Shudi Bao

Dr. Shudi Bao

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 May 2024 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
ZAZeeshan Ahmad
Zeeshan Ahmad
ZJZain ul Abidin Jaffri
Zain ul Abidin Jaffri
MCMeng Chen
Meng Chen
SBShudi Bao
Shudi Bao

10 February 2017 in Sensors
Verified
Journal Article
Open access
PDF file
SBShudi Bao
Shudi Bao
XMXiao-Li Meng
Xiao-Li Meng
Wendong XiaoWendong Xiao
Wendong Xiao
ZZZhiqiang Zhang
Zhiqiang Zhang
The wearable inertial/magnetic sensor based human motion analysis plays an important role in many biomedical applications, such as physical therapy, gait analysis and rehabilitation. One of the main challenges for the lower body bio-motion analysis is how to reliably provide position estimations of human subject during walking. In this paper, we propose a particle filter based human position estimation method using a foot-mounted inertial and magnetic sensor module, which not only uses the traditional zero velocity update (ZUPT), but also applies map information to further correct the acceleration double integration drift and thus improve estimation accuracy. In the proposed method, a simple stance phase detector is designed to identify the stance phase of a gait cycle based on gyroscope measurements. For the non-stance phase during a gait cycle, an acceleration control variable derived from ZUPT information is introduced in the process model, while vector map information is taken as binary pseudo-measurements to further enhance position estimation accuracy and reduce uncertainty of walking trajectories. A particle filter is then designed to fuse ZUPT information and binary pseudo-measurements together. The proposed human position estimation method has been evaluated with closed-loop walking experiments in indoor and outdoor environments. Results of comparison study have illustrated the effectiveness of the proposed method for application scenarios with useful map information.

16 November 2021 in EURASIP Journal on Wireless Communications and Networking
Verified
Journal Article
Open access
PDF file
ZAZeeshan Ahmad
Zeeshan Ahmad
MCMeng Chen
Meng Chen
SBShudi Bao
Shudi Bao
Electronic beam steering is an essential feature of state-of-the-art radar systems. Conventional phased array (PA) radars with fixed carrier frequencies are well-known for electronically steering their beam with high directivity. However, the resulting beampattern is angle-dependent but range-independent. Recently, a new electronic beam steering concept, referred to as frequency diverse array (FDA) radar, has attracted increasing attention due to its unique range-angle dependent beampattern. More importantly, the FDA radar employs a small frequency increment across the array elements to achieve beam steering as a function of angle, range, and time. In this paper, we review the development of the FDA radar since its inception in 2006. Since the frequency offset attaches great importance in FDAs to determine the beampattern shape, initially much of the research and development were focused on designing the optimal frequency offsets for improved beampattern synthesis. Specifically, we analyze characteristics of the FDA beampattern synthesis using various frequency offsets. In addition to analyzing the FDA beampattern characteristics, this study also focuses on the neglected propagation process of the transmitted signals in the early FDA literature, and discuss the time-variant perspective of FDA beampatterns. Furthermore, FDA can also play a significant role in wireless communications, owing to its potential advantages over the conventional PAs. Therefore, we highlight its potential applications in wireless communication systems. Numerical simulations are implemented to illustrate the FDA beampattern characteristics with various frequency offset functions.

21 July 2024 in Agronomy
Verified
Journal Article
Open access
PDF file
ZJZhengjie Ji
Zhengjie Ji
SBShudi Bao
Shudi Bao
MCMeng Chen
Meng Chen
LWLinjing Wei
Linjing Wei
The accurate identification of corn leaf diseases is crucial for preventing disease spread and improving corn yield. Plant leaf images are often affected by factors such as complex backgrounds, climate, light, and sample data imbalance. To address these issues, we propose a lightweight convolutional neural network, ICS-ResNet, based on ResNet50. This network incorporates improved spatial and channel attention modules as well as a deep separable residual structure to enhance recognition accuracy. (1) The residual connections in the ResNet network prevent gradient loss during deep network training. (2) The improved channel attention (ICA) and spatial attention (ISA) modules fully utilize semantic information from different feature layers to accurately localize key features of the network. (3) To reduce the number of parameters and lower computational costs, we replace traditional convolutional computation with a depth-separable residual structure. (4) We also employ cosine annealing to dynamically adjust the learning rate, enhancing the network’s training stability, improving model convergence, and preventing local optima. Experiments on the corn dataset in Plant Village compare the proposed ICS-ResNet with eight popular networks: CSPNet, InceptionNet_v3, EfficientNet, ShuffleNet, MobileNet, ResNet50, ResNet101 and ResNet152. The results show that the ICS-ResNet achieves an accuracy of 98.87%, which is 5.03%, 3.18%, 1.13%, 1.81%, 1.13%, 0.68%, 0.44% and 0.60% higher than the other networks, respectively. Furthermore, the number of parameters and computations are reduced by 69.21% and 54.88%, respectively, compared to the original ResNet50 network, significantly improving the efficiency of corn leaf disease classification. The study provides strong technical support for sustainable agriculture and the promotion of agricultural science and technology innovation.

31 January 2023 in Security and Safety
Verified
Journal Article
Open access
PDF file
NLNan Li
Nan Li
MDIP not review LiuMDIP not review Liu
MDIP not review Liu
QLQIMENG LI
QIMENG LI
JLJikui Liu
Jikui Liu
SBShudi Bao
Shudi Bao
HZHairong Zheng
Hairong Zheng
Precision medicine provides a holistic perspective of an individual’s health, including genetic, environmental, and lifestyle aspects to realize individualized therapy. The development of the internet of things (IoT) devices, the widespread emergence of electronic medical records (EMR), and the rapid progress of cloud computing and artificial intelligence provide an opportunity to collect healthcare big data throughout the lifespan and analyze the disease risk at all stages of life. Thus, the focus of precision medicine is shifting from treatment toward prediction and prevention,i.e., precision health. To this end, various types of data such as omics, imaging, EMR, continuous physiological monitoring, lifestyle, and environmental information, need to be collected, tracked, managed and shared. Thus, internet-of-medical things (IoMT) is crucial for assimilating the health systems, applications, services, and devices that can improve the speed and accuracy of diagnosis and treatments along with real-time monitoring and modification of patient behavior as well as health status. However, security has emerged as a growing concern owing to the proliferation of IoMT devices. The increasing interconnectivity of IoMT-enabled devices with health data reception, transmission, and processing significantly increases the number of potential vulnerabilities within a system. To address the security issues of precision health in IoMT systems, this study reviews the state-of-the-art techniques and schemes from the perspective of a hierarchical system architecture. We present an IoMT system model comprising three layers: the sensing layer, network layer, and cloud infrastructure layer. In particular, we discuss the vulnerabilities and threats to security in each layer and review the existing security techniques and schemes corresponding to the system components along with their functionalities. Owing to the unique nature of biometric features in medical and health services, we highlight the biometrics-based technologies applied in IoMT systems, which contribute toward a considerable difference between the security solutions of existing IoT systems. Furthermore, we summarize the challenges and future research directions of IoMT systems to ensure an improved and more secure future of precision health.

9 March 2017 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Open access
SBShudi Bao
Shudi Bao
MCMeng Chen
Meng Chen
GYGuang-Zhong Yang
Guang-Zhong Yang
A body sensor network that consists of wearable and/or implantable biosensors has been an important front-end for collecting personal health records. It is expected that the full integration of outside-hospital personal health information and hospital electronic health records will further promote preventative health services as well as global health. However, the integration and sharing of health information is bound to bring with it security and privacy issues. With extensive development of healthcare applications, security and privacy issues are becoming increasingly important. This paper addresses the potential security risks of healthcare data in Internet-based applications and proposes a method of signal scrambling as an add-on security mechanism in the application layer for a variety of healthcare information, where a piece of tiny data is used to scramble healthcare records. The former is kept locally and the latter, along with security protection, is sent for cloud storage. The tiny data can be derived from a random number generator or even a piece of healthcare data, which makes the method more flexible. The computational complexity and security performance in terms of theoretical and experimental analysis has been investigated to demonstrate the efficiency and effectiveness of the proposed method. The proposed method is applicable to all kinds of data that require extra security protection within complex networks.