Jiayan Gan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiayan Gan has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Huaizong Shao
University of Electronic Science and Technology of China
3 shared publications - Qiang Li
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications - Tao Yang
University of Electronic Science and Technology of China
2 shared publications - Ye Pan
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications - Zhongyi Wen
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications - Ang Hu
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
1 shared publication
Latest Publications
- 4 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Microwave and Wireless Technology Letters
- Vol. 35 (5) , 505-508
Hierarchical Multistate Optimization Based on Bayesian Nested Improved Meta-Heuristic Algorithm for Reconfigurable Bandpass Filter
This letter proposes a hierarchical multistate optimization (HMO) method for the microstrip reconfigurable bandpass filter (RBPF). HMO algorithm nests the inner global optimization algorithm within the outer global optimization algorithm. The Bayesian optimization (BO) algorithm is used to optimize the outer nontunable parameters, and the improved meta-heuristic algorithm is nested to optimize the tunable parameters. The proposed optimization method was applied to two microstrip RBPFs with seven fixed parameters, four sensitive tunable variables, and three tunable states. The method achieved a 42.1%–80.2% reduction in the loss function value, thereby validating its effectiveness.
- 4 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Microwave and Wireless Technology Letters
- Vol. 35 (5) , 505-508
Hierarchical Multistate Optimization Based on Bayesian Nested Improved Meta-Heuristic Algorithm for Reconfigurable Bandpass Filter
This letter proposes a hierarchical multistate optimization (HMO) method for the microstrip reconfigurable bandpass filter (RBPF). HMO algorithm nests the inner global optimization algorithm within the outer global optimization algorithm. The Bayesian optimization (BO) algorithm is used to optimize the outer nontunable parameters, and the improved meta-heuristic algorithm is nested to optimize the tunable parameters. The proposed optimization method was applied to two microstrip RBPFs with seven fixed parameters, four sensitive tunable variables, and three tunable states. The method achieved a 42.1%–80.2% reduction in the loss function value, thereby validating its effectiveness.
- 19 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (20) , 32557-32571
Cost-Effective RF Fingerprinting Based on Hybrid CVNN-RF Classifier With Automated Multidimensional Early-Exit Strategy
While the Internet of Things (IoT) technology is booming and offers huge opportunities for information exchange, it also faces unprecedented security challenges. As an important complement to the physical-layer security technologies for IoT, radio frequency fingerprinting (RFF) is of great interest due to its difficulty in counterfeiting. Recently, many machine learning (ML)-based RFF algorithms have emerged. In particular, deep learning (DL) has shown great benefits in automatically extracting complex and subtle features from raw data with high-classification accuracy. However, DL algorithms face the computational cost problem as the difficulty of the RFF task and the size of the deep neural network have increased dramatically. To address the above challenge, this article proposes a novel cost-effective early-exit neural network consisting of a complex-valued neural network (CVNN) backbone with multiple random forest branches, called hybrid CVNN-RF. Unlike conventional studies that use a single fixed DL model to process all radio frequency (RF) samples, our hybrid CVNN-RF considers differences in the recognition difficulty of RF samples and introduces an early-exit mechanism to dynamically process the samples. When processing “easy” samples that can be well classified with high confidence, the hybrid CVNN-RF can end early at the random forest branch to reduce computational cost. Conversely, subsequent network layers will be activated to ensure accuracy. To further improve the early-exit rate, an automated multidimensional early-exit strategy is proposed to achieve scheduling control from multiple dimensions within the network depth and classification category. Finally, our experiments on the public ADS-B data set show that the proposed algorithm can reduce the computational cost by 83% while improving the accuracy by 1.6% under a classification task with 100 categories.
- 19 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (20) , 32557-32571
Cost-Effective RF Fingerprinting Based on Hybrid CVNN-RF Classifier With Automated Multidimensional Early-Exit Strategy
While the Internet of Things (IoT) technology is booming and offers huge opportunities for information exchange, it also faces unprecedented security challenges. As an important complement to the physical-layer security technologies for IoT, radio frequency fingerprinting (RFF) is of great interest due to its difficulty in counterfeiting. Recently, many machine learning (ML)-based RFF algorithms have emerged. In particular, deep learning (DL) has shown great benefits in automatically extracting complex and subtle features from raw data with high-classification accuracy. However, DL algorithms face the computational cost problem as the difficulty of the RFF task and the size of the deep neural network have increased dramatically. To address the above challenge, this article proposes a novel cost-effective early-exit neural network consisting of a complex-valued neural network (CVNN) backbone with multiple random forest branches, called hybrid CVNN-RF. Unlike conventional studies that use a single fixed DL model to process all radio frequency (RF) samples, our hybrid CVNN-RF considers differences in the recognition difficulty of RF samples and introduces an early-exit mechanism to dynamically process the samples. When processing “easy” samples that can be well classified with high confidence, the hybrid CVNN-RF can end early at the random forest branch to reduce computational cost. Conversely, subsequent network layers will be activated to ensure accuracy. To further improve the early-exit rate, an automated multidimensional early-exit strategy is proposed to achieve scheduling control from multiple dimensions within the network depth and classification category. Finally, our experiments on the public ADS-B data set show that the proposed algorithm can reduce the computational cost by 83% while improving the accuracy by 1.6% under a classification task with 100 categories.
- 22 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
A Zynq-Based Platform With Conditional- Reconfigurable Complex-Valued Neural Network for Specific Emitter Identification
In wireless communication security and spectrum management, specific emitter identification (SEI) is a potential technology to identify individual emitters. Recently, a novel SEI algorithm based on complex-valued neural network (CVNN) has emerged, which exhibits powerful processing capabilities in complex domains. However, it also brings high computational complexity, which makes it difficult to meet the power efficiency requirements of the system. To address the above challenge, a Zynq-based SEI platform with conditional-reconfigurable CVNN is proposed in this article, including processing system (PS) and programming logic (PL). The platform can adaptively reconfigure CVNN based on sample difficulty to perform conditional computation between lightweight student network and high-performance teacher network, which achieves high power efficiency while maintaining high accuracy. Inside the PL, a conditional configuration engine and a configurable CVNN engine are specifically designed for CVNN acceleration and controlled by the PS. The experiment results on the public ORACLE RF dataset show that our platform can achieve a high power efficiency of 88.32 giga operations per second per watt (GOPS/W) and a high accuracy of 99.18%.
- 22 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
A Zynq-Based Platform With Conditional- Reconfigurable Complex-Valued Neural Network for Specific Emitter Identification
In wireless communication security and spectrum management, specific emitter identification (SEI) is a potential technology to identify individual emitters. Recently, a novel SEI algorithm based on complex-valued neural network (CVNN) has emerged, which exhibits powerful processing capabilities in complex domains. However, it also brings high computational complexity, which makes it difficult to meet the power efficiency requirements of the system. To address the above challenge, a Zynq-based SEI platform with conditional-reconfigurable CVNN is proposed in this article, including processing system (PS) and programming logic (PL). The platform can adaptively reconfigure CVNN based on sample difficulty to perform conditional computation between lightweight student network and high-performance teacher network, which achieves high power efficiency while maintaining high accuracy. Inside the PL, a conditional configuration engine and a configurable CVNN engine are specifically designed for CVNN acceleration and controlled by the PS. The experiment results on the public ORACLE RF dataset show that our platform can achieve a high power efficiency of 88.32 giga operations per second per watt (GOPS/W) and a high accuracy of 99.18%.
- Open Access
SAS-SEINet: A SNR-Aware Adaptive Scalable SEI Neural Network Accelerator Using Algorithm–Hardware Co-Design for High-Accuracy and Power-Efficient UAV Surveillance
As a potential air control measure, RF-based surveillance is one of the most commonly used unmanned aerial vehicles (UAV) surveillance methods that exploits specific emitter identification (SEI) technology to identify captured RF signal from ground controllers to UAVs. Recently many SEI algorithms based on deep convolution neural network (DCNN) have emerged. However, there is a lack of the implementation of specific hardware. This paper proposes a high-accuracy and power-efficient hardware accelerator using an algorithm–hardware co-design for UAV surveillance. For the algorithm, we propose a scalable SEI neural network with SNR-aware adaptive precision computation. With SNR awareness and precision reconfiguration, it can adaptively switch between DCNN and binary DCNN to cope with low SNR and high SNR tasks, respectively. In addition, a short-time Fourier transform (STFT) reusing DCNN method is proposed to pre-extract feature of UAV signal. For hardware, we designed a SNR sensing engine, denoising engine, and specialized DCNN engine with hybrid-precision convolution and memory access, aiming at SEI acceleration. Finally, we validate the effectiveness of our design on a FPGA, using a public UAV dataset. Compared with a state-of-the-art algorithm, our method can achieve the highest accuracy of 99.3% and an F1 score of 99.3%. Compared with other hardware designs, our accelerator can achieve the highest power efficiency of 40.12 Gops/W and 96.52 Gops/W with INT16 precision and binary precision.
Open AccessSAS-SEINet: A SNR-Aware Adaptive Scalable SEI Neural Network Accelerator Using Algorithm–Hardware Co-Design for High-Accuracy and Power-Efficient UAV Surveillance
As a potential air control measure, RF-based surveillance is one of the most commonly used unmanned aerial vehicles (UAV) surveillance methods that exploits specific emitter identification (SEI) technology to identify captured RF signal from ground controllers to UAVs. Recently many SEI algorithms based on deep convolution neural network (DCNN) have emerged. However, there is a lack of the implementation of specific hardware. This paper proposes a high-accuracy and power-efficient hardware accelerator using an algorithm–hardware co-design for UAV surveillance. For the algorithm, we propose a scalable SEI neural network with SNR-aware adaptive precision computation. With SNR awareness and precision reconfiguration, it can adaptively switch between DCNN and binary DCNN to cope with low SNR and high SNR tasks, respectively. In addition, a short-time Fourier transform (STFT) reusing DCNN method is proposed to pre-extract feature of UAV signal. For hardware, we designed a SNR sensing engine, denoising engine, and specialized DCNN engine with hybrid-precision convolution and memory access, aiming at SEI acceleration. Finally, we validate the effectiveness of our design on a FPGA, using a public UAV dataset. Compared with a state-of-the-art algorithm, our method can achieve the highest accuracy of 99.3% and an F1 score of 99.3%. Compared with other hardware designs, our accelerator can achieve the highest power efficiency of 40.12 Gops/W and 96.52 Gops/W with INT16 precision and binary precision.