Abstract
Low-code application development as proposed by the OutSystems Platform enables fast mobile and desktop application development and deployment. It hinges on visual development of the interface and business logic but also on easy integration with data stores and services while delivering robust applications that scale. Data integration increasingly means accessing a variety of NoSQL stores. Unfortunately, the diversity of data and processing models, that make them useful in the first place, is difficult to reconcile with the simplification of abstractions exposed to developers in a low-code platform. Moreover, NoSQL data stores also rely on a variety of general purpose and custom scripting languages as their main interfaces. In this paper we report on building a polyglot data access layer for the OutSystems Platform that uses SQL with optional embedded script snippets to bridge the gap between low-code and full access to NoSQL stores.

Abstract
This work presents some approaches to overcome current Reinforcement Learning limits. We implement a simple virtual environment and some state-of-the-art Reinforcement Learning algorithms for testing and producing a baseline for comparison. Then we implement a Relational Reinforcement Learning algorithm that shows superior performance to the baseline but requires introducing human knowledge. We also propose that Model-based Reinforcement Learning can help us overcome some of the barriers. For better World models, we explore Inductive Logic Programming methods, such as First-Order Inductive Learner, and develop an improved version of it, more adequate to Reinforcement Learning environments. Finally we develop a novel Neural Network architecture, the Inductive Logic Neural Network, to fill the gaps of the previous implementations, that shows great promise.

Abstract
Nowadays, the operation of the smart distribution system (SDS) is more complicated with the penetration of electric vehicles (EVs), due to EVs' uncertainties as well as the capability of vehicle-to-grid (V2G). On the other hand, distribution transformers (DTs) which have to meet the demand of EVs are one of the essential components of SDS; indeed, their failure can lead to irreparable damage. The cause of most of these failures is overloading and high ambient temperature. The overloading increases the temperature of the various parts of the DTs, especially hot spot temperature (HST). Increasing this temperature reduces the nominal life of the DTs. With a high number of EVs in the future, and as a consequence high energy demand which has not been taken into account in proper operating program, it could lead to the overloading of DTs. So, in this paper, the loss of life (LOL) of a DT that feeds the residential loads and an EV parking lot (EV PL) is investigated. The maximization of the profit of the distribution system operator (DSO) is considered in two different parts i.e. with/without the appropriate operation coefficient (OC) of DT. Also, two different scenarios are applied i.e. charging mode (CM) of EVs and charging/discharging mode (CDM) of EVs. The results show that if the OC is not properly considered, the LOL of the transformers will be significantly high, implying a higher total ownership cost.

Abstract
Inertial Measurement Units (IMUs) have become a popular solution for tracking human motion. The main problem of using IMU data for deriving the position of different body segments throughout time is related to the accumulation of the errors in the inertial data. The solution to this problem is necessary to improve the use of IMUs for position tracking. In this work, we present several Machine Learning (ML) methods to improve the position tracking of various body segments when performing different movements. Firstly, classifiers were used to identify the periods in which the IMUs were stopped (zero-velocity detection). The models Random Forest, Support Vector Machine (SVM) and neural networks based on Long-Short-Term Memory (LSTM) layers were capable of identifying those periods independently of the motion and body segment with a substantially higher performance than the traditional fixed-threshold zero-velocity detectors. Afterwards, these techniques were combined with ML regression models based on LSTMs capable of estimating the displacement of the sensors during periods of movement. These models did not show significant improvements when compared with the more straightforward double integration of the linear acceleration data with drift removal for translational motion estimate. Finally, we present a model based on LSTMs that combined simultaneously zero-velocity detection with the translational motion of sensors estimate. This model revealed a lower average error for position tracking than the combination of the previously referred methodologies.

Abstract
The penetration of distributed generation in medium (MV) and low (LV) voltage distribution grids has been steadily increasing every year in multiple countries, thus creating new technical challenges in grid operation and motivating developments in distributed optimization for flexibility management. The traditional centralized optimal power flow (OPF) algorithm can solve technical constraints violation. However, computational efficiency, new technologies (e.g., edge computing) and control architectures (e.g., web-of-cells) are demanding for distributed approaches. This work formulates a novel distributed multi-period OPF for three-phase unbalanced grids that is essential when integrating energy storage units in operational planning (e.g., day-ahead) of LV or local energy community grids. The decentralized constrained optimization problem is solved with the alternating direction method of multipliers (ADMM) adapted for unbalanced LV grids and multi-period optimization problems. A 33-bus LV distribution grid is used as a case-study in order to define optimal battery storage scheduling along a finite time horizon that minimizes overall grid operational costs, while complying with technical constraints of the grid (e.g., voltage and current limits) and battery state-of-charge constraints.

Abstract
As entity-oriented search takes the lead in modern search, the need for increasingly flexible tools, capable of motivating innovation in information retrieval research, also becomes more evident. Army ANT is an open source framework that takes a step forward in generalizing information retrieval research, so that modern approaches can be easily integrated in a shared evaluation environment. We present an overview on the system architecture of Army ANT, which has four main abstractions: (i) readers, to iterate over text collections, potentially containing associated entities and triples; (ii) engines, that implement indexing and searching approaches, supporting different retrieval tasks and ranking functions; (iii) databases, to store additional document metadata; and (iv) evaluators, to assess retrieval performance for specific tasks and test collections. We also introduce the command line interface and the web interface, presenting a learn mode as a way to explore, analyze and understand representation and retrieval models, through tracing, score component visualization and documentation.