During the pandemic, people around the world are expected to wear masks. So far, the ability to recognize the identity of a person who wears a mask is still a challenge. Face recognition is widely used in schools, hospitals, and companies as an attendance system, even as a criminal watchlist examination system. Thus, face recognition implementation is difficult to obtain the identity of people who are wearing masks, and moreover, computer systems might fail to detect the faces. This study used Haar-cascade Face detection and MobileNet while proposing the addition of the cosine distance method. This method compares the middle position of face detection results within the previous frame and the current. The proposed system can generate a person's name and identification number while wearing a mask. The system is designed to utilize multithreading by comparing the transfer learning methods of VGG16 and Triplet Loss FaceNet for face mask recognition with an accuracy rate of 100% and 82.20%. Real-time implementation speed resulted in 4 FPS and 22 FPS and successfully added cosine distance to generate a person's ID number.
Distillation is the most common method for separating components in chemical unit operation. This paper presents the mini batch distillation column modeling to facilitate a closed loop control design in the later stage. This mini plant is part of the development of a cyber physical system and will be a physical system controlled by DCS (Distributed Control System) with data transmission over the network in real time. In this study, ITB Honeywell mini plant for laboratory scale is used for separating binary mixtures, ethanol and water. An on-off condenser valve is chosen as an actuator to regulate the end product concentration.The plant is modeled by 2 approaches, i.e. White-box modeling approach by first principle, which produces nonlinear equations model of batch distillation column based on component mass balance, vapor-liquid equilibrium and others physical characteristics. Meanwhile, the Blackbox approach uses input-output experimental data to produce a linear model of the plant. The modelling is for two different locations of the concentration sensor, i.e. at the inflow or outflow of the end-product tank. The nonlinear model is not yet appropriate for control design purpose. Unlike the nonlinear model, the linear models developed at two different control inputs show marginal to good fit to the experimental data at respective operating points. However, it seems better to use a piecewise linear modelling over process operating regions for concentration control design purposes of the batch distillation column. Further development of the nonlinear model shall be done by considering the influence of temperature variability in the model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.