Accurate air quality monitoring requires processing of multi-dimensional, multi-location sensor data, which has previously been considered in centralised machine learning models. These are often unsuitable for resource-constrained edge devices. In this article, we address this challenge by: (1) designing a novel hybrid deep learning model for hourly PM_2.5 pollutant prediction; (2) optimising the obtained model for edge devices; and (3) examining model performance running on the edge devices in terms of both accuracy and latency. The hybrid deep learning model in this work comprises a 1D Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) to predict hourly PM_2.5 concentration. The results show that our proposed model outperforms other deep learning models, evaluated by calculating RMSE and MAE errors. The proposed model was optimised for edge devices, the Raspberry Pi 3 Model B+ (RPi3B+) and Raspberry Pi 4 Model B (RPi4B). This optimised model reduced file size to a quarter of the original, with further size reduction achieved by implementing different post-training quantisation. In total, 8272 hourly samples were continuously fed to the edge device, with the RPi4B executing the model twice as fast as the RPi3B+ in all quantisation modes. Full-integer quantisation produced the lowest execution time, with latencies of 2.19 s and 4.73 s for RPi4B and RPi3B+, respectively.

The significant decrease in agricultural land and the rapid development of hydroponic system technology such as Nutrient Film Technique (NFT), have brought huge challenge to farmers. This hydroponic system requires special attention to several parameters such as the water temperature, water level, acidity (pH), and the concentration of the nutrient (EC/PPM). We first monitor and collect information from NFT Hydroponic farmer and then systematically evaluate and analyze them. Unfortunately, it is still controlled by using the conventional way (human), for example in controlling the concentrations of nutrient has to be done at least once a day, so much time is wasted. In addressing these issues, we need a system that can be applied and used easily. We built a hydroponic monitoring and automation system that can monitored using sensors connected to the Arduino Uno microcontrollerm, Wi-Fi module ESP8266 and Raspberry Pi 2 Model B microcomputers as the webserver with the concept Internet of Things, in which each block hydroponic farming can communicate with the webserver (broker). Web used as the interface of the system that allows user to monitor and control the NFT hydroponic farming. The NFT hydroponic web interface management systems using a responsive web framework, such as Bootstrap for the front-end, JQuery and JavaScript libraries. The result shows that this system helps farmers to increase the effectivity and efficiency on monitoring and controlling NFT Hydroponic Farm.

A key challenge in building machine learning models for time series prediction is the incompleteness of the datasets. Missing data can arise for a variety of reasons, including sensor failure and network outages, resulting in datasets that can be missing significant periods of measurements. Models built using these datasets can therefore be biased. Although various methods have been proposed to handle missing data in many application areas, more air quality missing data prediction requires additional investigation. This study proposes an autoencoder model with spatiotemporal considerations to estimate missing values in air quality data. The model consists of one-dimensional convolution layers, making it flexible to cover spatial and temporal behaviours of air contaminants. This model exploits data from nearby stations to enhance predictions at the target station with missing data. This method does not require additional external features, such as weather and climate data. The results show that the proposed method effectively imputes missing data for discontinuous and long-interval interrupted datasets. Compared to univariate imputation techniques (most frequent, median and mean imputations), our model achieves up to 65% RMSE improvement and 20–40% against multivariate imputation techniques (decision tree, extra-trees, k-nearest neighbours and Bayesian ridge regressors). Imputation performance degrades when neighbouring stations are negatively correlated or weakly correlated.

Low-cost air quality monitoring devices can provide high-density spatiotemporal pollution data, thus offering a better opportunity to apply machine learning. Low-cost sensor nodes usually utilize microcontrollers as the main processors, and tinyML brings machine learning (ML) models to these resource-constrained devices. In this letter, we reported the development of a low-cost air quality monitoring device with embedded tinyML models. We deployed two tinyML models on a single microcontroller and performed two tasks: predicting air quality and power parameters (using model predictor) and imputing missing features (using model imputer). The proposed model predictor can estimate parameters with a coefficient of determination above 0.70, and the model imputer effectively estimates the testing data when missing rates are below 80%. By performing the post-training quantization technique, we can further reduce the model size but slightly degrade the accuracies.

This paper presents Rudas, a low cost and energy efficient system that fully operational for IP-based network. The system comprised of few embedded sensors and networking devices in the house that connected to the Internet architecture. It can be used in many applications, leading to the emerging concept of the Internet of Things (IoT). The IoT describes the future where everyday things (or objects) will be connected to the internet and be able to communicate themselves to other devices. In order to well maintain those sensor devices, it is often necessary to evolve devices to function correctly by allowing device management (DM) entities to remotely monitor and control devices without consuming significant resources. In particular, it includes a single board computer, microcontrollers, responsive web technology, database system, environmentally sensitive devices, tornado server software, cameras and could computing. The system is also implanted a fuzzy logic artificial intelligence to adjust the intensity of light and air condition in a room. Information will be recorded and calculated so that home owners will be more efficient in managing and monitoring all home devices. A result from this study is a well-worked home management and other aspects including security, energy saving and monitoring.

The rapid growth of connected sensing devices has resulted in enormous amounts of data being collected and processed. Air quality data collected from different monitoring stations is spatially and temporally correlated, and hence, collaborative learning can improve deep-learning (DL) model performance. Research on collaborative learning at the edge has not specifically focused so far on air quality prediction, which is the subject of this work. We compare three collaborative learning strategies and implement them on edge devices, such as the Raspberry Pi and Jetson Nano, with communication facilitated through the MQTT protocol. Federated learning (FL) is shown to enhance model accuracy in comparison to local training alone. An approach called clustered model exchange reduces communication costs during training. Finally, our proposed spatiotemporal data exchange approach exploits information from neighboring sensing stations to enhance model performance. It achieves the highest accuracy in air quality predictions, outperforming other methods in minimizing loss during training. It results in RMSE improvements ranging from 0.525% to 8.934% when compared to models that are only trained locally. We compare the real training costs of the three methods on real hardware to validate them.