Article Per Year (5 Year)
p-Index From 2021 - 2026
3.279
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Pamator : Jurnal Ilmiah Universitas Trunojoyo JOURNAL OF APPLIED INFORMATICS AND COMPUTING JURNAL INSTEK (Informatika Sains dan Teknologi) Prosiding SNITP (Seminar Nasional Inovasi Teknologi Penerbangan) JASIEK (Jurnal Aplikasi Sains, Informasi, Elektronika dan Komputer) Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika bit-Tech Jurnal Teknologi Informatika dan Komputer Jurnal Diferensial HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Enthusiastic : International Journal of Applied Statistics and Data Science MATHunesa: Jurnal Ilmiah Matematika Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Jurnal Komputer Indonesia Emerging Statistics and Data Science Journal INOVTEK Polbeng - Seri Informatika Prosiding Seminar Nasional Ilmu Teknik
Alfan Rizaldy Pratama
Universitas Pembangunan Nasional Veteran Jawa Timur
Aerospace Engineering Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mathematics Public Health Social Sciences Transportation

Published : 23 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 23 Documents
Search

 1   2   3 
PERBANDINGAN METODE DECISION TREE CART DAN K-NEAREST NEIGHBORS UNTUK KLASIFIKASI KUALITAS KISMIS PADA RAISIN DATASET: COMPARISON OF CLASSIFICATION AND REGRESSION TREE (CART) AND K-NEAREST NEIGHBORS (KNN) FOR RAISIN QUALITY CLASSIFICATION USING THE RAISIN DATASET Melly Agustin; Laras Ayu Pradanti; Fildzah Syarafina Sumantri; Alfan Rizaldy Pratama
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 17 No. 2 (2026): Jurnal HOAQ - Teknologi Informasi
Publisher : Universitas Uyelindo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol17no2.p351-361

Abstract

Kismis merupakan salah satu produk pertanian yang memiliki nilai ekonomis tinggi, sehingga klasifikasi kualitasnya menjadi aspek penting dalam proses seleksi dan distribusi. Penelitian ini bertujuan untuk membandingkan kinerja metode Decision Tree CART dan K-Nearest Neighbors (KNN) dalam mengklasifikasikan jenis kismis pada raisin dataset yang terdiri dari 900 data dengan dua kelas yaitu, besni dan kecimen. Dataset memiliki tujuh fitur morfologi, meliputi area, major axis length, minor axis length, eccentricity, convex area, extent, dan perimeter. Tahap preprocessing mencakup penanganan outlier menggunakan metode capping IQR, encoding label, standarisasi fitur dengan StandardScaler, serta pembagian data latih dan uji dengan rasio 80:20. Hasil evaluasi menunjukkan bahwa metode KKN dengan nilai k optimal sebesar 16 menghasilkan akurasi 88,33%, presisi 84,16%, recall 94,44%, dan FI-Score 89,01%. Sementara itu, Decision Tree CART memperoleh akurasi 84,44%, presisi 80,39%, recall 91,11%, dan F1-Score 85,42%. Berdasarkan perbandingan keempat metrik evaluasi tersebut, KNN terbukti unggul dibandingkan Decision Tree CART dalam mengklasifikasikan kualitas kismis pada dataset ini. KKN direkomendasikan sebagai metode yang lebih sesuai untuk klasifikasi kismis dengan karakteristik dataset serupa.   Raisins are one of the high-value agricultural products, making quality classification a critical aspect of their selection and distribution process. This study aims to compare the performance of the Decision Tree CART and K-Nearest Neighbors (KKN) methods in classifying raisin varieties using the raisin dataset, which consists of 900 instances with two classes: besni and kecimen. The dataset includes seven morphological features: area, major axis length, minor axis length, eccentricity, convex area, extent, and perimeter. Preprocessing steps included outlier handling using IQR capping, label encoding, feature standardization with StandardScaler, and an 80:20 train-test split. Evaluation results show that KNN with an optimal K value of 16 achieved an accuracy of 88,33%, precision of 84,16%, recall of 94,44%, and F1-Score of 89,01%. Decision Tree CART obtained an accuracy of 84,44%, precision of 80,39%, recall of 91,11%, and F1-Score of 85,42%. Based on all four evaluation metrics, KNN outperformed Decision Tree CART in classifying raisin quality on this dataset. KKN is therefore recommended as the more suitable method for raisin classification tasks with similar dataset characteristics.
Evaluating the Effect of Global Channel Attention on EfficientNetB0 for Distracted Driver Classification under Diverse Lighting Conditions Rabbani, Zufar Abdullah; Wahyu Syaifullah J. S; Alfan Rizaldy Pratama
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 11 No 2 (2026): OCTOBER
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/instek.v11i2.67721

Abstract

Image-based distracted driver classification has been widely studied to reduce the risk of traffic accidents, yet most studies use data captured under uniform lighting conditions. However, illumination variation can degrade feature extraction in Convolutional Neural Network (CNN) architectures. Channel attention (CA) has previously been shown to improve EfficientNetB0, but EfficientNetB0 with CA has not yet been extensively tested for distracted driver classification under diverse lighting conditions. This study aims to evaluate the performance of channel attention on EfficientNetB0 in classifying distracted driver activities under diverse lighting conditions. We used the State Farm Distracted Driver Dataset and a primary dataset of 10.080 images from three subjects captured under dark, semi-bright, and bright lighting conditions. The secondary data and two primary subjects were used for training, while one unseen primary subject was used for testing. Preprocessing included image resizing, normalization, and data augmentation. The models were trained using two-phase transfer learning (frozen backbone followed by fine-tuning) and evaluated using accuracy, precision, recall, and F1-score. The accuracies of baseline EfficientNetB0 versus EfficientNetB0+CA were 38.84% vs 60.36% (dark), 61.07% vs 32.59% (semi-bright), 67.14% vs 84.73% (bright), and 55.68% vs 59.23% (all conditions). CA improved accuracy in dark and bright conditions but reduced it in semi-bright conditions, so a consistent performance gain from adding CA cannot be concluded.
Analisis Perbandingan Metode XGBoost dan Extra Trees untuk Klasifikasi Penyakit Jantung pada Dataset UCI Heart Disease: Analisis Perbandingan Metode XGBoost dan Extra Trees untuk Klasifikasi Penyakit Jantung pada Dataset UCI Heart Disease Rifki, Erik Saputra; Azaria, Siti Rania; Praktiko, Angelina; Pratama, Alfan Rizaldy
Emerging Statistics and Data Science Journal Vol. 4 No. 3 (2026): Emerging Statistics and Data Science Journal
Publisher : Statistics Department, Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20885/esds.vol4.iss.3.art02

Abstract

Penelitian ini membandingkan XGBoost dan Extra Trees untuk klasifikasi penyakit jantung pada 303 data UCI Cleveland tanpa SMOTE. Data dibagi 80:20 secara stratifikasi, dengan imputasi median dan standardisasi berdasarkan data latih. XGBoost memperoleh akurasi 86,89% dan AUC 0,9437, sedangkan Extra Trees memperoleh akurasi 81,97% dan AUC 0,9535. Interval kepercayaan bootstrap untuk selisih kinerja mencakup nol, sementara uji McNemar menunjukkan perbedaan klasifikasi tidak signifikan (p = 0,4531). Berdasarkan skor komposit eksploratif, XGBoost dipilih sebagai model utama. Analisis permutation importance mengidentifikasi thal, ca, dan cp sebagai fitur prediktif penting. Pengujian pada dataset independen diperlukan untuk menilai kemampuan generalisasi model.
Co-Authors Abda Abda Adziima, Andri Fauzan Alvino Hadiyan Pradipta Andri Faudzan Adziima Andri Fauzan Adziima Annabel Gracia Puryani Anniswa, Iqbal Ramadhan Aviolla Terza Damaliana Aviolla Terza Damaliana Azaria, Siti Rania Azzahra, Melinda Putri Dadet Pramadihanto Dewi Mutiara Sari Difta Alzena Sakhi Dwito Armono, R. Haryo Faris Nur Tsani Fauzan Adziima, Andri Fildzah Syarafina Sumantri Firmansyah Putra Pratama Friza Nur Fatmala Gede Susrama Mas Diyasa, I I Gede Susrama Mas Diyasa I Gede Susrama Mas Diyasa idhom, Mohammad Iqbal Ramadhan Anniswa Karina Auralia Kristanaya, Mirechelin Laras Ayu Pradanti Maretta Fairuz Luthfia Winoto Putri Marta, Bayu Sandi Maulidya Prastita Syah Melly Agustin Mohammad Idhom Muhammad Azkiya Akmal Muhammad Nasrudin Muhammad Nasrudin Muhammad Rafli Feandika Nugroho Nariswari, Naura Ulayya Praktiko, Angelina Putra Pratama, Firmansyah R. Haryo Dwito Armono Rabbani, Zufar Abdullah Ramadhan Anniswa, Iqbal Reza Putri Angga Rifki, Erik Saputra Saputra, Wahyu S.J. Sari, Dewi Mutiara Shindi Shella May Wara Susrama Mas Diyasa, I Gede Syah, Maulidya Prastita Syaifullah J. S, Wahyu Trimono Tsabita Rosyidah Putri Wahyu Syaifullah J S Wahyu Syaifullah J. S Wahyu Syaifullah Jauharis Saputra Zufar Abdullah Rabbani