Claim Missing Document
Check
Articles

Found 3 Documents
Search

IMPLEMENTASI YOLOv11 UNTUK DETEKSI KATA BAHASA ISYARAT BISINDO DAN SIBI Ahmad Syaefudin; Hidayatus Sibyan; Rina Mahmudati; M. Fuat Asnawi; Nur Hasanah
Journal of Economic, Business and Engineering (JEBE) Vol. 7 No. 2 (2026): April
Publisher : Universitas Sains Al Qur'an

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32500/jebe.v7i2.11208

Abstract

Komunikasi merupakan hak dasar manusia, namun penyandang disabilitas rungu sering menghadapi hambatan dalam berinteraksi dengan masyarakat umum yang minim pemahaman bahasa isyarat. Penelitian ini bertujuan untuk mengimplementasikan dan mengevaluasi kinerja algoritma YOLOv11 dalam mendeteksi kata pada Bahasa Isyarat Indonesia (BISINDO) dan Sistem Isyarat Bahasa Indonesia (SIBI) secara real-time. Metode yang digunakan meliputi pengumpulan dataset sebanyak 1.745 citra yang mencakup 12 kelas kata, preprocessing menggunakan Roboflow untuk anotasi dan augmentasi, serta pelatihan model menggunakan Google Colab. Hasil penelitian menunjukkan bahwa model YOLOv11 mampu mendeteksi bahasa isyarat dengan sangat baik, mencapai nilai mean Average Precision (mAP@50) sebesar 98%, Precision 96.8%, dan Recall 96.4% pada tahap validasi. Implementasi sistem dilakukan berbasis web menggunakan framework Flask, memungkinkan deteksi interaktif melalui kamera. Secara keseluruhan, penelitian ini menunjukkan bahwa penerapan model YOLOv11 efektif dalam mendukung penerjemahan bahasa isyarat secara real-time. Implikasi dari penelitian ini adalah meningkatnya aksesibilitas komunikasi bagi penyandang disabilitas rungu, khususnya dalam interaksi sehari-hari dengan masyarakat umum, serta membuka peluang pengembangan sistem penerjemah bahasa isyarat yang lebih luas, adaptif, dan terintegrasi pada berbagai platform digital.
LSTM-Based Causal Attribution Modeling of the 2025 Sumatra Flash Flood Discourse on YouTube Kunti Najma Jalia; Adi Suwondo; Hidayatus Sibyan
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 10 No. 1 (2026)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v10i1.2132

Abstract

Existing disaster sentiment analysis mainly focuses on emotional polarity classification, while often over-looking the causal reasoning that shapes public discourse on responsibility for disaster outcomes. This study proposes and assesses a Long Short-Term Memory (LSTM)-based causal attribution classification framework to examine YouTube comments related to the 2025 Sumatra flash flood. It compares LSTM performance with Sup-port Vector Machine (SVM) and Naïve Bayes baselines. A total of 17,503 publicly available comments were collected through the YouTube Data API v3 and processed into a final dataset of 12,299 comments. The com-ments were classified into two causal categories, human factor and nature/prayer factor, using lexicon-based scoring validated by three independent annotators (Cohen's κ = 0.81). The experimental results show that LSTM achieves 98.17% accuracy with strong stability (±0.25% standard deviation) under stratified five-fold cross-validation, substantially outperforming SVM (82.83%) and Naïve Bayes (75.04%). These findings indi-cate that sequence-based architectures can capture the contextual dependencies in causal attribution dis-course, offering a replicable framework for disaster risk communication monitoring systems.
WBS-Pareto-ABC and CPI Model for Pre-Construction Cost Control of A-KRIS Hospital Building Endah Atika; Hermawan Hermawan; Hidayatus Sibyan
Journal of Infrastructure and Civil Engineering Vol. 6 No. 2 (2026)
Publisher : Program Studi Teknik Sipil Sekolah Tinggi Teknologi Pekanbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35583/jice.v6i2.195

Abstract

Pre-construction cost control in hospital ward completion projects requires a systematic approach capable of identifying cost concentration before construction begins because healthcare rehabilitation works involve complex interations among MEP-HVAC, sanitation, air-conditioning systems and functional building components. This study aims to develop a novel pre-construction cost control framework by integrating the Work Breakdown Structure (WBS), Pareto-ABC analysis, Area Cost Index (ACI) and a newly proposed Control Priority Index (CPI) for the A-KRIS Hospital Building completion project at RSUD Hj. Anna Lasmanah Banjarnegara. A quantitative descriptive case study was conducted through Bill of Quantity (BoQ) validation, WBS mapping, cost aggregation by work zone and sub-work, area cost index calculation, Pareto-ABC classification, and CPI formulation. The project cost was IDR 930,571,644 (including 11% VAT), with an area cost index of IDR 606,093/m2. Cost distribution was highly concentrated in Teratai Ward (60.18%) and Soka Ward (39.10%) accounted for 78.78% of the total project cost. The proposed CPI further differentiates priority among high-cost work items by integrating cost contribution, zone dominance, ABC classification, and optional technical risk, enabling more targeted prioritization of AHU isolation, air-conditioning, sanitation, piping, aluminium works and nurse station components. Unlike conventional Pareto-ABC analysis, which prioritizes work items solely based on cumulative cost, the proposed WBS-Pareto-ABC-CPI framework provides a structured decision-support model that links cost concentration with managerial control priorities during the pre-construction stage. The framework contributes to construction management by transforming conventional BoQ data into a practical and replicable tool for preventive cost, procurement, quality, schedule and safety control that can be applied tohospital rehabilitazion and other public-building projects.