Xiao Gu 顾潇
On the right is a broadcast of my taking part in the Youth Innovation Design Competition of Jiangsu Province and winning the Second Prize.It was a pity that my invention was not shown in this picture.
I was in Year 5 in primary school then. Maybe this can be viewed as the very beginning of my research, haha~
Projects
Supervisor: Professor Wei Chen
Project: Wearable Monitoring System of Neonatal Seizure | Research Assistant
A new system for the detection of neonatal seizures using the wearable sensor is presented. The system which consists of smart vest and system software aims for providing reliable continuous monitoring technique for doctors as well as a comfortable clinical environment for newborns. The system gives an alarm when seizure occurs on the basis of Electrocardiogram (ECG) and motion sensing techniques. The history data is saved for the optimization of the seizure detection algorithm. We put forward the concept of the neonatal vest that enables ECG signal acquisition by textile and motion measurement by MPU9250. The ECG signal which is preprocessed by ADS1292, together with motion data, is transferred to the processor MSP430 and then to the computer via Bluetooth 4.0. Furthermore, we develop a new software system which receives, processes, displays and stores data, as well as giving alarm.
-
Developed a new way of detecting neonatal seizures with mixture of physiological and acceleration signals.
-
Combined detection algorithms of neonatal seizure, exploiting both ECG and acceleration signals.
-
Assisted in designing application in mobile devices for real-time monitoring.
-
Won the 1st Prize of National Bioengineering Innovation Design Competition for University Students as Team Leader.
-
Assisted in performing clinical test in Children's Hospital affiliated to Fudan University.
Center for Intelligent Medical Electronics (CIME)
Department of Electronic Engineering, Fudan University, China
Contest Video
Prototype of our system
Promotion video for BME contest
Project: A New Monitoring System for Upper Limb Lymphedema Based on Depth Scanning and Information Analysis | Research Assistant
Upper limb lymphedema is a chronic disease that requires long-term intervention and treatment, which renders real-time monitoring significant. The existing measuring instruments and methods have the disadvantages of low price while low accuracy, high accuracy while high price, which are unfavorable to the promotion and use of clinical and family. The new lymphedema monitoring system proposed in this project is based on a small non-contact rotary scanning platform and advanced depth camera to reconstruct the upper limbs. The volume of the obtained image is calculated to determine the degree of local swelling. At the same time, these data and analysis results stored in the cloud platform for doctors to conduct historical records and telemedicine.
-
Proposed a novel approach for assessing lymphedema using 3D scanning of the upper limb with advanced depth camera.
-
Designed 3D scanning platform for the modeling of patients’ upper limbs with comfort and safety.
-
Improved existing scanning algorithms with external camera pose and information provided by the platform.
-
Performed clinical experiments and collected data for training and testing.
Prototype of scanning platform
Framework of our system
The Hamlyn Centre, Institute of Global Health Innovation,
Department of Computing, Imperial College London, UK
Supervisor:Dr. Fani Deligianni & Professor Guang-Zhong Yang
Project: Markerless Gait Analysis Based on a Single RGB Camera | Research Assistant
Gait analysis is an important tool for monitoring and preventing injuries as well as to quantify functional decline in neurological diseases and elderly people. In most cases, it is more meaningful to monitor patients in natural living environments with low-end equipment such as cameras and wearable sensors. However, inertial sensors cannot provide enough details on angular dynamics. We proposes a method that uses a single RGB camera to track the 2D joint coordinates with state-of-the-art vision algorithms. Reconstruction of the 3D trajectories uses sparse representation of an active shape model. Subsequently, we extract gait features and validate our results in comparison with a state-of-the-art commercial multi-camera tracking system.
-
Proposed a novel method for estimating 3D gait angular features of the lower limbs combined with 2D keypoints detection and 3D motion reconstruction.
-
Adopted a deep learning method for the detection of keypoints and image segmentation method for foot detection.
-
Adopted dictionary learning and sparse representation methods for higher dimension recovery from 2D keypoints to 3D postures.
-
Extracted both 2D and 3D angular features under different walking conditions and validated them based on ground truth data.
2D keypoints detection
Experiment settings (RGB for testing and multi-camera for ground truth)
Publications & Patents
Papers
-
Hongyu Chen, Xiao Gu, et al., “A Wearable Sensor System for Neonatal Seizure Monitoring”, 2017 IEEE 14th International Conference on Wearable and Implantable Body Sensor Networks (BSN), Eindhoven, 2017, pp. 27-30. | Paper | Poster |
-
Xiao Gu, Fani Deligianni, Benny Lo, Wei Chen, Guang-Zhong Yang, “Markerless Gait Analysis Based on a Single RGB Camera”, 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks (BSN), Las Vegas, 2018, pp. 42-45. | Paper | Oral Presentation |
-
Xinyu Jiang, Xiao Gu, Zhenning Mei, Haoran Ren, Wei Chen, "A Modified Common Spatial Pattern Algorithm Customized for Feature Dimensionality Reduction in fNIRS-Based BCIs", IEEE the 40th International Engineering in Medicine and Biology Conference (EMBC’18), Honolulu, Hawaii, USA, 2018, pp. 5073-5076. | Paper | Oral Presentation |
-
Zhenning Mei, Xiao Gu, Hongyu Chen, Wei Chen, “Automatic Atrial Fibrillation Detection Based on Heart Rate Variability and Spectral Features”, IEEE Access, vol. 6, pp. 53566–53575, 2018. | Paper |
Patents
-
Wei Chen, Xiao Gu, et al., “A Scanning Platform for Measuring Upper Limb Lymphedema”, Chinese Patent, CN207561890U. (Granted)
-
Wei Chen, Xiao Gu, et al., “A New Monitoring System for Upper Limb Lymphedema based on Depth Scanning Technique and Information Analysis”, Chinese Patent, Application No.201710220459.6 (Pending).
-
Wei Chen, Hongyu Chen, Zhenning Mei, Xiao Gu, et al., “Wearable Monitoring System for Neonatal Seizure”, Chinese Patent, Application No.201611249212.9 (Pending).
-
Wei Chen, Hongyu Chen, Zhenning Mei, Xiao Gu, et al., “Wearable Monitoring Device for Neonatal Seizure”, Chinese Patent, Application No.201621468670.7 (Pending).