Abstract
For the regularly medicated population, the management of the posology is of utmost importance. With increasing average life expectancy, people tend to become older and more likely to have chronic medical disorders, consequently taking more medicines. This is predominant in the older population, but it’s not exclusive to this generation. It’s a common problem for all those suffering from chronic diseases, regardless of age group. Performing a correct management of the medicines stock, as well as, taking them at the ideal time, is not always easy and, in some cases, the diversity of medicines needed to treat a particular medical disorder is a proof of that. Knowing what to take, how much to take, and ensuring compliance with the medication intervals, for each medication in use, becomes a serious problem for those who experience this reality. The situation is aggravated when the posology admits variable amounts, intervals, and combinations depending on the patient’s health condition. This paper presents a solution that optimizes the management of medication of users who use the services of institutions that provide health care to the elderly (e.g., day care centers or nursing homes). Making use of the NB-IoT network, artificial intelligence algorithms, a set of sensors and an Arduino MKR NB 1500, this solution, in addition to the functionalities already described, eHealthCare also has mechanisms that allow identifying the non-adherence to medication by the elderly.

Abstract
The location of a new substation is a key factor in the expansion of electrical distribution systems. This location is strategic from the point of view of the costs associated with energy supply; therefore, a holistic and integral planning of sub-transmission and primary distribution subsystems requires the development of suitable optimization methods to support the decision process. Although future electric load growth is a critical factor to define capacity and location of new substations, other technical, environmental, soil characteristics, risk, social, and administrative criteria that influence the final location are also crucial. A multicriteria decision analysis based on geographic information system is proposed in this paper to combine those criteria taking into account decision makers' preferences and physical restrictions on land use. The main contributions of this paper are the identification of the criteria and the analysis of service areas in existing substations to impose constraints on the problem. A spatial heat map that facilitates the visual interpretation of the spatial relations of the criteria is produced based on a suitability score. The proposed method was evaluated in the service area of an Ecuadorian distribution energy utility. It was found that the two more important criteria are the electric load density and the distance to subtransmission network with weights of 44% and 23%, respectively. The proposed analysis is able to identify ideal locations for new substations, which can be used by the planner to find the best long-term network expansion alternative.

Abstract
Quality automobile inspection is one of the critical application areas to achieve better quality at low cost and can be obtained with the advance computer vision technology. Whether for the quality inspection or the automatic assembly of automobile parts, automatic recognition of automobile parts plays an important role. In this article, vehicle parts are classified using deep neural network architecture designed based on ConvNet. The public dataset available in CompCars [1] were used to train and test a VGG16 deep learning architecture with a fully connected output layer of 8 neurons. The dataset has 20,439 RGB images of eight interior and exterior car parts taken from the front view. The dataset was first separated for training and testing purpose, and again training dataset was divided into training and validation purpose. The average accuracy of 93.75% and highest accuracy of 97.2% of individual parts recognition were obtained. The classification of car parts contributes to various applications, including car manufacturing, model verification, car inspection system, among others. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

Abstract
Wikipedia is an online, free, multi-language, and collaborative encyclopedia, currently one of the most significant information sources on the web. The open nature of Wikipedia contributions raises concerns about the quality of its information. Previous studies have addressed this issue using manual evaluations and proposing generic measures for quality assessment. In this work, we focus on the quality of health-related content. For this purpose, we use general and health-specific features from Wikipedia articles to propose health-specific metrics. We evaluate these metrics using a set of Wikipedia articles previously assessed by WikiProject Medicine. We conclude that it is possible to combine generic and specific metrics to determine health-related content's information quality. These metrics are computed automatically and can be used by curators to identify quality issues. Along with the explored features, these metrics can also be used in approaches that automatically classify the quality of Wikipedia health-related articles.

Abstract
Convolutional neural networks are shown to be vulnerable to changes in the background. The proposed method is an end-to-end method that augments the training set by introducing new backgrounds during the training process. These backgrounds are created by a generative network that is trained as an adversary to the model. A case study is explored based on overhead power line insulators detection using a drone - a training set is prepared from photographs taken inside a laboratory and then evaluated using photographs that are harder to collect from outside the laboratory. The proposed method improves performance by over 20% for this case study.

Abstract