The deteriorating water environment demands new approaches and technologies to achieve sustainable and smart management of urban water systems. Wireless sensor networks represent a promising technology for water quality monitoring and management. The use of wireless sensor networks facilitates the improvement of current centralized systems and traditional manual methods, leading to decentralized smart water quality monitoring systems adaptable to the dynamic and heterogeneous water distribution infrastructure of cities. However, there is a need for a low-cost wireless sensor node solution on the market that enables a cost-effective deployment of this new generation of systems. This paper presents the integration to a wireless sensor network and a preliminary validation in a wastewater treatment plant scenario of a low-cost water quality monitoring device in the close-to-market stage. This device consists of a nitrate and nitrite analyzer based on a novel ion chromatography detection method. The analytical device is integrated using an Internet of Things software platform and tested under real conditions. By doing so, a decentralized smart water quality monitoring system that is conceived and developed for water quality monitoring and management is accomplished. In the presented scenario, such a system allows online near-real-time communication with several devices deployed in multiple water treatment plants and provides preventive and data analytics mechanisms to support decision making. The results obtained comparing laboratory and device measured data demonstrate the reliability of the system and the analytical method implemented in the device.

Wireless sensor networks (WSNs) represent one of the most promising technologies for precision farming. Over the next few years, a significant increase in the use of such systems on commercial farms is expected. WSNs present a number of problems, regarding scalability, interoperability, communications, connectivity with databases and data processing. Different Internet of Things middleware is appearing to overcome these challenges. This paper checks whether one of these middleware, FIWARE, is suitable for the development of agricultural applications. To the authors’ knowledge, there are no works that show how to use FIWARE in precision agriculture and study its appropriateness, its scalability and its efficiency for this kind of applications. To do this, a testbed has been designed and implemented to simulate different deployments and load conditions. The testbed is a typical FIWARE application, complete, yet simple and comprehensible enough to show the main features and components of FIWARE, as well as the complexity of using this technology. Although the testbed has been deployed in a laboratory environment, its design is based on the analysis of an Internet of Things use case scenario in the domain of precision agriculture.

Wireless acoustic sensor networks are nowadays an essential tool for noise pollution monitoring and managing in cities. The increased computing capacity of the nodes that create the network is allowing the addition of processing algorithms and artificial intelligence that provide more information about the sound sources and environment, e.g., detect sound events or calculate loudness. Several models to predict sound pressure levels in cities are available, mainly road, railway and aerial traffic noise. However, these models are mostly based in auxiliary data, e.g., vehicles flow or street geometry, and predict equivalent levels for a temporal long-term. Therefore, forecasting of temporal short-term sound levels could be a helpful tool for urban planners and managers. In this work, a Long Short-Term Memory (LSTM) deep neural network technique is proposed to model temporal behavior of sound levels at a certain location, both sound pressure level and loudness level, in order to predict near-time future values. The proposed technique can be trained for and integrated in every node of a sensor network to provide novel functionalities, e.g., a method of early warning against noise pollution and of backup in case of node or network malfunction. To validate this approach, one-minute period equivalent sound levels, captured in a two-month measurement campaign by a node of a deployed network of acoustic sensors, have been used to train it and to obtain different forecasting models. Assessments of the developed LSTM models and Auto regressive integrated moving average models were performed to predict sound levels for several time periods, from 1 to 60 min. Comparison of the results show that the LSTM models outperform the statistics-based models. In general, the LSTM models achieve a prediction of values with a mean square error less than 4.3 dB for sound pressure level and less than 2 phons for loudness. Moreover, the goodness of fit of the LSTM models and the behavior pattern of the data in terms of prediction of sound levels are satisfactory.

Water pollution is an issue of global concern that requires continuous monitoring to maintain the integrity of surface and groundwater. This growing concern about environmental contamination has prompted the development and use of physical and chemical systems to control water quality in-situ in most ecosystems, including wastewater treatment plants. In most water reuse projects, effluents must meet applicable water quality standards, regardless of whether they are discharged to surface or groundwater bodies, for irrigation or industrial reuse. In this paper, an evaluation of the performance of an Internet of Things device for long-term monitoring and detection of nitrate and nitrite in wastewater is presented. This device is integrated in an Internet of Things system with these main components: an ion chromatography sensor to provide accurate data, together with mechanical elements for water sample acquisition and electronic circuits for the control of the whole monitoring process, a communication module to send real-time information, and a cloud software platform to store, analyze and visualize the obtained water quality metrics. This evaluation was carried out by comparing traditional laboratory results with data captured by the remote device during a long-term measurement campaign at three wastewater treatment plants located in Murcia, Spain. The results show a satisfactory validation against standardized laboratory values, demonstrating the long-term measurement capability of the system. Specifically, the coefficient of determination of the regression between laboratory and device procedures reaches 96.7% on average in the three wastewater treatment plants for both nitrate and nitrite and influent and effluent streams.

Wastewater from urban and industrial sources can be treated and reused for crop irrigation, which can certainly help to protect aquifers from overexploitation and potential environmental risks of groundwater pollution. In fact, water reuse can also have negative effects on the environment, such as increased salinity, pollution phenomena or soil degradation, among others. Consequently, reuse of wastewater requires rigorous treatment and a very detailed analysis of different parameters, in compliance with established quality limitation standards. Therefore, this study was carried out to develop a prediction of temporal changes in water quality by introducing a wastewater quality index (WWQI) for four regional wastewater treatment plants (WWTPs) in Murcia, Southeast Spain, where a significant number of physicochemical and biological parameters are obtained in time series over the period 2019–2021. For this purpose, multivariate statistical analyses have been adopted to predict the performance of WWQI. By robust PCA of the sixteen physicochemical variables of the raw and treated wastewater, five main principal components (PCs) were extracted, which explain between 21.39% and 36.79% of the data variability. From the loadings of the PCs, the relationships between the original parameters are analyzed. The accuracy of the developed models in terms of fit to the training dataset ranged from 74.3% to 97.9%, with p-values < 0.05. The techniques incorporated in this study provided a comprehensive evaluation framework for monitoring wastewater treatment.

Heart failure is the most common disease among elderly people, and the risk increases with age. The use of smart Internet of Things (IoT) systems for monitoring patients with chronic heart failure (CHF) in a non-intrusive manner can result in better control of the disease, improving proactive healthcare through real-time and historical patient’s data, promoting self-care in patients, reducing unneeded interaction between patients and doctors, reducing the number of hospitalizations and saving healthcare costs. This work presents an active assisted living (AAL) solution based on the IoT to provide a tele-assistance platform for CHF patients from the public health service of the region of Murcia in Spain, with formal and informal caregivers and health professionals also as key actors. In this article, we have detailed the methodology, results, and conclusions of the prevalidation phase for the set of IoT technologies to be integrated in the AAL platform, the first mandatory step before the deployment of a large-scale pilot that will lead to improving the innovation of the system from its current technology readiness level to the market. The work presented, in the framework of the H2020 Pharaon project, aims to serve as inspiration to the R&D community for the design, development, and deployment of AAL solutions based on heterogeneous IoT technologies, or similar approaches, for smart healthcare solutions in real healthcare institutions.