Article Per Year (5 Year)
p-Index From 2021 - 2026
1.925
P-Index
This Author published in this journals
All Journal Jurnal Informatika dan Teknik Elektro Terapan Jurnal Abdi Masyarakat Indonesia ELIT JOURNAL Electrotechnics And Information Technology Jurnal Sains Student Research SAINTEK Ambidextrous : Journal of Innovation, Efficiency and Technology in Organization Journal of Golden Generation Engineering
Dede Brahma Arianto
Fakultas Sains Dan Teknik, Universitas Faletehan, Indonesia
Aerospace Engineering Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mechanical Engineering Public Health Transportation Other

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
KLASIFIKASI PENYAKIT KANKER PAYUDARA MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) Rosi Susanti; Dede Brahma Arianto
Journal of Golden Generation Engineering Vol. 2 No. 2 (2026): Juli : Journal of Golden Generation Engineering
Publisher : PT. Lembaga Penerbit Penelitian Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65244/jggengineering.v2i2.786

Abstract

Kanker payudara dapat menurunkan kualitas hidup sehingga diperlukan skrining yang cepat dan konsisten. Penelitian ini mengembangkan sistem klasifikasi kanker payudara berbasis Convolutional Neural Network (CNN) yang diimplementasikan pada aplikasi skrining berbasis web. Dataset disusun ke dalam data latih, validasi, dan uji, kemudian citra diproses melalui penyesuaian ukuran 224×224, normalisasi, serta augmentasi pada data latih. Model dibangun menggunakan arsitektur MobileNetV3 Small dengan keluaran tiga kelas, yaitu Normal, Benign, dan Malignant. Sistem juga menerapkan validasi input untuk memastikan prediksi hanya dilakukan pada citra jaringan payudara sebelum proses inferensi. Hasil pengujian pada 300 data uji menunjukkan akurasi sebesar 88,00% dengan performa per kelas yang bervariasi, di mana kesalahan klasifikasi masih terjadi pada kelas-kelas yang memiliki kemiripan ciri visual. Hasil ini menunjukkan CNN efektif untuk mendukung skrining awal kanker payudara dan dapat ditingkatkan melalui penambahan data serta optimasi pelatihan pada penelitian selanjutnya
Classification of Symptoms of Disease in Early Childhood Using the Decision Tree Algorithm Nissa Albantaniyah; Dede Brahma Arianto
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 4 No. 02 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v4i02.494

Abstract

Diseases in early childhood often have similar symptoms, making it difficult to process early diagnosis. This study aims to classify disease symptoms in early childhood using the Decision Tree algorithm. The data used is in the form of child health symptom data which is processed through the pre-processing stage and divided into training data and testing data. The results of the study show that the Decision Tree algorithm is able to classify disease symptoms well and can help the early diagnosis process faster and more systematically. The results of the evaluation show that the implementation of immunization of school children in various regions has quite good achievements, with the percentage of immunization coverage in the range of 66% to more than 90%. This high percentage shows that most children have successfully received immunizations in accordance with the set targets, so that the immunization program can be said to be running consistently and effectively.
Implementation of Random Forest Algorithm to Determine Food Allergies Ratu Aisyah; Dede Brahma Arianto
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 4 No. 02 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v4i02.496

Abstract

Food allergy diagnosis faces challenges due to symptom variation and delays in conventional testing. This study aims to classify food allergy types using the Random Forest algorithm on patient data including age, gender, food type, symptoms, and severity. A quantitative experimental design was implemented with a secondary dataset of 1,000 medical records as the population, divided through stratified sampling (train-test ratio 80:20). Data preprocessing included label encoding of categorical variables, followed by supervised classification analysis using Python scikit-learn. The results showed a model accuracy of 85%, precision of 84%, recall of 86%, and F1-score of 85%, indicating strong performance with a balanced error rate in the validation confusion matrix. In conclusion, Random Forest effectively supports the rapid identification of food allergies, potentially serving as a clinical decision-making tool with the need for larger prospective datasets.
Predicting the Risk of Hypertension in Adult Patients Using the Random Forest Algorithm Santinah; Dede Brahma Arianto
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 4 No. 02 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v4i02.497

Abstract

Hypertension remains a persistent and widespread health problem in the adult population, yet many cases go undetected due to limited early symptoms and reliance on conventional clinical assessment. This study aims to develop and evaluate a hypertension risk prediction model in adult patients using the Random Forest algorithm. This study employed a quantitative approach with an exploratory–predictive study design based on electronic secondary data, with a descriptive–analytical framework utilizing data mining techniques. The study population comprised all adult patients registered at selected healthcare facilities, while the sample consisted of 120 adult patients selected by purposive sampling from the hypertension risk dataset on Kaggle. The instrument used was a structured electronic medical record table, including age, gender, body mass index (BMI), blood pressure, and relevant medical history. The data underwent preprocessing and encoding, then were analyzed using the Random Forest algorithm on the Python platform with the scikitlearn library. Model performance was evaluated using accuracy, precision, recall, and F1score metrics. The results showed that the Random Forest model provided an accuracy of 87.5%, precision of 91.7%, recall of 84.6%, and F1 score of 88.0%, indicating a strong hypertension risk classification capability. The study concluded that Random Forest can be utilized as a reliable decision support system for early detection of hypertension risk in adult populations, especially when integrated with electronic medical records.
Sistem Pendeteksian Jenis Kulit Wajah dan Rekomendasi Skincare Berbasis Android Menggunakan Convolutional Neural Network (CNN) Nurfalah Nurfalah; Dede Brahma Arianto
Journal of Golden Generation Engineering Vol. 2 No. 2 (2026): Juli : Journal of Golden Generation Engineering
Publisher : PT. Lembaga Penerbit Penelitian Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65244/jggengineering.v2i2.839

Abstract

Penelitian ini bertujuan untuk mengimplementasikan metode Convolutional Neural Network (CNN) dalam pendeteksian jenis kulit wajah dan rekomendasi skincare berbasis Android. Sistem mengklasifikasikan jenis kulit menjadi normal, kering, berminyak, berjerawat, dan sensitif menggunakan 750 citra wajah yang telah diberi label. Model dilatih dengan 50 epoch, ukuran citra 224×224 piksel, dan optimizer Adam. Hasil pelatihan menunjukkan bahwa akurasi meningkat seiring bertambahnya epoch, sementara nilai loss menurun. Evaluasi pada data uji menghasilkan akurasi sebesar 99% dengan loss 3,73%, yang menunjukkan performa model yang sangat baik. Sistem mampu mengklasifikasikan jenis kulit secara akurat serta memberikan rekomendasi skincare yang disesuaikan dengan kondisi kulit pengguna. Implementasi dalam aplikasi Android memudahkan pengguna dalam melakukan deteksi secara langsung melalui kamera smartphone, sehingga membantu dalam memilih produk perawatan yang tepat.
Analisis Risiko Penyebaran Penyakit Demam Berdarah Menggunakan Algoritma Naive Bayes Nisa Cherani Sutansi; Dede Brahma Arianto
Journal of Golden Generation Engineering Vol. 2 No. 2 (2026): Juli : Journal of Golden Generation Engineering
Publisher : PT. Lembaga Penerbit Penelitian Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65244/jggengineering.v2i2.935

Abstract

Demam Berdarah Dengue (DBD) merupakan salah satu penyakit menular yang masih menjadi permasalahan kesehatan masyarakat di Indonesia dan berbagai negara tropis. Penyakit ini disebabkan oleh virus dengue yang ditularkan melalui gigitan nyamuk Aedes aegypti. Tingginya jumlah kasus serta potensi terjadinya kejadian luar biasa (KLB) menunjukkan bahwa diperlukan metode analisis yang mampu mengidentifikasi pola risiko penyebaran penyakit secara sistematis dan akurat. Seiring berkembangnya teknologi informasi, pendekatan berbasis Machine Learning mulai dimanfaatkan dalam bidang kesehatan, khususnya dalam analisis data epidemiologi. Machine Learning memungkinkan sistem komputer untuk mempelajari pola dari data historis dan menghasilkan prediksi yang dapat digunakan sebagai dasar pengambilan keputusan. Salah satu algoritma yang sering digunakan adalah Naive Bayes yang bekerja berdasarkan teori probabilitas Bayes dengan asumsi bahwa setiap variabel bersifat independen. Dalam penelitian ini digunakan algoritma Naive Bayes untuk menganalisis risiko penyebaran penyakit Demam Berdarah berdasarkan beberapa faktor yang mempengaruhi, seperti kondisi lingkungan, kepadatan penduduk, serta data historis kasus penyakit. Metode ini diharapkan mampu menghasilkan model klasifikasi yang dapat membantu dalam proses pengambilan keputusan terkait pencegahan dan pengendalian penyakit DBD.
Application of Logistic Regression Method for Predicting Diabetes Mellitus Dendi Pratama Riawan; Dede Brahma Arianto
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 4 No. 03 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v4i02.539

Abstract

Diabetes is a chronic disease that requires early detection to prevent complications. This study refers to the analysis of diabetes prediction using the Logistic Regression algorithm. The data used comes from the open dataset platform, namely Kaggle, including health attributes such as Pregnancies, Glucose, Blood Pressure, Skin Thickness, Insulin, BMI, Age, Outcome. The process in this study includes data cleaning, model development, and prediction. Model assessment was carried out using Confusion Matrix to calculate accuracy, Precision, Recall, and F1-Score, which is supported by ROC Curve analysis. The findings in this study show that the Logistic Regression model achieved an accuracy level of 75.32% and an AUC of 0.8232, indicating that the classification performance is quite good in predicting diabetes conditions
ANALISIS PERBANDINGAN ALGORITMA RANDOM FOREST DAN ISOLATION FOREST DALAM DETEKSI ANCAMAN KEAMANAN SIBER Muhamad Farhan Qolbi; Dede Brahma Arianto
JOURNAL SAINS STUDENT RESEARCH Vol. 4 No. 4 (2026): Agustus: Jurnal Sains Student Research
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jssr.v4i4.11545

Abstract

Cybersecurity threats continue to increase in both number and complexity, necessitating a detection system capable of accurately and efficiently identifying malicious activity. This study aims to evaluate the performance of the Random Forest algorithm compared to the Isolation Forest in detecting cybersecurity threats by utilizing the Cybersecurity Threat Detection Logs Dataset. Experiments were conducted with three variations of data size: 100,000, 200,000, and 500,000 to assess the impact of data scale on model performance. The preprocessing process included feature selection, categorical data encoding, and the division of training and testing data using a stratified sampling technique. Model evaluation was performed using precision, recall, F1-score, and accuracy metrics based on a weighted average due to class imbalance in the dataset. The study findings revealed that Random Forest provided more stable and superior performance with precision, recall, F1-score, and accuracy values reaching 0.85 in all test scenarios. On the other hand, Isolation Forest showed good effectiveness in detecting anomalies, but also produced a higher false positive rate. Therefore, Random Forest is more suitable to be used as the main model for labeled cyber threat detection, while Isolation Forest can serve as a supporting system for anomaly detection.
PREDIKSI HARGA SAYURAN DI PASAR TRADISIONAL MENGGUNAKAN ALGORITMA K-NEARST NEIGHBOR (KNN) Nurhidayat Nurhidayat; Dede Brahma Arianto
JOURNAL SAINS STUDENT RESEARCH Vol. 4 No. 4 (2026): Agustus: Jurnal Sains Student Research
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jssr.v4i4.11584

Abstract

Sayuran merupakan komoditas musiman yang penting namun sering mengalami ketidakstabilan harga, yang dapat merugikan petani dan menyulitkan konsumen. Penelitian ini bertujuan untuk mengimplementasikan algoritma K-Nearest Neighbor (KNN) dalam memprediksi harga sayuran di pasar tradisional guna memberikan referensi bagi para pemangku kepentingan. Dataset yang digunakan mencakup data historis harga dan faktor yang mempengaruhinya seperti curah hujan atau luas panen. Hasil penelitian diharapkan dapat memberikan tingkat akurasi yang tinggi dalam memprediksi fluktuasi harga, serupa dengan penelitian sebelumnya yang mencapai akurasi hingga 91,67% untuk komoditas tertentu. Implementasi ini penting untuk membantu stabilitas pasar dan ketahanan pangan nasional
Implementasi Algoritma K-Nearest Neighbor dalam Prediksi Diabetes Mellitus Risya Sholehatun Nisa; Dede Brahma Arianto
JOURNAL SAINS STUDENT RESEARCH Vol. 4 No. 4 (2026): Agustus: Jurnal Sains Student Research
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jssr.v4i4.11619

Abstract

Diabetes melitus merupakan gangguan metabolik jangka panjang yang ditandai oleh meningkatnya kadar glukosa darah akibat ketidakseimbangan produksi maupun pemanfaatan hormon insulin dalam tubuh. Tingginya angka kejadian diabetes yang terus mengalami peningkatan menegaskan perlunya pendekatan prediksi yang mampu mendukung upaya deteksi dini secara lebih akurat. Penelitian ini mengkaji penerapan algoritma K-Nearest Neighbor (KNN) sebagai metode pembelajaran terawasi untuk melakukan klasifikasi risiko diabetes berdasarkan data medis pasien. Data yang digunakan bersumber dari dataset terbuka Kaggle dengan jumlah 768 sampel yang mencakup beberapa atribut klinis, antara lain kadar glukosa, tekanan darah, indeks massa tubuh, insulin, serta usia. Tahapan penelitian meliputi pengolahan awal data, pemisahan data latih dan data uji, serta proses klasifikasi menggunakan algoritma KNN dengan perhitungan jarak Euclidean. Kinerja model dievaluasi menggunakan parameter akurasi, presisi, recall, dan F1-score. Hasil pengujian menunjukkan bahwa model mampu mencapai tingkat akurasi sebesar 69%, dengan nilai presisi 68%, recall 69%, dan F1-score 68%. Capaian tersebut menunjukkan bahwa algoritma KNN dapat mengidentifikasi pola kedekatan antar data medis secara cukup efektif. Oleh karena itu, algoritma ini berpotensi dikembangkan sebagai sistem pendukung keputusan untuk membantu proses identifikasi dini penyakit diabetes
Co-Authors Ade Maulana Bilgis AHMAD SANUSI Ahmad Sanusi Andiko Nugraha Kusuma Dendi Pratama Riawan Muhamad Farhan Qolbi Muhamad Farhan Qolbi Nisa Cherani Sutansi Nissa Albantaniyah Nurfalah Nurfalah Nurhidayat Nurhidayat Octoberry Julyanto Ratu Aisyah Risya Sholehatun Nisa Risya Sholehatun Nisa Rosi Susanti Santinah Venia Setyarandini