 |
|
Highlights of Current Research Focuses: |
Check Our Lab Equipment |
Smart Traffic Control with Internet of Vehicles
|
City is becomming smarter and smarter with the "City Brain". One important aspect of city intelligentization is to enable smart traffic control where both the traffic control lights and the vehicles themselves are both able to learn and react to the traffic situations autonomously in an optimal way. In the 5G era, vehicules are also interconnected (IoV, one particular form of IoT) and the action space now admits the vehicles in addtion to the road infrastructure. This brings us a huge potential in optimizing the current traffic control mechanisms while we have to deal with both the huge state space and the huge action space when applying the reinforcement learning techniques. |
| The Internet of Things (IoT) is driving a digital transformation in all aspects of our lives and businesses. The growing number of connected devices is creating data at an exponential rate. Accordingly, we need to move computation, communication, control, and decision making to the network edge where data is being generated. This is called Fog/Edge Computing. Conventional machine learning requires at a central server. With distributed machine learing, the learning tasks are collaboratively carried out in ambient pervasive fog/edge nodes. | Distributed Machine Learning and Signal Processing in Internet of Things
|
Artificial Intelligence for Smarter Mobile Networks
|
Mobile networks in 5G and beyond are becoming ever complicated and advanced to support the digital information life. Artifical Intelligence has demonstrated its great potentials in solving complicated large-scale problems, e.g. speech and image recognition. Mobile networks have changed the world. The combination of AI and mobile networks, i.e. Mobile AI, will reshape the mobile neworks to approach the "network capacity" and change the world further! |
Different human behaviors introduce different multi-path distortions in Wi-Fi CSI. Key advantages of Wi-Fi CSI-based approaches are that they do not require lighting, provide better coverage as they can operate through walls, preserve user privacy, and do not require users to carry any devices as they rely on the Wi-Fi signals reflected by humans. Our research thrust in this direction will maintly exploit the unprecendented sensing capabilities offered by mmWave-based (massive) antenna arrays available in next-generation WiFi systems and demonstrate all the potentials to the world. |
Behavior Recognition with mmWave-Based Next-Generation WiFi
|
Signal Processing on Graph
|
We are also interested in the exciting “emerging” topic: “Signal Processing on Graphs” with applications in social, energy, transportation, sensor, and neuronal networks, where classical signal processing concepts including filtering, translation, modulation, dilation, and downsampling are generalized to analyze the irregular data structures on graphs. In particular, we are trying to expoit the SPoG tools to analyze the electroencephalography (EEG) signals which record the electrical activities of the brain. On the one hand, we expect a better signal classification can be acheived. On the other hand, we also expect to uncover the signal flow patterns in the brain through the EEG signals. |
Massive MIMO has been expoited in 5G. However, there are still many technical challenges in massive MIMO that have not been solved in previous studies. Full potential of massive MIMO is not yet achieved in 5G. Our group is carring out further researches in massive MIMO by leveraging on our previous work and will contribute to the development of next-generation wireless communication technologies, i.e. 6G. In particular, we are investigating the following topics: |
Massive MIMO Technologies |
Intelligent Metasurface
|
|
DIAL is defining & shaping next-generation communication & information processing |
|
This page was last edited in December, 2019 by Xiliang Luo. |
|
