Abstract

Abstract

Abstract

Abstract
Rural regions are a typology of region rooted around the world. Its identity and matrix are differentiated from the most urbanized regions. Associated with rural areas is a strong negative feeling of depopulation, undeveloped business fabric, less wealth and less ability to attract investment and where public and private services from various sectors of activity are not concentrated. This reality cannot be socially accepted and must be fought for greater equity within countries. To leverage this change, rural regions will have to become co-competitive and attractive regions. In order for this transformation to take place, Information and Communication Technologies (ICT) play a major role. This article characterizes the rural regions in their demographic and economic dimensions, emphasizing the case of the Northeast region of Portugal. Analyse and review a set of fundamental vectors where ICT can be a key driver and enabler for smart rural regions to be created. Finally, it is presented a conceptual model of what can be a smart rural region. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
This paper presents a two-level optimization problem for optimal day-ahead scheduling of an active distribution system that utilizes renewable energy sources, distributed generation units, electric vehicles, and energy storage units and sells its surplus electricity to the upward electricity market. The active distribution system transacts electricity with multiple downward energy hubs that are equipped with combined cooling, heating, and power facilities. Each energy hub operator optimizes its day-ahead scheduling problem and submits its bid/offer to the upward distribution system operator. Afterwards, the distribution system operator explores the energy hub's bids/offers and optimizes the scheduling of its system energy resources for the day-ahead market. Further, he/she utilizes a demand response program alternative such as time-of-use and direct load control programs for downward energy hubs. In order to demonstrate the preference of the proposed method, the standard IEEE 33-bus test system is used to model the distribution system, and multiple energy hubs are used to model the energy hubs system. The proposed method increases the energy hubs electricity selling benefit about 185% with respect to the base case value; meanwhile, it reduces the distribution system operational costs about 82.2% with respect to the corresponding base case value.

Abstract
The application of pattern recognition techniques to data collected from accelerometers available in off-the-shelf devices, such as smartphones, allows for the automatic recognition of activities of daily living (ADLs). This data can be used later to create systems that monitor the behaviors of their users. The main contribution of this paper is to use artificial neural networks (ANN) for the recognition of ADLs with the data acquired from the sensors available in mobile devices. Firstly, before ANN training, the mobile device is used for data collection. After training, mobile devices are used to apply an ANN previously trained for the ADLs' identification on a less restrictive computational platform. The motivation is to verify whether the overfitting problem can be solved using only the accelerometer data, which also requires less computational resources and reduces the energy expenditure of the mobile device when compared with the use of multiple sensors. This paper presents a method based on ANN for the recognition of a defined set of ADLs. It provides a comparative study of different implementations of ANN to choose the most appropriate method for ADLs identification. The results show the accuracy of 85.89% using deep neural networks (DNN).