Xu Liu

Dr. Xu Liu

orcid

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
24 December 2020 in IEEE Access
Verified
Journal Article
Open access
XLXu Liu
Xu Liu
AGAbdelouahed Gherbi
Abdelouahed Gherbi
ZWZhenzhou Wei
Zhenzhou Wei
WLWubin Li
Wubin Li
MCMohamed Cheriet
Mohamed Cheriet
Since multispectral images (MSIs) have much more sufficient spectral information than RGB images (RGBs), reconstructing MS images from RGB images is a severely underconstrained problem. We have to generate colossally different information between the two scopes. Almost all previous approaches are based on static and dependent neural networks, which fail to explain how to supplement the massive lost information. This paper presents a low-cost and high-efficiency approach, “VAE-GAN”, based on stochastic neural networks to directly reconstruct high-quality MSIs from RGBs. Our approach combines the advantages of the Generative Adversarial Network (GAN) and the Variational Autoencoder (VAE). The VAE undertakes the generation of the lost variational MS distributions by reparameterizing the latent space vector with sampling from Gaussian distribution. The GAN is responsible for regulating the generator to produce MSI-like images. In this way, our approach can create huge missed information and make the outputs look real, which also solves the previous problem. Moreover, we use several qualitative and quantitative methods to evaluate our approach and obtain excellent results. In particular, with much less training data than the previous approaches, we obtained comparable results on the CAVE dataset and surpassed state-of-the-art results on the ICVL dataset.

23 June 2021 in IEEE Access
Verified
Journal Article
Open access
XLXu Liu
Xu Liu
ZLZhenhao Li
Zhenhao Li
PXPeng Xu
Peng Xu
JLJialing Li
Jialing Li
One of the most significant problems in large-scale applications is how to allocate requests from end-users to datacenters. Most existing studies focus only on high bandwidth utilization of datacenters or low request delay of end-users, lacking the consideration of both at the same time. To achieve the joint optimization for bandwidth utilization of datacenter providers and delay of end-users, this paper proposes a novel Particle Swarm Optimization (PSO) based request allocation algorithm, based on the construction of a mathematical model for joint optimization. The algorithm adapts the coding scheme and redefines the operator to make PSO suitable for discrete optimization problems and use fitness function to get a global optimal solution. Through extensive simulations, it is demonstrated that the PSO based request allocation algorithm proposed in this study can improve the bandwidth utilization and keep the average request delay within acceptable limits or even better.

10 August 2021 in Sensors
Verified
Journal Article
Open access
PDF file
XLXu Liu
Xu Liu
AGAbdelouahed Gherbi
Abdelouahed Gherbi
WLWubin Li
Wubin Li
ZWZhenzhou Wei
Zhenzhou Wei
MCMohamed Cheriet
Mohamed Cheriet
Since multispectral images (MSIs) and RGB images (RGBs) have significantly different definitions and severely imbalanced information entropies, the spectrum transformation between them, especially reconstructing MSIs from RGBs, is a big challenge. We propose a new approach, the Taiji Generative Neural Network (TaijiGNN), to address the above-mentioned problems. TaijiGNN consists of two generators, G_MSI, and G_RGB. These two generators establish two cycles by connecting one generator’s output with the other’s input. One cycle translates the RGBs into the MSIs and converts the MSIs back to the RGBs. The other cycle does the reverse. The cycles can turn the problem of comparing two different domain images into comparing the same domain images. In the same domain, there are neither different domain definition problems nor severely underconstrained challenges, such as reconstructing MSIs from RGBs. Moreover, according to several investigations and validations, we effectively designed a multilayer perceptron neural network (MLP) to substitute the convolutional neural network (CNN) when implementing the generators to make them simple and high performance. Furthermore, we cut off the two traditional CycleGAN’s identity losses to fit the spectral image translation. We also added two consistent losses of comparing paired images to improve the two generators’ training effectiveness. In addition, during the training process, similar to the ancient Chinese philosophy Taiji’s polarity Yang and polarity Yin, the two generators update their neural network parameters by interacting with and complementing each other until they all converge and the system reaches a dynamic balance. Furthermore, several qualitative and quantitative experiments were conducted on the two classical datasets, CAVE and ICVL, to evaluate the performance of our proposed approach. Promising results were obtained with a well-designed simplistic MLP requiring a minimal amount of training data. Specifically, in the CAVE dataset, to achieve comparable state-of-the-art results, we only need half of the dataset for training; for the ICVL dataset, we used only one-fifth of the dataset to train the model, but obtained state-of-the-art results.

30 September 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
RCRuohan Cao
Ruohan Cao
HGHui Gao
Hui Gao
TWTan F. Wong
Tan F. Wong
YLYueMing Lu
YueMing Lu
XLXu Liu
Xu Liu
This paper investigates correlated and nonstationary attacks conducted by malicious Intelligent Reflecting Surface (IRS) for uplink massive MIMO systems. The malicious IRS reflects the data sequence of legitimate users with arbitrary phase shifts, thereby generating non-stationary interference sequences correlated with the data sequences, which are used to jam the massive MIMO uplink. Theoretical analyses are conducted to demonstrate the detrimental effects of correlated and non-stationary attacks on a traditional eigenvalue decomposition (EVD)-based channel estimation method. We further propose a empirical-distribution-based channel estimation approach to combat against this type of attacks. The proposed method works by capturing desired convex hulls from received signals at the BS on the basis of its empirical distribution, no secret or random phase is needed. Both analysis and simulations verify the robustness of our proposed channel estimation approach as compared with the traditional EVD-based method

20 September 2026 in Genes
Verified
Journal Article
Open access
PDF file
QLQingjie Liu
Qingjie Liu
XYXin-Wei Yao
Xin-Wei Yao
JMJinyan Ma
Jinyan Ma
HCHuilin Cheng
Huilin Cheng
HZHuahao Zhou
Huahao Zhou
XLXu Liu
Xu Liu
Background/Objectives: Accurate prediction of complex traits from high-dimensional genomic markers remains difficult in plant breeding. Linear models have limited capacity for non-linear interactions, and many deep learning models scale poorly on long marker sequences. This study introduces BiMSGP, a bidirectional Mamba-based model for scalable genomic prediction. Methods: BiMSGP extends a selective state space model with forward and backward processing so that each marker can integrate sequence context from both directions while retaining linear computational complexity; this is a modeling device for long-range marker dependencies, not a demonstration of biological epistasis. Regression was evaluated on Wheat599, Wheat2000, and SoyBase, and classification on SoyBase, using 10-fold cross-validation with shared fold assignments and no inner validation split; the held-out fold was used for checkpoint selection, learning-rate adjustment, and reporting. Ablation studies compared bidirectional and unidirectional stacks and different depths. Exploratory paired tests of fold-wise PCC differences were used to distinguish numerical rank from a paired difference under this protocol. Results: Under the reported evaluation protocol, BiMSGP attained the numerically highest mean Pearson correlation coefficient (PCC) in all four Wheat599 environments, six of eight Wheat2000 traits, and five of seven quantitative SoyBase traits. Several of these numerical ranks did not have exploratory pt<0.05 against the strongest baseline; GBLUP had a higher mean PCC for SoyBase oil (pt=0.025). Shallow bidirectional designs had higher mean PCC than deeper and unidirectional variants on Wheat599 Environment 1. Training cost was higher than that of lightweight baselines on larger datasets, but inference remained in the millisecond range. Conclusions: Under this protocol, bidirectional selective state space modeling yielded competitive mean scores with a higher training cost than lightweight baselines. The scores are exploratory and may be optimistic; they are not unbiased estimates of generalization. Evaluation that separates model selection from assessment, and tests in independent populations, years, or environments, remains future work.

14 September 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
QLQingjie Liu
Qingjie Liu
XYXin-Wei Yao
Xin-Wei Yao
JMJinyan Ma
Jinyan Ma
HCHuilin Cheng
Huilin Cheng
HZHuahao Zhou
Huahao Zhou
XLXu Liu
Xu Liu
Background/Objectives: Accurate prediction of complex traits from high-dimensional genomic markers remains difficult in plant breeding. Linear models have limited capacity for non-linear interactions, and many deep learning models scale poorly on long marker sequences. This study introduces BiMSGP, a bidirectional Mamba-based model for scalable genomic prediction. Methods: BiMSGP extends a selective state space model with forward and backward processing so that each marker can integrate sequence context from both directions while retaining linear computational complexity; this is a modeling device for long-range marker dependencies, not a demonstration of biological epistasis. Regression was evaluated on Wheat599, Wheat2000, and SoyBase, and classification on SoyBase, using 10-fold cross-validation with shared fold assignments. Ablation studies compared bidirectional and unidirectional stacks and different depths. Pairwise tests on the same folds were used to separate numerical rank from statistical significance. Results: BiMSGP attained the numerically highest Pearson correlation coefficient (PCC) in all four Wheat599 environments, six of eight Wheat2000 traits, and five of seven quantitative SoyBase traits. Several of these numerical ranks were not statistically significant against the strongest baseline; GBLUP was significantly better for SoyBase oil content. Shallow bidirectional designs had higher mean PCC than deeper and unidirectional variants. Training cost was higher than that of lightweight baselines on larger datasets, but inference remained in the millisecond range. Conclusions: Bidirectional selective state space modeling offers a practical accuracy–efficiency trade-off for genomic prediction under within-dataset cross-validation. Evaluation in independent populations, years, or environments remains future work.