Airwriting Recognition is the task of identifying letters written in free space with finger movement. It is a dynamic gesture recognition with the vocabulary of gestures corresponding to letters in a given language. Electromyography (EMG) is a technique used to record electrical activity during muscle contraction and relaxation as a result of movement and is widely used for gesture recognition. Most of the current research in gesture recognition is focused on identifying static gestures. However, dynamic gestures are natural and user-friendly for being used as alternate input methods in Human-Computer Interaction applications. Airwriting recognition using EMG signals recorded from forearm muscles is therefore a viable solution. Since the user does not need to learn any new gestures and a large range of words can be formed by concatenating these letters, it is generalizable to a wider population. There has been limited work in recognition of airwriting using EMG signals and forms the core idea of the current work. The SurfMyoAiR dataset comprising of EMG signals recorded during writing English uppercase alphabets is constructed. Several different time-domain features to construct EMG envelope and two different time-frequency image representations: Short-Time Fourier Transform and Continuous Wavelet Transform were explored to form the input to a deep learning model for airwriting recognition. Several different deep learning architectures were exploited for this task. Additionally, the effect of various parameters such as signal length, window length and interpolation techniques on the recognition performance is comprehensively explored. The best-achieved accuracy was 78.50% and 62.19% in user-dependent and independent scenarios respectively by using Short-Time Fourier Transform in conjunction with a 2D Convolutional Neural Network based classifier. Airwriting has great potential as a user-friendly modality to be used as an alternate input method in Human-Computer Interaction applications.
Didactic lecture is an effective method to quickly pass on a high volume of information to a large number of students. However, if not well designed, lectures can be monotonous and provide only passive learning, with little scope for higher order learning skills. To address this drawback of lectures, we supplemented it with case-based learning (CBL), which has been shown to promote self-learning. After giving an overview of gastrointestinal physiology through lectures, CBL on peptic ulcer disease was implemented for first-year Bachelor of Medicine, Bachelor of Surgery students. The present study aimed to evaluate the students’ and teachers’ opinions on the notion of supplementing lectures with CBL. In previous reports, discussion using clinical cases was primarily employed as the solitary component for conducting CBL. In the present study, three different but mutually exclusive components, such as case discussion, concept map, and critical thinking exercise on a specific topic in gastrointestinal pathophysiology, were integrated to form the multicomponent CBL (MC-CBL). Students reported that MC-CBL could promote application of the knowledge learned in lectures in a more appropriate context (92.42% positive response), enhance their learning efficiency (98.46% positive response), promote their active participation in the learning process (98.48% positive response), and help them in integrating physiological concepts with clinical science (98.46% positive response). Teachers observed that MC-CBL could promote active learning, analytic, and problem-solving skills of students. In conclusion, MC-CBL appeared to be an effective supplement for the lectures, providing an opportunity for the students to relate the knowledge learned during lectures.