Machine Learning-based Forecasting of Sensor Data for Enhanced Environmental Sensing

Abstract

This article presents a study that explores forecasting methods for multivariate time series data, which was collected from sensors monitoring CO2, temperature, and humidity. The article covers the preprocessing stages, such as dealing with missing values, data normalization, and organizing the time-series data into a suitable format for the model. This study aimed to evaluate Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNNs), Vector Autoregressive (VAR) models, Artificial Neural Networks (ANNs), and Random Forest performance in terms of forecasting different environmental dataset parameters. After implementing and testing fifteen different sensor forecast model combinations, it was concluded that the Long Short-Term Memory and Vector Autoregression models produced the most accurate results. The highest accuracy for all models was achieved when forecasting temperature data with CO2 and humidity as inputs. The least accurate models forecasted CO2 levels based on temperature and humidity.

Deep Learning for Time Series Forecasting: Advances and Open Problems

“…Year Application [47] 2017 ETFs prices [48] 2018 Electricity consumption [10] 2018 Solar power and electricity load [6] 2018 Electricity consumption [7] 2018 Electricity price [49] 2019 Electricity price and load forecasting [50] 2019 Building-level load [12] 2023 CO 2 /Temperature/Humidity…”

“…[18] 2020 Stock market [100] 2020 COVID-19 [79] 2020 Multiple time series [101] 2021 Weather/Air Quality/Clinical data [16] 2021 Air Quality Index [102] 2022 Financial markets [12] 2023 CO 2 /Temperature/Humidity…”

“…Time series forecasting estimates values that a time series takes in the future, allowing the implementation of decision-making strategies, e.g., abandonment of fossil fuels to reduce the surface temperature of the Earth. Specifically, time series forecasting is very relevant for the energy domain (e.g., electricity load demand [7,8], solar and wind power estimation [9,10]), meteorology (e.g., prediction of wind speed [11], temperature [12,13], humidity [12], precipitation [13,14]), air pollution monitoring (e.g., prediction of PM 2.5 , PM 10 , NO 2 , O 3 , SO 2 , and CO 2 concentrations [12,15,16]), the finance domain (e.g., stock market index and shares prediction [17,18], the stock price [19,20], exchange rate [21,22]), health (e.g., prediction of infective diseases diffusion [23], diabetes mellitus [24], blood glucose concentration [25], and cancer growth [26]), traffic (e.g., traffic speed and flow prediction [27][28][29][30]), and industrial production (e.g., petroleum production [31], remaining life prediction [23,32,33], industrial processes [34], fuel cells durability [35], engine faults [36]). Deep learning algorithms are currently the leading methods in machine learning due to their successful application to many computer science domains (e.g., computer vision, natural language processing, speech recognition).…”