Haojie Ruan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haojie Ruan has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Donghui Guo
Xiamen University
4 shared publications - Yabin Deng
School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen 361024, China
3 shared publications - Leilei Li
School of Electronic Science and Engineering, Xiamen University, Xiamen, Fujian, China
2 shared publications Shan He
R&D Center of Integrated Circuit, School of Electronic Science and Engineering (National Model Microelectronics College), Xiamen University, China
2 shared publicationsBingrui Guo
Peking University
1 shared publicationHailing Xu
Xiamen University
1 shared publication
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (10) , 3412-3425
Multimodal Spiking Neural Network With Generalized Distributive Law for Biosignal and Sensory Fusion
Multimodal signal fusion is a cornerstone of biomedical engineering and intelligent sensing, enabling holistic analysis of heterogeneous sources such as electroencephalography (EEG), peripheral signals, speech, and imaging data. However, integrating diverse modalities in a computationally efficient and biologically plausible manner remains a significant challenge. Transformer-based fusion architectures rely on global cross-attention to integrate multimodal information but incur high computational costs. In contrast, STDP-driven fully connected layers adopt local learning rules, which restrict their ability to autonomously form efficient sparse topologies for complex multimodal tasks. To address these issues, we propose a novel end-to-end framework—the Multimodal Spiking Neural Network (MSNN)—featuring a fusion module grounded in the Generalized Distributive Law (GDL). This principled mechanism provides an efficient and interpretable means of integrating heterogeneous biomedical and sensory signals. The MSNN further incorporates structure-adaptive leaky integrate-and-fire (SALIF) neurons, enabling dynamic optimization of sparse connectivity to enhance fusion efficiency. The proposed MSNN is validated on a range of datasets, demonstrating strong versatility: it achieves binary classification accuracies of 92.29% (valence) and 91.08% (arousal) on the DEAP dataset for affective state decoding and 99.77% on the WESAD dataset for stress detection, while delivering state-of-the-art performance on standard pattern recognition tasks (MNIST & TIDIGITS: 99.01%) and event-driven neuromorphic datasets (MNIST-DVS & N-TIDIGITS: 99.98%). These results demonstrate that MSNN offers an effective and energy-efficient solution for multimodal sensor fusion in biomedical and intelligent sensing applications.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (10) , 3412-3425
Multimodal Spiking Neural Network With Generalized Distributive Law for Biosignal and Sensory Fusion
Multimodal signal fusion is a cornerstone of biomedical engineering and intelligent sensing, enabling holistic analysis of heterogeneous sources such as electroencephalography (EEG), peripheral signals, speech, and imaging data. However, integrating diverse modalities in a computationally efficient and biologically plausible manner remains a significant challenge. Transformer-based fusion architectures rely on global cross-attention to integrate multimodal information but incur high computational costs. In contrast, STDP-driven fully connected layers adopt local learning rules, which restrict their ability to autonomously form efficient sparse topologies for complex multimodal tasks. To address these issues, we propose a novel end-to-end framework—the Multimodal Spiking Neural Network (MSNN)—featuring a fusion module grounded in the Generalized Distributive Law (GDL). This principled mechanism provides an efficient and interpretable means of integrating heterogeneous biomedical and sensory signals. The MSNN further incorporates structure-adaptive leaky integrate-and-fire (SALIF) neurons, enabling dynamic optimization of sparse connectivity to enhance fusion efficiency. The proposed MSNN is validated on a range of datasets, demonstrating strong versatility: it achieves binary classification accuracies of 92.29% (valence) and 91.08% (arousal) on the DEAP dataset for affective state decoding and 99.77% on the WESAD dataset for stress detection, while delivering state-of-the-art performance on standard pattern recognition tasks (MNIST & TIDIGITS: 99.01%) and event-driven neuromorphic datasets (MNIST-DVS & N-TIDIGITS: 99.98%). These results demonstrate that MSNN offers an effective and energy-efficient solution for multimodal sensor fusion in biomedical and intelligent sensing applications.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Time Expansion of Pulse Echo Signal Implemented for Laser Ranging System With High Precision
This article proposes a pulse laser ranging method based on the correlated sampling time expansion, which enhances the precision of pulse laser ranging. We introduced an additional sampling pulse signal, which has a certain frequency difference from the transmission signal. By utilizing the principle of correlation sampling, the sampling signal is used to sample the pulse echo signal, resulting in temporal expansion of the echo delay. The actual distance is then calculated based on the expansion factor. This method overcomes the limitations of traditional time-of-flight (TOF) methods that rely on time-to-digital converter (TDC) chip timing, substantially reducing timing errors. Our approach is implemented using a field-programmable gate array (FPGA), a sampling unit, and a set of laser transmission and reception devices, resulting in a low-cost system. Experimental results demonstrate that our method achieves high-precision ranging and effectively reduces errors in TOF ranging, with each measurement error reduced to the millimeter level or even lower. Our proposed method holds great promise in the field of high-precision ranging.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Time Expansion of Pulse Echo Signal Implemented for Laser Ranging System With High Precision
This article proposes a pulse laser ranging method based on the correlated sampling time expansion, which enhances the precision of pulse laser ranging. We introduced an additional sampling pulse signal, which has a certain frequency difference from the transmission signal. By utilizing the principle of correlation sampling, the sampling signal is used to sample the pulse echo signal, resulting in temporal expansion of the echo delay. The actual distance is then calculated based on the expansion factor. This method overcomes the limitations of traditional time-of-flight (TOF) methods that rely on time-to-digital converter (TDC) chip timing, substantially reducing timing errors. Our approach is implemented using a field-programmable gate array (FPGA), a sampling unit, and a set of laser transmission and reception devices, resulting in a low-cost system. Experimental results demonstrate that our method achieves high-precision ranging and effectively reduces errors in TOF ranging, with each measurement error reduced to the millimeter level or even lower. Our proposed method holds great promise in the field of high-precision ranging.
- 24 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 71 (10) , 2978-2990
A Biomimetic Visual Detection Model: Event-Driven LGMDs Implemented With Fractional Spiking Neuron Circuits
Objective: Lobula giant motion detectors (LGMDs) in locusts effectively predict collisions and trigger avoidance, with potential applications in autonomous driving and UAVs. Research on LGMD characteristics splits into two views: one focusing on the presynaptic visual pathway, the other on the postsynaptic LGMD neurons. Both perspectives have support, leading to two computational models, but they lack a biophysical description of the individual LGMD neuron behavior. This paper aims to mimic and explain LGMD behavior based on fractional spiking neurons (FSNs) and construct a biomimetic visual model for the LGMD compatible with these characteristics. Methods: We implement the visual model using an event camera to simulate photoreceptors and follow the ON/OFF visual pathway, incorporating lateral inhibition to mimic the LGMD system from the bottom up. Second, most computational models of motion perception use only the dendrites within the LGMD neurons as the ideal pathway for linear summation, ignoring dendritic effects inducing neuronal properties. Thus, we introduce FSN circuits by altering dendritic morphological parameters to simulate multi-scale spike frequency adaptation (SFA) observed in LGMDs. Additionally, we add one more circuit of dendritic trees into the FSNs to be compatible with the postsynaptic feed-forward inhibition (FFI) in LGMD neurons, providing a novel explanatory and predictive model. Results: We test that the event-driven biomimetic visual model can achieve collision detection and looming selection in different complex scenes, especially fast-moving objects.
- 24 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 71 (10) , 2978-2990
A Biomimetic Visual Detection Model: Event-Driven LGMDs Implemented With Fractional Spiking Neuron Circuits
Objective: Lobula giant motion detectors (LGMDs) in locusts effectively predict collisions and trigger avoidance, with potential applications in autonomous driving and UAVs. Research on LGMD characteristics splits into two views: one focusing on the presynaptic visual pathway, the other on the postsynaptic LGMD neurons. Both perspectives have support, leading to two computational models, but they lack a biophysical description of the individual LGMD neuron behavior. This paper aims to mimic and explain LGMD behavior based on fractional spiking neurons (FSNs) and construct a biomimetic visual model for the LGMD compatible with these characteristics. Methods: We implement the visual model using an event camera to simulate photoreceptors and follow the ON/OFF visual pathway, incorporating lateral inhibition to mimic the LGMD system from the bottom up. Second, most computational models of motion perception use only the dendrites within the LGMD neurons as the ideal pathway for linear summation, ignoring dendritic effects inducing neuronal properties. Thus, we introduce FSN circuits by altering dendritic morphological parameters to simulate multi-scale spike frequency adaptation (SFA) observed in LGMDs. Additionally, we add one more circuit of dendritic trees into the FSNs to be compatible with the postsynaptic feed-forward inhibition (FFI) in LGMD neurons, providing a novel explanatory and predictive model. Results: We test that the event-driven biomimetic visual model can achieve collision detection and looming selection in different complex scenes, especially fast-moving objects.
- 2 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 1081-1099
GSNN: A Neuromorphic Computing Model for the Flexible Path Planning in Various Constraint Environments
Spiking Neural Networks (SNNs) represent a new generation of artificial neural networks that draw inspiration from biological systems. However, due to the intricate dynamics they exhibit and the discontinuity inherent in spike signals, SNNs often encounter performance limitations when addressing optimization problems. In this paper, we introduce the Graph-connected Spiking Neural Network model (GSNN), an extension of the SNN framework. The GSNN model holds the potential for integration with various existing path planning methods, rendering it applicable to a wide array of common path planning tasks. We specifically present two fundamental models within the GSNN framework. The first model employs GSNN to extract heuristic information from constrained pixel maps. This extracted data is then amalgamated with a novel sampling method, resulting in enhanced planning efficiency when compared to conventional techniques. The second model leverages GSNN to map a weighted graph, effectively utilizing plasticity methods to ascertain the shortest path within the graph. Moreover, this model facilitates path planning under diverse constraint environments, encompassing dynamic considerations, cost-awareness, and the collision dimensions of moving objects. Recognizing that the size of pixel maps or the number of nodes within weighted graphs might constrain GSNN’s capabilities, we propose a partitioning strategy to address this limitation. Empirical results unequivocally demonstrate the superiority of both GSNN models in resolving static path planning problems. Furthermore, the second GSNN model demonstrates rational performance across various constrained scenarios. Note to Practitioners —The primary motivation behind this study is to explore the utilization of neural morphic computation methods in addressing path planning challenges. To accomplish this, we introduce an encompassing model named GSNN. Given the limited coverage of neural morphic computation within this field, we present a comprehensive overview of its potential applications, with the intention of providing a valuable reference for both researchers and practitioners. Moreover, GSNN has the capability to seamlessly integrate with existing advanced optimization methods, thereby leading to enhanced performance and the capacity to tackle even more intricate problems.
- 2 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 1081-1099
GSNN: A Neuromorphic Computing Model for the Flexible Path Planning in Various Constraint Environments
Spiking Neural Networks (SNNs) represent a new generation of artificial neural networks that draw inspiration from biological systems. However, due to the intricate dynamics they exhibit and the discontinuity inherent in spike signals, SNNs often encounter performance limitations when addressing optimization problems. In this paper, we introduce the Graph-connected Spiking Neural Network model (GSNN), an extension of the SNN framework. The GSNN model holds the potential for integration with various existing path planning methods, rendering it applicable to a wide array of common path planning tasks. We specifically present two fundamental models within the GSNN framework. The first model employs GSNN to extract heuristic information from constrained pixel maps. This extracted data is then amalgamated with a novel sampling method, resulting in enhanced planning efficiency when compared to conventional techniques. The second model leverages GSNN to map a weighted graph, effectively utilizing plasticity methods to ascertain the shortest path within the graph. Moreover, this model facilitates path planning under diverse constraint environments, encompassing dynamic considerations, cost-awareness, and the collision dimensions of moving objects. Recognizing that the size of pixel maps or the number of nodes within weighted graphs might constrain GSNN’s capabilities, we propose a partitioning strategy to address this limitation. Empirical results unequivocally demonstrate the superiority of both GSNN models in resolving static path planning problems. Furthermore, the second GSNN model demonstrates rational performance across various constrained scenarios. Note to Practitioners —The primary motivation behind this study is to explore the utilization of neural morphic computation methods in addressing path planning challenges. To accomplish this, we introduce an encompassing model named GSNN. Given the limited coverage of neural morphic computation within this field, we present a comprehensive overview of its potential applications, with the intention of providing a valuable reference for both researchers and practitioners. Moreover, GSNN has the capability to seamlessly integrate with existing advanced optimization methods, thereby leading to enhanced performance and the capacity to tackle even more intricate problems.