials
Abstract Introduction Tarlatamab is a Delta-like ligand 3 (DLL3) -directed bispecific T-cell engager recently approved for use in patients with advanced small cell lung cancer (SCL...
RNA Demethylase ALKBH5 Promotes Progression and Angiogenesis of Lung Cancer via Regulating the Stability of LncRNA PVT1
RNA Demethylase ALKBH5 Promotes Progression and Angiogenesis of Lung Cancer via Regulating the Stability of LncRNA PVT1
Abstract Background N6-methyladenosine (m6A) is the most common posttranscriptional modification of RNA and plays critical roles in human cancer progression. However, biol...
Time to Start Up: CT-Basted Radiomics in Children’s Lung Diseases
Time to Start Up: CT-Basted Radiomics in Children’s Lung Diseases
Radiomics is a new interdisciplinary field and a fusion product consisting by large data technology and medical image to aid diagnosis. Radiomics can gather information from differ...

Back to Top