Like Li

Like Li

Auto-generated profile, based on publicly available information

Like Li

College of Information Science and Engineering, Northeastern University, Shenyang, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
28 May 2022 in Talanta
Verified
Journal Article
Closed access
LLLike Li
Like Li
Ya-nan ZhangYa-nan Zhang
Ya-nan Zhang
WZWanlu Zheng
Wanlu Zheng
XLXuegang Li
Xuegang Li
Yong ZhaoYong Zhao
Yong Zhao

6 February 2025 in Information Fusion
Verified
Journal Article
Closed access
XLXiang Li
Xiang Li
LLLike Li
Like Li
YJYuchen Jiang
Yuchen Jiang
HWHao Wang
Hao Wang
XQXinyu Qiao
Xinyu Qiao
YZYong Zhao
Yong Zhao

25 September 2025 in Medical Image Analysis
Verified
Journal Article
Closed access
XLXiang Li
Xiang Li
LLLike Li
Like Li
MLMinglei Li
Minglei Li
PYPengfei Yan
Pengfei Yan
TFTing Feng
Ting Feng
Shen YinShen Yin
Shen Yin

7 August 2023 in Journal of Lightwave Technology
Verified
Journal Article
Closed access
Yong ZhaoYong Zhao
Yong Zhao
LLLike Li
Like Li
BHBo Han
Bo Han
WZWanlu Zheng
Wanlu Zheng
XLXuegang Li
Xuegang Li
Ya-nan ZhangYa-nan Zhang
Ya-nan Zhang
In this article, an ultra-sensitive optical sensor based on vernier effect for glucose concentration measurement is reported. First of all, the structure of lateral offset single side-hole optical fiber (SSHF) is designed, which can ingeniously excite two integrated parallel Mach-Zehnder interferometers (MZIs) with significantly different free spectral ranges (FSRs). Then, according to the optical path difference (OPD) theory, a novel FSR regulation scheme is proposed to solve the problem that the FSRs of two parallel MZIs are quite different. Finally, two integrated parallel MZIs with similar FSRs are constructed, which are respectively used as reference MZI and sensing MZI, and then vernier effect is formed in this in-fiber structure. An ultra-high refractive index (RI) sensitivity of more than 10, 0000 nm/RIU has been confirmed theoretically and experimentally. In addition, this ultra-sensitive configuration is used for direct measurement of clinically relevant glucose concentration. In the linear range of 0–30 mM, the glucose sensitivity is up to −2.47 nm/mM. The sensing configuration behaves the merits of simple preparation, high sensitivity and compact structure, and has great application potential in biochemical analysis, clinical diagnosis, dynamic process monitoring and other fields.

23 November 2020 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
LLLike Li
Like Li
Ya-nan ZhangYa-nan Zhang
Ya-nan Zhang
A fiber-optic pH sensor, based on layer-by-layer (LBL) self-assembly and surface plasmon resonance (SPR) technology, is proposed and experimentally confirmed. This paper proposes poly (diallyldimethylammonium chloride) PDDA as the pretreatment solution for the surface of the gold film and the highly sensitive PAA/CS self-assembled nanomembrane as the pH-sensitive film. It has been experimentally verified that the sensor can detect pH from 3.18 to 11.84 and exhibits a high average sensitivity of 32.31 nm/pH in this range. In addition, experiments have confirmed that the sensor has attractive stability, repeatability, and hysteresis characteristics.

9 December 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
YSYu Sun
Yu Sun
XLXiang Li
Xiang Li
LLLike Li
Like Li
Ting FengTing Feng
Ting Feng
Yong ZhaoYong Zhao
Yong Zhao
Shen YinShen Yin
Shen Yin
Federated learning (FL) faces significant challenges in medical image analysis due to data heterogeneity among clients, where balancing personalization and generalization is challenging. Existing methods often struggle to achieve both objectives simultaneously, as excessive personalization reduces generalization, while over-generalization weakens adaptation to client-specific features. To address these challenges, we propose a perceptual hashing hypernetwork personalized FL (PHH-FL) to enhance both personalization and generalization. PHH-FL first uses a perceptual hashing (pHash) algorithm to construct a similarity matrix that captures data distribution differences among clients and employs a hypernetwork to generate personalized parameters for each client. Meanwhile, the shared hypernetwork is introduced to promote knowledge transfer between clients, thereby enhancing the generalization ability of the local model. By selectively generating parameters for the initial layers of the target network, PHH-FL reduces computational and communication costs while maintaining performance. Experiments on medical image classification and segmentation tasks show that PHH-FL outperforms state-of-the-art methods. Ablation studies further demonstrate that the proposed framework effectively balances personalization and generalization.