Abstract
This paper presents the application of textile based electrodes for surface electromyography embedded in a wearable locomotion data capture system for gait analysis. The system that is under development will allow the measurement of several locomotion-related parameters in a practical and non-invasive way, comfortable to the user, reusable which can be used by patients from light to severe impairments or disabilities. The present paper gives an overview of the research, regarding the design of the textile electrodes, the textile support, and communications.

Abstract
Os sistemas vestíveis são uma tendência crescente na aquisição de sinais fisiológicos e de parâmetros biomecânicos de forma não obstrutiva. A utilização de elétrodos têxteis tornou-se muito popular devido à simplicidade e homogeneidade providenciada pela sua introdução em têxteis e peças de vestuário. Neste trabalho foi realizada a validação de elétrodos têxteis para medições electromiográficas através da comparação com elétrodos convencionais de cloreto de prata. Os resultados evidenciam que os elétrodos têxteis são capazes de medir potenciais mioeléctricos de forma semelhante aos elétrodos convencionais.

Abstract
It is extremely difficult to simplify the relation between several body parts, which perform human motion, into one set of features. Mainly, the upper-limb is capable of a wider range of actions, going from fine manipulation to prehension and grasping. Aiming to describe its complexity, several studies have been conducted in order to better understand the upper-limb specificities. However, most of studies restrain the task to pointing, reaching, or grasping, which seems not enough to explain the wide range of tasks possible to be performed in a daily scenario.

Abstract

Abstract
Background and Objectives: Early detection of cognitive impairment is crucial for timely clinical interventions aimed at delaying progression to dementia. However, existing screening tools are not ideal for wide population screening. This study explores the potential of combining machine learning, specifically, one-class classification, with simpler and quicker motor-cognitive tasks to improve the early detection of cognitive impairment. Methods: We gathered data on gait, fingertapping, cognitive, and dual tasks from older adults with mild cognitive impairment and healthy controls. Using one-class classification, we modeled the behavior of the majority group (healthy controls), identifying deviations from this behavior as abnormal. To account for confounding effects, we integrated confound regression into the classification pipeline. We evaluated the performance of individual tasks, as well as the combination of features (early fusion) and models (late fusion). Additionally, we compared the results with those from two-class classification and a standard cognitive screening test. Results: We analyzed data from 37 healthy controls and 16 individuals with mild cognitive impairment. Results revealed that one-class classification had higher predictive accuracy for mild cognitive impairment, whereas two-class classification performed better in identifying healthy controls. Gait features yielded the best results for one-class classification. Combining individual models led to better performance than combining features from the different tasks. Notably, the one-class majority voting approach exhibited a sensitivity of 87.5% and a specificity of 75.7%, suggesting it may serve as a potential alternative to the standard cognitive screening test. In contrast, the two-class majority voting failed to improve the low sensitivities achieved by the individual models due to the underrepresentation of the impaired group. Conclusion: Our preliminary results support the use of one-class classification with confound control to detect abnormal patterns of gait, fingertapping, cognitive, and dual tasks, to improve the early detection of cognitive impairment. Further research is necessary to substantiate the method's effectiveness in broader clinical settings.