Claim Missing Document
Check
Articles

Found 24 Documents
Search

IoT-Based Innovative Irrigation System for Chili Using Telegram Bot and Web Dashboard Zulfa Fahrunnisa; Arizal Mujibtamala Nanda Imron; Inta Nurkhaliza Agiska; Wahyu Muldayani; Gamma Aditya Rahardi; Candra Putri Rizkiyah Ramadhani
Journal of Applied Electrical Engineering Vol. 10 No. 1 (2026): JAEE, June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaee.v10i1.12251

Abstract

Chili cultivation requires timely irrigation to maintain soil moisture, yet manual watering is inefficient and difficult to supervise remotely. This paper proposes an IoT-based irrigation system integrating a Telegram bot and a web dashboard for real-time monitoring and control. A soil-moisture sensor provides input to an ESP32 microcontroller, which drives a relay-operated pump using a threshold rule (ON when moisture <30%) and supports manual override via Telegram commands. Sensor readings are logged to Firebase and visualized on a Flask-based dashboard, which features moisture trend graphs. Telegram delivers notifications and supports command-based interaction. Experiments demonstrate an average accuracy of 98,57% and precision of 99,93% compared to a reference meter. End-to-end tests confirm a 0% delivery error, a Telegram notification latency of 1,0–1,8 seconds, and a pump response time of 5,3–5,9 seconds, demonstrating effective automation with practical remote supervision.
Dynamic Thermofluid Study of Petrodiesel Droplet Combustion with Variations of Kesambi Biodiesel Composition Accompanied with TiO₂ Catalyst Dani Hari Tunggal Prasetiyo; Nasrul Ilminnafik; Audiananti Meganandi Kartini; Gamma Aditya Rahardi; Alief Muhammad
Jurnal Keteknikan Pertanian Vol. 13 No. 3 (2025): Jurnal Keteknikan Pertanian
Publisher : PERTETA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19028/jtep.013.3.462-480

Abstract

Meningkatnya permintaan energi global mendorong pengembangan bahan bakar alternatif berkelanjutan dengan karakteristik pembakaran yang kompetitif terhadap petrodiesel. Penelitian ini mengkaji fenomena termofluida dinamis pembakaran droplet campuran petrodiesel dan biodiesel minyak kesambi, baik tanpa maupun dengan penambahan katalis nanopartikel TiO₂ 100 ppm. Komposisi sampel bahan bakar yang digunakan terdiri dari B0, B10, B20, B30, B40, dan B100, serta masing-masing komposisi dengan penambahan TiO₂. Parameter yang dianalisis meliputi penundaan penyalaan, durasi pembakaran, tinggi nyala api, suhu optimal, dan visualisasi nyala api. Hasil penelitian menunjukkan bahwa peningkatan fraksi biodiesel menghasilkan durasi pembakaran yang lebih lama hingga 6,83 detik pada B100 dan penurunan suhu puncak sebesar 734,76°C, dibandingkan dengan B0 yang memiliki durasi pembakaran selama 3,22 detik dan suhu puncak sebesar 794,54°C. Penambahan TiO₂ secara konsisten meningkatkan kinerja pembakaran, ditunjukkan oleh suhu puncak yang lebih tinggi hingga 821,76°C pada B0+TiO₂, penundaan pengapian yang lebih singkat, dan nyala api yang lebih stabil. Tinggi nyala api tertinggi teramati pada B0+TiO2 sebesar 53,79 mm dan terendah pada B100 sebesar 40,87 mm. Selain itu, penundaan pengapian tertinggi terjadi pada komposisi B100 sebesar 7,95 detik, sementara terendah terjadi pada komposisi B0+TiO2 sebesar 1,65 detik. Hal ini menunjukkan adanya hubungan antara komposisi bahan bakar dan intensitas pembakaran.
A Multivariate LSTM Approach for Monthly Rice Production Forecasting in East Java Hasanur Mohammad Firdausi; Satryo Budi Utomo; Gamma Aditya Rahardi; Dani Hari Tunggal Prasetiyo
Jurnal Sistem Cerdas Vol. 8 No. 3 (2025)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v8i3.595

Abstract

Accurate forecasting of rice output is essential for improving regional food security planning, particularly in East Java Province, which serves as a major national rice granary. This study develops a Long Short-Term Memory (LSTM) model to predict rice production using monthly data on production and harvested area from 2018 to 2024. The methodology includes data preprocessing, normalization, sequence construction with a sliding window, training of a multivariate LSTM model, and performance evaluation using mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE). Results show that the LSTM model achieves superior predictive accuracy, with an MAE of 95,030.16, RMSE of 120,229.01, and MAPE of 16.64%, significantly outperforming baseline Moving Average and Linear Regression models. While the model effectively captures seasonal production trends, some inaccuracies remain during periods of anomalous production values. These findings suggest that the LSTM model is effective for projecting rice production and may provide a foundation for early warning systems and regional food distribution strategies. Further improvements could be realized by integrating climate variables or adopting a hybrid model architecture to enhance predictive precision.
Pelatihan dan Pendampingan Pemasaran UMKM Rengginang Singkong Berbasis Artificial Intelligence di Desa Banasare Hasanur Mohammad Firdausi; Moh Taufik; Achmad Faqih; Imam Anas Mubarok; Siti Sa’Adah; Nurul Hidayat; Bambang Sri Kaloko; Gamma Aditya Rahardi; Dani Hari Tunggal Prasetiyo
TEKIBA : Jurnal Teknologi dan Pengabdian Masyarakat Vol. 6 No. 3 (2026): TEKIBA : Jurnal Teknologi dan Pengabdian Masyarakat (September)
Publisher : Fakultas Teknik, Universitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/tekiba.v6i3.7605

Abstract

This community service program aims to improve the marketing performance of a cassava rengginang micro, small, and medium enterprise (MSME) located in Banasare Village, Rubaru District, which faces limitations in digital marketing capabilities and has not yet utilized artificial intelligence (AI) technology. The partner MSME relies on conventional marketing methods, resulting in limited market reach and low promotional effectiveness. The method employed in this program integrates structured training with hands-on assistance in the implementation of artificial intelligence for marketing purposes. The stages include partner needs analysis through observation and interviews, AI-based marketing training focusing on content creation, direct assistance in applying AI to digital marketing and customer services, and evaluation through a comparison of conditions before and after the program. The results indicate a significant improvement in the partner’s capacity to utilize AI for marketing activities. After participating in the program, the MSME was able to independently create structured digital promotional content using AI tools and implement simple chatbot-based customer service. These changes contributed to more effective promotion, improved service efficiency, and broader market reach compared to the initial condition. The outputs of this community service activity include increased digital marketing skills of the partner MSME, the adoption of AI-based marketing practices, and the development of a replicable training and assistance model suitable for traditional food MSMEs in rural areas. This program demonstrates that artificial intelligence can be applied in a simple and practical manner to support the digital transformation and competitiveness of rural MSMEs.