Huachuan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Huachuan Wang has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Jianxin Lin
Qingdao Innovation and Development Center of Harbin Engineering University, Qingdao, China
4 shared publications Qinrao Li
Harbin Engineering University
3 shared publications- Weihao Xia
College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China
3 shared publications Chen Qiu
2 shared publicationsHaiyang Qin
College of Intelligent Systems Science and Engineering
2 shared publicationsJames Lo
2 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25  (12) , 23035-23051
Every Data Point Count: Multi-Task Data Inference Without Historical Data in Sparse Mobile Crowdsensing
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25  (12) , 23035-23051
Every Data Point Count: Multi-Task Data Inference Without Historical Data in Sparse Mobile Crowdsensing
- 27 September 2026
- Published by American Chemical Society (ACS) in Langmuir
- Vol. 42  (40) , 29638-29647
Correlating Force–Conductance–Structure in Au–1,8-Octanedithiol–Au Molecular Electronics
Because atomic-scale junction configurations cannot be directly resolved during break-junction measurements, simulations are needed to connect experimental force and conductance signatures with plausible interfacial structures. Here, we use configurational-bias Monte Carlo, driven molecular dynamics, and DFT+NEGF transport calculations to interpret the electromechanical response of Au–1,8-octanedithiol (ODT)–Au junctions measured by conductive atomic force microscopy break-junction experiments. Under cyclic stretching and compression with a modulation amplitude of 1.2 Å, reproducible force and conductance responses are observed. The simulations generate metastable configurations containing one, two, and three bridging ODT molecules and reproduce characteristic force ranges and conductance levels consistent with experiment. Structural analysis reveals configuration-dependent load distribution, junction deformation, molecular reorientation, and local Au–S coordination. The DFT+NEGF results further show that conductance modulation is governed mainly by changes in the Au–S contacts rather than deformation of the alkane backbone. These findings provide an atomistic interpretation of the measured electromechanical responses and clarify how junction configuration and contact rearrangement influence transport in Au–ODT–Au molecular junctions.
- 27 September 2026
- Published by American Chemical Society (ACS) in Langmuir
- Vol. 42  (40) , 29638-29647
Correlating Force–Conductance–Structure in Au–1,8-Octanedithiol–Au Molecular Electronics
Because atomic-scale junction configurations cannot be directly resolved during break-junction measurements, simulations are needed to connect experimental force and conductance signatures with plausible interfacial structures. Here, we use configurational-bias Monte Carlo, driven molecular dynamics, and DFT+NEGF transport calculations to interpret the electromechanical response of Au–1,8-octanedithiol (ODT)–Au junctions measured by conductive atomic force microscopy break-junction experiments. Under cyclic stretching and compression with a modulation amplitude of 1.2 Å, reproducible force and conductance responses are observed. The simulations generate metastable configurations containing one, two, and three bridging ODT molecules and reproduce characteristic force ranges and conductance levels consistent with experiment. Structural analysis reveals configuration-dependent load distribution, junction deformation, molecular reorientation, and local Au–S coordination. The DFT+NEGF results further show that conductance modulation is governed mainly by changes in the Au–S contacts rather than deformation of the alkane backbone. These findings provide an atomistic interpretation of the measured electromechanical responses and clarify how junction configuration and contact rearrangement influence transport in Au–ODT–Au molecular junctions.
- 17 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
LightRNN: A lightweight recurrent neural network for edge computing
- 17 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
LightRNN: A lightweight recurrent neural network for edge computing
- Open Access
- 29 June 2026
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 11  (27) , 40417-40425
DFT Study of Yttrium Affinity and Interfacial Bonding for O-, N-, and S-Containing Inclusions in High-Cr–High-Ti Alloys
- 29 June 2026
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 11  (27) , 40417-40425
Open AccessDFT Study of Yttrium Affinity and Interfacial Bonding for O-, N-, and S-Containing Inclusions in High-Cr–High-Ti Alloys
- Open Access
- 21 April 2026
- Published by OAE Publishing Inc. in Energy Materials
- Vol. 6  (4)
Triboelectric-memristive coupling for self-powered neuromorphic computing: mechanisms, devices, and systems
Coupling triboelectric nanogenerators (TENGs) with memristors offers a direct route to integrating energy harvesting and adaptive learning within a single physical substrate, thereby enabling self-powered neuromorphic systems driven by ubiquitous mechanical stimuli. Unlike conventional electronics that rely on external power rails, triboelectric-memristive hybrids transduce mechanical excitations into programmable resistive states, supporting synaptic functions such as short-term plasticity, long-term plasticity, and spike-timing-dependent plasticity. This review synthesizes the physical mechanisms of triboelectric-memristive coupling and clarifies how charge transfer, interfacial electron-ion interactions, and device-level state dynamics collectively enable energy-to-information transduction for signal processing and learning. In contrast to previous surveys that focus on TENGs or memristors in isolation, we establish a unified transduction framework that links mechanical stimulus statistics to TENG waveform characteristics and further to memristive state-variable evolution, which serves as the organizing principle throughout the paper. We then present (â…°) a mechanism-guided taxonomy of representative device architectures and their achievable plasticity modes; and (â…±) a system-level perspective on the integration of self - powered sensing, in-memory learning, and multimodal data fusion. Finally, we summarize key challenges - including charge stability, humidity tolerance, device variability, and scalable integration - and discuss emerging directions such as large-area triboelectric materials for improved array uniformity, multiphysics co-learning for enhanced in-sensor intelligence, and physics-informed compact models to support device-circuit-algorithm co-design under stochastic energy inputs.
- 21 April 2026
- Published by OAE Publishing Inc. in Energy Materials
- Vol. 6  (4)
Open AccessTriboelectric-memristive coupling for self-powered neuromorphic computing: mechanisms, devices, and systems
Coupling triboelectric nanogenerators (TENGs) with memristors offers a direct route to integrating energy harvesting and adaptive learning within a single physical substrate, thereby enabling self-powered neuromorphic systems driven by ubiquitous mechanical stimuli. Unlike conventional electronics that rely on external power rails, triboelectric-memristive hybrids transduce mechanical excitations into programmable resistive states, supporting synaptic functions such as short-term plasticity, long-term plasticity, and spike-timing-dependent plasticity. This review synthesizes the physical mechanisms of triboelectric-memristive coupling and clarifies how charge transfer, interfacial electron-ion interactions, and device-level state dynamics collectively enable energy-to-information transduction for signal processing and learning. In contrast to previous surveys that focus on TENGs or memristors in isolation, we establish a unified transduction framework that links mechanical stimulus statistics to TENG waveform characteristics and further to memristive state-variable evolution, which serves as the organizing principle throughout the paper. We then present (â…°) a mechanism-guided taxonomy of representative device architectures and their achievable plasticity modes; and (â…±) a system-level perspective on the integration of self - powered sensing, in-memory learning, and multimodal data fusion. Finally, we summarize key challenges - including charge stability, humidity tolerance, device variability, and scalable integration - and discuss emerging directions such as large-area triboelectric materials for improved array uniformity, multiphysics co-learning for enhanced in-sensor intelligence, and physics-informed compact models to support device-circuit-algorithm co-design under stochastic energy inputs.
- Open Access
- 8 December 2025
- Published by MDPI AG in Electronics
- Vol. 14  (24) , 4828
Risk-Aware Distributional Reinforcement Learning for Safe Path Planning of Surface Sensing Agents
In spatially constrained water domains, surface sensing agents(SSAs) must achieve safe path planning, uncertain currents, and sensor noise. We present a decentralized motion planning and collision-avoidance framework based on distributional reinforcement learning (DRL) that models the full return distribution to enable risk-aware decision making. Each surface sensing agent autonomously proceeds to its designated coordinates without rigid spatial constraints, coordinating implicitly through learned policies and a lightweight safety shield that enforces separation and kinematic limits. The method integrates (i) distributional value estimation for controllable risk sensitivity near hazards, (ii) domain randomization of sea states and disturbances for robustness, and (iii) a shielded action layer compatible with standard reactive rules (e.g., velocity obstacle-style constraints) to guarantee feasible maneuvers. In simulations across cluttered maps and stochastic current fields, the proposed approach improves success rates and reduces near-miss events compared to non-distributional RL and classical planners, while maintaining competitive path length and computation time. The results indicate that DRL-based surface sensing agent navigation is a practical path toward safe, efficient environmental monitoring and surveying.
- 8 December 2025
- Published by MDPI AG in Electronics
- Vol. 14  (24) , 4828
Open AccessRisk-Aware Distributional Reinforcement Learning for Safe Path Planning of Surface Sensing Agents
In spatially constrained water domains, surface sensing agents(SSAs) must achieve safe path planning, uncertain currents, and sensor noise. We present a decentralized motion planning and collision-avoidance framework based on distributional reinforcement learning (DRL) that models the full return distribution to enable risk-aware decision making. Each surface sensing agent autonomously proceeds to its designated coordinates without rigid spatial constraints, coordinating implicitly through learned policies and a lightweight safety shield that enforces separation and kinematic limits. The method integrates (i) distributional value estimation for controllable risk sensitivity near hazards, (ii) domain randomization of sea states and disturbances for robustness, and (iii) a shielded action layer compatible with standard reactive rules (e.g., velocity obstacle-style constraints) to guarantee feasible maneuvers. In simulations across cluttered maps and stochastic current fields, the proposed approach improves success rates and reduces near-miss events compared to non-distributional RL and classical planners, while maintaining competitive path length and computation time. The results indicate that DRL-based surface sensing agent navigation is a practical path toward safe, efficient environmental monitoring and surveying.
- Open Access
From Invariance to Symmetry Breaking in FIM-Aware Cooperative Heterogeneous Agent Networks
We recast cooperative localization and scheduling in heterogeneous multi-agent systems through the lens of symmetry and symmetry breaking. On the geometric side, the Fisher Information Matrix (FIM) objective is invariant to rigid Euclidean transformations of the global frame, while its maximization admits symmetric optimal sensor formations; on the algorithmic side, heterogeneity and task constraints break permutation symmetry across agents, requiring policies that are sensitive to role asymmetries. We model communication as a random graph and quantify structural symmetry via topology metrics (average path length, clustering, betweenness) and graph automorphism-related indices, connecting these to estimation uncertainty. We then design a hybrid reward for reinforcement learning (RL) that is equivariant to agent relabeling within roles yet intentionally introduces asymmetry through distance/FIM terms to avoid degenerate symmetric configurations with poor observability. Simulations show that (i) symmetry-aware, FIM-optimized path planning reduces localization error versus symmetric but non-informative placements; and (ii) controlled symmetry breaking in policy learning improves robustness and data rate–reward trade-offs over baselines. Our results position symmetry/asymmetry as first-class design principles that unify estimation-theoretic invariances with learning-based coordination in complex heterogeneous networks. Under DDPG training, the total data rate (SDR) reaches and the average reward per step (ARPS) is , representing improvements of approximately over the baseline and over SAC , respectively. The network’s mean shortest-path length is , and the average betweenness centrality of the coordination nodes is ≈0.098. Moreover, the FIM-optimized path-planning strategy achieves the lowest localization error among all evaluated policies.Open AccessFrom Invariance to Symmetry Breaking in FIM-Aware Cooperative Heterogeneous Agent Networks
We recast cooperative localization and scheduling in heterogeneous multi-agent systems through the lens of symmetry and symmetry breaking. On the geometric side, the Fisher Information Matrix (FIM) objective is invariant to rigid Euclidean transformations of the global frame, while its maximization admits symmetric optimal sensor formations; on the algorithmic side, heterogeneity and task constraints break permutation symmetry across agents, requiring policies that are sensitive to role asymmetries. We model communication as a random graph and quantify structural symmetry via topology metrics (average path length, clustering, betweenness) and graph automorphism-related indices, connecting these to estimation uncertainty. We then design a hybrid reward for reinforcement learning (RL) that is equivariant to agent relabeling within roles yet intentionally introduces asymmetry through distance/FIM terms to avoid degenerate symmetric configurations with poor observability. Simulations show that (i) symmetry-aware, FIM-optimized path planning reduces localization error versus symmetric but non-informative placements; and (ii) controlled symmetry breaking in policy learning improves robustness and data rate–reward trade-offs over baselines. Our results position symmetry/asymmetry as first-class design principles that unify estimation-theoretic invariances with learning-based coordination in complex heterogeneous networks. Under DDPG training, the total data rate (SDR) reaches and the average reward per step (ARPS) is , representing improvements of approximately over the baseline and over SAC , respectively. The network’s mean shortest-path length is , and the average betweenness centrality of the coordination nodes is ≈0.098. Moreover, the FIM-optimized path-planning strategy achieves the lowest localization error among all evaluated policies. - Open Access
- 17 October 2025
- Published by Springer Nature in Research Square
Streaming Propagation Through Time: A New Computational Paradigm for Recurrent Neural Networks
Recurrent Neural Networks (RNNs) are foundational to numerous advances in artificial intelligence, yet their training has for decades predominantly relies on Backpropagation Through Time (BPTT), a paradigm that struggles with substantial computational and memory demands for long sequences. The inherently batch-oriented nature of BPTT further constrains RNNs’ ability to learn from streaming or online data. Earlier efforts toward online RNN training have been hindered by prohibitive costs in both computation and memory. Here, we introduce Streaming Propagation Through Time (SPTT), a new computational paradigm for RNN training. SPTT employs a streaming low-rank matrix decomposition to decouple gradient computation into two independent components: an optimization direction and an update magnitude. This incremental exploration of the gradient landscape enables efficient long-sequence processing while maintaining learning continuity.Across diverse sequence modeling benchmarks, SPTT outperforms BPTT, with stronger generalization and improved computational efficiency, thereby opening new possibilities for real-time and resource-constrained RNN applications.
- 17 October 2025
- Published by Springer Nature in Research Square
Open AccessStreaming Propagation Through Time: A New Computational Paradigm for Recurrent Neural Networks
Recurrent Neural Networks (RNNs) are foundational to numerous advances in artificial intelligence, yet their training has for decades predominantly relies on Backpropagation Through Time (BPTT), a paradigm that struggles with substantial computational and memory demands for long sequences. The inherently batch-oriented nature of BPTT further constrains RNNs’ ability to learn from streaming or online data. Earlier efforts toward online RNN training have been hindered by prohibitive costs in both computation and memory. Here, we introduce Streaming Propagation Through Time (SPTT), a new computational paradigm for RNN training. SPTT employs a streaming low-rank matrix decomposition to decouple gradient computation into two independent components: an optimization direction and an update magnitude. This incremental exploration of the gradient landscape enables efficient long-sequence processing while maintaining learning continuity.Across diverse sequence modeling benchmarks, SPTT outperforms BPTT, with stronger generalization and improved computational efficiency, thereby opening new possibilities for real-time and resource-constrained RNN applications.
- Open Access
- 16 August 2025
- Published by MDPI AG in Nanomaterials
- Vol. 15  (16) , 1267
Interstitial Ag+ Engineering Enables Superior Resistive Switching in Quasi-2D Halide Perovskites
Halide perovskite-based memristors are promising neuromorphic devices due to their unique ion migration and interface tunability, yet their conduction mechanisms remain unclear, causing stability and performance issues. Here, we engineer interstitial Ag+ ions within a quasi-two-dimensional (quasi-2D) halide perovskite ((C6H5C2H4NH3)2Csn−1PbnI3n+1) to enhance device stability and controllability. The introduced Ag+ ions occupy organic interlayers, forming thermodynamically stable structures and introducing deep-level energy states without structural distortion, which do not act as non-radiative recombination centers, but instead serve as efficient charge trapping centers that stabilize intermediate resistance states and facilitate controlled filament evolution during resistive switching. This modification also leads to enhanced electron transparency near the Fermi level, contributing to improved charge transport dynamics and device performance. Under external electric fields, these Ag+ ions act as mobile ionic species, facilitating controlled filament formation and stable resistive switching. The resulting devices demonstrate exceptional performance, featuring an ultrahigh on/off ratio (∼108) and low operating voltages (∼0.31 V), surpassing existing benchmarks. Our findings highlight the dual role of Ag+ ions in structural stabilization and conduction modulation, providing a robust approach for high-performance perovskite memristor engineering.
- 16 August 2025
- Published by MDPI AG in Nanomaterials
- Vol. 15  (16) , 1267
Open AccessInterstitial Ag+ Engineering Enables Superior Resistive Switching in Quasi-2D Halide Perovskites
Halide perovskite-based memristors are promising neuromorphic devices due to their unique ion migration and interface tunability, yet their conduction mechanisms remain unclear, causing stability and performance issues. Here, we engineer interstitial Ag+ ions within a quasi-two-dimensional (quasi-2D) halide perovskite ((C6H5C2H4NH3)2Csn−1PbnI3n+1) to enhance device stability and controllability. The introduced Ag+ ions occupy organic interlayers, forming thermodynamically stable structures and introducing deep-level energy states without structural distortion, which do not act as non-radiative recombination centers, but instead serve as efficient charge trapping centers that stabilize intermediate resistance states and facilitate controlled filament evolution during resistive switching. This modification also leads to enhanced electron transparency near the Fermi level, contributing to improved charge transport dynamics and device performance. Under external electric fields, these Ag+ ions act as mobile ionic species, facilitating controlled filament formation and stable resistive switching. The resulting devices demonstrate exceptional performance, featuring an ultrahigh on/off ratio (∼108) and low operating voltages (∼0.31 V), surpassing existing benchmarks. Our findings highlight the dual role of Ag+ ions in structural stabilization and conduction modulation, providing a robust approach for high-performance perovskite memristor engineering.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (28) , 29543-29544
Temporal Streaming Batch Principal Component Analysis for Time Series Classification (Student Abstract)
In multivariate time series classification, although current sequence analysis models have excellent classification capabilities, they show significant shortcomings when dealing with long sequence multivariate data. This paper focuses on optimizing model performance for long-sequence multivariate data by mitigating the impact of extended time series and multiple variables on the model. We propose a principal component analysis (PCA)-based temporal streaming compression and dimensionality reduction algorithm for time series data (temporal streaming batch PCA, TSBPCA), which continuously updates the compact representation of the entire sequence through streaming PCA time estimation with time block updates, enhancing the data representation capability of a range of sequence analysis models.We evaluated this method using various models on five datasets, and the experimental results show that our method demonstrates outstanding performance in both classification accuracy and time efficiency.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (28) , 29543-29544
Open AccessTemporal Streaming Batch Principal Component Analysis for Time Series Classification (Student Abstract)
In multivariate time series classification, although current sequence analysis models have excellent classification capabilities, they show significant shortcomings when dealing with long sequence multivariate data. This paper focuses on optimizing model performance for long-sequence multivariate data by mitigating the impact of extended time series and multiple variables on the model. We propose a principal component analysis (PCA)-based temporal streaming compression and dimensionality reduction algorithm for time series data (temporal streaming batch PCA, TSBPCA), which continuously updates the compact representation of the entire sequence through streaming PCA time estimation with time block updates, enhancing the data representation capability of a range of sequence analysis models.We evaluated this method using various models on five datasets, and the experimental results show that our method demonstrates outstanding performance in both classification accuracy and time efficiency.