UiTiOt - a Smart Weather Station using Libelium Technology and Deep Learning

UiTiOt - a Smart Weather Station using Libelium Technology and Deep Learning

연구 분야: Infrastructure

학회: ICIIT '24: Proceedings of the 2024 9th International Conference on Intelligent Information Technology

Weather forecasting is an essential task in smart agriculture, wide-area weather reports typically predict over a large geographic area likes city or province. In this paper, we deploy an environmental monitoring station on the rooftop of the building E at the University of Information Technology (UIT). In addition, we build a system to collect these environmental data and store them in a dataset, namely UiTiOt, whose metrics are temperature, humidity, pressure, nitro dioxide, etc. Noisy data points are filtered out using Kalman filter before training with Deep learning models such as Autoregressive integrated moving average (ARIMA), Gated Recurrent Unit (GRU), Long Short Term Memory (LSTM), and Bidirectional LSTM (Bi-LSTM). The process is evaluated using various metrics such as mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), root relative squared error (RRSE), and mean absolute percentage error (MAPE). The results show that ARIMA is the best model among the four models when measuring on three datasets. Furthermore, we observe that the smoothed UiTiOt dataset achieves lower values in measured metric indices than the unfiltered one.