Toward the Definition of a Soundscape Ranking Index (SRI) in an Urban Park Using Machine Learning Techniques.

The goal of estimating a soundscape index, aimed at evaluating the contribution of the environmental sound components, is to provide an accurate "acoustic quality" assessment of a complex habitat. Such an index can prove to be a powerful ecological tool associated with both rapid on-site and remote surveys. The soundscape ranking index (SRI), introduced by us recently, can empirically account for the contribution of different sound sources by assigning a positive weight to natural sounds (biophony) and a negative weight to anthropogenic ones. The optimization of such weights was performed by training four machine learning algorithms (decision tree, DT; random forest, RF; adaptive boosting, AdaBoost; support vector machine, SVM) over a relatively small fraction of a labeled sound recording dataset. The sound recordings were taken at 16 sites distributed over an area of approximately 22 hectares at Parco Nord (Northern Park) of the city Milan (Italy). From the audio recordings, we extracted four different spectral features: two based on ecoacoustic indices and the other two based on mel-frequency cepstral coefficients (MFCCs). The labeling was focused on the identification of sounds belonging to biophonies and anthropophonies. This preliminary approach revealed that two classification models, DT and AdaBoost, trained by using 84 extracted features from each recording, are able to provide a set of weights characterized by a rather good classification performance (F1-score = 0.70, 0.71). The present results are in quantitative agreement with a self-consistent estimation of the mean SRI values at each site that was recently obtained by us using a different statistical approach.

Self-Consistent Soundscape Ranking Index: The Case of an Urban Park.

We have performed a detailed analysis of the soundscape inside an urban park (located in the city of Milan) based on simultaneous sound recordings at 16 locations within the park. The sound sensors were deployed over a regular grid covering an area of about 22 hectares, surrounded by a variety of anthropophonic sources. The recordings span 3.5 h each over a period of four consecutive days. We aimed at determining a soundscape ranking index (SRI) evaluated at each site in the grid by introducing 4 unknown parameters. To this end, a careful aural survey from a single day was performed in order to identify the presence of 19 predefined sound categories within a minute, every 3 minutes of recording. It is found that all SRI values fluctuate considerably within the 70 time intervals considered. The corresponding histograms were used to define a dissimilarity function for each pair of sites. Dissimilarity was found to increase significantly with the inter-site distance in space. Optimal values of the 4 parameters were obtained by minimizing the standard deviation of the data, consistent with a fifth parameter describing the variation of dissimilarity with distance. As a result, we classify the sites into three main categories: "poor", "medium" and "good" environmental sound quality. This study can be useful to assess the quality of a soundscape in general situations.

Mapping of the Acoustic Environment at an Urban Park in the City Area of Milan, Italy, Using Very Low-Cost Sensors.

The-growing influence of urbanisation on green areas can greatly benefit from passive acoustic monitoring (PAM) across spatiotemporal continua to provide biodiversity estimation and useful information for conservation planning and development decisions. The capability of eco-acoustic indices to capture different sound features has been harnessed to identify areas within the Parco Nord of Milan, Italy, characterised by different degrees of anthropic disturbance and biophonic activity. For this purpose, we used a network of very low-cost sensors distributed over an area of approximately 20 hectares to highlight areas with different acoustic properties. The audio files analysed in this study were recorded at 16 sites on four sessions during the period 25-29 May (2015), from 06:30 a.m. to 10:00 a.m. Seven eco-acoustic indices, namely Acoustic Complexity Index (ACI), Acoustic Diversity Index (ADI), Acoustic Evenness Index (AEI), Bio-Acoustic Index (BI), Acoustic Entropy Index (H), Normalized Difference Soundscape Index (NSDI), and Dynamic Spectral Centroid (DSC) were computed at 1 s integration time and the resulting time series were described by seven statistical descriptors. A dimensionality reduction of the indices carrying similar sound information was obtained by performing principal component analysis (PCA). Over the retained dimensions, describing a large (∼80%) variance of the original variables, a cluster analysis allowed discriminating among sites characterized by different combination of eco-acoustic indices (dimensions). The results show that the obtained groups are well correlated with the results of an aural survey aimed at determining the sound components at the sixteen sites (biophonies, technophonies, and geophonies). This outcome highlights the capability of this analysis of discriminating sites with different environmental sounds, thus allowing to create a map of the acoustic environment over an extended area.

Combined Effects of Pesticides and Electromagnetic-Fields on Honeybees: Multi-Stress Exposure.

Honeybee and general pollinator decline is extensively reported in many countries, adding new concern to the general biodiversity loss. Many studies were addressed to assess the causes of pollinator decline, concluding that in most cases multi-stress effects were the most probable ones. In this research, the combined effects of two possible stress sources for bees, pesticides and electromagnetic fields (multi-stress conditions), were analyzed in the field. Three experimental sites were chosen: a control one far from direct anthropogenic stress sources, a pesticide-stress site and multi-stress one, adding to the same exposure to pesticides the presence of an electromagnetic field, coming from a high-voltage electric line. Experimental apiaries were monitored weekly for one year (from April 2017 to April 2018) by means of colony survival, queen activity, storage and brood amount, parasites and pathogens, and several biomarkers in young workers and pupae. Both exposure and effect biomarkers were analysed: among the first, acetylcholinesterase (AChE), catalase (CAT), glutathione S-transferase (GST) and alkaline phosphatase (ALP) and Reactive Oxygen Species (ROS); and among the last, DNA fragmentation (DNAFRAGM) and lipid peroxidation (LPO). Results showed that bee health conditions were the worst in the multi-stress site with only one colony alive out of the four ones present at the beginning. In this site, a complex picture of adverse effects was observed, such as disease appearance (American foulbrood), higher mortality in the underbaskets (common to pesticide-stress site), behavioral alterations (queen changes, excess of honey storage) and biochemical anomalies (higher ALP activity at the end of the season). The overall results clearly indicate that the multi-stress conditions were able to induce biochemical, physiological and behavioral alterations which severely threatened bee colony survival.

Smart Wireless Acoustic Sensor Network Design for Noise Monitoring in Smart Cities.

This Special Issue is focused on all the technologies necessary for the development of an efficient wireless acoustic sensor network, from the first stages of its design to the tests conducted during deployment; its final performance; and possible subsequent implications for authorities in terms of the definition of policies. This Special Issue collects the contributions of several LIFE and H2020 projects aimed at the design and implementation of intelligent acoustic sensor networks, with a focus on the publication of good practices for the design and deployment of intelligent networks in any locations.

Accuracy of the Dynamic Acoustic Map in a Large City Generated by Fixed Monitoring Units.

DYNAMAP, a European Life project, aims at giving a real image of the noise generated by vehicular traffic in urban areas developing a dynamic acoustic map based on a limited number of low-cost permanent noise monitoring stations. The system has been implemented in two pilot areas located in the agglomeration of Milan (Italy) and along the Motorway A90 (Rome-Italy). The paper reports the final assessment of the system installed in the pilot area of Milan. Traffic noise data collected by the monitoring stations, each one representative of a number of roads (groups) sharing similar characteristics (e.g., daily traffic flow), are used to build-up a "real-time" noise map. In particular, we focused on the results of the testing campaign (21 sites distributed over the pilot area and 24 h duration of each recording). It allowed evaluating the accuracy and reliability of the system by comparing the predicted noise level of DYNAMAP with field measurements in randomly selected sites. To this end, a statistical analysis has been implemented to determine the error associated with such prediction, and to optimize the system by developing a correction procedure aimed at keeping the error below some acceptable threshold. The steps and the results of this procedure are given in detail. It is shown that it is possible to describe a complex road network on the basis of a statistical approach, complemented by empirical data, within a threshold of 3 dB provided that the traffic flow model achieves a comparable accuracy within each single groups of roads in the network.

The soundscape quality in some urban parks in Milan, Italy.

Urban parks play an important role in preserving and promoting the health of citizens who are often exposed to noise pollution and the stress of daily life. The present study describes the main results obtained from a survey performed in five urban parks in Milan. Measurements of the acoustic environment were carried out in 29 sites together with interviews with 231 users on certain aspects of the parks not limited to merely sound. Acoustic data show that the surveyed parks mostly do not comply with the noise limit issued by the Italian legislation on protected areas. The unweighted 1/3-octave spectrum centre of gravity G and LA50 perform satisfactorily in discriminating among the acoustic environments. Such clear distinction was not observed in the subjective ratings on the perceived quality of the soundscape, likely due to the influence by non-acoustic factors that act as mediators in the assessment. This hypothesis is supported by the collected data on the perceived quality of quietness, which was rated worse than that of the soundscape. Comparing acoustic data with ratings, the perceived quality of the total environment was found to be less dependent on LAeq than soundscape and quietness.