Abstract

Abstract
There have been several research works proposing new Explainable AI (XAI) methods designed to generate model explanations having specific properties, or desiderata, such as fidelity, robustness, or human-interpretability. However, explanations are seldom evaluated based on their true practical impact on decision-making tasks. Without that assessment, explanations might be chosen that, in fact, hurt the overall performance of the combined system of ML model + end-users. This study aims to bridge this gap by proposing XAI Test, an application-grounded evaluation methodology tailored to isolate the impact of providing the end-user with different levels of information. We conducted an experiment following XAI Test to evaluate three popular XAI methods - LIME, SHAP, and TreeInterpreter - on a real-world fraud detection task, with real data, a deployed ML model, and fraud analysts. During the experiment, we gradually increased the information provided to the fraud analysts in three stages: Data Only, i.e., just transaction data without access to model score nor explanations, Data + ML Model Score, and Data + ML Model Score + Explanations. Using strong statistical analysis, we show that, in general, these popular explainers have a worse impact than desired. Some of the conclusion highlights include: i) showing Data Only results in the highest decision accuracy and the slowest decision time among all variants tested, ii) all the explainers improve accuracy over the Data + ML Model Score variant but still result in lower accuracy when compared with Data Only; iii) LIME was the least preferred by users, probably due to its substantially lower variability of explanations from case to case. © 2021 ACM.

Abstract
With the greater awareness of climate change, the exponential expansion in the world population's energy needs, and other factors, many countries are producing and using renewable energy sources. However, this type of energy comes with a high cost associated with operation and maintenance. The importance of predictive maintenance in this area is growing, providing valuable insights for strategic decision-making. This paper aims to detect failures in wind turbines early. In our first approach, we considered the Page-Hinkley Test with a sliding window on the different vital components' temperature as a fault detection method. The second approach involved moving averages methods for forecasting the temperature of the different components. Our results showed that both methods could detect failures at least three days before and one day after the failure occurs.

Abstract

Abstract
Analyzing the way individuals move is fundamental to understand the dynamics of humanity. Transportation mode plays a significant role in human behavior as it changes how individuals travel, how far, and how often they can move. The identification of transportation modes can be used in many applications and it is a key component of the internet of things (IoT) and the Smart Cities concept as it helps to organize traffic control and transport management. In this paper, we propose the use of ensemble methods to infer the transportation modes using raw GPS data. From latitude, longitude, and timestamp we perform feature engineering in order to obtain more discriminative fields for the classification. We test our features in several machine learning algorithms and among those with the best results we perform feature selection using the Boruta method in order to boost our accuracy results and decrease the amount of data, processing time, and noise in the model. We assess the validity of our approach on a real-world dataset with several different transportation modes and the results show the efficacy of our approach.

Abstract
This Portuguese project compares the classification of AI risks and vulnerabilities performed by humans and performed by the computing algorithms.