Article Per Year (5 Year)
p-Index From 2020 - 2025
3.696
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Fountain of Informatics Journal Sistemasi: Jurnal Sistem Informasi Swabumi (Suara Wawasan Sukabumi) : Ilmu Komputer, Manajemen, dan Sosial JITK (Jurnal Ilmu Pengetahuan dan Komputer) J-SAKTI (Jurnal Sains Komputer dan Informatika) JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Building of Informatics, Technology and Science Jurnal Mantik Journal of Computer System and Informatics (JoSYC) Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Jurnal Teknik Informatika (JUTIF) Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Jurnal Pendidikan dan Teknologi Indonesia J-SAKTI (Jurnal Sains Komputer dan Informatika) Jurnal Sains dan Teknologi STORAGE: Jurnal Ilmiah Teknik dan Ilmu Komputer
Susanto, Erliyan Redy
Unknown Affiliation
Aerospace Engineering Agriculture, Biological Sciences & Forestry Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Mathematics Mechanical Engineering Medicine & Pharmacology Nursing Public Health Social Sciences Veterinary

Published : 28 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 28 Documents
Search

 1   2   3 
Evaluasi Kinerja Model Random Forest Dalam Memprediksi Diabetes Berdasarkan Dataset Kesehatan di Indonesia Susanto, Erliyan Redy; Inzaghi, M. Rana; Amarudin, Amarudin; Neneng, Neneng
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 7 (2025): JPTI - Juli 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.871

Abstract

Penyakit  diabetes atau sering disebut dengan penyakit gula darah adalah sekelompok penyakit metabolik yang ditandai dengan tingginya kadar gula darah pada seseorang yang terkena, dan bertahan dalam jangka waktu lama. Di Indonesia sedikitnya terdapat 20 juta orang pada usia 20-79 tahun menderita diabetes pada tahun 2024. Hal ini disebabkan oleh kurangnya akses terhadap alat prediksi yang efektif, serta keterbatasan pada pendekatan tradisional bergantung pada diagnosis medis manual yang memakan waktu dan biaya. Permasalahan ini muncul karena kurangnya pemanfaatan teknologi berbasis data dalam menganalisis faktor risiko yang kompleks dan saling terkait.  Penelitian ini bertujuan menggunakan model random forest untuk melakukan klasifikasi terhadap penyakit diabetes serta mengevaluasi nilai akurasi dengan evaluasi model menggunakan metrik seperti akurasi, presisi, recall, dan F1-score. Teknik akurasi yang digunakan yaitu confusion matrix untuk mengukur performa dalam permasalahan sehingga menghasilkan nilai akurasi yang sesuai. Hasil penelitian ini dapat memberikan wawasan praktis tentang konfigurasi optimal model untuk aplikasi dunia nyata, sehingga meningkatkan akurasi dan keandalan sistem prediksi diabetes. Model diuji menggunakan data uji yang telah dipisahkan sebelumnya dengan rasio 80:20. Hasil evaluasi kinerja model menunjukkan akurasi sebesar 0.99%, presisi 0.99%, recall 0.99%, F1-score 0.99%, Specificity 0.99% dan ROC-AUC Score 89.2%.  Hasil penelitian bermanfaat untuk membantu dokter dan tenaga kesehatan serta masyarkat umum untuk mendeteksi penyakit diabetes sejak dini.
Deteksi Dini Stroke Menggunakan Machine Learning Kevinda Sari; Muhammad Fadli; Fudholi, Muhammad Fahmi; Susanto, Erliyan Redy
INSOLOGI: Jurnal Sains dan Teknologi Vol. 4 No. 4 (2025): Agustus 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/insologi.v4i4.5590

Abstract

Stroke is one of the leading causes of death and disability worldwide. Early detection of stroke risk is crucial to prevent more severe complications. This study aims to develop a stroke prediction model based on machine learning using an open dataset from Kaggle containing patients' medical and demographic information. Four machine learning algorithms were utilized and compared: AdaBoost, Gradient Boosting, LightGBM, and XGBoost. Data preprocessing steps included missing value imputation, categorical variable encoding, numerical feature normalization, and class balancing using the SMOTEENN method. Additionally, feature selection was performed using the Extra Trees algorithm to enhance model performance. The results showed that the XGBoost model delivered the best performance, achieving an accuracy of 97.16%, an F1-score of 97.49%, and an AUC of 99.75%. This model proved to be effective in detecting stroke cases and holds potential for integration into clinical decision support systems. The study concludes that a combination of modern boosting algorithms and optimal preprocessing techniques can yield a reliable stroke prediction system suitable for implementation in digital healthcare contexts.
Rancang Bangun Modul Kontrol Berbasis PID untuk Pengaturan Kecepatan dan Posisi Motor DC Menggunakan STM32 dan Rotary Encoder Doris Juarsa; Muhammad Fadli; Susanto, Erliyan Redy
INSOLOGI: Jurnal Sains dan Teknologi Vol. 4 No. 4 (2025): Agustus 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/insologi.v4i4.6081

Abstract

Precision control of DC motors in industrial and robotics applications is often compromised by external loads and the limitations of open-loop systems, which cause instability in rotational speed and angular position. This study aims to design and build a PID-based intelligent control module for integrated DC motor speed and position control using an STM32F103C8T6 microcontroller and a rotary encoder as feedback. This system is designed as a closed-loop system to reduce the error between the setpoint and the actual value. Tests were conducted under no-load and with-load conditions at various speed setpoints (10–30 RPM) and angular changes (slow and fast). The results show that the system is able to stabilize motor performance with an average speed error of −0.3033 and 0.2766 RPM (no-load) for Motors A and B, and 0.2633 and 3.47 RPM (with-load). For angular position control, the average errors were 0.69° and 0.895° (without load), and 0.475° and 0.335° (with load). These findings demonstrate the effectiveness of the PID-based intelligent control module in improving system accuracy and stability. This system offers a compact and practical solution for industrial automation and robotics applications requiring precise motor control.
Komparasi Algoritma Random Forest dan Support Vector Machine dalam Memprediksi Risiko PMS Simarmata, Yohanes; Maylanda, Putri Oktaria; Susanto, Erliyan Redy
SWABUMI (Suara Wawasan Sukabumi): Ilmu Komputer, Manajemen, dan Sosial Vol 13, No 2 (2025): Volume 13 Nomor 2 Tahun 2025
Publisher : Universitas Bina Sarana Informatika Kota Sukabumi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/swabumi.v13i2.25580

Abstract

Penyakit Menular Seksual (PMS) merupakan permasalahan kesehatan global yang memerlukan deteksi dini untuk pencegahan dan pengobatan yang lebih efektif. Studi ini membandingkan performa algoritma pembelajaran mesin, yaitu Random Forest dan Support Vector Machine (SVM), dalam memprediksi risiko PMS. Dataset yang digunakan mencakup variabel epidemiologis utama dan diklasifikasikan ke dalam dua kategori risiko. Hasil penelitian menunjukkan bahwa Random Forest memiliki akurasi tertinggi sebesar 99.87%, dengan keunggulan dalam menangani dataset tidak seimbang serta mengenali pola kompleks. Namun, model ini berisiko mengalami overfitting sehingga memerlukan tuning parameter dan validasi silang untuk meningkatkan generalisasi. Sementara itu, SVM memperoleh akurasi 97.96% dan lebih stabil dalam menangani data berdimensi tinggi, tetapi memiliki recall 0.91 untuk kelas risiko tinggi, yang menunjukkan adanya kasus yang tidak terdeteksi secara optimal. Penelitian ini menunjukkan bahwa pemilihan algoritma bergantung pada kebutuhan spesifik analisis: Random Forest unggul dalam akurasi tinggi, sedangkan SVM lebih seimbang dalam generalisasi data. Studi lebih lanjut disarankan untuk mengoptimalkan kinerja model melalui tuning hyperparameter dan teknik ensemble learning guna meningkatkan akurasi deteksi dini PMS.Keywords: Penyakit Menular Seksual, Machine Learning, Random Forest, Support Vector Machine, Prediksi Risiko.
Comparison of Machine Learning Models for Predicting Lung Cancer Severity Lestari, Ninik; Susanto, Erliyan Redy
Sistemasi: Jurnal Sistem Informasi Vol 14, No 6 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i6.5258

Abstract

This study aims to compare the performance of four machine learning algorithms Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), and K-Nearest Neighbors (KNN) in predicting lung cancer severity based on patient medical data. The dataset includes clinical information with the target variable categorized into three severity levels: low, medium, and high. Experiments were conducted using an 80:20 train-test split without feature scaling. The results show that RF achieved 100% accuracy, LR 99%, KNN 82%, and SVM 43%. The superior performance of Random Forest can be attributed to its ensemble of decision trees, which mitigates overfitting in medium-dimensional numerical features, whereas SVM (kernel = RBF, C = 1.0, gamma = "scale") failed to adapt due to the absence of scaling and hyperparameter tuning. Recall, precision, and F1-score further confirm the dominance of RF and LR. This study provides insights into the effectiveness of machine learning algorithms in lung cancer diagnosis and highlights the contribution of a multi-algorithm approach. The findings recommend using RF as the primary model and LR as a complementary control within clinical decision support systems, enabling physicians to make earlier, more personalized treatment decisions and ultimately improve lung cancer patient prognosis.
Penerapan Logika Fuzzy Dan Metode Profile Matching Pada Sistem Pakar Medis Untuk Diagnosis Covid-19 Dan Penyakit Lain Rusliyawati, Rusliyawati; Wantoro, Agus; Susanto, Erliyan Redy
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 9 No 5: Oktober 2022
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2022955406

Abstract

COVID-19 masih menjadi masalah di seluruh dunia. Gejala infeksi COVID-19 berupa batuk, demam, sesak napas, pilek, dan diare mirip dengan penyakit lain, sehingga menyulitkan dokter untuk membedakan infeksi COVID-19 atau penyakit lain, sehingga diperlukan diagnosis. Kesalahan diagnosis menyebabkan kesalahan dalam upaya pengobatan. Berbagai macam upaya diagnosis telah dilakukan, seperti Rapid Diagnostic Test (RDT), RT-PCR, CT-Scan Image, dan machine learning, namun masih memiliki beberapa kelemahan. RTD dan RT-PCR membutuhkan waktu yang relatif lama dan biaya yang mahal. Pasien merasakan nyeri pada hidung dan tenggorokan serta mengalami batuk dan bersin. Diagnosis menggunakan CT-Scan menghasilkan radiasi yang dapat meningkatkan risiko kanker karena pasien menerima dosis zat yang mengandung yodium yang dapat menyebabkan reaksi alergi seperti rasa logam di mulut, gatal, dan sesak napas. Tujuan dari penelitian ini adalah untuk membangun sistem pakar medis dengan menggunakan metode yang berbeda yaitu dengan menggunakan logika Fuzzy-Profile Matching untuk diagnosis COVID-19 dan penyakit lainnya berdasarkan gejala klinis pasien seperti demam, batuk kering, batuk berdahak, lesu, sesak nafas, nyeri sendi, sakit kepala, bersin, pilek, hidung tersumbat, mata berair, sakit tenggorokan, dan diare. Hasil evaluasi menggunakan 30 data dari puskesmas di Bandar Lampung, metode usulan memiliki akurasi sebesar 90%. Metode usulan yang dikembangkan mampu memberikan hasil yang cepat, murah dan tanpa efek samping. AbstractCOVID-19 is still a problem all over the world. Symptoms of COVID-19 infection in the form of cough, fever, shortness of breath, runny nose, and diarrhea are similar to other diseases, making it difficult for doctors to distinguish between COVID-19 infection or other diseases, so a diagnosis is needed. Misdiagnosis leads to errors in treatment attempts. Various kinds of diagnostic efforts have been made, such as Rapid Diagnostic Test (RDT), RT-PCR, CT-Scan Image, and machine learning, but still have some weaknesses. RTD and RT-PCR take a relatively long time and are expensive. The patient feels pain in the nose and throat and experiences coughing and sneezing. Diagnosis using CT-Scan produces radiation that can increase the risk of cancer because the patient receives doses of substances containing iodine which can cause allergic reactions such as metallic taste in the mouth, itching, and shortness of breath. The purpose of this research is to build a medical expert sistem using different methods, namely by using Fuzzy-Profile Matching logic for the diagnosis of COVID-19 and other diseases based on the patient's clinical symptoms such as fever, dry cough, cough with phlegm, lethargy, shortness of breath, pain. joints, headache, sneezing, runny nose, nasal congestion, watery eyes, sore throat, and diarrhea. The results of the evaluation used 10 data from health centers in Bandar Lampung, the proposed method had an accuracy of 90%. The proposed method developed is able to provide fast, inexpensive and no side effects.
DESIGN OF A WORDPRESS BASED E-COMMERCE WEBSITE AND INTEGRATION OF CRYPTOCURRENCY PAYMENT GATEWAY Anggoro, Restu; Susanto, Erliyan Redy
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024 - SENIKO
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2067

Abstract

The Internet has become one of the main media, especially e-commerce transactions, which are increasingly popular and play an important role in the growth of online businesses. The RestLyfe store uses the Itemku platform, which uses a Business to Customer (B2C) and Customer to Customer (C2C) model, to sell digital products such as digital vouchers and game keys. However, some of the issues faced when using the platform include high costs, limited market reach, and payment methods that can only be used by certain customers. Building an e-commerce website and adding a cryptocurrency payment gateway will hopefully solve these problems. To achieve this goal, an e-commerce website based on the WordPress content management system (CMS) with the WooCommerce plugin will be built. This plugin will incorporate a cryptocurrency payment gateway and facilitate transaction design. To collect related data, observation and literature review were conducted. The waterfall model System Life Cycle Development (SDLC) method will be used to build the e-commerce website. The results and conclusions of this study show that the website built can solve the problem with implementation results that meet the needs of the initial analysis, and the results of black box testing conducted on the website show good results. In addition, this study demonstrates the use of modern sales strategies for cryptocurrencies and the optimization of the latest technologies. Thus, the e-commerce site offers more opportunities to reach the target market and meet the needs of an increasingly digitized market.
REFORMULATION OF MULTI-ATTRIBUTE UTILITY THEORY NORMALIZATION TO HANDLE ASYMMETRIC DATA IN MADM Puspaningrum, Ajeng Savitri; Susanto, Erliyan Redy; Hendrastuty, Nirwana; Setiawansyah, Setiawansyah
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 2 (2025): JITK Issue November 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i2.7273

Abstract

Multi-Attribute Utility Theory (MAUT) is a widely used multi-attribute decision-making (MADM) method due to its ability to integrate multiple criteria into a single utility value. However, conventional MAUT faces limitations when handling asymmetric data, where standard normalization processes often lead to value distortion and less representative rankings. This study aims to reformulate the normalization function in MAUT to improve adaptability to non-symmetric data distributions and to enhance ranking validity in decision-making. A modification approach called MAUT-A was developed by applying an adaptive normalization mechanism capable of accommodating extreme distributions and outliers by adding Z-score normalization. The performance of MAUT-A was evaluated by comparing the correlation of its ranking results with reference rankings, and the outcomes were benchmarked against conventional MAUT. The experimental findings indicate that conventional MAUT achieved a correlation value of 0.9688 with the reference ranking, while the proposed MAUT-A method achieved a higher correlation of 0.9792. This improvement represents that MAUT-A has better suitability, stability, and reliability in managing asymmetric data. The study contributes by offering a reformulated MAUT framework through adaptive normalization, providing more accurate, stable, and fair ranking outcomes. This approach enhances the validity of MADM applications, particularly in contexts involving asymmetric data distributions
Co-Authors ., Rusliyawati Adela, Marsya Agus Wantoro Amarudin, Amarudin Amelya, Eka Andi Nurkholis Az Zahra, Renny Fatimah Budiman, Ega Cahyana, Agum David Kurniawan DAVID KURNIAWAN Doris Juarsa Eka Pranajaya, Akbar Estri Pratiwi, Kyky Fidya Fadli, Muhammad Fudholi, Muhammad Fahmi Hendratno, Hary Inzaghi, M. Rana Irawan, Made Kevinda Sari Lestari, Ninik Maylanda, Putri Oktaria Misdiantoro, Diky Muhammad Fadli Neneng Neneng Neneng, N Nirwana Hendrastuty Purwanti, Dian Sri Putri, Made Yuninda Rahmada, Alfin Ramadhani, Resvi Restu Anggoro S, Muhammad Ikhsan Setiawansyah Setiawansyah Simarmata, Yohanes Surono, Muhammad Tyas, Khoirunisa Cahyaning Ulum, Faruk Wijaya, Suhenda Yulian, Tri