Hand preference and degree of handedness are two different aspects of human behavior which are often confused to be one. While hand preference is affected by various natural, environmental, and socio-cultural causes, degree of handedness reflects the inherent capability of a human gained by nature which can be modified with training. In this paper, we present two novel methods to quantify the degree of handedness for the first time using handwriting features of dominant and non-dominant hand on three categories of subjects- “Unidextrous”, “Partially-Unidextrous”, and “Ambidextrous”. Methods: Time, static, and dynamic variables of handwriting signal were used as the features for quantification of degree of handedness. Davies Bouldin Score as a statistical method and Neural Network accuracy-based 4-point scale as an automated method for this quantification were presented and compared with the well-known degree of handedness assessment questionnaires from Edinburgh Inventory (EI). Results: Davies Bouldin Score and 4-point scale from Neural Network were found to be in accordance with the EI questionnaires. 4-point scale was preferred over Davies Bouldin score as a robust grading mechanism. Conclusion: The presented methods can be used as an assessment tool for quantifying degree of handedness with multiple applications in i) determining the feasibility of switching hand preference under societal norms ii) neuro-rehabilitation strategies iii) neurological disorder diagnosis iv) study of brain lateralization and activation levels v) forensics vi) sports applications vii) human behavioral assessments.

An accurate estimation of muscle fatigue is critical  for adaptive control of existing assistive devices, such as an  exoskeleton, prosthesis, and functional electrical stimulation  (FES)-based neuroprostheses. However, the estimation of muscle  fatigue using surface electromyography (sEMG) for a long  duration of time becomes challenging due to loosening of sEMG  sensors, sweating, and other accidental failures. These problems  can be potentially solved by forecasting future sEMG signals using  initially recorded high-quality data points. For the first time, we  attempt to forecast the fatigue-induced electromyography signal  using the initial sEMG recorded for a shorter interval of time,  during biceps curl with weights of 1 kg, 2 kg, 3 kg, and 4 kg. An  attention-based deep CNN-BiLSTM neural network model that  captures input sEMG dynamics to forecast future sEMG signals  corresponding to fatigue state was trained and tested. An average mean absolute percentage error (MAPE) of 26.7% between  forecasted and recorded sEMG was observed across eight  subjects, five muscles, and four weights. In addition, the time  domain features like integrated EMG (IEMG), root-mean-square  (RMS) value, and variance of EMG (VEMG) were compared  between forecasted and recorded sEMG (fatigue state), which  yielded an average MAPE of 8%, 19.2%, and 31.7%, across eight  subjects, five muscles, and four weights, for (IEMG and MAV),  RMS, and (VEMG and SSI) respectively. The results encourage  combining the proposed approach with wearable technology for  forecasting fatigue-induced sEMG to drive stimulation devices like  FES and robotic devices.