Light Control Smart Farm Monitoring System with Reflector Control

Comparative analysis of data using machine learning algorithms: A hydroponics system use case

“…The light quantity, temperature, humidity, and carbon (IV) oxide within a smart farm can be measured using various sensors [23]. They have collected all these data and use them to predict future light intensity within their region.…”

“…Different optimizers have been considered for the hyper tuning of the hydroponic systems such as Adam and SGD optimizers using different learning rates values ranging from zero (0) to one (1) to obtain the optimal convergence as shown in Figs. 15,16,17,18,19,20,21,22,23 which represent the results of the AER Loss using Adam optimizer (Learning rate=0.0000001), AER Loss using Adam optimizer (Learning rate=0.1), AER Loss using SGD optimiser (learning=0.0000001), AG loss using Adam optimizer (Learning rate=0.01), AG loss using SGD optimizer (Learning rate=0.0000001), Float loss using Adam optimizer (Learning rate=0.01), Float loss using SGD optimiser (Learning rate=0.000001), NFT loss using Adam optimizer (Learning rate=0.01), NFT loss using SGD optimizer (Learning rate=0.000001) respectively, it can be inferred that the floating hydroponic systems, produced the optimal convergence using the Adam optimizer at a learning rate of 0.01, this indicates that the floating hydroponic systems is the preferred hydroponic systems for the Onion bulb diameter predictions using a decentralised split learning network.…”

Prototype Alat Monitoring Suhu, Kelembaban dan Kecepatan Angin Untuk Smart Farming Menggunakan Komunikasi LoRa dengan Daya Listrik Menggunakan Panel Surya

“…Karena adanya gerakan matahari yang berulang setiap tahun maka dapat dilakukan pengontrolan reflektor sesuai dengan akumulasi data ini. Sistem ini telah diimplementasikan sebagai server dan aplikasi mobile yang menyediakan berbagai sensor untuk kontrol lingkungan, Arduino, Wemos untuk upload server Wifi, dan pemantauan UI [4].…”