Claim Missing Document
Check
Articles

Found 9 Documents
Search

IMPLEMENTASI ALGORITMA DECISION TREE UNTUK KLASIFIKASI DATA PESERTA DIDIK Sutoyo, Imam
Jurnal Pilar Nusa Mandiri Vol 14 No 2 (2018): Pilar Nusa Mandiri : Journal of Computing and Information System Periode Septemb
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1037.935 KB) | DOI: 10.33480/pilar.v14i2.70

Abstract

Klasifikasi peserta didik bertujuan untuk mengelompokkan peserta program pendidikan agar kegiatan pembelajaran dapat disesuaikan dengan kelompok-kelompok tersebut. Metode tradisional untuk melaksanakan klasifikasi ini adalah dengan mengurutkan peserta didik menggunakan satu atribut, yaitu nilai akhir mereka kemudian membagi mereka berdasarkan ukuran tertentu. Metode yang lebih baik adalah dengan menggunakan algoritma Data Mining yang mampu menggunakan lebih dari satu atribut. Pada penelitian ini, algoritma Decision Tree digunakan untuk melaksanakan klasifikasi. Metodologi yang digunakan adalah CRISP-DM. Algoritma Decision Tree yang diujicoba adalah C4.5 dan Random Forest. Validasi dilaksanakan menggunakan 10-Fold Cross Validation untuk dicari algoritma yang memberikan akurasi paling tinggi. Berdasarkan percobaan, didapatkan hasil bahwasanya Decission Tree C.45 memberikan hasil terbaik dengan akurasi 96,73 %. Oleh karena itu, pada tahap Deployment dari metodologi CRISP-DM, model dan rule dari C4.5 digunakan untuk membuat aplikasi untuk klasifikasi ini.
Perancangan Sistem Informasi Input Nilai Santri Dengan Fitur Pengawasan Menggunakan Model Prototype Sutoyo, Imam
IJCIT (Indonesian Journal on Computer and Information Technology) Vol 5, No 2 (2020): November 2020
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (907.517 KB) | DOI: 10.31294/ijcit.v5i2.7640

Abstract

Kegiatan pengolahan nilai merupakan kegiatan rutin yang dilaksanakan oleh semua lembaga pendidikan tidak terkecuali pada lembaga pendidikan berbasis pesantren. Pengolahan nilai yang masih menggunakan prosedur-prosedur manual mengalami banyak kendala. Oleh karena itu, diperlukan sistem informasi berbasis komputer untuk mengatasi kendala-kendala tersebut. Penelitian ini bertujuan untuk mengembangkan sistem informasi input nilai menggunakan metode Evolutionary Process Flow dengan model prototype dan Unified Modelling Language untuk rancangannya. Hasil dari penelitian ini adalah sistem informasi input nilai yang dapat diterapkan pada lembaga pendidikan terutama yang berbasis pesantren untuk meningkatkan efektifitas dan efisiensi dari kegiatan input nilai.Students grading activities are routine activities carried out by every educational institution, including Islamic boarding school educational institution. These activities that only using manual procedures experience many obstacles. Therefore, a computer-based information system is needed to overcome these obstacles. This study aims to develop a student score input information system using the Evolutionary Process Flow method with a prototype model and Unified Modeling Language for the design. The results of this study are information systems that can be applied to educational institutions especially those based on Islamic boarding school to increase the effectiveness and efficiency of these activities.
Prediksi dan Pencegahan Risiko Burnout pada Pekerja Fleksibel Menggunakan Algoritma Random Forest Fauziah Mk, Noha Noor; Hakim, Dimas Lukman; Cahyani, Ainun; Sariasih, Findi Ayu; Rakhmah, Syifa Nur; Sutoyo, Imam
Jurnal Sains dan Teknologi Informasi Vol 5 No 1 (2025): Desember 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jussi.v5i1.8937

Abstract

Flexible workers operating under remote, hybrid, and freelance schemes face burnout risks that are difficult to detect early due to irregular work patterns and blurred work-time boundaries. Conventional burnout monitoring relying on manual surveys is static and lacks sensitivity to the dynamics of workers' psychological changes. This study aims to develop a machine learning-based burnout prediction system for flexible workers capable of providing real-time risk predictions accompanied by personalized prevention recommendations. The method employed is Random Forest Classifier using a dataset from Kaggle titled "Mental Health & Burnout in the Workplace" encompassing 5.000 observations. System development follows the Agile approach and is implemented through a Streamlit-based web application. Preprocessing stages include binary label transformation, data leakage elimination, one-hot encoding, class imbalance handling using SMOTE, and stratified split with a 90:10 ratio. The Random Forest model is configured with 800 trees, max_depth of 20, and other optimal hyperparameters. Evaluation results demonstrate that the model achieves 87% accuracy with precision of 0.89, recall of 0.91, and F1-score of 0.90 for the burnout class. Feature importance analysis identifies CareerGrowthScore, StressLevel, and ProductivityScore as dominant factors. The system provides real-time predictions with latency <2 seconds and prevention recommendations tailored to individual risk profiles. This research contributes a practical solution for self-monitoring mental health among flexible workers and provides organizations with an instrument for monitoring remote workforce well-being. Black-box testing validates that all functionalities operate according to specifications.
Penerapan Algoritma Machine Learning Random Forest untuk Prediksi Risiko Konversi Sindrom Terisolasi Klinis Menjadi Multiple Sclerosis Ripaldi, Riki; Tambunan, Leonardo Sebastian; Edowardo, Samuel; Rahkmah, Syifa Nur; Sutoyo, Imam; Sariasih, Findi Ayu
Journal Global Technology Computer Vol 5 No 1 (2025): Desember 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jogtc.v5i1.8847

Abstract

Clinically Isolated Syndrome (CIS) is an initial neurological episode potentially developing into Multiple Sclerosis (MS), a chronic neurodegenerative disorder of the central nervous system. Early detection of risk factors for CIS to MS conversion is crucial for supporting timely medical interventions and slowing down disease progression. This study aims to develop a risk prediction model for CIS to MS conversion using a Machine Learning algorithm, comprehensively evaluate the model's performance, and implement it as a web-based clinical decision support system. The research employs a machine learning approach utilizing the Random Forest Classifier to predict the conversion risk using the public dataset Conversion Predictors of CIS to Multiple Sclerosis. The dataset comprises 273 patients with clinical variables including demographics, initial symptom characteristics, Magnetic Resonance Imaging (MRI) findings across various brain regions and the spinal cord, and Oligoclonal Bands (OCB) test results. The methodology involved addressing class imbalance using weight adjustments, cross-validation, and implementing a custom threshold of 0.57 to minimize false positives, ensuring clinical diagnostic safety. Test results demonstrate that the Random Forest model achieved optimal performance with an Accuracy of 81.82%, an F1-Score of 0.82, and an Area Under the Curve (AUC) of 0.9140, indicating excellent discriminative capability. Feature Importance analysis revealed that Oligoclonal Bands (OCB), Initial Symptoms (specifically sensory and visual disturbances), and MRI lesions (especially Periventricular) are the most influential predictors. The model is subsequently implemented into a web-based prediction system to facilitate interactive risk assessment by medical professionals. This implementation serves as an accurate and explainable prototype of a Clinical Decision Support System.
Prediksi Risiko Kesehatan Bayi Berbasis Parameter Tumbuh Kembang dengan Menggunakan Gradient Boosting Hulu, Astatia; Aimar, Juan Sebastian; Nabilah, Firyal Aufa; Rakhmah, Syifa Nur; Sariasih, Findi Ayu; Sutoyo, Imam
Informatics and Computer Engineering Journal Vol 6 No 1 (2026): Periode Februari 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat (LPPM) Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/icej.v6i1.11066

Abstract

Kesehatan bayi merupakan indikator penting kualitas generasi masa depan, namun deteksi dini risiko kesehatan sering terkendala keterbatasan tenaga medis dan sistem pemantauan efektif. Penelitian ini mengembangkan sistem prediksi risiko kesehatan bayi berusia 0-30 hari menggunakan algoritma Gradient Boosting berdasarkan parameter tumbuh kembang. Metode pengembangan sistem menggunakan Agile Scrum dengan dataset "Infant Wellness and Risk Evaluation" yang melalui tahap pra-pemrosesan data dan feature engineering. Hasil evaluasi menunjukkan model mencapai akurasi 94%, recall 84% untuk kelas berisiko, dan precision 71%. Analisis feature importance mengidentifikasi age_days, oxygen_saturation, dan heart_rate_zscore sebagai fitur paling berpengaruh. Sistem prediksi berbasis web yang dihasilkan ini nantinya diharapkan dapat menjadi alat bantu yang efektif bagi tenaga medis. Infant health is an important indicator of future generation quality, but early detection of health risks is often constrained by limitations of medical personnel and effective monitoring systems. This research develops a health risk prediction system for infants aged 0-30 days using Gradient Boosting algorithm based on growth and development parameters. The system development method uses Agile Scrum with "Infant Wellness and Risk Evaluation" dataset through data preprocessing and feature engineering stages. Evaluation results show the model achieves 94% accuracy, 84% recall for at-risk class, and 71% precision. Feature importance analysis identifies age_days, oxygen_saturation, and heart_rate_zscore as the most influential features. The resulting web-based system has potential as an effective assistance tool for medical personnel.  
SISTEM REKOMENDASI MAKANAN MULTI – KRITERIA UNTUK KONSUMEN DENGAN ANGGARAN TERBATAS MENGGUNAKAN ALGORITMA CONTENT BASED FILTERING Azhar, Raniah; Shidqin, Dhuha Shobiyan; Prakoso, Azzam Ade; Rakhmah, Syifa Nur; Sariasih, Findi Ayu; Sutoyo, Imam
JTIK (Jurnal Teknik Informatika Kaputama) Vol. 10 No. 1 (2026): Volume 10, Nomor 1, Januari 2026
Publisher : STMIK KAPUTAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59697/jtik.v10i1.1186

Abstract

ABSTRACTThe primary challenge in current digital recommendation services is aligning product quality with the economic constraints of the user. This study focuses on the development and implementation of a Food Recommendation System operating on Multi-Criteria, namely Maximum Budget (Price) and Quality (Predicted Rating). The methodology applied is Content-Based Filtering, where the system analyzes nutritional content data and the estimated ingredient cost of each menu to determine the level of compatibility with the user’s preference profile. The processing flow begins with receiving a price limit set by the consumer, followed by a strict filtering phase to exclude menus outside the budget, and subsequently ranking the qualified menus based on the quality score generated by a Machine Learning model. This implementation successfully delivers ordered and cost-efficient menu recommendations, demonstrating its high potential as an effective assistant in supporting food purchasing decisions for consumers facing financial limitations.Keywords: Recommendation System, Multi-Criteria, Budget Constraint, Content-Based Filtering, Predicted Rating.
Pengembangan Aplikasi Kecerdasan Buatan Untuk Analisis Pasar Produk Online Dan Rekomendasi Peluang Usaha Mesta; Febrian K, Felix; Afya Rachman, Rafi; Nur Rakhmah, Syifa; Sutoyo, Imam; Ayu Sariasih, Findi
Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI) Vol. 4 No. 3 (2026): Februari 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i3.685

Abstract

Calon wirausaha kerap menemui kesulitan dalam menganalisis produk pasar daring yang jumlahnya sangat banyak. Aplikasi yang berfungsi untuk menganalisis berbagai produk dari berbagai lokapasar daring Indonesia menjadi tujuan dari hasil penelitian ini. Rekomendasi produk untuk dijual kembali sebagai peluang usaha dibuat sebagai salah satu fitur aplikasi selain dari fitur analisis produk lokapasar daring. Penelitian ini menerapkan metode agile dengan pendekatan siklus pengembangan Extreme Programming (XP) dengan tahapan yang berulang dan efisien. Pengembangan aplikasi melibatkan beberapa kerangka kerja diantaranya Flutter untuk mengembangkan antarmuka pengguna, Python yang berfungsi mengolah data dengan algoritma Random Forest untuk menetapkan hasil analisis, dan SerpApi yaitu pihak ketiga yang menyediakan himpunan data yang diperlukan untuk analisis. Pengujian aplikasi dilakukan pada tahap listening pada siklus metode XP, pengujian dilakukan berulang sampai memenuhi kebutuhan pengguna. Kelebihan aplikasi terletak pada singkatnya waktu yang didapat saat ingin menganalisis suatu kata kunci produk. Aplikasi ini membantu calon wirausahawan menganalisis pasar daring secara cepat, meskipun hasil analisis tetap memerlukan verifikasi riset lanjutan.
SISTEM CERDAS BERBASIS MACHINE LEARNING UNTUK DIAGNOSIS PENYAKIT PADA KUCING Setiawan, Ade; Silap, Renatan Hosea; Fahrezi, Rio; Nur Rakhmah, Syifa; Ayu Sariasih, Findi; Sutoyo, Imam
Informasi Interaktif : Jurnal Informatika dan Teknologi Informasi Vol 11 No 1 (2026): Bahasa Indonesia
Publisher : Program Studi Informatika Fakultas Teknik Universitas Janabadra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The challenge of diagnosing cat diseases quickly and accurately, caused by the tendency of cats to hide pain and often non-specific clinical symptoms, forms the primary background of this research. This study aims to design and build an intelligent system based on machine learning that can provide initial diagnostic recommendations for common cat diseases based on symptom data. The research method used adopts the Agile Scrum framework , with the K-Nearest Neighbor (KNN) algorithm as the classification core. System testing was conducted on 200 test data points covering five main diseases: Cat Flu, Worms, Fungal Infection, Rabies, and Diarrhea. The test results showed excellent performance with an average accuracy rate of 92.50%. Specifically, the system successfully classified 185 data points correctly and 15 incorrectly , with Rabies recording the highest accuracy (96.67%). Although there is still an error rate of 7.5% , this system is proven feasible for use as an initial diagnostic aid; however, its use must still be supported by direct confirmation from a professional veterinarian.
Sistem Rekomendasi Destinasi Wisata Menggunakan Content-Based Filtering dan Analisis Fitur Geospasial Widika, Arya; Susilo, Putri Salsabila; Ramadhan, Andhika Ibnu; Rakhmah, Syifa Nur; Sariasih, Findi Ayu; Sutoyo, Imam
Informasi Interaktif : Jurnal Informatika dan Teknologi Informasi Vol 11 No 1 (2026): Bahasa Indonesia
Publisher : Program Studi Informatika Fakultas Teknik Universitas Janabadra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study develops a tourism destination recommendation system based on Content-Based Filtering integrated with geospatial feature analysis to enhance the relevance and contextual accuracy of recommendations for users. The system addresses the limitations of existing tourism recommendation platforms that primarily focus on popularity and ratings without considering users’ location proximity and personal preferences. The dataset used in this research originates from Tourism in Indonesia (Kaggle), focusing on the Jakarta and Bandung regions. Text features are extracted using the Term Frequency–Inverse Document Frequency (TF-IDF) method, while the similarity between destinations is measured using Cosine Similarity. Additionally, geographic distances are analyzed through the Haversine formula to strengthen the spatial context of the recommendations. The system was developed using the Agile (Scrum) methodology to ensure an iterative and adaptive development process aligned with user needs. Evaluation results indicate strong system performance, achieving a Precision of 0.63, Recall of 0.90, and an F1-Score of 0.73. These findings demonstrate that integrating content-based and spatial analysis approaches effectively improves the accuracy and personalization of tourism recommendations based on users’ preferences and location context.