http://repository.ipb.ac.id/handle/123456789/151265 Wed, 12 Aug 2026 23:55:26 GMT 2026-08-12T23:55:26Z http://repository.ipb.ac.id/handle/123456789/178473 Implementasi IoT untuk Pemantauan pH dan Suhu Air dalam Analisis Pertumbuhan Ikan Nila pada Akuaponik Dwiputra, Dhimas Agung Kualitas air, terutama pH dan suhu, sangat menentukan keberhasilan budi daya ikan nila (Oreochromis niloticus) pada sistem akuaponik, sedangkan pemantauan manual berfrekuensi terbatas sehingga kurang responsif terhadap perubahan kondisi air. Penelitian ini merancang sistem Internet of Things (IoT) untuk memantau pH dan suhu air secara real-time, membandingkan efektivitasnya dengan sistem konvensional, serta menganalisis hubungan kedua parameter terhadap pertumbuhan ikan nila. Sistem dibangun menggunakan ESP32, sensor pH DFRobot v1.1 dan DS18B20, basis data Supabase, notifikasi Telegram, LCD, dan dashboard web. Evaluasi kinerja sistem menunjukkan delay transmisi data sebesar 7-10 detik dan kemampuan pemulihan koneksi otomatis dalam 20-30 detik. Hasil kalibrasi menunjukkan kedua sensor sangat valid, dan sistem IoT memantau kualitas air lebih kontinu serta, pada kondisi pengamatan ini, menunjukkan capaian pertumbuhan, kelangsungan hidup, dan kepatuhan kualitas air yang lebih baik daripada sistem konvensional. Sistem ini diharapkan membantu pembudidaya menjaga kestabilan kualitas air untuk mendukung pertumbuhan ikan nila; Water quality, especially pH and temperature, strongly determines the success of Nile tilapia (Oreochromis niloticus) cultivation in aquaponic systems, whereas manual monitoring is infrequent and less responsive to changing water conditions. This study designed an Internet of Things (IoT) system to monitor water pH and temperature in real time, to compare its effectiveness with the conventional system, and to analyze their relationship with tilapia growth. The system was built using an ESP32, DFRobot pH v1.1 and DS18B20 sensors, a Supabase database, Telegram notifications, an LCD, and a web dashboard. System performance evaluation showed a data transmission delay of 7-10 seconds and an automatic connection recovery capability within 20-30 seconds. Calibration showed that both sensors were highly valid, and, under the observed conditions, the IoT system provided more continuous water quality monitoring and showed better growth, survival, and water quality compliance than the conventional system. This system is expected to help farmers maintain stable water quality to support Nile tilapia growth. Thu, 01 Jan 2026 00:00:00 GMT http://repository.ipb.ac.id/handle/123456789/178473 2026-01-01T00:00:00Z http://repository.ipb.ac.id/handle/123456789/178467 Pembangunan Sistem Keamanan Parkir Berbasis YOLOv8 Melalui Integrasi ESP32-CAM dan Notifikasi Telegram islam, Fatahillah saiful Penelitian ini membangun prototipe sistem keamanan parkir berbasis visi komputer dengan ESP32-CAM sebagai sumber video, YOLOv8s sebagai model deteksi kendaraan roda dua, server sebagai pusat pemrosesan, dashboard web sebagai antarmuka, serta Telegram Bot sebagai kanal notifikasi. Dataset terdiri atas 6.678 citra satu kelas Motorcycle yang dibagi menjadi 5.480 citra latih, 813 citra validasi, dan 385 citra uji. Model dilatih dari bobot YOLOv8s.pt dengan ukuran input 960 piksel dan batch size 24. Evaluasi validation set pada epoch ke-65 menghasilkan Precision 95,55%, Recall 83,11%, F1-Score 88,89%, mAP@0.5 sebesar 92,03%, dan mAP@0.5:0.95 sebesar 67,52%. Sistem mampu menerima stream kamera, mendeteksi dan melacak kendaraan, memeriksa posisi terhadap Region of Interest, mencatat event, menampilkan riwayat, mengekspor data, serta mengirimkan notifikasi missing dan removed. Integrasi sistem telah berjalan sebagai prototipe pemantauan parkir, dengan keterbatasan pada cakupan verifikasi lapangan dan kondisi pencahayaan rendah.; This study developed a computer-vision-based parking security prototype using an ESP32-CAM as the video source, YOLOv8s as the motorcycle detection model, a server as the processing center, a web dashboard as the interface, and a Telegram Bot as the notification channel. The dataset contained 6,678 images of one Motorcycle class, consisting of 5,480 training, 813 validation, and 385 test images. The model was trained from YOLOv8s.pt weights with a 960-pixel input and a batch size of 24. Validation at epoch 65 yielded 95.55% precision, 83.11% recall, an F1-score of 88.89%, mAP@0.5 of 92.03%, and mAP@0.5:0.95 of 67.52%. The system received the camera stream, detected and tracked motorcycles, checked a Region of Interest, recorded events, displayed histories, exported data, and sent missing and removed notifications. The integration functioned as a parking monitoring prototype, with limitations related to field verification coverage and low-light conditions. Thu, 01 Jan 2026 00:00:00 GMT http://repository.ipb.ac.id/handle/123456789/178467 2026-01-01T00:00:00Z http://repository.ipb.ac.id/handle/123456789/178381 Analisis Kinerja Distribusi Air Berdasarkan Akurasi Volume dan Kestabilan Tekanan pada Sistem Irigasi Presisi Berbasis IoT Septrian, Rendi Ketersediaan air adalah faktor krusial dalam pertanian, namun ketersediaannya semakin terbatas. Praktik irigasi konvensional di Indonesia umumnya tidak efisien dan boros air. Konsep irigasi presisi berbasis Internet of Things (IoT) hadir sebagai solusi, namun sistem yang ada saat ini kebanyakan masih fokus memantau kelembapan tanah. Aspek kinerja distribusi air, seperti kestabilan tekanan dan volume aktual yang keluar, justru belum banyak dievaluasi. Padahal, tekanan yang tidak stabil dapat memicu masalah teknis seperti kebocoran atau penyumbatan. Penelitian ini bertujuan merancang dan menganalisis kinerja distribusi sistem irigasi presisi berbasis mikrokontroler ESP32 yang mengintegrasikan flow sensor YF-B1 (pengukur debit/volume) dan pressure transducer 0–1 MPa (pemantau tekanan) secara real-time. Arsitektur perangkat lunak dibangun menggunakan protokol MQTT untuk transmisi data, Node.js sebagai server, MySQL sebagai database, dan React.js sebagai dashboard monitoring interaktif. Kinerja sistem dievaluasi menggunakan tiga parameter utama: akurasi volume (dianalisis dengan MAPE), kestabilan tekanan (dianalisis dengan SD dan CV), serta kemampuan deteksi anomali. Diharapkan model ini dapat menyediakan data kuantitatif yang valid mengenai akurasi dan kestabilan distribusi air serta menjadi acuan dalam penerapan smart farming di Indonesia.; Water availability is a crucial factor in agriculture, yet its availability is increasingly limited. Conventional irrigation practices in Indonesia are generally inefficient and wasteful. The concept of precision irrigation based on the Internet of Things (IoT) has emerged as a solution, but most existing systems still focus on monitoring soil moisture. Water distribution performance aspects, such as pressure stability and actual volume discharged, have not been widely evaluated. However, unstable pressure can trigger technical problems like leaks or blockages. This study aims to design and analyze the distribution performance of a precision irrigation system based on an ESP32 microcontroller that integrates a YF-B1 flow sensor (to measure flow rate/volume) and a 0–1 MPa pressure transducer (to monitor water pressure) in real-time. The software architecture is built using the MQTT protocol for data transmission, Node.js as a server, MySQL as a database, and React.js as an interactive monitoring dashboard. System performance is evaluated using three main parameters: volume accuracy (analyzed with MAPE), pressure stability (analyzed with SD and CV), and anomaly detection capabilities. It is expected that this model can provide valid quantitative data on water distribution accuracy and stability and serve as a reference for the implementation of smart farming in Indonesia. Thu, 01 Jan 2026 00:00:00 GMT http://repository.ipb.ac.id/handle/123456789/178381 2026-01-01T00:00:00Z http://repository.ipb.ac.id/handle/123456789/178369 Rancang Bangun Sensor Anemometer Berbiaya Rendah Berbasis Sensor Efek Hall dengan Integrasi IoT Putra, Bharliana Ackbar Sonjaya Stasiun Cuaca Otomatis (AWS) komersial umumnya mahal, mendorong pengembangan AWS berbiaya rendah berbasis cetak 3D. Namun, anemometer berbiaya rendah saat ini masih banyak menggunakan reed switch mekanis yang rentan aus dan menghasilkan data tidak stabil akibat contact bouncing. Penelitian ini merancang bangun sensor anemometer beriaya rendah berbasis sensor magnetik efek Hall bebas bouncing, terintegrasi dengan platform IoT. Sistem menggunakan mikrokontroler Wemos D1 Mini untuk mengakumulasi putaran rotor yang dideteksi sensor efek Hall KY-003 secara non-kontak, lalu mentransmisikan data ke basis data time-series InfluxDB melalui WiFi untuk divisualisasikan real-time pada dasbor Grafana. Biaya komponen inti hanya Rp232.300, lebih terjangkau dibanding produk komersial sejenis. Pengujian kalibrasi menunjukkan hubungan linear kuat antara RPM dan kecepatan angin aktual (R² = 0,960), dengan MAE 0,657 km/jam, RMSE 0,739 km/jam, dan error relatif rata-rata 6,63% pada rentang operasional normal. Pengujian konektivitas IoT 30 hari mencatatkan uptime 94,39%. Rancang bangun ini terbukti andal, mengatasi kelemahan reed switch, dan berpotensi menjadi instrumen pemantau cuaca jarak jauh yang presisi dan terjangkau.; Commercial Automatic Weather Stations (AWS) are generally expensive, prompting development of low-cost AWS using 3D printing. However, current low-cost anemometers still largely rely on mechanical reed switches, prone to wear and unstable data due to contact bouncing. This study designs a low-cost anemometer based on a solid-state Hall effect magnetic sensor free from bouncing, integrated with an IoT platform. The system uses a Wemos D1 Mini microcontroller to accumulate rotor rotations detected by the KY-003 Hall effect sensor non-contactly, then transmits data to an InfluxDB time-series database via WiFi for real-time visualization on a Grafana dashboard. Core component cost is only Rp232,300, more affordable than similar commercial products. Calibration testing showed a strong linear relationship between RPM and actual wind speed (R² = 0.960), with MAE 0.657 km/h, RMSE 0.739 km/h, and average relative error 6.63% within the normal range. 30-day IoT connectivity testing recorded an uptime of 94.39%. This design is reliable, overcomes reed switch weaknesses, and holds strong potential as a precise, affordable remote weather monitoring instrument. Thu, 01 Jan 2026 00:00:00 GMT http://repository.ipb.ac.id/handle/123456789/178369 2026-01-01T00:00:00Z