An important subfield of brain–computer interface is the classification of motor imagery (MI) signals where a presumed action, for example, imagining the hands' motions, is mentally simulated. The brain dynamics of MI is usually measured by electroencephalography (EEG) due to its noninvasiveness. The next generation of brain–computer interface systems can benefit from the generative deep learning (GDL) models by providing end‐to‐end (e2e) machine learning and increasing their accuracy. In this study, to exploit the e2e‐property of deep learning models, a novel GDL methodology is proposed where only minimal objective‐free preprocessing steps are needed. Furthermore, to deal with the complicated multi‐class MI–EEG signals, an innovative multilevel GDL‐based classifying scheme is proposed. The effectiveness of the proposed model and its robustness against noisy MI–EEG signals is evaluated using two different GDL models, that is, deep belief network and stacked sparse autoencoder in e2e manner. Experimental results demonstrate the effectiveness of the proposed methodology with improved accuracy compared with the widely used filter bank common spatial patterns algorithm.

Data mining techniques are often confined to the delivery of frequent patterns and stop short of suggesting how to act on these patterns for business decision-making. They require human experts to post-process the discovered patterns manually. Therefore a significant need exists for techniques and tools with the ability to assist users in analyzing a large number of patterns to find usable knowledge. Action mining is one of these techniques which intelligently and automatically suggests some changes in the state of an object with the aim of gaining some profit in the corresponding domain. Up to now little research has been done in this field; in all cases continuous-valued data is handled by discretizing the associated attributes in advance or during the learning process. One inherent disadvantage in these methods is that using this sharp behavior can result in missing the optimal action. To overcome this problem this paper presents a method based on fuzzy set theory.In this paper, we concentrate on the fuzzy set based approach for the enhancement of Yang's method and present an algorithm that suggests actions which will decrease the degree to which a certain object belongs to an undesired status and increase the degree to which it belongs to a desired one. Our algorithm takes into account the fuzzy cost of actions, and further, it attempts to maximize the fuzzy net profit. The contribution of the work is in taking the output from fuzzy decision trees, and producing novel, actionable knowledge through automatic fuzzy post-processing. The performance of the proposed algorithm is compared with Yang's method using several real-life datasets taken from the UCI Machine Learning Repository. Experimental results show that the proposed algorithm outperforms Yang's method not only in finding more actions but also in finding actions with more fuzzy net profit.

In many business contexts, the ultimate goal of knowledge discovery is not the knowledge itself, but putting it to use. Models or patterns found by data mining methods often require further post-processing to bring this about. For instance, in churn prediction, data mining may give a model that predicts which customers are likely to end their contract, but companies are not just interested in knowing who is likely to do so, they want to know what they can do to avoid this. The models or patterns have to be transformed into actionable knowledge. Action mining explicitly addresses this.Currently, many action mining methods rely on a predictive model, obtained through data mining, to estimate the effect of certain actions and finally suggest actions with desirable effects. A major problem with this approach is that predictive models do not necessarily reflect a causal relationship between their inputs and outputs. This makes the existing action mining methods less reliable. In this paper, we introduce ICE-CREAM, a novel approach to action mining that explicitly relies on an automatically obtained best estimate of the causal relationships in the data. Experiments confirm that ICE-CREAM performs much better than the current state of the art in action mining. P. Shamsinejadbabaki et al. / Causality-based cost-effective action miningis not merely interested in predicting which customers it is going to lose, it wants to know what can be done to avoid this.Action Mining (AM) is the process of learning action rules from data. Not much work has been done in this area up till now. Existing work includes Yang et al.'s method for learning actions from decision trees [2,3], and several versions of Ras et al.'s DEAR system for discovering action rules [4][5][6]. In all of these methods, input data is in the form of a set of attribute-value pairs for each object. Furthermore, a certain profit is associated with specific values of one particular attribute, called the target attribute. These methods then try to uncover existing associations between the target attribute and other attributes, and use these associations for finding the most beneficial actions. The main difference between these methods is in the technique by which they find associations. For example, Yang's method uses decision trees, while DEAR 2 uses classification rules.Despite all innovations presented in existing AM methods, they suffer from an important drawback: they implicitly rely on the assumption that the available models (decision trees, association rules) are causal. It is well-known from statistics that association or correlation does not imply causation. Even though the learned models do not merely express the existence of a correlation, but its nature (in the form of a predictive function), they suffer from the same problem. If a function f : X → Y learned from a data set is found to be accurate, this means that, when we observe X = x in a new object, we can accurately predict that Y = f (x); but if we manually change the object's X value to X = x , the...