The European flounder Platichthys flesus is a widely distributed epibenthic species and an important component of demersal fish assemblages in the European Atlantic coastal waters. In Portuguese estuaries, this species reaches high densities, especially in Minho estuary (NW Iberian Peninsula, Europe), potentially playing an important role in the system's ecology. In this context, the population structure, production and the habitat use of juvenile P. flesus were investigated. Sampling took place monthly, from February 2009 until July 2010 along the entire estuarine gradient (5 sampling stations distributed in the first 29 km from the river mouth, with S1 located near the river mouth, S2 inside A C C E P T E D M A N U S C R I P T ACCEPTED MANUSCRIPT2 a salt marsh, S3 in a salinity transition zone, while S4 and S5 were located in the upper estuary). Flounder's density varied significantly among sampling stations and seasons (Two-way PERMANOVA: p < 0.001), with the majority of the individuals being found during the spring (30.1%) and in S3 and S4 (72.6%). Males and females presented an even distribution, with a higher proportion of males observed during summer. Fish length also differed among sampling stations and seasons (Two-way PERMANOVA: p < 0.001), with larger fishes being found in S1 during the autumn (168.50 ± 59.50 mm) and the smallest in S4 during the spring (33.80 ± 3.12 mm). Size classes associated differently with environmental variables, with larger juveniles being more abundant in the downstream areas of the estuary, whereas smaller juveniles were related to higher water temperatures, suggesting a habitat segregation of P. flesus of different sizes. The fish condition of P. flesus in Minho estuary was higher than in other systems, probably due to the dominance of juveniles on the population. Also, the densities found in this estuary were up to 32 times higher than in other locations, suggesting that Minho estuary is an important nursery area for the species. The estimated secondary production of P. flesus was lower than previous studies acknowledged in the system (0.037 g.WWm -2 .year -1 ), indicating that the production of this species in estuaries can vary considerably depending of several factors such as the sampling year and strategy, population and fish size.

Audio recognition can be used in smart cities for security, surveillance, manufacturing, autonomous vehicles, and noise mitigation, just to name a few. However, urban sounds are everyday audio events that occur daily, presenting unstructured characteristics containing different genres of noise and sounds unrelated to the sound event under study, making it a challenging problem. Therefore, the main objective of this literature review is to summarize the most recent works on this subject to understand the current approaches and identify their limitations. Based on the reviewed articles, it can be realized that dl architectures, attention mechanisms, data augmentation techniques, and pretraining are the most crucial factors to consider while creating an efficient sound classification model. The best-found results were obtained by Mushtaq and Su, in 2020, using a DenseNet-161 with pretrained weights from ImageNet, and NA-1 and NA-2 as augmentation techniques, which were of 97.98%, 98.52%, and 99.22% for UrbanSound8K, ESC-50, and ESC-10 datasets, respectively. Nonetheless, the use of these models in real-world scenarios has not been properly addressed, so their effectiveness is still questionable in such situations.

Many relevant sound events occur in urban scenarios, and robust classification models are required to identify abnormal and relevant events correctly. These models need to identify such events within valuable time, being effective and prompt. It is also essential to determine for how much time these events prevail. This article presents an extensive analysis developed to identify the best-performing model to successfully classify a broad set of sound events occurring in urban scenarios. Analysis and modelling of Transformer models were performed using available public datasets with different sets of sound classes. The Transformer models’ performance was compared to the one achieved by the baseline model and end-to-end convolutional models. Furthermore, the benefits of using pre-training from image and sound domains and data augmentation techniques were identified. Additionally, complementary methods that have been used to improve the models’ performance and good practices to obtain robust sound classification models were investigated. After an extensive evaluation, it was found that the most promising results were obtained by employing a Transformer model using a novel Adam optimizer with weight decay and transfer learning from the audio domain by reusing the weights from AudioSet, which led to an accuracy score of 89.8% for the UrbanSound8K dataset, 95.8% for the ESC-50 dataset, and 99% for the ESC-10 dataset, respectively.