Recent advancement in wearable technologies, particularly smart watches embedded with powerful processors, memory subsystems with various built-in sensors such as accelerometer, gyroscope and optical sensor in one single package has opened a whole new application space. One of the main applications of interest is the monitoring of movement patterns, heart rate, ECG and PPG particularly for longer duration's in natural environments. In this study, we conducted a performance evaluation on the optical heart rate sensor of the smartwatch with respect to the commonly used ECG and PPG devices. Results have shown that the heart rate acquired from the smartwatch is reasonably accurate with a high degree of correlation. Further, we conducted a preliminary exerise to evaluate sleep quality using the heart rate readings and accelerometer readings captured from the smartwatch and compared with a commercially available and clinically used non-contact sleep sensor, RESMED S+.

Abstract-This paper proposes and evaluates an evolutionary multiobjective optimization algorithm (EMOA) that eliminates dominance ranking in selection and performs indicator-based selection with the R2 indicator. Although it is known that the R2 indicator possesses desirable properties to quantify the goodness of a solution or a solution set, few attempts have been made until recently to investigate indicator-based EMOAs with the R2 indicator. The proposed EMOA, called R2-IBEA, is designed to obtain a diverse set of Pareto-approximated solutions by correcting an inherent bias in the R2 indicator. (The R2 indicator has a stronger bias to the center of the Pareto front than to its edges.) Experimental results demonstrate that R2-IBEA outperforms existing indicator-based, decomposition-based and dominance ranking based EMOAs in the optimality and diversity of solutions. R2-IBEA successfully produces diverse individuals that are distributed well in the objective space. It is also empirically verified that R2-IBEA scales well from twodimensional to five-dimensional problems.

parametric analysis of cerebellar Ataxia (cA) could be of immense value compared to its subjective clinical assessments. this study focuses on a comprehensive scheme for objective assessment of cA through the instrumented versions of 9 commonly used neurological tests in 5 domains-speech, upper limb, lower limb, gait and balance. Twenty-three individuals diagnosed with CA to varying degrees and eleven age-matched healthy controls were recruited. Wearable inertial sensors and Kinect camera were utilised for data acquisition. Binary and multilabel discrimination power and intra-domain relationships of the features extracted from the sensor measures and the clinical scores were compared using Graph Theory, Centrality Measures, Random Forest binary and multilabel classification approaches. An optimal subset of 13 most important Principal Component (PC) features were selected for CAcontrol classification. This classification model resulted in an impressive performance accuracy of 97% (F1 score = 95.2%) with Holmesian dimensions distributed as 47.7% Stability, 6.3% Timing, 38.75% Accuracy and 7.24% Rhythmicity. Another optimal subset of 11 PC features demonstrated an F1 score of 84.2% in mapping the total 27 PC across 5 domains during CA multilabel discrimination. In both cases, the balance (Romberg) test contributed the most (31.1% and 42% respectively), followed by the peripheral tests whereas gait (Walking) test contributed the least. These findings paved the way for a better understanding of the feasibility of an instrumented system to assist informed clinical decisionmaking.

No abstract

Cerebellar Ataxia (CA) leads to deficiencies in muscle movement and lack of coordination that is often manifested as gait and balance disabilities. Conventional CA clinical assessments are subjective, cumbersome and provide less insight into the functional capabilities of patients. This cross-sectional study investigates the use of wearable inertial sensors strategically positioned on the front-chest and upper-back locations during the Romberg and Trunk tests for objective assessment of human postural balance due to CA. The primary aim of this paper is to quantify the performance of postural stability of 34 patients diagnosed with CA and 22 healthy subjects as controls. Several forms of entropy descriptions were considered to uncover characteristics of movements intrinsic to CA. Indeed, correlation with clinical observation is vital in ascertaining the validity of the inertial measurements in addition to capturing unique features of movements not typically observed by the practicing clinician. Both of these aspects form an integral part of the underlying objective assessment scheme. Uncertainty in the velocity contained a significant level of information with respect to truncal instability and, based on an extensive clustering and discrimination analysis, fuzzy entropy was identified as an effective measure in characterising the underlying disability. Front-chest measurements demonstrated a strong correlation with clinical assessments while the upper-back measurements performed better in classifying the two cohorts, inferring that the standard clinical assessments are relatively influenced by the frontal observations. The Romberg test was confirmed to be an effective test of neurological diagnosis as well as a potential candidate for objective assessment resulting in a significant correlation with the clinical assessments. In contrast, the Trunk test is observed to be relatively less informative.