The development of a portable elbow exoskeleton with a Twisted Strings Actuator to assist patients with upper limb inhabitation

Over the years, the number of exoskeleton devices utilized for upper-limb rehabilitation has increased dramatically, each with its own set of pros and cons. Most exoskeletons are not portable, limiting their utility to daily use for house patients. Additionally, the huge size of some grounded exoskeletons consumes space while maintaining a sophisticated structure and require more expensive materials. In other words, to maintain affordability, the device's structure must be simple. Thus, in this work, a portable elbow exoskeleton is developed using SolidWorks to incorporate a Twisted Strings Actuator (TSA) to aid in upper-limb rehabilitation and to provide an alternative for those with compromised limbs to recuperate. Experiments are conducted to identify the optimal value for building a more flexible elbow exoskeleton prototype by analyzing stress, strain conditions, torque, forces, and strings. Preliminary computational findings reveal that for the proposed intended prototype, a string length of.033 m and a torque value ranging from 1.5 Nm to 3 Nm are optimal.

Driver Drowsiness Detection Using Ensemble Convolutional Neural Networks on YawDD

Driver drowsiness detection using videos/images is one of the most essential areas in today's time for driver safety. The development of deep learning techniques, notably Convolutional Neural Networks (CNN), applied in computer vision applications such as drowsiness detection, has shown promising results due to the tremendous increase in technology in the recent few decades. Eyes that are closed or blinking excessively, yawning, nodding, and occlusion are all key aspects of drowsiness. In this work, we have applied four different Convolutional Neural Network (CNN) techniques on the YawDD dataset to detect and examine the extent of drowsiness depending on the yawning frequency with specific pose and occlusion variation. Preliminary computational results show that our proposed Ensemble Convolutional Neural Network (ECNN) outperformed the traditional CNN-based approach by achieving an F1 score of 0.935, whereas the other three CNN, such as CNN1, CNN2, and CNN3 approaches gained 0.92, 0.90, and 0.912 F1 scores, respectively.