Zhenlei Dai

Zhenlei Dai

Auto-generated profile, based on publicly available information

Zhenlei Dai

School of Computer and Information, Anhui Normal University, Wuhu, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
24 June 2021 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
LHLiangchen Hu
Liangchen Hu
WZWensheng Zhang
Wensheng Zhang
ZDZhenlei Dai
Zhenlei Dai
With the dramatic increase of dimensions in the data representation, extracting latent low-dimensional features becomes of the utmost importance for efficient classification. Aiming at the problems of weakly discriminating marginal representation and difficulty in revealing the data manifold structure in most of the existing linear discriminant methods, we propose a more powerful discriminant feature extraction framework, namely, joint sparse locality-aware regression (JSLAR). In our model, we formulate a new strategy induced by the nonsquared $L_{2}$ norm for enhancing the local intraclass compactness of the data manifold, which can achieve the joint learning of the locality-aware graph structure and the desirable projection matrix. Besides, we formulate a weighted retargeted regression to perform the marginal representation learning adaptively instead of using the general average interclass margin. To alleviate the disturbance of outliers and prevent overfitting, we measure the regression term and locality-aware term together with the regularization term by forcing the row sparsity with the joint $L_{2,1}$ norms. Then, we derive an effective iterative algorithm for solving the proposed model. The experimental results over a range of benchmark databases demonstrate that the proposed JSLAR outperforms some state-of-the-art approaches.

18 October 2024 in Neural Networks
Verified
Journal Article
Closed access
ZDZhenlei Dai
Zhenlei Dai
LHLiangchen Hu
Liangchen Hu
HSHuaijiang Sun
Huaijiang Sun

10 August 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
LHLiangchen Hu
Liangchen Hu
ZDZhenlei Dai
Zhenlei Dai
LTLei Tian
Lei Tian
WZWensheng Zhang
Wensheng Zhang
As one of the learning ways for inducing efficient image compact representation, graph embedding (GE) based manifold learning has been widely developed over the last two decades. Good graph embedding depends on the construction of graphs concerning intra-class compactness and inter-class separability, which are crucial indicators of the effectiveness of a model in generating discriminative features. Unsupervised approaches are designed to reveal the data structure information from a local or global perspective, but the resulting compact representation often has poorly inter-class margins due to the lack of label information. Moreover, supervised techniques only consider enhancing the adjacency affinity within classes, but exclude the affinity of different classes, resulting in inadequate capture of marginal structures between different class distributions. To overcome these issues, we propose a learning framework that implements Class-Oriented Self-Learning Graph Embedding (COSLGE), in which we achieve a flexible low-dimensional compact representation by imposing an adaptive graph learning process across the entire data while examining the inter-class separability of low-dimensional embedding by jointly learning a linear classifier. Besides, our framework can be easily extended to semi-supervised scenarios. Extensive experiments on several widely-used benchmark databases demonstrate the effectiveness of the proposed method in comparison to some state-of-the-art approaches.

3 February 2020 in Wireless Networks
Verified
Journal Article
Closed access
PDF file
LHLiangchen Hu
Liangchen Hu
HSHuahao Shou
Huahao Shou
ZDZhenlei Dai
Zhenlei Dai

2 May 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZDZhenlei Dai
Zhenlei Dai
LHLiangchen Hu
Liangchen Hu
HSHuaijiang Sun
Huaijiang Sun
Linear regression, a widely-used method in representation learning, initially faced limitations in incorporating structural information within the regression space. Existing models designed to extract structural insights often prioritize the proximity of data points in feature space, while overlooking crucial interdependencies and co-occurrences among them. In response to the challenges posed by the inherent limitations, we introduce a novel representation learning model based on linear regression. This model seamlessly integrates three essential modules: flexible regression learning, graph embedding learning, and embedded block-diagonal self-representation learning. The collaborative functioning of these modules establishes a closed optimization loop. The self-representation matrix directly captures the latent graph structure across the entire data domain, without the need for setting additional parameters such as the neighborhood scale of the graph. Concurrently, it facilitates flexible regression learning by uncovering latent structural patterns. Experimental results on multiple benchmark datasets demonstrate the superiority of our approach over state-of-the-art methods, providing a more comprehensive solution for representation learning.

20 March 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
LHLiangchen Hu
Liangchen Hu
ZDZhenlei Dai
Zhenlei Dai
Zhenghua ChenZhenghua Chen
Zhenghua Chen
WZWensheng Zhang
Wensheng Zhang
PHPeng Hu
Peng Hu
YLYonglong Luo
Yonglong Luo
In the context of advancing industrial automation, sensor-generated image data often exhibit high dimensionality and complexity, presenting challenges for effective feature extraction. Especially when sensors are deployed in complex and dynamic environments, image data can be affected by various factors, leading to increased noise and thus impacting the performance of feature extraction. To tackle these issues, this paper introduces a method combining the dynamic sparse graph learning jointly with projective graph embedding for feature extraction from sensor images. Initially, sparse representation learning constructs similarity graphs among the data, pruning unnecessary connections to retain the most pertinent features. Then, projective graph embedding maps the image data into a lower-dimensional space, achieving a more concise and discriminative feature representation. These two primary modules in our model form an optimized closed loop, achieving overall optimality. The integrated approach effectively reveals the local manifold structure within the data. Experimental results indicate significant performance enhancements compared to several state-of-the-art methods across multiple benchmark datasets.