Abstract

Abstract
Non-native plant species can have a negative impact in the ecosystems and in local economies when they spread uncontrollably. Monitoring tools can support their management and spread. In this paper, an exploratory approach is presented for pixelwise detection of Acacia dealbata from UAV-based imagery acquired from RGB and multispectral sensors. Four machine learning algorithms-k-nearest neighbors (KNN), random forest (RF), adaptive boosting (AdaBoost) and a linear kernel SVM (LSVM)-Are trained using four datasets (hue, saturation and value-HSV, multispectral-MSP, RGB and a combination of all features) and their classification performance is evaluated. RF classifier obtained the overall best performance, with an accuracy above 86% in all data combinations, with LSVM showing the poorer results. Obtained results are encouraging for monitoring invasive species and can serve as a base for future improvements to detect invasive species.

Abstract
This paper presents a novel method for resiliency assessment of the distribution system considering smart homes' arbitrage strategies in the day-ahead and real-time markets. The main contribution of this paper is that the impacts of smart homes' arbitrage strategy on the resilient operation of the distribution system are explored. The optimal commitment of smart homes in external shock conditions is another contribution of this paper. An arbitrage index is proposed to explore the impacts of this process on the system costs and resiliency of the system. A two-level optimization process is proposed for day-ahead and real-time markets. At the first stage of the first level, the optimal bidding strategies of smart homes are estimated for the day-ahead market. Then, the database is updated and the optimal bidding strategies of smart homes for real-time horizon are assessed in the second stage of the first level problem. At the first stage of the second level problem, the optimal day-ahead scheduling of the distribution system is performed considering the arbitrage and resiliency indices. At the second stage of the second level, the distribution system optimal scheduling is carried out for the real-time horizon. Finally, at the third stage of the second level, if an external shock is detected, the optimization process determines the optimal dispatch of system resources. The proposed method is assessed for the 33-bus and 123-bus IEEE test systems. The proposed framework reduced the expected values of aggregated costs of 33-bus and 123-bus systems by about 62.14 % and 32.06 % for the real-time horizon concerning the cases in which the smart homes performed arbitrage strategies. Furthermore, the average values of the locational marginal price of 33-bus and 123-bus systems were reduced by about 59.38 % and 63.98 % concerning the case that the proposed method was not implemented.

Abstract
Driven by the high fidelity and low cost of the latest head-mounted devices reaching the consumer market, Virtual Reality (VR) is a technology upon which rests increased expectations for improving education and training outcomes. The unique capacity of VR to produce experiences with high levels of immersion, presence, and interactivity, opens a series of prospects to improve the learning of declarative, procedural, and practical knowledge through a new modality of educational content. This paper explores some of the most promising opportunities of VR through the development and evaluation of Sea of Cells, an immersive VR interactive experience to enhance the learning of the prokaryotic cell. Methodologies to introduce the VR experience, both inside and outside classes, were also explored by analysing assessments from several Portuguese biology teachers. A test pilot made through video demonstration, shows a promising future for VR in education. Despite the physical limitations of the pilot study, due to Covid, after presenting the project to 7 10th grade Biology teachers, it was concluded that VR might be a relevant and innovative tool for educational settings. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Abstract
Deep learning (DL) is becoming increasingly popular in numerous application fields within the current Fourth Industrial Revolution (4IR) era. This is mainly due to its capability for providing accurate predictions and reliable consistency in decision-making. Bridge engineering focused on structure monitoring and inspection is a crucial activity for disaster prevention. Therefore, it is an application field wherein synergies between professional knowledge and sophisticated machine-based analytics strategies can be established and even drive time-effective interventions. This paper presents a comparison of DL models used to detect defects in bridges, resorting to the following architectures: MobileNetV2, Xception, InceptionV3, NASNetMobile, Visual Geometry Group Network-16 (VGG16), and InceptionResNetV2. Different optimizers (e.g., Nadam, Adam, RMSprop, and SGD) crossed with distinct learning rates (e.g., 1, 10-1, 10-2, 10-3, 10-4, and 10-5) were employed. VGG16, Xception, and NASNetMobile showed the most stable learning curves. Moreover, Gradient-weighted Class Activation Mapping (Grad-CAM) overlapping images clarifies that InceptionResNetV2 and InceptionV3 models seek features outside the areas of interest (defects). Comparing optimizers performance, the adaptive ones outperform SGD with decay schedulers for learning rates.

Abstract
This study aimed to validate the Patient Health Questionnaire (PHQ-8) in a sample of military personnel, through the analysis of psychometric properties, reliability, and confirmatory factorial analysis. The questionnaire consists of 8 items that allow the assessment of depressive symptoms. The sample included 127 Portuguese military personnel aged between 21 and 78 years old. The results revealed a good internal consistency (a=.90) and good adjustment indices (?2/df=1.332, GFI=.956, CFI=.988, RMSEA=.051, SRMR=.30). In addition, convergent validity also showed to be good and composite reliability was .873. Thus, the PHQ-8 reveals good psychometric properties, being recommended for use in clinical practice and research with Portuguese military. © 2022 AIDEP. All rights reserved.