Research

02/2020 - Present：Wearable sensor-based rehabilitation exercise assessment platform for use in stroke rehabilitation

In this project, we are proposing to use wearable sensor based assessment systems to assist the doctors in monitoring their post-stroke patients in the outpatient rehabilitation stage. An important part of developing a performance assessment algorithm is to have a high-precision activity recognition. Convolutional Neural Networks (CNN) are known to give very accurate results, but they require the data to be of a specific structure that differs from the sequential time series format collected from the wearable sensors.

05/2019 - Present：Adaptive Deep Learning Hardware for Embedded Platforms

We are investigating different hardware architectures for accelerating various deep learning (DL) algorithms using adaptive hardware acceleration platforms. This project proposes to design a new flexible hardware architecture to enable adaptive support for a variety of DL algorithms on embedded devices. To produce lower cost, lower power and higher processing efficiency DL-inference hardware that can be dynamically configured for dedicated application specifications and operating environments, this will require radical innovation in the optimisation of network architecture, software and hardware of current DL techniques

• We are participating Xilinx adaptive computing challenge 2020: https://www.xilinx.com/community/contest2020.html, and we have won a Zynq® UltraScale+™ MPSoC ZCU104 Evaluation Kit

• Project details can be found from here at hackster.io

09/2018 - Present：National Centre for Nuclear Robotics

We are developing resilient embedded systems software and measuring radiation effects on such system at the University of Essex.

The radiation rich environments jeopardize the reliability of the vision sensors, memory, processors by causing:

• Transient damage

• Permanente damage

05/2017 - 04/2019：Computer Enabled Radiological Resource for Blood Flow Rates in Aneurysms Using Lattice-Boltzmann

Automated Aneurysm Segmentation on Reconfigurable SoC

The project aims to implement a real-time automated segmentation technique for cerebral aneurysm on the Zynq SoC to create an virtualised interactive environment for doctor training purposes.

Lattice Boltzmann on Zynq SoC for Blood Flow Measurements

The project involves the application and implementation of Lattice Boltzmann (LB) fluid dynamics algorithm, which could provide hemodynamic estimation of blood flow used in a training environment to train the surgeons to rehearse and precisely place the clip near aneurysm.

01/2017 - 04/2019：Embedded Multi-core Systems for Multi-critical Applications

• The work aims to use innovative and sustainable service-oriented architecture approach for mixed criticality application in multi-modal real-time environments.

01/2016 - 12/2016：A low latency real-time gas classification system.

• This project is in collaboration with Qatar University, the aim is to propose a low latency real-time gas classification service system to rapidly respond and take the necessary actions in case of fault detection.

03/2016 - 07/2016: URSS-2016：Investigating and Designing on Teaching Hardware/Software Co-design using FPGA

• This project aims to investigate and design teaching projects for the second year undergraduate students on hardware/software oriented topics using Filed Programmable Gate Array (FPGA)

06/2015 - 06/2016: Enhanced Biometric Security and Privacy Using ECG on the Zynq SoC

• The work unifies a wireless health-care monitoring system with the identification of individuals using ECG signals, which enables patients to be monitored and treated remotely from their home, and patients’ data and medical records within a connected health system can be securely stored and transmitted for further analysis and diagnosis.

12/2013 - 10/2015: SWIPE: Space Wireless Sensor Networks for Planetary Exploration, funded by EU FP7.

• Developed a set of data fusion/processing algorithms that could be used in Wireless Sensor Networks (WSNs) for the purposed of planetary surface characterisation, in particular, targeting on the processing of the data gathered from the sensors in an energy efficient manner using state-of-the-art data fusion techniques.

12/2012 - 12/2013：SYSIASS – Autonomous and Intelligent Healthcare System funded by the European Regional Development Fund, ERDF Interreg IVA 2 Mers Seas Zeeën Programme.

12/2012 - 05/2013: RoBoSAS: Gobal engagement with NASA JPL and ESA in Robotics, Brain Computer Interfaces, and Secure Adaptive Systems for Space Applications” funded by EPSRC

• Developed FPGA and ARM based experimental platform for implementing and testing secure communication technologies called ICMetrics (Integrated Circuit metrics).