5G AI-IoT System for Bird Species Monitoring and Song Classification.

Identification of different species of animals has become an important issue in biology and ecology. Ornithology has made alliances with other disciplines in order to establish a set of methods that play an important role in the birds' protection and the evaluation of the environmental quality of different ecosystems. In this case, the use of machine learning and deep learning techniques has produced big progress in birdsong identification. To make an approach from AI-IoT, we have used different approaches based on image feature comparison (through CNNs trained with Imagenet weights, such as EfficientNet or MobileNet) using the feature spectrogram for the birdsong, but also the use of the deep CNN (DCNN) has shown good performance for birdsong classification for reduction of the model size. A 5G IoT-based system for raw audio gathering has been developed, and different CNNs have been tested for bird identification from audio recordings. This comparison shows that Imagenet-weighted CNN shows a relatively high performance for most species, achieving 75% accuracy. However, this network contains a large number of parameters, leading to a less energy efficient inference. We have designed two DCNNs to reduce the amount of parameters, to keep the accuracy at a certain level, and to allow their integration into a small board computer (SBC) or a microcontroller unit (MCU).

AI-IoT Low-Cost Pollution-Monitoring Sensor Network to Assist Citizens with Respiratory Problems.

The proliferation and great variety of low-cost air quality (AQ) sensors, combined with their flexibility and energy efficiency, gives an opportunity to integrate them into Wireless Sensor Networks (WSN). However, with these sensors, AQ monitoring poses a significant challenge, as the data collection and analysis process is complex and prone to errors. Although these sensors do not meet the performance requirements for reference regulatory-equivalent monitoring, they can provide informative measurements and more if we can adjust and add further processing to their raw measurements. Therefore, the integration of these sensors aims to facilitate real-time monitoring and achieve a higher spatial and temporal sampling density, particularly in urban areas, where there is a strong interest in providing AQ surveillance services since there is an increase in respiratory/allergic issues among the population. Leveraging a network of low-cost sensors, supported by 5G communications in combination with Artificial Intelligence (AI) techniques (using Convolutional and Deep Neural Networks (CNN and DNN)) to predict 24-h-ahead readings is the goal of this article in order to be able to provide early warnings to the populations of hazards areas. We have evaluated four different neural network architectures: Multi-Linear prediction (with a dense Multi-Linear Neural Network (NN)), Multi-Dense network prediction, Multi-Convolutional network prediction, and Multi-Long Short-Term Memory (LSTM) network prediction. To perform the training of the prediction of the readings, we have prepared a significant dataset that is analyzed and processed for training and testing, achieving an estimation error for most of the predicted parameters of around 7.2% on average, with the best option being the Multi-LSTM network in the forthcoming 24 h. It is worth mentioning that some pollutants achieved lower estimation errors, such as CO2 with 0.1%, PM10 with 2.4% (as well as PM2.5 and PM1.0), and NO2 with 6.7%.

Bacteria spatial tracking in Urban Park soils with MALDI-TOF Mass Spectrometry and Specific PCR.

Urban parks constitute one of the main leisure areas, especially for the most vulnerable people in our society, children, and the elderly. Contact with soils can pose a health risk. Microbiological testing is a key aspect in determining whether they are suitable for public use. The aim of this work is to map the spatial distribution of potential dangerous Enterobacteria but also bioremediation useful (lipase producers) isolates from soils in an urban park in the area of Valencia (Spain). To this end, our team has collected 25 samples of soil and isolated 500 microorganisms, using a mobile application to collect information of the soil samples (i.e. soil features, temperature, humidity, etc.) with geolocation. A combined protocol including matrix-assisted laser desorption/ionization time of flight mass spectrometry (MALDI-TOF MS) and 16S rDNA sequencing PCR has been established to characterize the isolates. The results have been processed using spatial statistical techniques (using Kriging method), taking into account the number of isolated strains, also proving the reactivity against standard pathogenic bacterial strains (Escherichia coli, Bacillus cereus, Salmonella, Pseudomonas and Staphylococcus aureus), and have increased the number of samples (to 896 samples) by interpolating spatially each parameter with this statistical method. The combined use of methods from biology and computer science allows the quality of the soil in urban parks to be predicted in an agile way, which can generate confidence in its use by citizens.

Water IoT Monitoring System for Aquaponics Health and Fishery Applications.

Aquaponic health is a very important in the food industry field, as currently there is a huge amount of fishing farms, and the demands are growing in the whole world. This work examines the process of developing an innovative aquaponics health monitoring system that incorporates high-tech back-end innovation sensors to examine fish and crop health and a data analytics framework with a low-tech front-end approach to feedback actions to farmers. The developed system improves the state-of-the-art in terms of aquaponics life cycle monitoring metrics and communication technologies, and the energy consumption has been reduced to make a sustainable system.

Spatial Distribution of Antibiotic-Producing Bacteria in Urban Areas. A Case Study in València (Spain).

The emergence of pathogenic bacteria that are multi-resistant to antibiotics lurks in today's society. In the golden age of the discovery of new antibiotic-producing microorganisms, each contribution was a step forward, but currently the progression is no longer so spectacular. The probability of finding new microorganisms and different antibiotics is lower and lower. The use of spatial statistical methods such as the Kriging technique has been shown to be suitable for mapping each parameter, allowing us to determine areas with greater possibilities of locating these microorganisms. For a practical approach of our estimations a total of 12 isolates capable of inhibiting the growth of several control strains (Escherichia coli, Bacillus cereus and at least one other) were analyzed. The isolates were preliminarily characterized, and subsequently identified at the species level by DNA sequence analyses (16S rDNA PCR) and protein analyses (MALDI-TOF MS). Geospatial mapping with RStudio software provide a satisfactory predictive tool for isolation of new microbial isolates.

Implementation of Antibiotic Discovery by Student Crowdsourcing in the Valencian Community Through a Service Learning Strategy.

Antibiotic misuse is a public health problem due to the appearance of resistant strains in almost all human pathogens, making infectious diseases more difficult to treat. The search for solutions requires the development of new antimicrobials as well as novel strategies, including increasing social awareness of the problem. The Small World Initiative (SWI) and the Tiny Earth (TE) network are citizen science programs pursuing the discovery of new antibiotics from soil samples and the promotion of scientific culture. Both programs aim to bring scientific culture and microbiological research closer to pre-university students through a crowdsourcing strategy and a Service Learning (SL) educational approach, with a 2-fold objective: to encourage students to pursue careers in science and to involve them in the discovery of soil microorganisms producing new antimicrobials. SWI and TE projects were put into practice in Spain under the common name MicroMundo. MicroMundo@Valencia was implemented at the Universitat de València (UV) during the academic years 2017-2018 and 2018-2019. It trained 140 university students to disseminate this initiative into 23 high/secondary schools, and one primary school, involving about 900 people (teachers and students) as researchers. A total of 7,002 bacterial isolates were obtained from 366 soil samples and tested for antibiosis at UV and high/secondary school centers. About 1 or 7% of them produced inhibition halos for the Escherichia coli or Bacillus cereus target strains, respectively. Geolocation of sampling sites by an application developed ad hoc and Kriging analysis also allowed detection of soil foci of antibiotic-producing bacteria. Evaluation of the project by university, high/secondary, and primary school students revealed their strong positive perception and their increased interest in science, as a consequence of acquiring new scientific and pedagogical concepts and skills that they were able to pass on to other classmates, younger students, or relatives. To further expand the dissemination of the project in the Valencian Community, diverse extramural activities deemed to include a gender perspective and aimed at different age groups, were also carried out, obtaining very satisfactory results, increasing sensitivity and awareness to the global antibiotic crisis.

Spatio-Temporal Analysis of Urban Acoustic Environments with Binaural Psycho-Acoustical Considerations for IoT-Based Applications.

Sound pleasantness or annoyance perceived in urban soundscapes is a major concern in environmental acoustics. Binaural psychoacoustic parameters are helpful to describe generic acoustic environments, as it is stated within the ISO 12913 framework. In this paper, the application of a Wireless Acoustic Sensor Network (WASN) to evaluate the spatial distribution and the evolution of urban acoustic environments is described. Two experiments are presented using an indoor and an outdoor deployment of a WASN with several nodes using an Internet of Things (IoT) environment to collect audio data and calculate meaningful parameters such as the sound pressure level, binaural loudness and binaural sharpness. A chunk of audio is recorded in each node periodically with a microphone array and the binaural rendering is conducted by exploiting the estimated directional characteristics of the incoming sound by means of DOA estimation. Each node computes the parameters in a different location and sends the values to a cloud-based broker structure that allows spatial statistical analysis through Kriging techniques. A cross-validation analysis is also performed to confirm the usefulness of the proposed system.

Practical Considerations in the Implementation of Collaborative Beamforming on Wireless Sensor Networks.

Wireless Sensor Networks (WSNs) are composed of spatially distributed autonomous sensor devices, named motes. These motes have their own power supply, processing unit, sensors and wireless communications However with many constraints, such as limited energy, bandwidth and computational capabilities. In these networks, at least one mote called a sink, acts as a gateway to connect with other networks. These sensor networks run monitoring applications and then the data gathered by these motes needs to be retrieved by the sink. When this sink is located in the far field, there have been many proposals in the literature based on Collaborative Beamforming (CB), also known as Distributed or Cooperative Beamforming, for these long range communications to reach the sink. In this paper, we conduct a thorough study of the related work and analyze the requirements to do CB. In order to implement these communications in real scenarios, we will consider if these requirements and the assumptions made are feasible from the point of view of commercial motes and their constraints. In addition, we will go a step further and will consider different alternatives, by relaxing these requirements, trying to find feasible assumptions to carry out these types of communications with commercial motes. This research considers the nonavailability of a central clock that synchronizes all motes in the WSN, and all motes have identical hardware. This is a feasibility study to do CB on WSN, using a simulated scenario with randomized delays obtained from experimental data from commercial motes.