A model based on environmental factors for diameter distribution in black wattle in Brazil

Towards Amazon Forest Restoration: Automatic Detection of Species from UAV Imagery

Precise assessments of forest species’ composition help analyze biodiversity patterns, estimate wood stocks, and improve carbon stock estimates. Therefore, the objective of this work was to evaluate the use of high-resolution images obtained from Unmanned Aerial Vehicle (UAV) for the identification of forest species in areas of forest regeneration in the Amazon. For this purpose, convolutional neural networks (CNN) were trained using the Keras–Tensorflow package with the faster_rcnn_inception_v2_pets model. Samples of six forest species were used to train CNN. From these, attempts were made with the number of thresholds, which is the cutoff value of the function; any value below this output is considered 0, and values above are treated as an output 1; that is, values above the value stipulated in the Threshold are considered as identified species. The results showed that the reduction in the threshold decreases the accuracy of identification, as well as the overlap of the polygons of species identification. However, in comparison with the data collected in the field, it was observed that there exists a high correlation between the trees identified by the CNN and those observed in the plots. The statistical metrics used to validate the classification results showed that CNN are able to identify species with accuracy above 90%. Based on our results, which demonstrate good accuracy and precision in the identification of species, we conclude that convolutional neural networks are an effective tool in classifying objects from UAV images.

Heracles: A Context-Based Multisensor Sensor Data Fusion Algorithm for the Internet of Things

In the Internet of Things (IoT), extending the average battery duration of devices is of paramount importance, since it promotes uptime without intervention in the environment, which can be undesirable or costly. In the IoT, the system’s functionalities are distributed among devices that (i) collect, (ii) transmit and (iii) apply algorithms to process and analyze data. A widely adopted technique for increasing the lifetime of an IoT system is using data fusion on the devices that process and analyze data. There are already several works proposing data fusion algorithms for the context of wireless sensor networks and IoT. However, most of them consider that application requirements (such as the data sampling rate and the data range of the events of interest) are previously known, and the solutions are tailored for a single target application. In the context of a smart city, we envision that the IoT will provide a sensing and communication infrastructure to be shared by multiple applications, that will make use of this infrastructure in an opportunistic and dynamic way, with no previous knowledge about its requirements. In this work, we present Heracles, a new data fusion algorithm tailored to meet the demands of the IoT for smart cities. Heracles considers the context of the application, adapting to the features of the dataset to perform the data analysis. Heracles aims at minimizing data transmission to save energy while generating value-added information, which will serve as input for decision-making processes. Results of the performed evaluation show that Heracles is feasible, enhances the performance of decision methods and extends the system lifetime.