Sign language recognition (SLR) enables the deaf and speech-impaired community to integrate and communicate effectively with the rest of society. Word level or isolated SLR is a fundamental yet complex task with the main objective of using models to correctly recognize signed words. Sign language consists of very fast and complex hand, body, face movements, and mouthing cues that make the task very challenging. Several input modalities; RGB, optical Flow, RGB-D, and pose/skeleton have been proposed for SLR. However, the complexity of these modalities and the state-of-the-art (SOTA) methodologies tend to be exceedingly sophisticated and over-parametrized. In this paper, our focus is to use the hands and body poses as an input modality. One major problem in pose-based SLR is extracting the most valuable and distinctive features for all skeleton joints. In this regard, we propose an accurate, efficient, and lightweight pose-based pipeline leveraging a graph convolution network (GCN) along with residual connections and a bottleneck structure. The proposed architecture not only facilitates efficient learning during model training providing significantly improved accuracy scores but also alleviates computational complexity. With the proposed architecture in place, we are able to achieve improved accuracies on three different subsets of the WLASL dataset and the LSA-64 dataset. Our proposed model outperforms previous SOTA pose-based methods by providing a relative improvement of 8.91%, 27.62%, and 26.97% for WLASL-100, WLASL-300, and WLASL-1000 subsets. Moreover, our proposed model also outperforms previous SOTA appearance-based methods by providing a relative improvement of 2.65% and 5.15% for WLASL-300 and WLASL-1000 subsets. For the LSA-64 dataset, our model is able to achieve 100% test recognition accuracy. We are able to achieve this improved performance with far less computational cost as compared to existing appearance-based methods.

The human sense of touch is an integral part of daily life. For tasks involving grasping and manipulation of objects, force feedback is a key requirement. Most of the systems give contact point or complete grasping force feedback; for precision grasping and other physical interactions, finger awareness and force feedback from independent fingers is essential. In this study a novel, wearable proprioceptive rehabilitation system is designed which restores the ability of identifying and distinguishing between individual fingers of a prosthetic hand or an exoskeleton in a non-invasive manner. Moreover, it provides different levels of force feedback from every finger as well, which enables the user to distinguish and control force in precision grasping activities. For testing the system accuracy, classical psychophysical methods were used on a group of 14 voluntary disabled subjects. The tests were conducted in both, ideal and real-world conditions i.e. without and with distractions and accuracies were calculated accordingly. A p-test was also conducted to observe significance between the samples of with and without distraction datasets. The system performed with an overall accuracy of 82.04% which was well above the min. performance measure of 60%. Vi-HaB is standalone system and can be mounted on any upper limb rehabilitation (prosthesis, exoskeleton) system for finger awareness and force feedback.

Recent research has shown reliability in robotic therapies for improvement in core impairments of autism. To improve the efficiency of communication using robots, this study evaluates the effectiveness of three different stimuli in a robotic intervention for children with autism spectrum disorder. Three different reinforcement stimuli presented in least-to-most (LTM) order introduced in this therapy using NAO robot are: visual (color variation), auditory and motion cues. The therapy was tested on 12 ASD children, 4 out of 12 children fall under mild category whereas 8 fall under the minimal category of autism. The experimentation was conducted for 2 months. Total 8 experiments were conducted with 1 trial per week. Total 12 cues were given per trial, 4 cues corresponding to each category. In total 96 cues were given per subject, 32 cues from each category. The results indicate a general trend for linking a particular autism category with the most effective stimulus for that category. It can be concluded that visual cue (color variation) is the most effective reinforcement stimulus for children with minimal autism as 8 out of 8 i.e., 100% were more responsive to visual cues whereas for children with mild autism category, 3 out of 4 i.e., 75% are more receptive towards the motion stimulus. The parameters used for assessment were joint attention and the time eye contact is maintained. Single factor ANOVA was used for the statistical analysis of results with alpha is 0.05 and p-value 0.0342, F value is 3.7456 and F critical value is 3.2834. The test was performed on 96 (8x12) trails in total, therefore ensuring the significance and reliability of our results.

This research article presents a preliminary longitudinal study to check the improvement in multi-human communication of children with Autism Spectrum Disorder (ASD) using a standardized multi-robot therapy. The research is based on a 3 step framework: 1) Human-Human Interaction, Stage-1 (HHI-S1), 2) Human-Robot Interaction, Stage-2 (HRI-S2), and 3) Human-Human Interaction, Stage-3 (HHI-S3). All three stages of the therapy consist of two command sets: 1) Controls commands and 2) Evaluation commands (auditory commands, visual commands, and combination of both). The concept of multiple robots is introduced to help multi-human communication and discourage isolation in ASD children. The joint attention of an ASD child is improved by the robotic therapy in stage 2 considering it as a key parameter for a multi-human communication scenario. The improvement in joint attention results in better command following in a triad multi-human communication scenario in stage 3 as compared to stage 1. The proposed intervention has been tested on 8 ASD subjects with 10 sessions over a period of two and a half months (10 weeks). Each session of human-human interaction (stage 1 and 3) consisted of 14 cues whereas 18 cues were presented by each robot for human-robot interaction (stage 2). The results indicate an overall 86% improvement in the social communication skills of ASD children in case of a multi-human scenario. Validation of results and effectiveness of the therapy has been further accomplished through the use of the Childhood Autism Rating Scale (CARS) score.

Seawater desalination is an affordable and viable solution to the growing freshwater scarcity problem in water scarce regions. The current study focuses on cost analysis of Vacuum Membrane Distillation (VMD) setup for removing salts from water. The membrane used in the flat sheet VMD module was Polytetrafluoroethylene (PTFE) with 250 mm × 200 mm dimensions and 165 µm thickness. The experiments were carried out with variations in parameters such as velocity, pressure, concentration, and temperature. For the cost analysis, the operational, maintenance, instrumentation, and capital cost of the lab model was considered and then upscaled. A range of experiments was performed for NaCl and KCl under variations of operating parameters. It was noted that, for the NaCl solution, the increase in temperature from 50 °C to 70 °C doubled the permeate flux. However, for the conditions tested, the concentration shift from 0.25 M to 0.75 M decreased the permeate flux by 1.4% because the increase in ion concentrations along the membrane lowers the vapor pressure, restricting the permeate flux. The results trend for the KCl solution was similar to the NaCl; at temperature T1, it was noted that increased concentration from 0.25 M to 0.75 M significantly reduces the permeate flow. The reduction in permeate flow was nonlinear for a given pressure 30 kPa and velocity 5.22 m/s, but linear for all other variables. It was also observed that with an increase in temperature from 60 °C to 70 °C, the permeate flux for concentration 0.25 M was 49% for all the combinations of pressure and velocity. In addition, permeate flow increased 53% from temperature 50 °C to 60 °C and 49% from temperature 60 °C to 70 °C for both the solutions at a concentration of 0.25 M. This shows that the temperature also had a profound impact on the permeate flux. The economic analysis and market survey shows that the cost of clean water at the lab level was high which can be significantly reduced using a large-scale setup providing 1,000,000 L/H of distilled water.