Clustering is a powerful machine learning tool for detecting structures in datasets. In the medical field, clustering has been proven to be a powerful tool for discovering patterns and structure in labeled and unlabeled datasets. Unlike supervised methods, clustering is an unsupervised method that works on datasets in which there is no outcome (target) variable nor is anything known about the relationship between the observations, that is, unlabeled data. In this paper, we focus on studying and reviewing clustering methods that have been applied to datasets of neurological diseases, especially Alzheimer’s disease (AD). The aim is to provide insights into which clustering technique is more suitable for partitioning patients of AD based on their similarity. This is important as clustering algorithms can find patterns across patients that are difficult for medical practitioners to find. We further discuss the implications of the use of clustering algorithms in the treatment of AD. We found that clustering analysis can point to several features that underlie the conversion from early-stage AD to advanced AD. Furthermore, future work can apply semi-clustering algorithms on AD datasets, which will enhance clusters by including additional information.

Detecting the cognitive profiles of learners is an important step towards personalized and adaptive learning. Electroencephalograms (EEG) have been used to detect the subject’s emotional and cognitive states. In this paper, an approach for detecting two cognitive skills, focused attention and working memory, using EEG signals is proposed. The proposed approach consists of the following main steps: first, subjects undergo a scientifically-validated cognitive assessment test that stimulates and measures their full cognitive profile while putting on a 14-channel wearable EEG headset. Second, the scores of focused attention and working memory are extracted and encoded for a classification problem. Third, the collected EEG data are analyzed and a total of 280 time- and frequency-domain features are extracted. Fourth, several classifiers were trained to correctly classify and predict three levels (low, average, and high) of the two cognitive skills. The classification accuracies that were obtained on 86 subjects were 84% and 81% for the focused attention and working memory, respectively. In comparison with similar approaches, the obtained results indicate the generalizability and suitability of the proposed approach for the detection of these two skills. Thus, the presented approach can be used as a step towards adaptive learning where real-time adaptation is to be done according to the predicted levels of the measured cognitive skills.

Detecting cognitive profiles is critical to efficient adaptive learning systems that automatically adjust the content delivered depending on the learner’s cognitive states and skills. This study explores electroencephalography (EEG) and facial expressions as physiological monitoring tools to build models that detect two cognitive states, namely, engagement and instantaneous attention, and three cognitive skills, namely, focused attention, planning, and shifting. First, while wearing a 14-channel EEG Headset and being videotaped, data has been collected from 127 subjects taking two scientifically validated cognitive assessments. Second, labeling was performed based on the scores obtained from the used tools. Third, different shallow and deep models were experimented in the two modalities of EEG and facial expressions. Finally, the best performing models for the analyzed states are determined. According to the used performance measure, which is the f-beta score with beta = 2, the best obtained results for engagement, instantaneous attention, and focused attention are EEG-based models with 0.86, 0.82, and 0.63 scores, respectively. As for planning and shifting, the best performing models are facial expressions-based models with 0.78 and 0.81, respectively. The obtained results show that EEG and facial expressions contain important and different cues and features about the analyzed cognitive states, and hence, can be used to automatically and non-intrusively detect them.

No abstract

In this paper, we extend the Maximum Satisfiability (MaxSAT) problem to Lukasiewicz logic. The MaxSAT problem for a set of formulae Φ is the problem of finding an assignment to the variables in Φ that satisfies the maximum number of formulae. Three possible solutions (encodings) are proposed to the new problem: (1) Disjunctive Linear Relations (DLRs), (2) Mixed Integer Linear Programming (MILP) and (3) Weighted Constraint Satisfaction Problem (WCSP). Like its Boolean counterpart, the extended fuzzy MaxSAT will have numerous applications in optimization problems that involve vagueness.