Abstract

Abstract
This article reports on the development of a Web platform for the study of Adverse Drug Events (ADEs). The platform is able to import ADE episodes from official Web sites, like OpenFDA, analyse the chemistry of the drugs involved, together with patient data, and produce a potential explanation based on the drugs interactions. Each study uses chemical knowledge to enrich the information on the molecules involved in the episodes. Data Mining is then used to construct models that can help in the explanation of the ADE occurrence and to predict future events. This paper reports on the Web portal developed and the Data Mining experiments conducted to evaluate the quality, and potential explanations of the forecasted adverse reactions, using real reports of drug administration and the subsequent adverse events. The results showed that it was possible to predict the outcomes of ADEs based on the structure of the molecules of the drugs involved and the data collected from real reports of drug administration up to an accuracy of 79%, while also predicting, with high accuracy, the severity of events where the outcome is the death of the patient (with a precision of 98.9%). The platform provides a less expensive and more accurate way of predicting adverse drug reactions compared to traditional methods. This study highlights the importance of understanding drug interactions at a molecular level and the usefulness of utilising Data Mining techniques in predicting ADEs.

Abstract
The oral microbiota is a highly complex and diversified part of the human microbiome. Being located at the interface between the human body and the exterior environment, this microbiota can deepen our understanding of the environmental impacts on the global status of human health. This research topic has been well addressed in Westernized populations, but these populations only represent a fraction of human diversity. Papua New Guinea hosts very diverse environments and one of the most unique human biological diversities worldwide. In this study we performed the first known characterization of the oral microbiome in 85 Papua New Guinean individuals living in different environments, using a qualitative and quantitative approach. We found a significant geographical structure of the Papua New Guineans oral microbiome, especially in the groups most isolated from urban spaces. In comparison to other global populations, two bacterial genera related to iron absorption were significantly more abundant in Papua New Guineans and Aboriginal Australians, which suggests a shared oral microbiome signature. Further studies will be needed to confirm and explore this possible regional-specific oral microbiome profile.

Abstract
Bin picking is a challenging problem that involves using a robotic manipulator to remove, one-by-one, a set of objects randomly stacked in a container. When the objects are prone to entanglement, having an estimation of their pose and shape is highly valuable for more reliable grasp and motion planning. This paper focuses on modeling entangled tubes with varying degrees of curvature. An unconventional machine learning technique, Inductive Logic Programming (ILP), is used to construct sets of rules (theories) capable of modeling multiple tubes when given the cylinders that constitute them. Datasets of entangled tubes are created via simulation in Gazebo. Experiments using Aleph and SWI-Prolog illustrate how ILP can build explainable theories with a high performance, using a relatively small dataset and low amount of time for training. Therefore, this work serves as a proof-of-concept that ILP is a valuable method to acquire knowledge and validate heuristics for pose and shape estimation in complex bin picking scenarios.

Abstract
Machine learning models are widely used in time series forecasting. One way to reduce its computational cost and increase its efficiency is to select only the relevant exogenous features to be fed into the model. With this intention, a study on the feature selection methods: Pearson correlation coefficient, Boruta, Boruta-Shap, IMV-LSTM, and LIME is performed. A new method focused on interpretability, SHAP-LSTM, is proposed, using a deep learning model training process as part of a feature selection algorithm. The methods were compared in 2 different datasets showing comparable results with lesser computational cost when compared with the use of all features. In all datasets, SHAP-LSTM showed competitive results, having comparatively better results on the data with a higher presence of scarce occurring categorical features.

Abstract
Nowadays, all kinds of sensors generate data, and more metrics are being measured. These large quantities of data are stored in large data centers and used to create datasets to train Machine Learning algorithms for most different areas. However, processing that data and training the Machine Learning algorithms require more time, and storing all the data requires more space, creating a Big Data problem. In this paper, we propose simple techniques for reducing large time series datasets into smaller versions without compromising the forecasting capability of the generated model and, simultaneously, reducing the time needed to train the models and the space required to store the reduced sets. We tested the proposed approach in three public and one private dataset containing time series with different characteristics. The results show, for the datasets studied that it is possible to use reduced sets to train the algorithms without affecting the forecasting capability of their models. This approach is more efficient for datasets with higher frequencies and larger seasonalities. With the reduced sets, we obtain decreases in the training time between 40 and 94% and between 46 and 65% for the memory needed to store the reduced sets.