Rui Hao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rui Hao has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Jianwen Xiang
Wuhan University of Technology, Wuhan, China
7 shared publications - Xiaohai Dai
Huazhong University of Science and Technology
5 shared publications - Junhong Liu
The University of Hong Kong
3 shared publications - Songsong Liao
School of Computer Science and Artificial Intelligence, Engineering Research Center of Transportation Information and Safety, ERCTIS, MoE of China, Wuhan University of Technology, Wuhan, China
3 shared publications Xia Xie
3 shared publications- Dongdong Zhao
School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 468-478
A Neuromorphic Dual-Stage Swin Transformer for Wetland Classification on Edge Platforms
Accurate coastal wetland classification using hyperspectral remote sensing is crucial for conservation, restoration, and sustainable management of these ecologically vital regions. With the proliferation of edge computing, there is a growing demand for real-time hyperspectral analysis on sensing platforms such as satellites and unmanned aerial vehicles. However, the spectral complexity of wetland scenes, the high computational cost of modern CNNs and Transformers, and frequent memory accesses impose substantial overhead on resource-constrained edge platforms. To address these challenges, we propose the Dual-Stage Spiking Swin Transformer (D2S-SwinT), a neuromorphic architecture that integrates the feature representation capability of Swin Transformers with the event-driven efficiency of brain-inspired computation. The model employs a compact dual-stage design to reduce architectural redundancy and leverages the Expectation Compensation and Multi-Threshold (ECMT) mechanism to transform dense arithmetic operations into sparse, event-driven processes. Extensive experiments on four wetland datasets show that D2S-SwinT reaches 99.62% OA on Huanghekou at T = 4. Additional experiments on IP and SA provide evidence that the model generalizes beyond wetland-specific scenes. At T = 1, its normalized operation-level energy is reduced to 8% of the ANN-proxy reference. At T = 3, a memristor-based architecture-level mapping yields a projected OA of 96.69% and an energy per sample equal to 0.66% of the software reference. These results indicate the potential of D2S-SwinT for accurate and energy-efficient hyperspectral wetland monitoring on resource-constrained edge platforms.
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 468-478
Open AccessA Neuromorphic Dual-Stage Swin Transformer for Wetland Classification on Edge Platforms
Accurate coastal wetland classification using hyperspectral remote sensing is crucial for conservation, restoration, and sustainable management of these ecologically vital regions. With the proliferation of edge computing, there is a growing demand for real-time hyperspectral analysis on sensing platforms such as satellites and unmanned aerial vehicles. However, the spectral complexity of wetland scenes, the high computational cost of modern CNNs and Transformers, and frequent memory accesses impose substantial overhead on resource-constrained edge platforms. To address these challenges, we propose the Dual-Stage Spiking Swin Transformer (D2S-SwinT), a neuromorphic architecture that integrates the feature representation capability of Swin Transformers with the event-driven efficiency of brain-inspired computation. The model employs a compact dual-stage design to reduce architectural redundancy and leverages the Expectation Compensation and Multi-Threshold (ECMT) mechanism to transform dense arithmetic operations into sparse, event-driven processes. Extensive experiments on four wetland datasets show that D2S-SwinT reaches 99.62% OA on Huanghekou at T = 4. Additional experiments on IP and SA provide evidence that the model generalizes beyond wetland-specific scenes. At T = 1, its normalized operation-level energy is reduced to 8% of the ANN-proxy reference. At T = 3, a memristor-based architecture-level mapping yields a projected OA of 96.69% and an energy per sample equal to 0.66% of the software reference. These results indicate the potential of D2S-SwinT for accurate and energy-efficient hyperspectral wetland monitoring on resource-constrained edge platforms.
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 436-445
Algorithm--Hardware Co-Design of Spiking Transformers for In-Memory Neuromorphic Edge Vision
Reliable, ultra-low-power neuromorphic vision on edge devices requires attention mechanisms that combine accuracy with parallel, memory-efficient execution. Current Spiking Transformers suit neuromorphic data but retain the \(\mathcal {O}(N^2D)\) complexity of standard self-attention and weak temporal modeling, limiting their efficiency on in-memory edge hardware. We propose the Temporal Hadamard Transformer (THT), a spiking model co-designed with hardware for in-memory edge vision. Its Temporal Hadamard Attention (THA) combines a lightweight Temporal Processing Unit (TPU) for short-term temporal fusion with a binary Mask&Add operator. By replacing Query–Key–Value computation with accumulate-and-fire logic that maps efficiently onto memristor crossbars, THA reduces attention complexity to \(\mathcal {O}(ND)\) and enables highly parallel in-memory execution. On CIFAR10-DVS, THT achieves a peak Accuracy-to-Energy ratio of 157.06. THT consumes 0.51–2.19 mJ per inference. Its lowest-energy configuration uses up to 16 × lower energy than the compared models, while the largest configuration reaches 81.8% accuracy. We further design a detailed hardware deployment scheme and evaluate its robustness through non-ideal memristor crossbar simulations. Accounting for conductance drift and IR drop, the simulated deployment maintains 81.1% accuracy. Thus, THT integrates sparse algorithms with parallel hardware execution, providing a practical path toward real-time edge systems under realistic resource constraints and physical device non-idealities.- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 436-445
Open AccessAlgorithm--Hardware Co-Design of Spiking Transformers for In-Memory Neuromorphic Edge Vision
Reliable, ultra-low-power neuromorphic vision on edge devices requires attention mechanisms that combine accuracy with parallel, memory-efficient execution. Current Spiking Transformers suit neuromorphic data but retain the \(\mathcal {O}(N^2D)\) complexity of standard self-attention and weak temporal modeling, limiting their efficiency on in-memory edge hardware. We propose the Temporal Hadamard Transformer (THT), a spiking model co-designed with hardware for in-memory edge vision. Its Temporal Hadamard Attention (THA) combines a lightweight Temporal Processing Unit (TPU) for short-term temporal fusion with a binary Mask&Add operator. By replacing Query–Key–Value computation with accumulate-and-fire logic that maps efficiently onto memristor crossbars, THA reduces attention complexity to \(\mathcal {O}(ND)\) and enables highly parallel in-memory execution. On CIFAR10-DVS, THT achieves a peak Accuracy-to-Energy ratio of 157.06. THT consumes 0.51–2.19 mJ per inference. Its lowest-energy configuration uses up to 16 × lower energy than the compared models, while the largest configuration reaches 81.8% accuracy. We further design a detailed hardware deployment scheme and evaluate its robustness through non-ideal memristor crossbar simulations. Accounting for conductance drift and IR drop, the simulated deployment maintains 81.1% accuracy. Thus, THT integrates sparse algorithms with parallel hardware execution, providing a practical path toward real-time edge systems under realistic resource constraints and physical device non-idealities. - Open Access
- 1 September 2026
- Published by Elsevier in SSRN Electronic Journal
CrossBot: Android GUI Testing via Efficient Cross-Device History Reuse
Context: Android applications are increasingly released as multiple device-specific variants, such as phone, tablet, in-vehicle, and TV versions. Existing automated GUI testing tools usually test these variants independently, repeatedly spending testing budget on common functionality and providing little guidance when a new phone variant is explored.Objectives: This paper aims to improve phone-target Android GUI testing by reusing testing histories collected offline from non-phone variants of the same app, while remaining robust to cross-device differences in layouts, widgets, and interaction flows.Methods: We present \texttt{CrossBot}, a widget-level history reuse framework. \texttt{CrossBot} summarizes source-side testing histories as probabilistic event-to-widget transition priors, matches semantically corresponding widgets across device variants using text, resource-id, and activity context, and injects the transferred priors into online phone-side exploration. To reduce online overhead, \texttt{CrossBot} further applies embedding caching and locality-sensitive hashing. We evaluate \texttt{CrossBot} on 14 commercial Android apps under Tablet-to-Phone, TV-to-Phone, Car-to-Phone, and Multi-to-Phone reuse settings.Results: Compared with \texttt{Fastbot2}, \texttt{CrossBot-With-X} improves activity coverage by 16.5\%--24.2\% and widget coverage by 62.0\%--88.5\% at 60 minutes. It also outperforms a resource-ID-only reuse baseline and sustains coverage growth in four-hour sessions. In the LSH ablation, LSH-backed matching increases throughput by 97.3\% and reduces amortized cost by 46.8\% on average.Conclusion: The results show that widget-level cross-device history reuse can effectively guide phone-target GUI exploration under UI differences, and that efficient approximate matching makes such reuse practical for long-running Android testing.
- 1 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCrossBot: Android GUI Testing via Efficient Cross-Device History Reuse
Context: Android applications are increasingly released as multiple device-specific variants, such as phone, tablet, in-vehicle, and TV versions. Existing automated GUI testing tools usually test these variants independently, repeatedly spending testing budget on common functionality and providing little guidance when a new phone variant is explored.Objectives: This paper aims to improve phone-target Android GUI testing by reusing testing histories collected offline from non-phone variants of the same app, while remaining robust to cross-device differences in layouts, widgets, and interaction flows.Methods: We present \texttt{CrossBot}, a widget-level history reuse framework. \texttt{CrossBot} summarizes source-side testing histories as probabilistic event-to-widget transition priors, matches semantically corresponding widgets across device variants using text, resource-id, and activity context, and injects the transferred priors into online phone-side exploration. To reduce online overhead, \texttt{CrossBot} further applies embedding caching and locality-sensitive hashing. We evaluate \texttt{CrossBot} on 14 commercial Android apps under Tablet-to-Phone, TV-to-Phone, Car-to-Phone, and Multi-to-Phone reuse settings.Results: Compared with \texttt{Fastbot2}, \texttt{CrossBot-With-X} improves activity coverage by 16.5\%--24.2\% and widget coverage by 62.0\%--88.5\% at 60 minutes. It also outperforms a resource-ID-only reuse baseline and sustains coverage growth in four-hour sessions. In the LSH ablation, LSH-backed matching increases throughput by 97.3\% and reduces amortized cost by 46.8\% on average.Conclusion: The results show that widget-level cross-device history reuse can effectively guide phone-target GUI exploration under UI differences, and that efficient approximate matching makes such reuse practical for long-running Android testing.
- Open Access
- 20 July 2026
- Published by Elsevier in Engineering
Tuna: Optimal-Resilience Asynchronous DAG-Based BFT with Lower Latency
- 20 July 2026
- Published by Elsevier in Engineering
Open AccessTuna: Optimal-Resilience Asynchronous DAG-Based BFT with Lower Latency
- 16 July 2026
- Published by Springer Nature
- p. 618-632
Industrial Protocol Data Model and State Model Generation Based on Large Language Model
- 16 July 2026
- Published by Springer Nature
- p. 618-632
Industrial Protocol Data Model and State Model Generation Based on Large Language Model
- 22 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. PP (5) , 1
Cancellable Iris Recognition Scheme Based on Positive-Negative Mapping and Negative Selection
Iris recognition technology is widely used in identity verification and other fields due to its high accuracy and strong security. However, with the popularization of the technology, the privacy protection of iris data has become increasingly prominent. Existing systems are often difficult to protect personal data privacy while guaranteeing recognition accuracy, especially when facing data leakage and attacks, iris features cannot be modified once leaked, which is extremely risky. Therefore, proposing an efficient and accurate protection scheme that can ensure the security of iris data has become an important issue that needs to be solved urgently. In this paper, we propose an iris template protection framework based on positive-negative mapping and the negative selective algorithm, called the IrisPN-NS. The framework effectively protects iris data by constructing a complex system of inequality equations and combining it with the negative selection algorithm, thus increasing the difficulty for attackers to crack. Based on this framework, we propose two iris template protection methods, IrisPNM-NS and IrisPNS-NS. We conducted experiments on the CASIA-IrisV3-Interval, CASIA-IrisV4-Lamp, and IIT Delhi Iris datasets. The experimental results show that the scheme achieves high performance and effectively resists the attack of the greedy algorithm, while satisfying the requirements of irreversibility, revocability, and unlinkability.
- 22 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. PP (5) , 1
Cancellable Iris Recognition Scheme Based on Positive-Negative Mapping and Negative Selection
Iris recognition technology is widely used in identity verification and other fields due to its high accuracy and strong security. However, with the popularization of the technology, the privacy protection of iris data has become increasingly prominent. Existing systems are often difficult to protect personal data privacy while guaranteeing recognition accuracy, especially when facing data leakage and attacks, iris features cannot be modified once leaked, which is extremely risky. Therefore, proposing an efficient and accurate protection scheme that can ensure the security of iris data has become an important issue that needs to be solved urgently. In this paper, we propose an iris template protection framework based on positive-negative mapping and the negative selective algorithm, called the IrisPN-NS. The framework effectively protects iris data by constructing a complex system of inequality equations and combining it with the negative selection algorithm, thus increasing the difficulty for attackers to crack. Based on this framework, we propose two iris template protection methods, IrisPNM-NS and IrisPNS-NS. We conducted experiments on the CASIA-IrisV3-Interval, CASIA-IrisV4-Lamp, and IIT Delhi Iris datasets. The experimental results show that the scheme achieves high performance and effectively resists the attack of the greedy algorithm, while satisfying the requirements of irreversibility, revocability, and unlinkability.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 6521-6537
Vega: An Asynchronous BFT With Lower Communication Overhead and Lower Latency
The low-altitude economy has experienced significant growth recently, due to the flexibility, affordability, and versatility of low-altitude aircraft. A typical setup uses multiple devices in a distributed system, where the Byzantine Fault Tolerance (BFT) consensus ensures data consistency. However, existing BFT protocols, such as those based on the BKR paradigm with HoneybadgerBFT as a representative, suffer from high communication overhead and latency, limiting scalability and performance. In this paper, we introduce Vega, a novel BFT protocol designed to overcome these challenges. Vega replaces the traditional Reliable Broadcast (RBC) protocol with a more efficient linear Consistent Broadcast (CBC), reducing communication overhead from $O(n^{3})$ to $O(n^{2})$. However, this change introduces a new challenge related to totality, which may impact liveness. Additionally, Vega incorporates a fast path for block agreement, which reduces agreement latency to two communication rounds under optimistic conditions, with a fallback to the original Asynchronous Binary Agreement (ABA) in less favorable cases. However, this introduces another challenge: ensuring consistency between blocks committed via the fast and normal paths. To solve these challenges, we introduce a block retrieval mechanism and a preparation step, ensuring both liveness and consistency. Our experimental results show that Vega significantly outperforms existing protocols, reducing latency by up to 45% and achieving up to 1.8x higher throughput compared to HoneybadgerBFT.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 6521-6537
Vega: An Asynchronous BFT With Lower Communication Overhead and Lower Latency
The low-altitude economy has experienced significant growth recently, due to the flexibility, affordability, and versatility of low-altitude aircraft. A typical setup uses multiple devices in a distributed system, where the Byzantine Fault Tolerance (BFT) consensus ensures data consistency. However, existing BFT protocols, such as those based on the BKR paradigm with HoneybadgerBFT as a representative, suffer from high communication overhead and latency, limiting scalability and performance. In this paper, we introduce Vega, a novel BFT protocol designed to overcome these challenges. Vega replaces the traditional Reliable Broadcast (RBC) protocol with a more efficient linear Consistent Broadcast (CBC), reducing communication overhead from $O(n^{3})$ to $O(n^{2})$. However, this change introduces a new challenge related to totality, which may impact liveness. Additionally, Vega incorporates a fast path for block agreement, which reduces agreement latency to two communication rounds under optimistic conditions, with a fallback to the original Asynchronous Binary Agreement (ABA) in less favorable cases. However, this introduces another challenge: ensuring consistency between blocks committed via the fast and normal paths. To solve these challenges, we introduce a block retrieval mechanism and a preparation step, ensuring both liveness and consistency. Our experimental results show that Vega significantly outperforms existing protocols, reducing latency by up to 45% and achieving up to 1.8x higher throughput compared to HoneybadgerBFT.
- 8 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (1) , 221-245
Aging-Related Bug Prediction Based on Multi-View Graph Feature Learning and Graph-Transformer
Software aging, characterized by an increasing failure rate or performance degradation in long-running software systems, poses significant risks, including substantial financial losses and potential threats to human lives. This phenomenon is primarily driven by the accumulation of runtime errors, commonly referred to as aging-related bugs (ARBs). Aging-related bug prediction (ARBP) has been proposed to facilitate the detection and remediation of ARBs prior to software release. However, ARBP’s effectiveness heavily depends on the quality of dataset features used. Previous research has largely relied on a standard set of manually designed metrics, often overlooking that these metrics may fail to distinguish between code segments with different semantics, even when they exhibit identical metric values. While some studies have attempted to develop models that learn semantic features from source code, they typically focus on token-level or graph-level features, neglecting a comprehensive exploration of ARB characteristics within the source code. Specifically, there is insufficient discussion on whether deep semantic features can adequately capture the essential traits that trigger aging phenomena. In this paper, we propose a novel multi-view graph feature learning framework based on Graph-Transformer, which integrates newly proposed ARB features extracted from Abstract Syntax Trees with Code Property Graphs for feature learning. Our approach effectively captures hierarchical structures and variable dependencies, facilitating the identification of complex interactions that contribute to ARBs. Additionally, we implement sub-graph sampling and class imbalance strategies to enhance model performance. Experimental results across three datasets demonstrate that our method surpasses state-of-the-art approaches, a code property graph-based feature extraction method (specifically SGT), achieving precision improvements of 8.2% on Linux, 15.4% on MySQL, and 2.5% on NetBSD, thereby establishing a new benchmark for ARB prediction.
- 8 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (1) , 221-245
Aging-Related Bug Prediction Based on Multi-View Graph Feature Learning and Graph-Transformer
Software aging, characterized by an increasing failure rate or performance degradation in long-running software systems, poses significant risks, including substantial financial losses and potential threats to human lives. This phenomenon is primarily driven by the accumulation of runtime errors, commonly referred to as aging-related bugs (ARBs). Aging-related bug prediction (ARBP) has been proposed to facilitate the detection and remediation of ARBs prior to software release. However, ARBP’s effectiveness heavily depends on the quality of dataset features used. Previous research has largely relied on a standard set of manually designed metrics, often overlooking that these metrics may fail to distinguish between code segments with different semantics, even when they exhibit identical metric values. While some studies have attempted to develop models that learn semantic features from source code, they typically focus on token-level or graph-level features, neglecting a comprehensive exploration of ARB characteristics within the source code. Specifically, there is insufficient discussion on whether deep semantic features can adequately capture the essential traits that trigger aging phenomena. In this paper, we propose a novel multi-view graph feature learning framework based on Graph-Transformer, which integrates newly proposed ARB features extracted from Abstract Syntax Trees with Code Property Graphs for feature learning. Our approach effectively captures hierarchical structures and variable dependencies, facilitating the identification of complex interactions that contribute to ARBs. Additionally, we implement sub-graph sampling and class imbalance strategies to enhance model performance. Experimental results across three datasets demonstrate that our method surpasses state-of-the-art approaches, a code property graph-based feature extraction method (specifically SGT), achieving precision improvements of 8.2% on Linux, 15.4% on MySQL, and 2.5% on NetBSD, thereby establishing a new benchmark for ARB prediction.
- 19 February 2025
- Published by Elsevier in Computers & Security
- Vol. 152
Cancelable iris template based on slicing
- 19 February 2025
- Published by Elsevier in Computers & Security
- Vol. 152
Cancelable iris template based on slicing