Abstract
Analysis of sports performance using mobile and wearable devices is becoming increasingly popular, helping users improve their sports practice. In this context, the goal of this work has been the development of an Apple Watch application, capable of detecting important strokes in the table tennis sport, using a deep learning (DL) model. A dataset of table tennis strokes has been created based on the watch's accelerometer and gyroscope sensors. The dataset collection was done in the Portuguese table tennis federation training sites, from several athletes, supervised by their coaches. To obtain the best DL model, three different architecture models where trained, compared and evaluated, using the complete dataset: a LSTM based on Create ML/Core ML frameworks (62.70% F1 score) and two Tensorflow based architectures, a CNN-LSTM (96.02% F1 score) and a ConvLSTM (97.33% F1 score).

Abstract

Abstract
Performance indicators, such as the SAIFI and the SAIDI, are commonly used by regulatory agencies to evaluate the performance of distribution companies (DisCos). Based on such indicators, it is common practice to apply penalties or grant rewards if the indicators are greater to or less than a given threshold. This work proposes a new multi-objective optimization model for pinpointing the critical assets involved in outage events based on past performance indicators, such as the SAIDI and the System Average Interruption Duration Exceeding Threshold (SAIDET) indexes. Our approach allows to retrieve the minimal set of assets in large historical interruption datasets that most contribute to past performance indicators. A case study using a real interruption dataset between the years 2011-2104 from a Brazilian DisCo revealed that the optimal inspection plan according to the decision maker preferences consist of 332 equipment out of a total of 5873. This subset of equipment, which contribute 61.90% and 55.76% to the observed SAIFI and SAIDET indexes in that period, can assist managerial decisions for preventive maintenance actions by prioritizing technical inspections to assets deemed as critical.

Abstract
Meta-learning is increasingly used to support the recommendation of machine learning algorithms and their configurations. These recommendations are made based on meta-data, consisting of performance evaluations of algorithms and characterizations on prior datasets. These characterizations, also called meta-features, describe properties of the data which are predictive for the performance of machine learning algorithms trained on them. Unfortunately, despite being used in many studies, meta-features are not uniformly described, organized and computed, making many empirical studies irreproducible and hard to compare. This paper aims to deal with this by systematizing and standardizing data characterization measures for classification datasets used in meta-learning. Moreover, it presents an extensive list of meta-features and characterization tools, which can be used as a guide for new practitioners. By identifying particularities and subtle issues related to the characterization measures, this survey points out possible future directions that the development of meta-features for meta-learning can assume.

Abstract
Manual vineyard yield estimation approaches are easy to use and can provide relevant information at early stages of plant development. However, such methods are subject to spatial and temporal variability as they are sample-based and dependent on historical data. The present work aims at comparing the accuracy of a new non-invasive and multicultivar, image-based yield estimation approach with a manual method. Non-disturbed grapevine images were collected from six cultivars, at three vineyard plots in Portugal, at the very beginning of veraison, in a total of 213 images. A stepwise regression model was used to select the most appropriate set of variables to predict the yield. A combination of derived variables was obtained that included visible bunch area, estimated total bunch area, perimeter, visible berry number and bunch compactness. The model achieved an R-2 = 0.86 on the validation set. The image-based yield estimates outperformed manual ones on five out of six cultivar data sets, with most estimates achieving absolute errors below 10%. Higher errors were observed on vines with denser canopies. The studied approach has the potential to be fully automated and used across whole vineyards while being able to surpass most bunch occlusions by leaves.

Abstract
This study investigates the potential of dynamically adjusting WIP cap levels to maximize the throughput (TH) performance and minimize work in process (WIP), according to real-time system state arising from process variability associated with low volume and high-variety production systems. Using an innovative approach based on state-of-the-art deep reinforcement learning (proximal policy optimization algorithm), we attain WIP reductions of up to 50% and 30%, with practically no losses in throughput, against pure-push systems and the statistical throughput control method (STC), respectively. An exploratory study based on simulation experiments was performed to provide support to our research. The reinforcement learning agent's performance was shown to be robust to variability changes within the production systems.