Abstract
Analysis of student concentration can help to enhance the learning process. Emotions are directly related and directly reflect students’ concentration. This task is particularly difficult to implement in an e-learning environment, where the student stands alone in front of a computer. In this paper, a prototype system is proposed to figure out the concentration level in real-time from the expressed facial emotions during a lesson. An experiment was performed to evaluate the prototype system that was implemented using a client-side application that uses the C# code available in Microsoft Azure Emotion API. We have found that the emotions expressed are correlated with the concentration of the students, and devised three distinct levels of concentration (high, medium, and low). © Springer Nature Switzerland AG 2019.

Abstract
If done properly, physical exercise can help maintain fitness and health. The benefits of physical exercise could be increased with real time monitoring by measuring physical exercise intensity, which refers to how hard it is for a person to perform a specific task. This parameter can be estimated using various sensors, including contactless technology. Physical exercise intensity is usually synchronous to heart rate; therefore, if we measure heart rate, we can define a particular level of physical exercise. In this paper, we proposed a Convolutional Neural Network (CNN) to classify physical exercise intensity based on the analysis of facial images extracted from a video collected during sub-maximal exercises in a stationary bicycle, according to standard protocol. The time slots of the video used to extract the frames were determined by heart rate. We tested different CNN models using as input parameters the individual color components and grayscale images. The experiments were carried out separately with various numbers of classes. The ground truth level for each class was defined by the heart rate. The dataset was prepared to classify the physical exercise intensity into two, three, and four classes. For each color model a CNN was trained and tested. The model performance was presented using confusion matrix as metrics for each case. The most significant color channel in terms of accuracy was Green. The average model accuracy was 100%, 99% and 96%, for two, three and four classes classification, respectively. © 2019, Springer Nature Switzerland AG.

Abstract
In order to determine the physiological state of a plant it is necessary to monitor it throughout the developmental period. One of the main parameters to monitor is the Leaf Area Index (LAI). The objective of this work was the development of a non-destructive methodology for the LAI estimation in wine growing. This method is based on stereo images that allow to obtain a bard 3D representation, in order to facilitate the segmentation process, since to perform this process only based on color component becomes practically impossible due to the high complexity of the application environment. In addition, the Normalized Difference Vegetation Index will be used to distinguish the regions of the trunks and leaves. As an low-cost and non-evasive method, it becomes a promising solution for LAI estimation in order to monitor the productivity changes and the impacts of climatic conditions in the vines growth. © Springer Nature Switzerland AG 2019.

Abstract
Steep slope vineyards are a complex scenario for the development of ground robots due to the harsh terrain conditions and unstable localization systems. Automate vineyard tasks (like monitoring, pruning, spraying, and harvesting) requires advanced robotic path planning approaches. These approaches usually resort to Simultaneous Localization and Mapping (SLAM) techniques to acquire environment information, which requires previous navigation of the robot through the entire vineyard. The analysis of satellite or aerial images could represent an alternative to SLAM techniques, to build the first version of occupation grid map (needed by robots). The state of the art for aerial vineyard images analysis is limited to flat vineyards with straight vine’s row. This work considers a machine learning based approach (SVM classifier with Local Binary Pattern (LBP) based descriptor) to perform the vineyard segmentation from public satellite imagery. In the experiments with a dataset of satellite images from vineyards of Douro region, the proposed method achieved accuracy over 90%. © Springer Nature Switzerland AG 2019.

Abstract
The possibility to engage in autonomous flight through geolocation-based missions turns Unmanned Aerial Vehicles (UAV) into valuable tools that save time and resources in services like deliveries and surveillance. Amazon is already developing a drop-by delivery service, but there are limitations regarding the client’s id, that can be analyzed in three phases: the approach to the potential receiver, the authorization through the client id and the delivery itself. This work shows a solution for the first of these phases. Firstly, the receiver identifies the GPS coordinates where he wants to receive the package. The UAV flights to that place and tries to locate the receiver on the arrival through Computer Vision (CV) techniques, more precisely Deep Neural Networks (DNN), to continue to the next phase, the identification. After the proposal of the system’s architecture and the prototype’s implementation, a test scenario to analyze the feasibility of the proposed techniques was created. The results were quite good considering a system to look for one person in a limited area defined by the destination coordinates, confirming the detection of one person with an up to 92% accuracy from a 10 m height and 5 m horizontal distance in low resolution images. © Springer Nature Switzerland AG 2020.

Abstract
AppVox is a mobile application that provides support for children with speech and language impairments in their speech therapy sessions, while also allowing autonomous training at home. The application simulates a vocalizer with an audio stimulus feature, which can be used to train and amend the pronunciation of specific words through repetition. In this paper, we aim to present the development of the application as an assistive technology option, by adding new features to the vocalizer as well as assessing it as a usable option for daily training interaction for children with speech and language impairments. In this regard, we invited 15 children with speech and language impairments and 20 with no impairments to perform training activities with the application. Likewise, we asked three speech therapists and three usability experts to interact, assess, and give their feedback. In this assessment, we include the following parameters: successful conclusion of the training tasks (effectiveness); number of errors made, as well as number and type of difficulties found (efficiency); and the acceptance and level of comfort in completing the requested tasks (satisfaction). Overall, the results showed that children conclude the training tasks successfully and helped to improve their language and speech capabilities. Therapists and children gave positive feedback to the AppVox interface.