Claim Missing Document
Check
Articles

RANCANG BANGUN APLIKASI MONITORING ALAT PEMBERI PAKAN IKAN OTOMATIS BERBASIS WEB MENGGUNAKAN PROTOKOL HYBRID WEBSOCKET DAN MQTT DENGAN METODE MODEL V Muhammad Al Fatih; Sartika Lina Mulani Sitio
Journal of Research and Publication Innovation Vol 3 No 4 (2025): OCTOBER
Publisher : Journal of Research and Publication Innovation

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

Abstract

Freshwater fish farm is one of the most profitable industrial sectors in Indonesia. With a tropical climate and high market demand, freshwater fish farm widely practiced by our community. However, technological advancements are still minimally applied in this sector. The development of a special device that can provide scheduled fish feeding and can be configured via a mobile application would greatly assist the operations of freshwater fish farmers in our country. This device can solve several problems in this sector including the number of human resources, negligence in feeding schedules, and errors in feed quantity. This research was conducted using methods of observation, literature study, and system design with the aim to designing and building an IoT-based (Internet of Things) feeder device. The system is integrated with the Arduino IoT Cloud service as a server for the application and device, allowing users to control the feeder device using the Arduino IoT Remote application available on smartphones. The feeder device is designed using Wemos D1 Mini ESP8288 as the microcontroller, HC-SR04 ultrasonic sensor to detect remaining feed in the feeder tube, relay module to control the motor, and synchronous motor to dispense the feed. The development of this tool is expected to contribute to the implementation of technological advancements in all industrial sectors in our country.
COMPARATIVE ANALYSIS OF BAGGING AND BOOSTING MODELS IN ENSEMBLE LEARNING FOR GRADUATION PREDICTION Sartika Lina Mulani Sitio; Darmawati; Yuda Samudra
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 3 (2026): JITK Issue February 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i3.7579

Abstract

Student graduation prediction is an important aspect in supporting academic decision-making in higher education. However, conventional evaluation approaches have not been able to identify the risk of early graduation delays. This study aims to compare the performance of two ensemble learning approaches, namely Bagging using Random Forest and Boosting using XGBoost, in predicting student graduation. The study used  the Predict Students' Dropout and Academic Success dataset  consisting of 4,424 student data. Both models were trained on the same data and evaluated using the Accuracy, Precision, Recall, F1-Score, and ROC-AUC metrics. The results of the experiment showed that both models had almost equal accuracy, i.e. 82.6% for Random Forest and 82.5% for XGBoost. However, XGBoost showed better performance on Recall (0.878) and F1-Score (0.834), which indicated a higher ability to detect students who actually graduated. Based on these results, this study concludes that XGBoost is more effective than Random Forest in the context of predicting student graduation and is more suitable to be applied to  the Academic Early Warning System in universities
Penerapan K-Means dalam Menganalisis Pola Pembelian Pelanggan Pada Data Transaksi E-Commerce Budi Apriyanto; Sartika Lina Mulani Sitio
bit-Tech Vol. 7 No. 3 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v7i3.2195

Abstract

Tujuan dari penelitian ini adalah untuk  menggunakan algoritma K-Means untuk memeriksa pola konsumen di lingkungan e-commerce. Di era digital saat ini, sangat penting untuk memiliki pemahaman yang mendalam tentang perilaku konsumen, yang membuat bisnis tetap kompetitif. Dengan menggunakan data transaksional yang mencakup faktor -faktor seperti harga akhir dan  diskon, konsumen konsumen penelitian ini  berdasarkan perilaku belanja mereka. Metode Elbow digunakan untuk mengidentifikasi jumlah kelompok yang paling tepat, yang merupakan langkah penting dalam analisis ini. Setelah menentukan jumlah cluster yang optimal dengan menggunakan algoritma K-Means  untuk mengenali berbagai segmen konsumen. K-Means adalah metode yang relatif sederhana dan mudah dipahami yang mencakup pilihan serangkaian centroid (titik tengah) dan pengelompokan data berdasarkan kedekatan centroid. Dengan mengelompokkan pelanggan ke dalam kelompok yang berbeda, K-means dapat membantu untuk mengidentifikasi pola pembelian yang jelas seperti preferensi produk, frekuensi pembelian, dan perilaku belanja. Hasil yang diperoleh menunjukkan bahwa kelompok yang berpendidikan dengan skor siluet 0,54 sangat terpisah dan jelas, menunjukkan bahwa ini menunjukkan kualitas kelompok yang baik. Temuan ini memberikan pemahaman yang berharga tentang perusahaan e-commerce dalam merancang strategi pemasaran yang efisien, mempersonalisasikan pengalaman bagi konsumen, dan memahami perilaku konsumen di pasar online. Oleh karena itu, penelitian ini tidak hanya berkontribusi pada literatur akademik, tetapi juga memberikan pengetahuan praktis yang dapat diterapkan pada strategi bisnis.
Rancang Bangun Aplikasi Manajemen Medical Record Pasien dengan Restful API: Optimalisasi Efisiensi dan Keamanan Data Klinik Bayu Fadlan Rosid; Sartika Lina Mulani Sitio
Journal of Artificial Intelligence and Innovative Applications (JOAIIA) Vol. 7 No. 1 (2026): February
Publisher : Teknik Informatika Universitas Pamulang

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

Abstract

Manual medical record management in many clinics often leads to various problems such as long queues, slow service, data loss risks, and limited information exchange among medical personnel. This study aims to design and develop a web-based medical record management application integrated with a RESTful API to enhance operational efficiency and data security in clinical environments. The development process includes requirements analysis, database and UML design, system implementation, and evaluation using Black Box Testing and the System Usability Scale (SUS). The results indicate that the system successfully streamlines patient registration, queue management, medical examinations, prescription processing, and inpatient services in a more structured and efficient manner. Black Box Testing confirms that all core features operate properly, while the SUS evaluation involving 15 respondents produced an average score of 71.5, categorized as “Acceptable”. Therefore, the proposed system is considered feasible for use and capable of improving data accuracy, service speed, and integrated information flow within the clinic.