Abstract
Ambient assisted living (AAL) environments represent a key concept for dealing with the inevitable problem of population-ageing. Until recently, the use of computational intensive techniques, like Machine Learning (ML) or Computer Vision (CV), were not suitable for IoT end-nodes due to their limited resources. However, recent advances in edge intelligence have somehow changed this landscape for smart environments. This paper presents an AAL scenario where the use of ML is tested in kitchen appliances recognition using CV. The goal is to help users working with those appliances through Augmented Reality (AR) on a mobile device. Seven types of kitchen appliances were selected: blender, coffee machine, fridge, water kettle, microwave, stove, and toaster. A dataset with nearly 4900 images was organized. Three different deep learning (DL) models from the literature were selected, each with a total number of parameters and architecture compatibles with their execution on mobile devices. The results obtained in the training of these models reveal precision in the test set above 95% for the model with better results. The combination of edge AI and ML opens the application of CV in smart homes and AAL without compromising mandatory requirements as system privacy or latency.

Abstract
The knowledge of the optical properties of biological tissues in a wide spectral range is highly important for the development of noninvasive diagnostic or treatment procedures. The absorption coefficient is one of those properties, from which various information about tissue components can be retrieved. Using transmittance and reflectance spectral measurements acquired from ex vivo rabbit brain cortex samples allowed to calculate its optical properties in the ultraviolet to the near infrared spectral range. Melanin and lipofuscin, the two pigments that are related to the aging of tissues and cells were identified in the cortex absorption. By subtracting the absorption of these pigments from the absorption of the brain cortex, it was possible to evaluate the true ratios for the DNA/RNA and hemoglobin bands in the cortex—12.33-fold (at 260 nm), 12.02-fold (at 411 nm) and 4.47-fold (at 555 nm). Since melanin and lipofuscin accumulation increases with the aging of the brain tissues and are related to the degeneration of neurons and their death, further studies should be performed to evaluate the evolution of pigment accumulation in the brain, so that new optical methods can be developed to aid in the diagnosis and monitoring of brain diseases.

Abstract
In recent years, simultaneous participation in energy and ancillary services (AS) markets has been very profitable for microgrids (MG). High penetration of renewable energy sources (RES) in energy supply, due to the uncertainties of these products, increases the need for AS. Also, active and reactive powers are completely related, so in this paper the microgrid simultaneous participation in the active and reactive power and ancillary services (regulation up and regulation down, spinning reserve and non-spinning reserve) markets is modeled considering uncertainty of wind and solar generations. The relation between active and reactive power generation of each generator is calculated based on capability diagrams and mathematical equations. Conditional value at risk (CVaR) is used for risk management, and probability of calling ancillary services is calculated. Uncertainties of wind and solar generations are modeled using their probability distribution functions (PDFs). The ERCOT market simulation is discussed to calculate the participation of each unit in all the mentioned markets based on realworld data.

Abstract
This paper proposes a two-objective linearized resilient architecture (LRA) model for distribution networks to achieve a strictly resilient network during natural disasters like earthquakes and floods. To obtain this goal, the proposed LRA framework is based on the planning of the energy storage system (ESS), hardening and tie lines, and backup distributed generation (DG). Therefore, the proposed model minimizes the sum of planning and expected operation costs in the first objective function, and the total load shedding and repair costs originates from earthquakes and floods in the second objective function. Also, it constraints to the network planning model, linearized equations of the system operation, and system reconfiguration formulation. Moreover, stochastic programming models the uncertain availability of the network equipment during the natural disaster condition, the load and electricity price. In the next step, the e-constraint-based Pareto optimization is used to achieve an equivalent single-objective LRA model and obtain the best compromise solution. Finally, the proposed strategy is applied to a standard test distribution network. Numerical simulation confirms the capability of the proposed method in obtaining a resilient distribution network during natural disasters.

Abstract
Small and medium-sized enterprises (SMEs) in Europe are conscious that their competitive position depends on their success to embrace digitalisation challenges. However, some decision-makers in companies discard digital transformation because they do not understand how it can be incorporated into their businesses. Therefore, academia, research centres, and technological clusters are responsible for building the infrastructures and providing the support and the training that will progressively change this mindset. This paper aims to report an experience on designing a training program to train the trainers under the digital transformation topic. To define strategies to understand better the companies (and professionals) needs and motivations and the requisites to deliver the training course, the focus group methodology was applied. In this paper, we present a training program methodology and structure that intend to respond to industrial requests and, in this way to accelerate the digital transformation of companies, especially SMEs.

Abstract
Hyperspectral sensors mounted in unmanned aerial vehicles offer new opportunities to explore high-resolution multitemporal spectral analysis in remote sensing applications. Nevertheless, the use of hyperspectral data still poses challenges mainly in postprocessing to correct from high geometric deformation of images. In general, the acquisition of high-quality hyperspectral imagery is achieved through a time-consuming and complex processing workflow. However, this effort is mandatory when using hyperspectral imagery in a multisensor data fusion perspective, such as with thermal infrared imagery or photogrammetric point clouds. Push-broom hyperspectral sensors provide high spectral resolution data, but its scanning acquisition architecture imposes more challenges to create geometrically accurate mosaics from multiple hyperspectral swaths. In this article, an efficient method is presented to correct geometrical distortions on hyperspectral swaths from push-broom sensors by aligning them with an RGB photogrammetric orthophoto mosaic. The proposed method is based on an iterative approach to align hyperspectral swaths with an RGB photogrammetric orthophoto mosaic. Using as input preprocessed hyperspectral swaths, apart from the need of introducing some control points, the workflow is fully automatic and consists of: adaptive swath subdivision into multiple fragments; detection of significant image features; estimation of valid matches between individual swaths and the RGB orthophoto mosaic; and calculation of the best geometric transformation model to the retrieved matches. As a result, geometrical distortions of hyperspectral swaths are corrected and an orthomosaic is generated. This methodology provides an expedite solution able to produce a hyperspectral mosaic with an accuracy ranging from two to five times the ground sampling distance of the high-resolution RGB orthophoto mosaic, enabling the hyperspectral data integration with data from other sensors for multiple applications.