Abstract
Increasing the penetration of renewables on prosumers' side brings about operational challenges in the distribution grid due to their variable and uncertain behavior. In fact, these resources have increased the distribution grid net load fluctuation during recent years. In this article, the flexibility-oriented stochastic scheduling of a microgrid is suggested to capture the net load variability at the distribution grid level. In this scheduling, the flexibility limits are set to manage the net load fluctuation at a desirable level for the main grid operator. The uncertainties of load and renewables are considered, and their uncertainties are under control by the risk-averse strategy. Moreover, multiperiod islanding constraints are added to the problem, preparing the microgrid for a resilient response to disturbances. The model is examined on a typical distribution feeder consisting of prosumers and a microgrid. The numerical results are compared for both flexibility-oriented and traditional scheduling of a microgrid at the distribution level. The proposed model reduces the net load ramping of the distribution grid using an efficient dispatch of resources in the microgrid. A sensitivity analysis is also carried out to show the effectiveness of the model.

Abstract
Hybrid balancing is a recently-proposed class of battery balancing systems that simultaneously provide capacity and thermal equalization, while enabling hybridization with supercapacitors. This integration of functions poses a challenging control problem, requiring the fulfillment of multiple objectives (e.g., reduction of charge and temperature imbalances, energy losses and battery stress) and the coordination of a large number of power converters. To tackle this challenge, we propose a multi-layer model predictive control (MPC) framework, which splits the control tasks into two layers. The first layer uses long prediction horizons and a simplified model of the energy storage system to compute the state-of-charge reference for the supercapacitors. The second layer uses module-level models of the battery pack to track this reference, while minimizing charge and temperature imbalances with a small prediction horizon. Simulation results demonstrate that the multi-layer MPC provides similar performance as single-layer MPC, but at a fraction of the computational effort.

Abstract
Glaucoma is a silent disease that shows symptoms when severe, leading to partial vision loss or irreversible blindness. Early screening permits treating patients in time. For glaucoma screening, retinal images are very important since they enable the observation of initial glaucoma lesions, which typically begins with the cupping formation in the optic disc (OD). In clinical settings, practical indicators such as Cup-to-Disc Ratio (CDR) are frequently used to evaluate the presence and stage of glaucoma. The ratio between the cup and the optic disc can be measured using the vertical or horizontal diameter, or the area of the two. Mass screening programs are limited by the high costs of specialised teams and equipment. Current deep learning (DL) methods can assist the glaucoma mass screening, lower the cost and allow it to be extended to larger populations. With DL methods in the OD and optic cup (OC) segmentation, is possible to evaluate the presence of glaucoma in the patient more quickly based on cupping formation in the OD, using CDR. In this work, is assessed the contribution of Multi-Class and Single-Class segmentation methods for glaucoma screening using the 3 types of CDR. U-Net architecture is trained using transfer learning models (Inception V3 and Inception ResNet V2) to segment the OD and OC and then evaluate glaucoma prediction based on different types of CDRs indicators. The models were trained and evaluated on main public known databases (REFUGE, RIM-ONE r3 and DRISHTI-GS). The segmentation of both OD and OC reach Dice over 0.8 and IoU above 0.7. The CDRs were computed to glaucoma assessment where was reach sensitivity above 0.8, specificity of 0.7, F1-Score around 0.7 and AUC above 0.85. Finally, conclusions of segmentation methods showing adequate performance to be used in practical glaucoma screening.

Abstract
We present the CRAN R package MAINT.Data for the modelling and analysis of multivariate interval data, i.e., where units are described by variables whose values are intervals of IR, representing intrinsic variability. Parametric inference methodologies based on probabilistic models for interval variables have been developed, where each interval is represented by its midpoint and log-range, for which multivariate Normal and Skew-Normal distributions are assumed. The intrinsic nature of the interval variables leads to special structures of the variance-covariance matrix, which are represented by four different possible configurations. MAINT.Data implements the proposed methodologies in the S4 object system, introducing a specific data class for representing interval data. It includes functions and methods for modelling and analysing interval data, in particular maximum likelihood estimation, statistical tests for the different configurations, (M)ANOVA and Discriminant Analysis. For the Gaussian model, Model-based Clustering, robust estimation, outlier detection and Robust Discriminant Analysis are also available.

Abstract
This exploratory study aims to shed light on the e-commerce phenomenon and the impact of the pandemic COVID-19, namely in a period of social distancing and isolation. We study two prominent examples, via secondary data: Japan and the USA. We then analyze digital consumption behaviors and patterns in Portugal. For this, a questionnaire was created - using Google Forms - where both quantitative and qualitative perspectives were gathered. The research sample was a convenience sample, popular in business research, and it included 185 responses from Portuguese citizens. Through a cautious analysis of the primary data obtained, it was possible to compare the consumption levels in an ante- and post-COVID-19 context; what type of products are the most pursued; by whom they are most sought after; what are the most used platforms; and, additionally, the satisfaction levels regarding the use of these platforms. No statistically significant association (chi-square statistic) was found between gender or age and the preference for physical versus online stores. The data also uncovers that there is still a general preference for a more secure, traditional way of life in Portugal due to the fact that people still reveal some insecurities and fears regarding shopping through the Internet and a preference to buy in physical stores, which clearly leads people, in general, to buy online not so regularly as in other countries. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
In this paper we present three studies that demonstrate the applicability of spectroscopy methods and optical clearing treatments in pathology identification and monitoring. In the first study, by obtaining the absorption spectra of human healthy and pathological (adenocarcinoma) colorectal mucosa tissues, it was possible to identify a higher content of a pigment in the diseased tissues. This study also shows that machine learning methods can be used to reach the same differentiated results in vivo through diffuse reflectance spectroscopy. In the second study, the combination of collimated transmittance spectroscopy with optical clearing treatments allowed to obtain the diffusion coefficients of glucose in healthy and pathological colorectal mucosa as: Dglucose10´=5.8–7 cm2 /s and Dglucose10´=4.4–7 cm2/s, respectively. This study also demonstrated that the diseased tissues contains about 5% more mobile water than the healthy tissues. The third study was performed to evaluate the protein dissociation mechanism of optical clearing. By treating both healthy and pathological colorectal mucosa tissues with 93%-glycerol, a protein dissociation rate of about 3 times higher was obtained for the pathological mucosa. All the discriminating parameters that result from these studies can be obtained in the in vivo situation through diffuse reflectance spectroscopy and further studies to evaluate their values in different stages of cancer progression are of great importance to develop disease monitoring protocols. © J-BPE.