Peng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Peng Zhang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Fuqiang Wang
Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China
3 shared publications - Jianqiang Zhang
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China
3 shared publications - Wei Zhao
Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China
2 shared publications - Xiaoming Wu
Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China
2 shared publications A.A. Kazeka
1 shared publicationA.Yu. Kliutsky
1 shared publication
Latest Publications
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Speech Emotion Recognition via Multi-Level Acoustic Modeling and Cross-Modal Temporal Fusion
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSpeech Emotion Recognition via Multi-Level Acoustic Modeling and Cross-Modal Temporal Fusion
- 12 June 2025
- Published by IOP Publishing in Physica Scripta
- Vol. 100 (7) , 076004
Final-XGBoost: a Bayesian-tuned machine learning model for quantum key distribution optimization
As the number of users in quantum key distribution (QKD) networks continues to grow, parameter selection (e.g., probability of X-bases, signal state strength, and decoy state levels) has become increasingly complex. Traditional methods such as local search algorithms (LSA) are commonly employed for parameter optimization but suffer from significant computational overhead, slow execution on low-power platforms, and resultant system delays. These limitations hinder the scalability and real-time requirements of large-scale QKD networks. To address these challenges, this paper proposes an innovative approach that combines Bayesian optimization with XGBoost model to optimize QKD system parameters. The proposed model is evaluated against random forest (RF) and back-propagation neural network (BPNN) models based on three critical metrics: prediction accuracy, model fitting, and training efficiency. Simulation results demonstrate that the proposed model significantly outperforms both RF and BPNN in terms of accuracy and computational efficiency. Notably, while achieving predictive performance comparable to LSA, the proposed method reduces computation time by three orders of magnitude. This research introduces a novel and efficient framework for QKD parameter optimization, providing new insights and directions for enhancing the performance, scalability, and real-time adaptability of QKD systems.
- 12 June 2025
- Published by IOP Publishing in Physica Scripta
- Vol. 100 (7) , 076004
Final-XGBoost: a Bayesian-tuned machine learning model for quantum key distribution optimization
As the number of users in quantum key distribution (QKD) networks continues to grow, parameter selection (e.g., probability of X-bases, signal state strength, and decoy state levels) has become increasingly complex. Traditional methods such as local search algorithms (LSA) are commonly employed for parameter optimization but suffer from significant computational overhead, slow execution on low-power platforms, and resultant system delays. These limitations hinder the scalability and real-time requirements of large-scale QKD networks. To address these challenges, this paper proposes an innovative approach that combines Bayesian optimization with XGBoost model to optimize QKD system parameters. The proposed model is evaluated against random forest (RF) and back-propagation neural network (BPNN) models based on three critical metrics: prediction accuracy, model fitting, and training efficiency. Simulation results demonstrate that the proposed model significantly outperforms both RF and BPNN in terms of accuracy and computational efficiency. Notably, while achieving predictive performance comparable to LSA, the proposed method reduces computation time by three orders of magnitude. This research introduces a novel and efficient framework for QKD parameter optimization, providing new insights and directions for enhancing the performance, scalability, and real-time adaptability of QKD systems.
- Open Access
- 6 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Speech Spoofing Detection Based on Graph Attention Networks with Spectral and Temporal Information
Automatic speaker verification (ASV) systems are vulnerable to synthetic speech attacks. Synthetic algorithms usually introduce artifacts in specific sub-bands or time segments. However, under unknown spoofing attacks, it is challenging to choose the right domain for effective detection. In this paper, we propose a speech spoofing detection method based on graph attention networks with spectral and temporal information. First, high-level features of raw audio are extracted using SENet channel attention to enhance the spatial correlation between speech frames. Then, spectral graph and temporal graph are constructed for the high-level features using graph attention networks. Finally, we design a new heterogeneous multi-domain co-graph attention module to process the information from different domains for effective speech spoofing detection. The proposed model was evaluated on the ASVspoof 2019 dataset and obtains a min t-DCF of 0.0264 and an EER of 0.94%, exhibiting competitive performance. Experiments also show its effectiveness when detecting unknown types of attacks.
- 6 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSpeech Spoofing Detection Based on Graph Attention Networks with Spectral and Temporal Information
Automatic speaker verification (ASV) systems are vulnerable to synthetic speech attacks. Synthetic algorithms usually introduce artifacts in specific sub-bands or time segments. However, under unknown spoofing attacks, it is challenging to choose the right domain for effective detection. In this paper, we propose a speech spoofing detection method based on graph attention networks with spectral and temporal information. First, high-level features of raw audio are extracted using SENet channel attention to enhance the spatial correlation between speech frames. Then, spectral graph and temporal graph are constructed for the high-level features using graph attention networks. Finally, we design a new heterogeneous multi-domain co-graph attention module to process the information from different domains for effective speech spoofing detection. The proposed model was evaluated on the ASVspoof 2019 dataset and obtains a min t-DCF of 0.0264 and an EER of 0.94%, exhibiting competitive performance. Experiments also show its effectiveness when detecting unknown types of attacks.