Huiyi Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Huiyi Liu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Chenbin Yang
College of Computer and Soft, Hohai University, Nanjing 211100, China
2 shared publications - Chongyuan Wang
College of Computer and Information, Hohai University, Nanjing 210098, China
2 shared publications - Bailin Zou
College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China
1 shared publication - Bailin Zou
College of Computer Science and Software Engineering, Hohai University, Nanjing, China
1 shared publication - Baobin Duan
Institute of Intelligence Science and Technology, Hohai University, Nanjing 211100, China
1 shared publication - Dongming Hu
Jiangsu Special Equipment Safety Supervision and Inspection Institute, Wuxi 214174, China
1 shared publication
Latest Publications
- 22 October 2026
- Published by Springer Nature in Soft Computing
- Vol. 30 (11) , 8027-8041
File fragment type identification based on parallel cross convolutional neural network
- 22 October 2026
- Published by Springer Nature in Soft Computing
- Vol. 30 (11) , 8027-8041
File fragment type identification based on parallel cross convolutional neural network
- Open Access
- 3 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (7) , 1507
Hierarchical Deep Learning for File Fragment Classification
File fragment classification is crucial in digital forensics, aiding in the recovery and reconstruction of fragmented files, which serve as key evidence; while deep learning techniques have advanced in this area, challenges remain, particularly regarding the consideration of inter-file-type relationships and the granularity of classification. To overcome these challenges, we introduce a hierarchical classification approach that leverages an agglomerative hierarchical clustering algorithm combined with a dynamic adjustment mechanism, optimizing category distribution among leaf nodes. This structure is further enhanced by developing specific classifiers for each leaf node, tailored to its unique characteristics. Experimental results on the FFT-75 dataset show that our method achieves 76.3% accuracy in a 75-class scenario (512-byte blocks), surpassing the accuracy achieved with existing approaches. This method improves classification accuracy, addressing misclassification issues caused by excessive classification types.
- 3 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (7) , 1507
Open AccessHierarchical Deep Learning for File Fragment Classification
File fragment classification is crucial in digital forensics, aiding in the recovery and reconstruction of fragmented files, which serve as key evidence; while deep learning techniques have advanced in this area, challenges remain, particularly regarding the consideration of inter-file-type relationships and the granularity of classification. To overcome these challenges, we introduce a hierarchical classification approach that leverages an agglomerative hierarchical clustering algorithm combined with a dynamic adjustment mechanism, optimizing category distribution among leaf nodes. This structure is further enhanced by developing specific classifiers for each leaf node, tailored to its unique characteristics. Experimental results on the FFT-75 dataset show that our method achieves 76.3% accuracy in a 75-class scenario (512-byte blocks), surpassing the accuracy achieved with existing approaches. This method improves classification accuracy, addressing misclassification issues caused by excessive classification types.
- Open Access
RADE: A Symmetry-Inspired Resource-Adaptive Differential Evolution for Lightweight Dendritic Learning in Classification Tasks
This study proposes Resource-Adaptive Differential Evolution (RADE), a novel optimization algorithm for training lightweight and interpretable dendritic neuron models (DNMs) in classification tasks. RADE introduces dynamic population partitioning, poor-individual-guided mutation, adaptive parameter control, and lightweight archiving to achieve efficient and robust learning. Inspired by biological and algorithmic symmetry, RADE leverages structural and behavioral balance in both the evolutionary process and the DNM architecture. DNMs inherently exhibit symmetric processing through multiple dendritic branches that independently and equivalently aggregate localized inputs. RADE preserves and enhances this structural symmetry by promoting balanced learning dynamics and pruning redundant dendritic components, leading to compact and interpretable neuron morphologies. Extensive experiments on real-world and synthetic datasets demonstrate that RADE consistently outperforms existing methods in terms of classification accuracy, convergence stability, and model compactness. Furthermore, the resulting neuron structures can be mapped to logical circuits, making the RADE-DNM highly suitable for neuromorphic and edge computing applications. This work highlights the synergistic role of symmetry in achieving resource-efficient and transparent artificial intelligence.
Open AccessRADE: A Symmetry-Inspired Resource-Adaptive Differential Evolution for Lightweight Dendritic Learning in Classification Tasks
This study proposes Resource-Adaptive Differential Evolution (RADE), a novel optimization algorithm for training lightweight and interpretable dendritic neuron models (DNMs) in classification tasks. RADE introduces dynamic population partitioning, poor-individual-guided mutation, adaptive parameter control, and lightweight archiving to achieve efficient and robust learning. Inspired by biological and algorithmic symmetry, RADE leverages structural and behavioral balance in both the evolutionary process and the DNM architecture. DNMs inherently exhibit symmetric processing through multiple dendritic branches that independently and equivalently aggregate localized inputs. RADE preserves and enhances this structural symmetry by promoting balanced learning dynamics and pruning redundant dendritic components, leading to compact and interpretable neuron morphologies. Extensive experiments on real-world and synthetic datasets demonstrate that RADE consistently outperforms existing methods in terms of classification accuracy, convergence stability, and model compactness. Furthermore, the resulting neuron structures can be mapped to logical circuits, making the RADE-DNM highly suitable for neuromorphic and edge computing applications. This work highlights the synergistic role of symmetry in achieving resource-efficient and transparent artificial intelligence.
- Open Access
- 29 April 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (9) , 1465
Toward Next-Generation Biologically Plausible Single Neuron Modeling: An Evolutionary Dendritic Neuron Model
Conventional deep learning models rely heavily on the McCulloch–Pitts (MCP) neuron, limiting their interpretability and biological plausibility. The Dendritic Neuron Model (DNM) offers a more realistic alternative by simulating nonlinear and compartmentalized processing within dendritic branches, enabling efficient and transparent learning. While DNMs have shown strong performance in various tasks, their learning capacity at the single-neuron level remains underexplored. This paper proposes a Reinforced Dynamic-grouping Differential Evolution (RDE) algorithm to enhance synaptic plasticity within the DNM framework. RDE introduces a biologically inspired mutation-selection strategy and an adaptive grouping mechanism that promotes effective exploration and convergence. Experimental evaluations on benchmark classification tasks demonstrate that the proposed method outperforms conventional differential evolution and other evolutionary learning approaches in terms of accuracy, generalization, and convergence speed. Specifically, the RDE-DNM achieves up to 92.9% accuracy on the BreastEW dataset and 98.08% on the Moons dataset, with consistently low standard deviations across 30 trials, indicating strong robustness and generalization. Beyond technical performance, the proposed model supports societal applications requiring trustworthy AI, such as interpretable medical diagnostics, financial screening, and low-energy embedded systems. The results highlight the potential of RDE-driven DNMs as a compact and interpretable alternative to traditional deep models, offering new insights into biologically plausible single-neuron computation for next-generation AI.
- 29 April 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (9) , 1465
Open AccessToward Next-Generation Biologically Plausible Single Neuron Modeling: An Evolutionary Dendritic Neuron Model
Conventional deep learning models rely heavily on the McCulloch–Pitts (MCP) neuron, limiting their interpretability and biological plausibility. The Dendritic Neuron Model (DNM) offers a more realistic alternative by simulating nonlinear and compartmentalized processing within dendritic branches, enabling efficient and transparent learning. While DNMs have shown strong performance in various tasks, their learning capacity at the single-neuron level remains underexplored. This paper proposes a Reinforced Dynamic-grouping Differential Evolution (RDE) algorithm to enhance synaptic plasticity within the DNM framework. RDE introduces a biologically inspired mutation-selection strategy and an adaptive grouping mechanism that promotes effective exploration and convergence. Experimental evaluations on benchmark classification tasks demonstrate that the proposed method outperforms conventional differential evolution and other evolutionary learning approaches in terms of accuracy, generalization, and convergence speed. Specifically, the RDE-DNM achieves up to 92.9% accuracy on the BreastEW dataset and 98.08% on the Moons dataset, with consistently low standard deviations across 30 trials, indicating strong robustness and generalization. Beyond technical performance, the proposed model supports societal applications requiring trustworthy AI, such as interpretable medical diagnostics, financial screening, and low-energy embedded systems. The results highlight the potential of RDE-driven DNMs as a compact and interpretable alternative to traditional deep models, offering new insights into biologically plausible single-neuron computation for next-generation AI.
- Open Access
Intelligent Fault Diagnosis Method Based on Neural Network Compression for Rolling Bearings
Rolling bearings are often exposed to high speeds and pressures, leading to the symmetry in their rotating structure being disrupted, which can lead to serious failures. Intelligent rolling bearing fault diagnosis is a critical part of ensuring operation of machinery, and it has been facilitated by the growing popularity of convolutional neural networks (CNNs). The outstanding performance of fault diagnosis CNNs results from complex and redundant network structures and parameters, resulting in huge storage and computational requirements, which makes it challenging to implement these models in resource-limited industrial devices. This study aims to address this problem by proposing a comprehensive compression method for CNNs that is applied to intelligent fault diagnosis. It involves several different compression methods, including tensor train decomposition, parameter quantization, and knowledge distillation for deep network compression. This results in a significant decrease in redundancy and speeding up the training of CNN models. Firstly, tensor train decomposition is applied to reduce redundant connections in both convolutional and fully connected layers. The next step is to perform parameter quantization to minimize the bits needed for parameter representation and storage. Finally, knowledge distillation is used to restore accuracy to the compressed model. The effectiveness of the proposed approach is confirmed by an experiment and ablation study with different models on several datasets. The results show that it can significantly reduce redundant information and floating-point operations with little degradation in accuracy. Notably, on the CWRU dataset, with about 60% parameter reduction, there is no degradation in our model’s accuracy. The proposed approach is a new attempt at the intelligent fault diagnosis of rolling bearings in industrial equipment.
Open AccessIntelligent Fault Diagnosis Method Based on Neural Network Compression for Rolling Bearings
Rolling bearings are often exposed to high speeds and pressures, leading to the symmetry in their rotating structure being disrupted, which can lead to serious failures. Intelligent rolling bearing fault diagnosis is a critical part of ensuring operation of machinery, and it has been facilitated by the growing popularity of convolutional neural networks (CNNs). The outstanding performance of fault diagnosis CNNs results from complex and redundant network structures and parameters, resulting in huge storage and computational requirements, which makes it challenging to implement these models in resource-limited industrial devices. This study aims to address this problem by proposing a comprehensive compression method for CNNs that is applied to intelligent fault diagnosis. It involves several different compression methods, including tensor train decomposition, parameter quantization, and knowledge distillation for deep network compression. This results in a significant decrease in redundancy and speeding up the training of CNN models. Firstly, tensor train decomposition is applied to reduce redundant connections in both convolutional and fully connected layers. The next step is to perform parameter quantization to minimize the bits needed for parameter representation and storage. Finally, knowledge distillation is used to restore accuracy to the compressed model. The effectiveness of the proposed approach is confirmed by an experiment and ablation study with different models on several datasets. The results show that it can significantly reduce redundant information and floating-point operations with little degradation in accuracy. Notably, on the CWRU dataset, with about 60% parameter reduction, there is no degradation in our model’s accuracy. The proposed approach is a new attempt at the intelligent fault diagnosis of rolling bearings in industrial equipment.
- Open Access
- 12 February 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (4) , 1491
Stable Low-Rank CP Decomposition for Compression of Convolutional Neural Networks Based on Sensitivity
Modern convolutional neural networks (CNNs) play a crucial role in computer vision applications. The intricacy of the application scenarios and the growing dataset both significantly raise the complexity of CNNs. As a result, they are often overparameterized and have significant computational costs. One potential solution for optimizing and compressing the CNNs is to replace convolutional layers with low-rank tensor decomposition. The most suitable technique for this is Canonical Polyadic (CP) decomposition. However, there are two primary issues with CP decomposition that lead to a significant loss in accuracy. Firstly, the selection of tensor ranks for CP decomposition is an unsolved issue. Secondly, degeneracy and instability are common problems in the CP decomposition of contractional tensors, which makes fine-tuning the compressed model difficult. In this study, a novel approach was proposed for compressing CNNs by using CP decomposition. The first step involves using the sensitivity of convolutional layers to determine the tensor ranks for CP decomposition effectively. Subsequently, to address the degeneracy issue and enhance the stability of the CP decomposition, two novel techniques were incorporated: optimization with sensitivity constraints and iterative fine-tuning based on sensitivity order. Finally, the proposed method was examined on common CNN structures for image classification tasks and demonstrated that it provides stable performance and significantly fewer reductions in classification accuracy.
- 12 February 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (4) , 1491
Open AccessStable Low-Rank CP Decomposition for Compression of Convolutional Neural Networks Based on Sensitivity
Modern convolutional neural networks (CNNs) play a crucial role in computer vision applications. The intricacy of the application scenarios and the growing dataset both significantly raise the complexity of CNNs. As a result, they are often overparameterized and have significant computational costs. One potential solution for optimizing and compressing the CNNs is to replace convolutional layers with low-rank tensor decomposition. The most suitable technique for this is Canonical Polyadic (CP) decomposition. However, there are two primary issues with CP decomposition that lead to a significant loss in accuracy. Firstly, the selection of tensor ranks for CP decomposition is an unsolved issue. Secondly, degeneracy and instability are common problems in the CP decomposition of contractional tensors, which makes fine-tuning the compressed model difficult. In this study, a novel approach was proposed for compressing CNNs by using CP decomposition. The first step involves using the sensitivity of convolutional layers to determine the tensor ranks for CP decomposition effectively. Subsequently, to address the degeneracy issue and enhance the stability of the CP decomposition, two novel techniques were incorporated: optimization with sensitivity constraints and iterative fine-tuning based on sensitivity order. Finally, the proposed method was examined on common CNN structures for image classification tasks and demonstrated that it provides stable performance and significantly fewer reductions in classification accuracy.
- Open Access
- 9 February 2018
- Published by MDPI AG in Information
- Vol. 9 (2) , 38
Local Patch Vectors Encoded by Fisher Vectors for Image Classification
The objective of this work is image classification, whose purpose is to group images into corresponding semantic categories. Four contributions are made as follows: (i) For computational simplicity and efficiency, we directly adopt raw image patch vectors as local descriptors encoded by Fisher vector (FV) subsequently; (ii) For obtaining representative local features within the FV encoding framework, we compare and analyze three typical sampling strategies: random sampling, saliency-based sampling and dense sampling; (iii) In order to embed both global and local spatial information into local features, we construct an improved spatial geometry structure which shows good performance; (iv) For reducing the storage and CPU costs of high dimensional vectors, we adopt a new feature selection method based on supervised mutual information (MI), which chooses features by an importance sorting algorithm. We report experimental results on dataset STL-10. It shows very promising performance with this simple and efficient framework compared to conventional methods.
- 9 February 2018
- Published by MDPI AG in Information
- Vol. 9 (2) , 38
Open AccessLocal Patch Vectors Encoded by Fisher Vectors for Image Classification
The objective of this work is image classification, whose purpose is to group images into corresponding semantic categories. Four contributions are made as follows: (i) For computational simplicity and efficiency, we directly adopt raw image patch vectors as local descriptors encoded by Fisher vector (FV) subsequently; (ii) For obtaining representative local features within the FV encoding framework, we compare and analyze three typical sampling strategies: random sampling, saliency-based sampling and dense sampling; (iii) In order to embed both global and local spatial information into local features, we construct an improved spatial geometry structure which shows good performance; (iv) For reducing the storage and CPU costs of high dimensional vectors, we adopt a new feature selection method based on supervised mutual information (MI), which chooses features by an importance sorting algorithm. We report experimental results on dataset STL-10. It shows very promising performance with this simple and efficient framework compared to conventional methods.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (2160133X) , 1531-1535
A Simplification Algorithm of View-Dependent Dynamic Multiresolution Terrain Based on Adaptive Quadtree
This paper introduces a simplification algorithm of view-dependent multiresolution terrain based on adaptive quadtree. In order to realize real-time rendering of comparatively complex terrain surface model, the algorithm selectively refines various areas of terrain based on the viewpoint position, and accelerates terrain data simplification with multiresolution level of detail model of uniform grid model. In the proposed algorithm, block is taken as a space unit for large area simplification of terrain model. Meanwhile, grid crack between terrain blocks of different resolution is avoided by vertex inter-dependency. The experiment results show the validity of the algorithm.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (2160133X) , 1531-1535
A Simplification Algorithm of View-Dependent Dynamic Multiresolution Terrain Based on Adaptive Quadtree
This paper introduces a simplification algorithm of view-dependent multiresolution terrain based on adaptive quadtree. In order to realize real-time rendering of comparatively complex terrain surface model, the algorithm selectively refines various areas of terrain based on the viewpoint position, and accelerates terrain data simplification with multiresolution level of detail model of uniform grid model. In the proposed algorithm, block is taken as a space unit for large area simplification of terrain model. Meanwhile, grid crack between terrain blocks of different resolution is avoided by vertex inter-dependency. The experiment results show the validity of the algorithm.
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 2160133X,p. 85-88
Multi-Robot Cooperation Coalition Formation Based on Genetic Algorithm
Coalition formation is a key problem in multi-robot cooperation. The formation of multi-robot cooperation for single or multi-task is settled via finding the coalition maximum value or the coalition structure with the largest total coalition value. Traditionally, exhaustive method is used to get the optimal coalition or coalition structure with huge consumption in both computation time and communication overhead, which possibly results in search combination explosion. In this paper, agent coalition cooperation in MAS (multi-agent system) is applied in multi-robot system with genetic algorithm for the formation of multi-robot coalition and coalition structure in order to gain the possible maximum coalition value during task execution through finding the optimal solution or feasible solution for multi-robot coalition and coalition structure
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 2160133X,p. 85-88
Multi-Robot Cooperation Coalition Formation Based on Genetic Algorithm
Coalition formation is a key problem in multi-robot cooperation. The formation of multi-robot cooperation for single or multi-task is settled via finding the coalition maximum value or the coalition structure with the largest total coalition value. Traditionally, exhaustive method is used to get the optimal coalition or coalition structure with huge consumption in both computation time and communication overhead, which possibly results in search combination explosion. In this paper, agent coalition cooperation in MAS (multi-agent system) is applied in multi-robot system with genetic algorithm for the formation of multi-robot coalition and coalition structure in order to gain the possible maximum coalition value during task execution through finding the optimal solution or feasible solution for multi-robot coalition and coalition structure