FOG affects between 50% and 80% of people with PD (Weiss et al., 2015), and its presence is associated with an increased risk of falls, affecting the quality of life (Moore et al., 2007). When a FOG episode appears, PD patients can present variability in the gait pattern, with a reduction in step length, shuffling steps, trembling of the legs, and total akinesia with a loss of movement of the limbs or trunk (Okuma, 2014). FOG episodes can have a duration of a few seconds (1 second or less for very short episodes and more than 5 seconds for long episodes) and appear more frequently during typical daily-life conditions than during straight walking assessments in clinical and laboratory settings (Okuma, 2014; Nonnekes et al., 2015). FOG assessment involves the identification of the presence (or absence) of FOG episodes and also aims to identify their severity (Mancini et al., 2019). Assessing FOG in the clinical practice is difficult because of the lack of an optimal freezing score, and difficulties related to the clinical assessment often performed on conditions that hinder the appearance of FOG events during evaluation; for example, the assessment is usually made in the ON state, while FOG occurs more often in OFF state (Schaafsma et al., 2003; Mancini et al., 2021). Although the clinical assessment provides relevant indicators for the characterization of FOG, the conditions whereby these are performed do not accurately represent the severity of FOG in daily life (Rahman et al., 2008; Snijders et al., 2008), such as the patients' homes, where FOG events tend to occur more frequently (Nieuwboer et al., 1998).

Robust strategies for Alzheimer's disease (AD) detection are important, given the high prevalence of AD. In this paper, we study the performance and generalizability of three approaches for AD detection from speech on the recent ADReSSo challenge dataset: 1) using conventional acoustic features 2) using novel pre-trained acoustic embeddings 3) combining acoustic features and embeddings. We find that while feature-based approaches have a higher precision, classification approaches relying on pre-trained embeddings prove to have a higher, and more balanced cross-validated performance across multiple metrics of performance. Further, embedding-only approaches are more generalizable. Our best model outperforms the acoustic baseline in the challenge by 2.8%.

Emotion recognition based on EEG has become an active research area. As one of the machine learning models, CNN has been utilized to solve diverse problems including issues in this domain. In this work, a study of CNN and its spatiotemporal feature extraction has been conducted in order to explore capabilities of the model in varied window sizes and electrode orders. Our investigation was conducted in subject-independent fashion. Results have shown that temporal information in distinct window sizes significantly affects recognition performance in both 10-fold and leave-one-subject-out cross validation. Spatial information from varying electrode order has modicum effect on classification. SVM classifier depending on spatiotemporal knowledge on the same dataset was previously employed and compared to these empirical results. Even though CNN and SVM have a homologous trend in window size effect, CNN outperformed SVM using leave-one-subject-out cross validation. This could be caused by different extracted features in the elicitation process.