Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Indonesian Journal of Health Science Panthera : Jurnal Ilmiah Pendidikan Sains dan Terapan Madani: Multidisciplinary Scientific Journal Socius: Social Sciences Research Journal
Surbakti, Christina Amanda
Unknown Affiliation
Religion Agriculture, Biological Sciences & Forestry Arts Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Dentistry Economics, Econometrics & Finance Education Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Medicine & Pharmacology Nursing Physics Public Health Social Sciences Veterinary Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Perbandingan mtode K-Nearest Neighbors (K-NN) dan regresi logistik biner dalam memprediksi kanker Surbakti, Christina Amanda; Sinaga, Albert Samuel; Simorangkir, Agnes Monica; Sarah, Auta Shinta; Harefa, Clara Jocelyn; Dalimunthe, Syairal Fahmy
Indonesian Journal of Health Science Vol 5 No 2 (2025)
Publisher : PT WIM Solusi Prima

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54957/ijhs.v5i2.1456

Abstract

Latar Belakang: Kanker merupakan salah satu penyakit yang memiliki tingkat kematian tinggi, sehingga dibutuhkan metode klasifikasi yang akurat untuk mendukung proses diagnosis. Penelitian ini membandingkan performa metode K-Nearest Neighbors (KNN) dan Regresi Logistik Biner dalam mengklasifikasikan kanker sebagai ganas atau jinak. Metode: Penelitian ini menggunakan dataset sekunder dari Kaggle yang terdiri dari 569 data pasien kanker dengan 11 variabel independen yang mencakup karakteristik tumor. Model dikembangkan dengan menggunakan normalisasi data, pembagian data training dan testing, serta teknik K-Fold Cross Validation untuk optimasi parameter K dalam KNN. Evaluasi model dilakukan berdasarkan akurasi, presisi, recall, serta uji McNemar dan ANOVA untuk menguji signifikansi perbedaan performa model. Hasil: Model KNN dengan K=13 menunjukkan akurasi 95,58%, presisi 95,83%, dan recall 97,18%, sementara Regresi Logistik Biner memiliki akurasi 94,69%, presisi 92,86%, dan recall 92,86%. Hasil uji McNemar menunjukkan bahwa tidak terdapat perbedaan signifikan antara kedua model (p-value = 1), sedangkan hasil ANOVA menunjukkan bahwa semua variabel independen berkontribusi terhadap model. Kesimpulan: Kedua metode menunjukkan performa yang baik dalam klasifikasi kanker, tetapi KNN dengan K=13 memiliki sedikit keunggulan dalam akurasi dan recall dibandingkan Regresi Logistik Biner. Implementasi model ini dapat mendukung sistem pendukung keputusan dalam diagnosis kanker untuk meningkatkan ketepatan hasil klasifikasi.
Perbandingan Metode K-Nearest Neighbors (K-NN) dan Regresi Logistik Biner Dalam Memprediksi Kanker Surbakti, Christina Amanda; Sinaga, Albert Samuel; Simorangkir, Agnes Monica; Sarah, Auta Shinta; Harefa, Clara Jocelyn; Dalimunthe, Syairal Fahmy
Madani: Jurnal Ilmiah Multidisiplin Vol 3, No 2 (2025): March
Publisher : Penerbit Yayasan Daarul Huda Kruengmane

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.15074826

Abstract

Background: Cancer is one of the diseases with a high mortality rate, so an accurate classification method is needed to support the diagnosis process. This study compares the performance of the K-Nearest Neighbors (KNN) method and Binary Logistic Regression in classifying cancer as malignant or benign. Methods: This study used a secondary dataset from Kaggle consisting of 569 cancer patient data with 11 independent variables covering tumor characteristics. The model was developed using data normalization, training and testing data division, and the K-Fold Cross Validation technique to optimize the K parameter in KNN. Model evaluation was carried out based on accuracy, precision, recall, and the McNemar and ANOVA tests to test the significance of differences in model performance. Results: The KNN model with K=13 showed an accuracy of 95.58%, a precision of 95.83%, and a recall of 97.18%, while Binary Logistic Regression had an accuracy of 94.69%, a precision of 92.86%, and a recall of 92.86%. The McNemar test results showed that there was no significant difference between the two models (p-value = 1), while the ANOVA results showed that all independent variables contributed to the model. Conclusion: Both methods performed well in cancer classification, but KNN with K=13 had a slight advantage in accuracy and recall compared to Binary Logistic Regression. The implementation of this model can support decision support systems in cancer diagnosis to improve the accuracy of classification results. 
Analisis Pengaruh PDRB Per Kapita, Umur Harapan Hidup, dan Harapan Lama Sekolah Terhadap Indeks Pembangunan Manusia di Provinsi Sulawesi Utara Surbakti, Christina Amanda; Sinaga, Kezia Theodora; Damanik, Ayu Lestari
Socius: Jurnal Penelitian Ilmu-Ilmu Sosial Vol 2, No 12 (2025): July 2025
Publisher : Penerbit Yayasan Daarul Huda Kruengmane

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.15692817

Abstract

Pembangunan manusia adalah aspek fundamental dalam kemajuan suatu negara, dan Indeks Pembangunan Manusia (IPM) menjadi indicator Utama untuk mengukur kesejahteraan masyarakat. Penelitian ini bertujuan untuk menganalisis pengaruh Produk Domestik Regional Bruto (PDRB) per kapita, umur harapan hidup (UHH), dan harapan lama sekolah (HLS) terhadap IPM di Provinsi Sulawesi Utara. Menggunakan pendekatan kuantitatif dengan model regresi linier berganda, penelitian ini melibatkan data sekunder dari Badan Pusat Statistik untuk 15 kabupaten/kota selama periode 2020 hingga 2024. Hasil analisis menunjukkan bahwa semua variable independent secara signifikan mempengaruhi IPM, baik secara parsial maupun simultan. Model regresi awal yang hanya menggunakan PDRB memiliki kemampuan terbatas dalam menjelaskan variasi IPM, sementara penambahan UHH dan HLS secara signifikan meningkatkan kinerja model. Transformasi logaritmik diterapkan untuk memperbaiki spesifikasi model, dan hasilnya menunjukkan bahwa model log-log adalah yang paling efisien dengan nilai Adjusted R² sebesar 0,955 dan AIC terendah. Kesimpulannya, PDRB, UHH, dan HLS memiliki peran penting dalam pembangunan manusia di Sulawesi Utara. Penelitian ini merekomendasikan penambahan variable lain dan pengembangan model prediktif untuk penelitian selanjutnya guna meningkatkan akurasi dan daya jelaskan model terhadap IPM.
Analisis Perbandingan Premi Asuransi Jiwa Berjangka Model Diskrit dan Kontinu dengan Suku Bunga CIR Sinaga, Anita; Surbakti, Christina Amanda; Hondro, Yizhar Saputra
Panthera : Jurnal Ilmiah Pendidikan Sains dan Terapan Vol. 6 No. 2 (2026): April
Publisher : Lembaga Pendidikan, Penelitian, dan Pengabdian Kamandanu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36312/panthera.v6i2.1234

Abstract

This study aims to analyze and compare the calculation of the net single premium of term life insurance using the discrete and continuous model approaches with the Cox-Ingersoll-Ross (CIR) stochastic interest rate. The data used are the BI Rate interest rate for the period January 2022 to February 2026, as well as the 2023 Indonesian Population Mortality Table (TMPI) for the female category. The CIR model parameter estimation was carried out using the Ordinary Least Squares (OLS) method. The estimation results show that the model has mean reversion characteristics with a long-term average of 0.05 (5%) and a variance of 0.0000002, which indicates relatively stable interest rate fluctuations. The interest rate rate (force of interest) is obtained at δ = 0.036025. Furthermore, the model is used to calculate the discount factor and premium. The calculation results show that the net single premium with the discrete approach is Rp 911,088.22, smaller than the continuous approach of Rp 927,703.73. This difference is due to the timing of benefit payments. The discrete model assumes payment at the end of the year of death, while the continuous model assumes payment at the time of death. Therefore, the continuous approach yields a greater present value of future benefits. This study shows that the choice of premium model and interest rate assumptions significantly influence premium amounts.
Co-Authors Damanik, Ayu Lestari Harefa, Clara Jocelyn Hondro, Yizhar Saputra Sarah, Auta Shinta Simorangkir, Agnes Monica Sinaga, Albert Samuel Sinaga, Anita Sinaga, Kezia Theodora Syairal Fahmy Dalimunthe