The advanced communication research group comprises of two research streams;
Spectrum of radio frequency (RF) communications is limited and expensive to install new applications. Free space optical (FSO) communication is a viable technology which offers enormous bandwidth, license free installation, inexpensive deployment and error prone links. The FSO links degrade significantly due to the varying atmospheric and weather conditions (fog, cloud, snow, haze and combination of these). We are moving towards hybrid FSO/RF adaptive communication system which adapts the varying nature of atmosphere and weather. For the adaption of varying atmosphere and weather scenarios, we are developing a novel optimization algorithm. The research within the group covers the following topics:
We are interested in machine learning methodology and application to problems in science, engineering, and industries. The special case is the healthcare systems. For example, Robots with telepresence capabilities are typically employed for tasks where human presence is not feasible due to geography, safety risks like fire or radiation exposure, or other factors like any epidemic disease. Time delay is a significant consideration in controlling a telepresence robot. A deep learning-based approach can be utilized to compensate for the delay by predicting the behaviour of the teleoperator. We can integrate a recurrent neural network (RNN) based on the Long Short-Term Memory (LSTM) architecture with the reinforcement learning-based Deep Deterministic Policy Gradient (DDPG) algorithm. The other example is the application telepresence robot in healthcare centers to get the basic information ready for healthcare providers. The research within the group covers the following topics:
Dr. Muhammad Nasir Khan
Professor, Electrical Engineering Department, GCU Lahore
