Claim Missing Document
Check
Articles

Found 2 Documents
Search

SMALL ROAD MONITORING SYSTEM FOR FOUR WHEEL VEHICLES Solang, Efraim William; Suarjaya, I Made Agus Dwi; Pratama , I Putu Agus Eka
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 4 No. 1 (2023): Januari
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jimik.v4i1.139

Abstract

The application of the vehicle regulation system at intersections in rural areas does not yet have a good regulatory system compared to the vehicle control system in urban areas. The lack of equitable distribution of road widening in rural areas makes people often have problems accessing roads when using four-wheeled vehicles. People often experience problems when accessing small roads, especially when more than one vehicle passes at the same time. This problem was also experienced in DesaTanjung Sari, Kecamatan Cijeruk, Kabupaten Bogor. This study aims to design and build a small road monitoring system so that car drivers get a warning if there are four-wheeled vehicles that have passed the small road. The object recognition method used in the small road monitoring system for four-wheeled vehicles is the HC-SR04 ultrasonic sensor which is placed on the left, right, and top sides. Arduino Uno R3 microcontroller will be used as the main system device. The communication between points used is LoRa Ra-02 as the sender and receiver. The results of this study show the results of the system prototype running well in accordance with the planned functions.
Evaluasi Machine Learning untuk Prediksi Pembatalan Hotel dengan Threshold Adjustment dan Cost-Based Evaluation: Machine Learning Evaluation for Hotel Cancellation Prediction with Threshold Adjustment and Cost-Based Evaluation Solang, Efraim William; Adu, Franco Xander; Dharma, Agus; Gunantara, Nyoman
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 1 (2026): MALCOM January 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i1.2466

Abstract

Pembatalan pemesanan hotel merupakan permasalahan krusial yang berdampak langsung pada pendapatan dan perencanaan operasional. Penelitian ini mengevaluasi penerapan threshold adjustment dan cost-based evaluation untuk meningkatkan kualitas pengambilan keputusan bisnis. Penelitian ini melibatkan perbandingan beberapa jenis model machine learning menggunakan dataset hotel booking demand. Kinerja model dinilai menggunakan metrik F0.5-Score, precision, ROC AUC, dan pendekatan cost-based evaluation berbasis net revenue. Hasil penelitian menunjukkan bahwa Random Forest memberikan kinerja terbaik dengan F0.5-Score 0.8279, precision 0.878 dan ROC AUC 0.9165. Model lain seperti Logistic Regression (baseline) dengan F0.5-Score 0.7816, XGBoost dengan F-.5-Score 0.8108 dan ANN dengan F0.5-Score 0.8091 menunjukan performa lebih relatif lebih rendah, mengindikasikan bahwa dataset ini lebih cocok menggunakan pendekatan ensamble learning. Temuan penting mengungkapkan bahwa penyesuaian threshold berdasarkan F0.5-Score tidak selalu menghasilkan keuntungan ekonomi maksimum. Penggunaan threshold (0.52) terbukti menghasilkan nilai net revenue lebih tinggi dibandingkan threshold optimal berbasis F0.5-Score. Pendekatan ini diharapkan dapat meningkatkan kualitas pengambilan keputusan bisnis bagi manajer hotel dalam pengelolaan risiko finansial.