Peningkatan Akurasi Klasifikasi Backpropagation Menggunakan Artificial Bee Colony dan K-NN Pada Penyakit Jantung

Putra, Pandito Dewa; Sukemi, Sukemi; Rini, Dian Palupi

doi:10.30865/mib.v5i1.2634

Cited by 6 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The C4.5 algorithm, also known as the decision tree, is a classifiable algorithm with fast processing speed that can handle numerical and discrete data as well as identify and remove already missing attributes and generate easy-to-implement rules [21]. The C4.5 algorithm uses an attribute as root, creating a branch for each value in the case, and the process will continue to be repeated until each branch case has the same class [22].…”

Section: C45 (Decision Tree)mentioning

confidence: 99%

A Soft Voting Ensemble Classifier to Improve Survival Rate Predictions of Cardiovascular Heart Failure Patients

Munandar,

Maulana Baihaqi,

Nurhopipah

2023

Ilk. J. Ilm.

View full text Add to dashboard Cite

Cardiovascular disease is one of the deadliest diseases, claiming around 17 million lives worldwide each year. According to data from the World Health Organization (WHO), more than four out of five deaths from cardiovascular disease are caused by heart attacks and strokes, and one-third of these deaths occur prematurely in people under the age of 70. Machine learning approaches can be used to detect the disease. This research aims to improve the prediction model of cardiovascular heart failure patient survival using C4.5, KNN, Logistic Regression algorithms, and the ensemble learning method of Voting Classifier. Based on the testing results, each model showed a significant increase in accuracy in the 70:30 ratio. Logistic Regression and C4.5 achieved the same accuracy, 89.47%, KNN obtained 91.23%, and Voting Classifier experienced a considerable improvement, reaching 94.74%. In testing with ratios of 90:10, 80:20, and 70:30, KNN demonstrated high accuracy but had significant overfitting, with a difference of 7-9% between training and testing accuracy scores in the 90:10 and 80:20 ratios. On the other hand, Voting Classifier showed stable performance in the 70:30 ratio, with an accuracy difference between training and testing scores below 1%. The conclusion of this research is that the Voting Classifier can assist the performance improvement of algorithms for classifying the survival expectancy of cardiovascular heart failure patients into 'Survived' or 'Deceased', compared to Logistic Regression, KNN, and C4.5.

show abstract

Section: C45 (Decision Tree)mentioning

confidence: 99%

A Soft Voting Ensemble Classifier to Improve Survival Rate Predictions of Cardiovascular Heart Failure Patients

Munandar,

Maulana Baihaqi,

Nurhopipah

2023

Ilk. J. Ilm.

View full text Add to dashboard Cite

show abstract

“…Klasifikasi penyakit jantung telah banyak diteliti dengan berbagai metode yang ada pada data mining seperti penelitian yang dilakukan oleh [1], [2], [8]- [15], [16]. Penelitian yang dilakukan oleh Riski Annisa dalam penelitiannya mendapatkan hasil dimana algoritma random forest (RF) dan decision menunjukkan kinerja terbaik dalam klasifikasi pada dataset yang digunakan.…”

Section: Pendahuluanunclassified

Sistem Klasifikasi Penyakit Jantung Menggunakan Teknik Pendekatan SMOTE Pada Algoritma Modified K-Nearest Neighbor

Novitasari

Haerani

Nazir

et al. 2023

bits

View full text Add to dashboard Cite

The heart is a vital organ that plays a crucial role in pumping oxygenated blood and nutrients throughout the body. Heart disease refers to damage to the heart that can occur in various forms, caused by infections or congenital abnormalities. The World Health Organization (WHO) reports nearly 17.9 million deaths each year due to heart disease. In Indonesia, the prevalence of heart disease is around 1.5%, meaning that in 2018, approximately 15 out of 1,000 people, or nearly 2,784,060 individuals, were affected by this disease, according to the Basic Health Research data (Riskesdas) 2018. Many people have limited knowledge about heart health, leading to a lack of awareness of their heart conditions. This can be attributed to a lack of understanding regarding the importance of medical checkups related to heart health. Modified K-Nearest Neighbors (MKNN) is one of the data mining methods applied for classifying the risk of heart disease. The research utilized data obtained from the UCI dataset repository, which consists of 918 records with 12 attributes. To balance the imbalanced dataset with minority classes, the Synthetic Minority Over-sampling Technique (SMOTE) approach was used to generate new synthetic samples from the minority class. The objective of developing a web-based system for heart disease classification is to assist the public in assessing their risk of heart disease as early as possible, enabling them to take preventive actions sooner. The accuracy results of the MKNN algorithm with a 90:10 ratio are 80.37%, while with the MKNN+SMOTE approach, the accuracy increased to 84.00%. The use of the SMOTE approach improved the accuracy of low-performing data.

show abstract

“…Hasil penelitian terdahulu menggunakan algoritma K-Nearest Neighbor pada penelitian sinyal eeg terlihat algoritma ini mampu melakukan penelitian tehadap respondensi yang diminta untuk meminum air antioksidan untuk melihat gelombang alpa dan gelombang beta yang dihasilkan beberapa perbedaan sebesar 2,8% dan tingkat akurasi pada penilaian menggunakan algoritma ini sebesar 83% [9]. Pada penelitian terdahulu menjelaskan penggunaan algoritma K-Nearest Neighbor membantu meningkatkan akurasi dengan penggunaan algoritma [10] lainnya jauh lebih tinggi yaitu Algoritma Backpropagation tanpa kombinasi mencapai akurasi optimal 88% sedangkan algoritma "Backpropagation yang dikombinasi dengan ABC-kNN untuk seleksi fitur berhasil mencapai akurasi yang lebih baik yaitu sebesar 94%".…”

Section: Pendahuluanunclassified

Prediksi Pengajuan Kredit Usaha Pada Koperasi Menggunakan Algoritma K-Nearest Neighbor

Harpad

Bustomi

2022

bits

View full text Add to dashboard Cite

Cooperative activities have become the activities most needed by many people because they are related to money, cooperatives are places that provide loans to housewives and also workers in a certain area or environment, the lack of interest offered by this cooperative is considered very easy. and very helpful for many parties in facilitating financial affairs, especially in financial matters, because the convenience offered by the cooperative makes many interested people ask for the same thing resulting in vulnerability to fraud, the importance of making predictions on prospective new business loan applications can help reduce the worst risks from various risks that occur in the future, in this study the k-nearest neighbor algorithm will be used as a prediction algorithm for prospective business credit applications at cooperatives, the value obtained is the value of training data or data records of several previous customers so as to easier to know new data as test data in a study. The results found in this study for prospective business credit applications are "Not Eligible" seen to the closest value based on the smallest value with (closest distance) between one another as many as 3 distances, namely numbers 1, 2 and 3 where number 1 states "Not feasible ”, at the second closest distance stating “Eligible” and number 3 stating “Not Eligible”, the most results stated Not Eligible so that the decision value on new customers had to be rejected “Not eligible” to be accepted

show abstract

Peningkatan Akurasi Klasifikasi Backpropagation Menggunakan Artificial Bee Colony dan K-NN Pada Penyakit Jantung

Cited by 6 publications

References 22 publications

A Soft Voting Ensemble Classifier to Improve Survival Rate Predictions of Cardiovascular Heart Failure Patients

A Soft Voting Ensemble Classifier to Improve Survival Rate Predictions of Cardiovascular Heart Failure Patients

Sistem Klasifikasi Penyakit Jantung Menggunakan Teknik Pendekatan SMOTE Pada Algoritma Modified K-Nearest Neighbor

Prediksi Pengajuan Kredit Usaha Pada Koperasi Menggunakan Algoritma K-Nearest Neighbor

Contact Info

Product

Resources

About