Claim Missing Document
Check
Articles

Analisis Ketersediaan Stok Mata Uang Asing Terhadap Volume Kebutuhan Konsumen Menggunakan Metode K-Means: Studi Kasus : PT. Haji La Tunrung AMC Kota Makassar Muhammad Fuad; Mashur Razak; Imran Taufik
SemanTIK : Teknik Informasi Vol. 11 No. 1 (2025): Vol. 11 No. 1 (2025): SemanTIK Teknik Informasi
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55679/semantik.v11i1.104

Abstract

Penelitian ini bertujuan untuk menganalisis ketersediaan stok mata uang asing pada cabang PT. Haji La Tunrung AMC terhadap volume kebutuhan konsumen menggunakan metode K-Means. Penelitian didasarkan pada banyaknya kebutuhan mata uang asing untuk penukaran sehingga ada kelebihan dan kekurangan stok mata uang asing yang mengakibatkan penumpukan stok. Diperlukannya analisis data besar atas  ketersedian stok mata uang asing secara cepat dan akurat dalam memenuhi permintaan mata uang asing yang dibutuhkan. Peneliti menggunakan data primer dari PT Haji La Tunrung AMC periode 2019-2023  dengan akumulasi data terhadap penjualan 352.990 mata uang asing dan data sekunder dari literatur.  Terdapat hasil 5 klaster adalah yang terbaik berdasarkan Elbow Method dengan DBI terendah (0.2922) dan Silhouette Score tinggi (0.7913). Hasil ini menunjukan juga mata uang mana saja yang direkomendasi dengan skala preoritas sesuai kebutuhan stok, Cluster 0: "Kategori Tinggi" Cluster 1: "Kategori Menengah Tinggi" Cluster 2: "Kategori Menengah" Cluster 3: "Kategori Menengah Rendah" Cluster 4: "Kategori Rendah". This study aims to analyze the Availability of Foreign Currency Stock at PT. Haji La Tunrung AMC Branch Against the Volume of Consumer Needs Using the K-Means Method. The study is based on the large amount of foreign currency in circulation for exchange so that there is an excess and shortage of foreign currency stock which results in accumulation. It is necessary to analyze big data on the availability of Foreign Currency Stock quickly and accurately in meeting the demand for foreign currency needed. The researcher used primary data from PT Haji La Tunrung AMC for the period 2019-2023 with accumulated data on sales of 352,990 and secondary data from the literature. 5 clusters are the best based on the Elbow Method with the lowest DBI (0.2922) and high Silhouette Score (0.7913). These results also show which currencies are recommended with a priority scale according to stock needs, Cluster 0: "High Category" Cluster 1: "High Medium Category" Cluster 2: "Middle Category" Cluster 3: "Low Medium Category" Cluster 4: "Low Category".
Analysis of Cryptocurrency Candlestick Patterns using Gramian Angular Field and Hybrid Deep Learning Hasriadi Hasriadi; Mashur Razak; Abdul Jalil
SISTEMASI Vol 15, No 2 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i2.5883

Abstract

Cryptocurrency markets such as Bitcoin, Ethereum, and Solana exhibit high volatility, making price forecasting difficult when relying solely on conventional technical analysis. This study aims to analyze cryptocurrency candlestick patterns by utilizing Gramian Angular Field (GAF) representations and to evaluate the performance of a hybrid deep learning model combining CNN–LSTM–Transformer to support investment decision-making. The proposed method involves processing daily historical Open, High, Low, and Close (OHLC) data from three major cryptocurrency assets: Bitcoin (BTC-USD), Ethereum (ETH-USD), and Solana (SOL-USD), covering the period from January 1, 2020, to September 30, 2024, obtained from Yahoo Finance. The time-series data were transformed into 64×64 pixel GAF images and used to train a baseline CNN model as well as a hybrid CNN–LSTM–Transformer model. Model evaluation was conducted across multiple forecasting horizons, including 1 day, 7 days, 30 days, 180 days, and 1 year, and was further complemented by real-time testing using the CoinGecko API in March 2025. The results indicate that the hybrid model achieved the best performance at different horizons for each asset: BTC-USD at the 30-day horizon with an R² of 0.971 and an SMAPE of 0.77%, ETH-USD at the 1-year horizon with an R² of 0.948 and an SMAPE of 0.81%, and SOL-USD at the 1-year horizon with an R² of 0.910 and an SMAPE of 4.72%. Real-time testing demonstrated that the model consistently captured the overall price movement trends despite high market volatility. It can be concluded that the integration of GAF representations and the hybrid CNN–LSTM–Transformer model has strong potential to enhance cryptocurrency candlestick analysis and can be utilized as a component of a Decision Support System for digital asset investment.
Multimodal Sensor Evaluation for Fish Pond Water Quality Monitoring Zein Rifal; Syafruddin Syarif; Imran Taufik; Mashur Razak; Supriadi Sahibu; Respaty Namruddin
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12656

Abstract

Freshwater aquaculture requires continuous water quality monitoring because rapid changes in temperature, pH, dissolved oxygen, turbidity, total dissolved solids, and water level can affect fish health and pond productivity. This study evaluates a multimodal sensor system for real-time fish pond water quality monitoring and dashboard-based actuator control. The system integrates six sensors with Arduino Mega for signal acquisition, ESP32 for Wi-Fi communication, Firebase for cloud data storage and command exchange, and a Flutter dashboard for visualization and manual control. Field testing was conducted in two tilapia ponds with different initial conditions. Sensor performance was evaluated by comparing five measurable parameters with reference instruments using percentage error, accuracy, mean absolute error, and root mean square error, while turbidity was assessed through functional contrast testing and short-term stability because a turbidity reference instrument was unavailable. The average accuracy of the five validated parameters was 87.37% in pond 1 and 95.58% in pond 2. Temperature and water level showed the highest accuracy, above 98% in both ponds. Dissolved oxygen and total dissolved solids showed larger deviations, especially in pond 1, indicating sensitivity to field conditions and calibration stability. Actuator commands for the aerator and circulation pumps responded within 1-2 seconds under stable network conditions. The results show that the system is useful as a preliminary field-validated monitoring and semi-automatic control platform, but further work is required for long-term drift testing, turbidity validation using a commercial meter, and automatic control evaluation.
ANALISIS SENTIMEN KEBIJAKAN PPN 12% BERBASIS SEMI-SUPERVISED CNN Mochammad Asril Berlian Abdullah; Mashur Razak; Nasrullah Nasrullah
JURNAL INFORMATIKA DAN KOMPUTER Vol 10, No 2 (2026): Juni 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiko.v10i2.2676

Abstract

Penelitian ini bertujuan untuk menganalisis sentimen publik terhadap kebijakan Pajak Pertambahan Nilai (PPN) 12% menggunakan pendekatan deep learning berbasis Convolutional Neural Network (CNN) dengan skema semi-supervised learning. Permasalahan utama dalam penelitian ini adalah keterbatasan data berlabel, sehingga digunakan teknik pseudo-labeling untuk memanfaatkan data tidak berlabel. Tahapan penelitian meliputi pengumpulan data dari media sosial, pra-pemrosesan teks, pelabelan awal, serta pelatihan model CNN. Evaluasi dilakukan menggunakan confusion matrix dengan metrik accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model yang diusulkan mampu mengklasifikasikan sentimen dengan baik dan menghasilkan distribusi sentimen yang didominasi oleh sentimen negatif. Selain itu, pendekatan semi-supervised learning terbukti meningkatkan performa model melalui pemanfaatan data tidak berlabel.
Pengembangan Ekowisata Berbasis Konservasi Lingkungan dan Ekonomi Sirkular Zainal Abidin; Mashur Razak; Ahmad Firman; Muhammad Idris; Fitriani Latief; Pierre Johnson
CARADDE: Jurnal Pengabdian Kepada Masyarakat Vol. 9 No. 1 (2026): Agustus
Publisher : Ilin Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31960/caradde.v9i1.3320

Abstract

Sustainable tourism development is an important strategy for addressing environmental challenges in tourist destinations. This community service activity aims to develop a circular economy–based ecotourism model through strengthening community waste bank institutions in the Rammang-Rammang tourism area. The main problems faced by partners are suboptimal waste management and the limited integration of tourism activities with environmental conservation. The implementation method uses a Participatory Action Research approach which includes socialization, waste management training, and institutional mentoring. The activity was carried out in November 2025 involving international speakers and local educators. The results show an increase in community understanding of zero waste tourism, the formation of community commitment to waste bank management, and practical training in the use of composters for organic waste. This program is expected to support community economic independence through recycled products while maintaining the sustainability of the Rammang-Rammang karst ecosystem.
Co-Authors ABDUL JALIL Abdul Jalil Abdul Latief Arda Abdul Wahab Achmad Gani achmadi achmadi achmadi Agunawan, Agunawan Ahmad Firman Amir Amir Andi Indriapati Andi Muhammad Ridwan ANITHA NITA TAHIR Anshar, Muh. Ashary Arwien, Riswin Arwien Asri Asri Astik Martini Martini Badaruddin Bambang Suharnanto Barhaman Barhaman Djalante, Andi Djasim, A. Kachsyfur Fatmasari Fatmasari Fatmasari Fatmasari Fatmawati Fatmawati Fiqri Haikal Gusti, Didiek Handayani Haedar Dahing Haeruddin Harlinda Harniati Arfan Harlindah Harniati Harun, Rusni Haryono, Didi Hasriadi Hasriadi Hazriani, Hazriani Hengky Yasing Ibnu Munzier Hasri Gani Imran Taufik Japaruddin Japaruddin Jeni Kamase Kamaluddin, La Ode Amijaya Kartini Jafar Khaeriah Khaeriah Khaerullah H Khaerullah H Khaerullah H, Khaerullah H Latief, Fitriani Lili Handayani, Lili M. Ihsan Indra Jaya Maryanita, Maryanita Masdar J Pratama Maslim Maslim, Maslim Megawaty, Megawaty Mochammad Asril Berlian Abdullah Mudinillah, Adam Muh. Ashary Anshar Muhammad Amin Muhammad Fuad Muhammad Hdayatullah Rahman Muhammad Hidayat Muhammad Hidayat Muhammad Hidayat Muhammad Idris Muhammad Rizal Mukhtar Hamzah Muliana Muliana Mulyawan Amin Nadya Utari Gunawan Nasrullah Nur Ainun Alwi Nur Baya Nur, Sadikah Nuraeni Nuraeni Nurbayati Nurbayati Nurjannah Nurjannah Pierre Johnson Qadri, Khaerul Rabi’a H Maudjik Rahmat Saleh Rahmawaty, Ika Respaty Namruddin risman Umar Rosnaini Daga Safirah Syihab Sahibu, Supriadi Salam, Erick Sarial Budi Saripuddin D Sry Devianty Subriah Subriah Suharnanto, Bambang Suharnanto, Bambang Sujatmiko Sujatmiko Supriadi Sahibu Surianti Surianti Surianto Surianto Sutiara, Sutiara Syafruddin Syarif Syamsul Alam Syarifuddin Syarifuddin Yusnani Yunus YUSRI YUNUS Yuyun Zainal Abidin Zainuddin Mustapa Zein Rifal