Reconstructing secondary data based on air quality, meteorological and traffic data considering spatiotemporal components.

This paper introduces the reconstructed dataset along with procedures to implement air quality prediction, which consists of air quality, meteorological and traffic data over time, and their monitoring stations and measurement points. Given the fact that those monitoring stations and measurement points are located in different places, it is important to incorporate their time series data into a spatiotemporal dimension. The output can be used as input for various predictive analyses, in particular, we used the reconstructed dataset as input for grid-based (Convolutional Long Short-Term Memory and Bidirectional Convolutional Long Short-Term Memory) and graph-based (Attention Temporal Graph Convolutional Network) machine learning algorithms. The raw dataset is obtained from the Open Data portal of the Madrid City Council.

Bidirectional convolutional LSTM for the prediction of nitrogen dioxide in the city of Madrid.

Nitrogen dioxide is one of the pollutants with the most significant health effects. Advanced information on its concentration in the air can help to monitor and control further consequences more effectively, while also making it easier to apply preventive and mitigating measures. Machine learning technologies with available methods and capabilities, combined with the geospatial dimension, can perform predictive analyses with higher accuracy and, as a result, can serve as a supportive tool for productive management. One of the most advanced machine learning algorithms, Bidirectional convolutional LSTM, is being used in ongoing work to predict the concentration of nitrogen dioxide. The model has been validated to perform more accurate spatiotemporal analysis based on the integration of temporal and geospatial factors. The analysis was carried out according to two scenarios developed on the basis of selected features using data from the city of Madrid for the periods January-June 2019 and January-June 2020. Evaluation of the model's performance was conducted using the Root Mean Square Error and the Mean Absolute Error which emphasises the superiority of the proposed model over the reference models. In addition, the significance of a feature selection technique providing improved accuracy was underlined. In terms of execution time, due to the complexity of the Bidirectional convolutional LSTM architecture, convergence and generalisation of the data took longer, resulting in the superiority of the reference models.

Data on CO2, temperature and air humidity records in Spanish classrooms during the reopening of schools in the COVID-19 pandemic.

In order to reduce the advance of the pandemic produced by COVID-19, many actions and restrictions have been applied and the field of education has been no exception. In Spain, during the academic year 2020-2021, face-to-face teaching generally continued in both primary and secondary schools. Throughout the year, different measures have been taken to reduce the likelihood of contagion in classrooms, one of which was to improve ventilation by opening windows and doors. One of the most commonly used techniques to check for good ventilation has been CO2 monitoring. This work provides a set of 80,000 CO2 concentration records collected by low-cost Internet of Things nodes, primarily located within twelve classrooms in two primary schools. The published observations were collected between 1 May 2020 and 23 June 2021. Additionally, the same dataset includes temperature, air humidity and battery level observations.

Data on records of environmental phenomena using low-cost sensors in vineyard smallholdings.

Inadequate weather conditions are one of the main threats to the correct development of sensitive crops, where a bad situation can lead to greater stress on plants and their weakness against various diseases. This statement is especially decisive in the cultivation of the vineyard. Meteorological monitoring of vineyard parcels is vital to detect and prevent possible fungal diseases. The development of new Information and Communication Technologies, linked to the Smart Farming movement, together with the reduced cost of electronic components, have favoured a greater availability of meteorological monitoring stations to get to know first-class hand the state of the vineyard smallholdings. This work provides a set of over 750,000 environmental raw data records collected by low-cost Internet of Things nodes, primarily located within vineyard smallholdings. The published observations were collected between 2018-04-01 and 2018-10-31 and were validated in previous research to determine the data's reliability.

Reliability Evaluation of the Data Acquisition Potential of a Low-Cost Climatic Network for Applications in Agriculture.

Temperature, humidity and precipitation have a strong influence on the generation of diseases in different crops, especially in vine. In recent years, advances in different disciplines have enabled the deployment of sensor nodes on agricultural plots. These sensors are characterised by a low cost and so the reliability of the data obtained from them can be compromised, as they are built from low-confidence components. In this research, two studies were carried out to determine the reliability of the data obtained by different SEnviro nodes installed in vineyards. Two networks of meteorological stations were used to carry out these studies, one official and the other professional. The first study was based on calculating the homogenisation of the data, which was performed using the Climatol tool. The second study proposed a similarity analysis using cross-correlation. The results showed that the low-cost node can be used to monitor climatic conditions in an agricultural area in the central zone of the province of Castelló (Spain) and to obtain reliable observations for use in previously published fungal disease models.

An IoT Platform Based on Microservices and Serverless Paradigms for Smart Farming Purposes.

Nowadays, the concept of "Everything is connected to Everything" has spread to reach increasingly diverse scenarios, due to the benefits of constantly being able to know, in real-time, the status of your factory, your city, your health or your smallholding. This wide variety of scenarios creates different challenges such as the heterogeneity of IoT devices, support for large numbers of connected devices, reliable and safe systems, energy efficiency and the possibility of using this system by third-parties in other scenarios. A transversal middleware in all IoT solutions is called an IoT platform. the IoT platform is a piece of software that works like a kind of "glue" to combine platforms and orchestrate capabilities that connect devices, users and applications/services in a "cyber-physical" world. In this way, the IoT platform can help solve the challenges listed above. This paper proposes an IoT agnostic architecture, highlighting the role of the IoT platform, within a broader ecosystem of interconnected tools, aiming at increasing scalability, stability, interoperability and reusability. For that purpose, different paradigms of computing will be used, such as microservices architecture and serverless computing. Additionally, a technological proposal of the architecture, called SEnviro Connect, is presented. This proposal is validated in the IoT scenario of smart farming, where five IoT devices (SEnviro nodes) have been deployed to improve wine production. A comprehensive performance evaluation is carried out to guarantee a scalable and stable platform.

Interactive guidelines: Public communication of data-based research in cities.

Scientific research results are traditionally published as articles in peer-reviewed conference proceedings or journals. These articles often use technical jargon, which precludes the general public from consuming the results achieved. New ways to communicate scientific results are thus necessary to transfer scientific insights to non-experts, and this work proposes the concept of interactive guidelines to fill this gap. A web tool, called Interactive Guidelines Tool, was developed as a proof-of-concept for the idea. It was used in the context of the GEO-C project to communicate research outputs in smart cities scenarios to the public. A comparative analysis between the Interactive Guidelines Tool and related tools helps to highlight the progress it enables beyond the current state of the art. Interactive Guidelines Tool is available as an open-source tool and can be customised/extended by any interested researcher, in the process of making scientific knowledge and insights more accessible and understandable to a broader public.

Promoting Pollution-Free Routes in Smart Cities Using Air Quality Sensor Networks.

Nowadays, citizens have a huge concern about the quality of life in their cities, especially regarding the level of pollution. Air quality level is of great importance, not only to plan our activities but also to take precautionary measures for our health. All levels of governments are concerned about it and have built their indexes to measure the air quality level in their countries, regions or cities. Taking into account the existing sensor infrastructure within smart cities, it makes possible to evaluate these indices and to know anywhere the level of pollution in real-time. In this scenario, the main objective of the current work is to foster citizens' awareness about pollution by offering pollution-free routes. To achieve this goal, a technology-agnostic methodology is presented, which allows for creating pollution-free routes across cities depending on the level of pollution in each zone. The current work includes an extensive study of existing air quality indices, and proposes and carries forward to deployment of the defined methodology in a big city, such as Madrid (Spain).

SEnviro: a sensorized platform proposal using open hardware and open standards.

The need for constant monitoring of environmental conditions has produced an increase in the development of wireless sensor networks (WSN). The drive towards smart cities has produced the need for smart sensors to be able to monitor what is happening in our cities. This, combined with the decrease in hardware component prices and the increase in the popularity of open hardware, has favored the deployment of sensor networks based on open hardware. The new trends in Internet Protocol (IP) communication between sensor nodes allow sensor access via the Internet, turning them into smart objects (Internet of Things and Web of Things). Currently, WSNs provide data in different formats. There is a lack of communication protocol standardization, which turns into interoperability issues when connecting different sensor networks or even when connecting different sensor nodes within the same network. This work presents a sensorized platform proposal that adheres to the principles of the Internet of Things and theWeb of Things. Wireless sensor nodes were built using open hardware solutions, and communications rely on the HTTP/IP Internet protocols. The Open Geospatial Consortium (OGC) SensorThings API candidate standard was used as a neutral format to avoid interoperability issues. An environmental WSN developed following the proposed architecture was built as a proof of concept. Details on how to build each node and a study regarding energy concerns are presented.