As machine learning models become increasingly prevalent in time series applications, Explainable Artificial Intelligence (XAI) methods are essential for understanding their predictions. Within XAI, feature attribution methods aim to identify which input features contributed the most to a model's prediction, with their evaluation typically relying on perturbation-based metrics. Through empirical analysis across multiple datasets, model architectures, and perturbation strategies, we identify important class-dependent effects in these metrics: they show varying effectiveness across classes, achieving strong results for some while remaining less sensitive to others. In particular, we find that the most effective perturbation strategies often demonstrate the most pronounced class differences. Our analysis suggests that these effects arise from the learned biases of classifiers, indicating that perturbation-based evaluation may reflect specific model behaviors rather than intrinsic attribution quality. We propose an evaluation framework with a class-aware penalty term to help assess and account for these effects in evaluating feature attributions. Although our analysis focuses on time series classification, these class-dependent effects likely extend to other structured data domains where perturbation-based evaluation is common.

This empirical study proposes a novel methodology to measure users' perceived trust in an Explainable Artificial Intelligence (XAI) model. To do so, users' mental models are elicited using Fuzzy Cognitive Maps (FCMs). First, we exploit an interpretable Machine Learning (ML) model to classify suspected COVID-19 patients into positive or negative cases. Then, Medical Experts' (MEs) conduct a diagnostic decision-making task based on their knowledge and then prediction and interpretations provided by the XAI model. In order to evaluate the impact of interpretations on perceived trust, explanation satisfaction attributes are rated by MEs through a survey. Then, they are considered as FCM's concepts to determine their influences on each other and, ultimately, on the perceived trust. Moreover, to consider MEs' mental subjectivity, fuzzy linguistic variables are used to determine the strength of influences. After reaching the steady state of FCMs, a quantified value is obtained to measure the perceived trust of each ME. The results show that the quantified values can determine whether MEs trust or distrust the XAI model. We analyze this behavior by comparing the quantified values with MEs' performance in completing diagnostic tasks.

In this paper, we integrate the concepts of feature importance with implicit bias in the context of pattern classification. This is done by means of a three-step methodology that involves (i) building a classifier and tuning its hyperparameters, (ii) building a Fuzzy Cognitive Map model able to quantify implicit bias, and (iii) using the SHAP feature importance to active the neural concepts when performing simulations. The results using a real case study concerning fairness research support our two-fold hypothesis. On the one hand, it is illustrated the risks of using a feature importance method as an absolute tool to measure implicit bias. On the other hand, it is concluded that the amount of bias towards protected features might differ depending on whether the features are numerically or categorically encoded.

This paper proposes an algorithm called Forward Composition Propagation (FCP) to explain the predictions of feed-forward neural networks operating on structured pattern recognition problems. In the proposed FCP algorithm, each neuron is described by a composition vector indicating the role of each problem feature in that neuron. Composition vectors are initialized using a given input instance and subsequently propagated through the whole network until we reach the output layer. It is worth mentioning that the algorithm is executed once the network's training network is done. The sign of each composition value indicates whether the corresponding feature excites or inhibits the neuron, while the absolute value quantifies such an impact. Aiming to validate the FCP algorithm's correctness, we develop a case study concerning bias detection in a state-of-the-art problem in which the ground truth is known. The simulation results show that the composition values closely align with the expected behavior of protected features.

In this paper, we present a recurrent neural system named Long Short-term Cognitive Networks (LSTCNs) as a generalisation of the Short-term Cognitive Network (STCN) model. Such a generalisation is motivated by the difficulty of forecasting very long time series in an efficient, greener fashion. The LSTCN model can be defined as a collection of STCN blocks, each processing a specific time patch of the (multivariate) time series being modelled. In this neural ensemble, each block passes information to the subsequent one in the form of a weight matrix referred to as the prior knowledge matrix. As a second contribution, we propose a deterministic learning algorithm to compute the learnable weights while preserving the prior knowledge resulting from previous learning processes. As a third contribution, we introduce a feature influence score as a proxy to explain the forecasting process in multivariate time series. The simulations using three case studies show that our neural system reports small forecasting errors while being up to thousands of times faster than state-of-the-art recurrent models.