Prognosis and health management depend on sufficient prior knowledge of the degradation process of critical components to predict the remaining useful life. This task is composed of two phases: learning and prediction. The first phase uses the available information to learn the system’s behavior. The second phase predicts future behavior based on the available information of the system and estimates its remaining lifetime. Deep learning approaches achieve good prognostic performance but usually suffer from a high computational load and a lack of interpretability. Complex feature extraction models do not solve this problem, as they lose information in the learning phase and thus have a poor prognosis for the remaining lifetime. A new prepossessing approach is used with feature clustering to address this issue. It allows for restructuring the data into homogeneous groups strongly related to each other using a simple architecture of the LSTM model. It is advantageous in terms of learning time and the possibility of using limited computational capabilities. Then, we focus on the interpretability of deep learning prognosis using Explainable AI to achieve interpretable RUL prediction. The proposed approach offers model improvement and enhanced interpretability, enabling a better understanding of feature contributions. Experimental results on the available NASA C-MAPSS dataset show the performance of the proposed model compared to other common methods.

To assess the dental status of institutionalized intellectually disabled individuals in Lebanon and the role of background and behavioural determinants.

In predictive maintenance, the complexity of the data often requires the use of Deep Learning models. These models, called “black boxes”, have proved their worth in predicting the Remaining Useful Life (RUL) of industrial machines. However, the inherent opacity of these models requires the incorporation of post-hoc explanation methods to enhance transparency. The quality of the explanations provided is then assessed using so-called evaluation metrics. Modeling is a whole process that includes an important data preprocessing phase, with parameter selection such as time window, smoothing parameter, or rectified RUL when dealing with multivariate time series dataset. We propose to analyze the impact of these preprocessing methods on the quality of explanations provided by the local post-hoc models LIME, KernelSHAP, and L2X, utilizing six evaluation metrics: stability, consistency, congruence, selectivity, completeness, and acumen. This analysis will be based on NASA's Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset with the LSTM model. Our findings reveal that the choice of specific pre-processing parameters can significantly improve predictive performance. Furthermore, the quality of explanations depends on the selection of explicability methods. In addition, a factorial analysis of the evaluation metrics reveals that they do not all point in the same direction.Indeed, understanding the nuanced relationships between evaluation metrics is essential for a comprehensive and accurate assessment of explainability methods.