Yuli Li

Yuli Li

Auto-generated profile, based on publicly available information

Yuli Li

Wuhan University of Technology,Intelligent Transportation Systems Research Center,Wuhan,China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
23 November 2022 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
Xiao LuXiao Lu
Xiao Lu
YLYuli Li
Yuli Li
WCWei Cui
Wei Cui
HWHaixia Wang
Haixia Wang
Despite the intense effort from the research community, state-of-the-art WiFi-based human activity recognition (HAR) performance remains unsatisfactory. Current approaches usually use individual characteristics of CSI, i.e., amplitude or phase measurements, to model the relationship between the changes of channel state information (CSI) and human activities, which lead to their failure to achieve satisfactory accuracy due to information loss. To deal with this issue, this article proposes CeHAR, a CSI-based HAR using a channel-exchanging fusion network to deep fuse the CSI amplitude and phase features to obtain the informative features for HAR. The proposed CeHAR is a parameter-free dual-characteristic fusion framework that dynamically exchanges channels between subnetworks of two kinds of characteristics to comprehensively learn informative features from both. Specifically, the proposed approach employs two subnetworks using convolutional neural networks to learn features from each characteristic of CSI. The magnitude of the batch-normalization (BN) scaling factor is used to determine the channel importance of each characteristic, and then guides the exchange process. The proposed CeHAR also shares convolutional filters, but keeps private BNs layers in different characteristics, which, as an added benefit, allows our characteristic fusion network to be nearly as compact as a single-characteristic network. Extensive real-world experiments have been conducted to evaluate the performance of our proposed CeHAR, and the experimental results illustrate that our proposed approach outperforms baselines.

4 August 2023
Verified
Conference Paper
Closed access
ZXZidong Xu
Zidong Xu
DZDi Zhang
Di Zhang
LFLiang Fan
Liang Fan
HMHAOWEI MA
HAOWEI MA
YLYuli Li
Yuli Li
Synthetic Aperture Radar (SAR) is an active Earth observation system that can obtain high-resolution ocean images all day and all weather. It can be used for monitoring the marine environment, maritime traffic, and oil spills at sea. SAR provides accurate and real-time ocean information, which can ensure water traffic safety and ecological environment. Therefore, it plays an irreplaceable role in maritime surveillance. At present, deep-learning based object detection methods have achieved certain results in the application of ship detection in SAR images. Ship targets in SAR images have strong angular reflection characteristics, causing some parts of them to have large grayscale values, appearing as scattering points. At the same time, the heading of ship usually has a certain angle with the horizontal direction. Traditional deep-learning models do not have sufficient generalization ability for these situations. Horizontal bounding boxes also contain a large amount of background features, which affects the accuracy of the model. In response to these characteristics, first use convolutional neural network to extract ship features; Secondly, generate oriented proposals to reduce the impact of background features; Thirdly, using Canny and Harris to obtain features of ship edges and scattering points as attention mechanisms to enhance bounding box regression and classification; Finally, optimize the loss function, which will consider the influence of angle. Comparative experiments were conducted on the SSDD dataset, and the experimental results showed that compared to existing methods, the improved model has better ship detection performance and can achieve accurate detection of small ship targets in complex scene SAR images.

27 September 2021 in European Neuropsychopharmacology
Verified
Journal Article
Closed access
PHPhilip D Harvey
Philip D Harvey
TBTim Bigdeli
Tim Bigdeli
YLYuli Li
Yuli Li
NRNallakkandi Rajeevan
Nallakkandi Rajeevan
BGBryan Gorman
Bryan Gorman
SMSumitra Muralidhar
Sumitra Muralidhar