Research Area

Machine Learning for Signal Processing 

Machine learning is a new paradigm for solving detection problems. Unlike the classical hypothesis test based on known probabilistic characteristics, machine learning solves the detection or hypothesis problems using excessive dataset. The concept of deep learning based on the convolutional neural network (CNN) enables us to implement very feasible classifier for solving the detection problem in a variety of signal processing fields with significantly improved accuracy compared to the classical approaches. AiSLab studies machine learning algorithm and theory for signal processing such as wireless communications, radar, and computer vision.

In regards to machine learning for signal processing, the AiSLab is studying the following topics:

 

Beyond 4G and 5G Wireless Mobile Communications 

Wireless benefits people by providing 1) total PC portability and location independence, 2) improved responsiveness, and 3) easier and cheaper network expansion. Traditionally, the wireless cellular system was used mainly for voice calls, and is now expanding its range of application from internet adaption and connectivity to a variety of cloud platforms such as google and Facebook.

Machine learning is a new paradigm for solving detection problems. Unlike the classical hypothesis test based on known probabilistic characteristics, machine learning solves the detection or hypothesis problems using excessive dataset. The above figure shows an example of the convolutional neural network (CNN) for radar to detect the target type. The concept of deep learning based on this CNN enables us to implement very feasible classifier for solving the detection problem with significantly improved accuracy compared with the classical approaches. AiSLab studies machine learning algorithm and theory for signal processing such as wireless communications, radar, and computer vision.

As a result, the amount of mobile wireless traffics is expected to grow exponentially over time, and hence improving spectral efficiency is of great importance to accommodate these heavy traffic demands. As shown in the figure below, the 3GPP and IEEE standard bodies are developing a next generation wireless cellular system beyond 4G (known as LTE-Advanced), which achieves tens of Gbps data rates.

standard

In regards to next generation wireless communication systems, the AiSLab is studying the following topics:

 

Information Technology Convergence

Recently, innovation in mining is being driven by the convergence of communication information technology (IT). The communication information technology has grown very fast in the past decade, and the technology is pretty mature. The big idea is to create a new value and market through a synergetic combination of the IT technology and existing industries or technologies. As shown the figure below, the communication technology can create a variety of important industries, such as green communication, emergency network, social group communication, underwater communication, and machine-to-machine communications. It is no doubt the importance of IT convergence shall be more and more emphasized in the future.  

IT_convergence

The AiSLab is conducting the following studies towards IT Convergence: