Miao Liu

Dr. Miao Liu

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
10 September 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
BSBenyun Shi
Benyun Shi
LFLiu Feng
Liu Feng
HHHailun He
Hailun He
YHYingjian Hao
Yingjian Hao
YPYue Peng
Yue Peng
JLJiming Liu
Jiming Liu
Accurate prediction of sea surface temperature (SST) is crucial in the field of oceanography, as it has a significant impact on various physical, chemical and biological processes in the marine environment. In this study, we propose a physics-guided attention-based neural network (PANN) to address the spatiotemporal SST prediction problem. The PANN model incorporates data-driven spatiotemporal convolution operations and the underlying physical dynamics of SSTs using a cross-attention mechanism. First, we construct a spatiotemporal convolution module (SCM) using ConvLSTM to capture the spatial and temporal correlations present in the time series of the SST data. We then introduce a physical constraints module (PCM) to mimic the transport dynamics in fluids based on data assimilation techniques used to solve partial differential equations (PDEs). Consequently, we employ an attention fusion module (AFM) to effectively combine the data-driven and PDE-constrained predictions obtained from the SCM and PCM, aiming at enhancing the accuracy of the predictions. To evaluate the performance of the proposed model, we conduct short-term SST forecasts in the East China Sea (ECS) with forecast lead times ranging from 1 to 10 days, by comparing it with several state-of-the-art models, including ConvLSTM, PredRNN, TCTN, ConvGRU, and SwinLSTM. The experimental results demonstrate that our proposed model outperforms these models in terms of multiple evaluation metrics for short-term predictions.

3 September 2018 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
MLMiao Liu
Miao Liu
ZLZhongkui Li
Zhongkui Li
This paper studies the systemic performance of double-integrator consensus networks in the presence of stochastic noises. The systemic performance is characterized in terms of the network coherence, which is equal to the squared H2 norm of the network and can capture the deviation from network average. Four different types of structured noises are mainly considered and for each type of noise, a consensus protocol without velocity measurements is proposed to guarantee consensus achieving. For the cases with dynamics noise, sensor noise and communication channel noise, it is shown that the network coherence can be explicitly expressed by a function of the nonzero eigenvalues of the Laplacian matrix and the network size. For the case with receiver noise, a sufficient condition is derived to ensure that the network coherence is less than a given constant.

10 March 2026 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
MLMiao Liu
Miao Liu
LXLongbiao Xie
Longbiao Xie
LXLong Xiao
Long Xiao
SGSHAOPAN GUO
SHAOPAN GUO
In the field of Unmanned Aerial Vehicles(UAVs) decision-making, cooperative target search by multiple UAVs rep resents a central research focus. Recent advancements in neural network-based deep reinforcement learning, coupled with improvements in UAV performance, have significantly enhanced the intelligent decision-making capabilities of UAVs in unknown and dynamic environments. However, as search scenarios grow in scale and complexity, existing UAV search methods increasingly struggle to maintain efficient search performance. To address these challenges, this study introduces a Multi-Agent Deep Deterministic Policy Gradient integrated with a self-attention mechanism (SA MADDPG) algorithm which integrates a self-attention mechanism to facilitate global spatial information modeling. By effectively capturing long-range dependencies within complex, high-dimensional spatial data, such as obstacle distributions, teammate positions, and target probabilities, the algorithm overcomes the constraints of localized receptive fields inherent in conventional architectures. This enables agents to prioritize critical environmental features, thereby significantly enhancing collaborative decision-making in obstacle-dense settings. Furthermore, we develop a dual-incentive exploration mechanism that synthesizes Bayesian-updated target probability maps with Voronoi-region partitioning to enhance multi UAV collaborative coordination and search reliability. Experimental results reveal that the proposed SA-MADDPG method significantly outperforms existing search strategies across critical metrics, including collision rate, coverage rate, and target detection rate.

30 April 2026 in IEEE Control Systems Letters
Verified
Journal Article
Closed access
MLMiao Liu
Miao Liu
MKMingxing Ke
Mingxing Ke
This paper investigates robust bipartite output consensus for heterogeneous linear multi-agent systems over undirected, structurally balanced signed graphs with bounded multiplicative channel uncertainties. A signed-network dynamic compensator is introduced to generate bipartite synchronization signals. By combining gauge transformation, Laplacian modal decomposition, and an interval-based robustness treatment, we derive a scalable synthesis condition in the form of a single small-scale LMI independent of the network size. Building on the compensator layer, an observer-based distributed output-feedback protocol is constructed via regulator-equation techniques to drive each physical output to its compensator signal, thereby achieving robust bipartite output consensus. Numerical simulations with heterogeneous agents illustrate the effectiveness of the proposed design under the prescribed uncertainty bounds.

9 May 2026 in Electronics
Verified
Journal Article
Open access
PDF file
ZCZhiwen Chen
Zhiwen Chen
YZYijia Zhang
Yijia Zhang
MLMiao Liu
Miao Liu
YPYue Peng
Yue Peng
Flat label supervision often constrains multi-label image classification, as it struggles to fully capture inherent label dependencies. It provides limited guidance to the hierarchical features that naturally emerge in Vision Transformers. To address this structural misalignment, we propose Dynamic Topic-based Hierarchical Prompt Learning (DyT-HPL). Instead of relying on predefined and fixed label graphs, DyT-HPL utilizes offline hierarchical clustering to construct multi-granularity semantic priors, from which hierarchical prompts are dynamically retrieved. A frozen visual query branch generates stable semantic queries, which are then used to retrieve discrete prompts from constructed coarse-mid-fine prompt pools. These hierarchical prompts are adaptively injected into different network depths, ensuring that semantic guidance with different abstraction levels is introduced at the most suitable architectural stages. To maintain stable routing and prevent prompt mode collapse, we jointly optimize the architecture with asymmetric classification, surrogate matching, and intra-pool diversity losses. This tripartite design promotes a diverse prompt space and isolates routing updates from final predictions. Comprehensive experiments on MS-COCO, NUS-WIDE, and Corel5k demonstrate that DyT-HPL achieves consistent and favorable performance across diverse settings, highlighting the value of hierarchical semantic guidance with different abstraction levels.

20 July 2026 in Electronics
Verified
Journal Article
Open access
PDF file
MLMiao Liu
Miao Liu
JWJiaying Wu
Jiaying Wu
MKMingxing Ke
Mingxing Ke
YZYijia Zhang
Yijia Zhang
This paper develops a stability-certified distributed residual neural network (ResNN) controller for leaderless consensus of continuous-time first-order multi-agent systems over undirected connected graphs. Unlikeconventional linear protocols and post-training verification methods, the proposed framework combines nonlinear transient shaping with certificate feasibility throughout learning. Each agent uses relative state differences with neighboring agents and applies a shared ResNN policy composed of a linear diffusive backbone and a bias-free neural residual branch. A computable residual-gain bound yields a sufficient condition for global exponential consensus, with the certified rate determined by the backbone–residual gain margin and the algebraic connectivity of the graph. Spectral-norm projection and gain reparameterization preserve this condition after every training update. A complementary forward-Euler certificate provides an explicit step-size condition for exponentially convergent digital implementation. The controller is trained through differentiable closed-loop simulation using an objective that balances disagreement and control effort. Ournumerical results verify the certified decay bound, demonstrate competitive transient trade-offs against three baselines, and evaluate direct deployment across different graph topologies and network sizes.