In this paper, a preliminary work on improving fitness for the post-stroke rehab application is investigated.For this purpose, a fusion of the Electrocardiographic (ECG) and Electromyographic (EMG) biosignals is proposed to produce a significant control signal and to achieve a biosignals multimodal fusion system. In this work, a mathematical approach such as the Bayesian network will be applied in order to combine both ECG and EMG biosignals. Furthermore, the significant fused elements can be applied to manipulate the control of physiological devices (PDs) for emulating the classic rehabilitation exercise (e.g., cycling). Consequently, the proposed method for a multimodal fusion of muscle contractions for heart and lower limbs shall give improvement on monitoring the rehabilitation progress with better accuracy for signals fusion.

Gender recognition is trivial for a physiotherapist, but it is considered a challenge for computers. The electromyography (EMG) and heart rate variability (HRV) were utilized in this work for gender recognition during exercise using a stepper. The relevant features were extracted and selected. The selected features were then fused to automatically predict gender recognition. However, the feature selection for gender classification became a challenge to ensure better accuracy. Thus, in this paper, a feature selection approach based on both the performance and the diversity between the two features from the rank-score characteristic (RSC) function in a combinatorial fusion approach (CFA) (Hsu et al.) was employed. Then, the features from the selected feature sets were fused using a CFA. The results were then compared with other fusion techniques such as naive bayes (NB), decision tree (J48), k-nearest neighbor (KNN) and support vector machine (SVM). Besides, the results were also compared with previous researches in gender recognition. The experimental results showed that the CFA was efficient and effective for feature selection. The fusion method was also able to improve the accuracy of the gender recognition rate. The CFA provides much better gender classification results which is 94.51% compared to Barani's work (90.34%), Nazarloo's work (92.50%), and other classifiers.

No abstract

This study is aimed to explore the heart rate variability (HRV)

Cardiorespiratory fitness (CRF) is known to reduce metabolic-related diseases like cardiovascular diseases (CVD), obesity, hypertension, and type II diabetes. On the other hand, the gold standard to measure CRF is by measuring maximal oxygen consumption, VO2 max over the years. This study is performed to identify parameters that influence CRF without solely relying on invasive features such as VO2 max. A number of 31 UTM staff aged between 30 and 40 years old have participated in this study with 17 female subjects and 14 male subjects. Anthropometric measurements are obtained by direct measurement and body composition analysis using a body composition monitor. Multiparameter trend measurements were obtained from vital sign monitors at rest. Single feature analysis was performed in terms of accuracy, specificity and sensitivity to identify which feature influences CRF the most. The features collected are body mass index (BMI), body fat (BF), muscle mass (MM), bone density (BD), waist circumference (WC), resting heart rate (RHR), resting systolic blood pressure (RSBP), forced expiratory volume in one second (FEV1), and recovery trend heart rate (RecHR). Next, all these features were validated using Naïve Bayes (NB) and Decision Tree (DT) classifiers. Finally, six features which are BF, BM, BD, RHR, RSBP and FEV1, with accuracy more than 70% were selected and identified as the features which influence CRF of UTM staff.