Kunfeng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Kunfeng Zhang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Bo Tang
National University of Defense Technology
2 shared publications - Chengye Jiang
National University of Defense Technology
2 shared publications - Falin Liu
University of Science and Technology of China
2 shared publications - Junning Zhang
National University of Defense Technology
2 shared publications - Junsen Wang
University of Science and Technology of China
2 shared publications - Qi Zhang
Institute for Advanced Study, Shaoxing University, Shaoxing, PR China
2 shared publications
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Machine Learning in Communications and Networking
- Vol. 4, 1676-1690
Complex-Valued Kolmogorov–Arnold Network With Filtered Signal Segmentation for Digital Predistortion of Broadband Transmitters
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Machine Learning in Communications and Networking
- Vol. 4, 1676-1690
Open AccessComplex-Valued Kolmogorov–Arnold Network With Filtered Signal Segmentation for Digital Predistortion of Broadband Transmitters
- 29 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-15
Complexity-Reduced Neural Network for Behavioral Modeling and Digital Predistortion of RF Wireless Transmitters
Neural networks (NNs) are promising for behavioral modeling and compensation of complicated nonlinearities in 5G transmitters with broadband high-efficiency structural power amplifiers (PAs). The high computational complexity of NNs, however, poses a serious challenge to their practical implementation. In response to this challenge, a complexity-reduced NN (CR-NN) approach is proposed in this paper, which builds on the relationship between data features and model capacity. Considering the memory fading property of RF PAs, the CR-NN first utilizes post-filtering to significantly reduce the input features of the NN body. This is followed by the employment of adaptive non-uniform piecewise linear unit to improve the model capacity without increasing the complexity. In order to validate the proposed method, the experiments are carried out based on a two-stage Doherty PA and a GaN-based Doherty PA. Experimental results show that the proposed CR-NN method can suppress the strong nonlinearity of PA from -23.24/-24.34 dBc to -51.18/-50.72 dBc with a computational complexity comparable to that of the linear-in-parameters models, thus demonstrating that the proposed method can significantly improve the performance-complexity tradeoff of NN-DPDs and contribute to the linearization of 5G and future systems.
- 29 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-15
Complexity-Reduced Neural Network for Behavioral Modeling and Digital Predistortion of RF Wireless Transmitters
Neural networks (NNs) are promising for behavioral modeling and compensation of complicated nonlinearities in 5G transmitters with broadband high-efficiency structural power amplifiers (PAs). The high computational complexity of NNs, however, poses a serious challenge to their practical implementation. In response to this challenge, a complexity-reduced NN (CR-NN) approach is proposed in this paper, which builds on the relationship between data features and model capacity. Considering the memory fading property of RF PAs, the CR-NN first utilizes post-filtering to significantly reduce the input features of the NN body. This is followed by the employment of adaptive non-uniform piecewise linear unit to improve the model capacity without increasing the complexity. In order to validate the proposed method, the experiments are carried out based on a two-stage Doherty PA and a GaN-based Doherty PA. Experimental results show that the proposed CR-NN method can suppress the strong nonlinearity of PA from -23.24/-24.34 dBc to -51.18/-50.72 dBc with a computational complexity comparable to that of the linear-in-parameters models, thus demonstrating that the proposed method can significantly improve the performance-complexity tradeoff of NN-DPDs and contribute to the linearization of 5G and future systems.
- Open Access
- 24 June 2022
- Published by Springer Nature in Environmental Sciences Europe
- Vol. 34 (1) , 1-17
Characterization of antibiotic resistance genes in drinking water sources of the Douhe Reservoir, Tangshan, northern China: the correlation with bacterial communities and environmental factors
Background: Antibiotics and antibiotic resistance genes (ARGs) threaten ecological sustainability and human health, especially the drinking water sources of the Douhe Reservoir, which have critical significance amid their direct use by people and the ecological hub of flora and fauna. Although antibiotics and ARGs pollution in reservoirs have been reported, it is of no practical significance to only study the changes (increase or decrease) of the abundance and diversity of ARGs, and it is more important to explore the mechanisms of the changes affecting ARGs. Thus, the occurrence and prevalence characterizations of the spatial and seasonal of the ARGs, mobile genetic elements (MGEs) and bacterial communities were comprehensively studied in present study. Results: 263 ARG (nine types of ARGs) and 51 MGE subtypes were detected in 56 samples, and the characteristics of the temporal and spatial distribution of ARGs, MGEs and the composition of bacterial communities were significantly different. Moreover, the correlation among the ARGs, bacterial communities, MGEs and environmental factors were defined, and the co-occurrence patterns associated with ARG subtypes, bacterial genera, and MGE subtypes between water and sediment of the Douhe Reservoir were different. Conclusions: In summary, ARGs were ubiquitous presence in water and sediment of the Douhe Reservoir, and the multidrug, aminoglycoside and macrolide–lincosamide–streptogramin B (MLSB) were main types of ARGs. Bacterial genera and the environmental factors [such as temperature (T), nitrate–nitrogen (NO– 3–N), total dissolved nitrogen (TDN), and total phosphorus (TP)] significantly affected the distribution pattern of ARGs. Overall, this research revealed the spatiotemporal change and transmission mechanisms of ARGs in the typical drinking water sources of reservoirs, which will supply clues to ensure the safety of water sources.
- 24 June 2022
- Published by Springer Nature in Environmental Sciences Europe
- Vol. 34 (1) , 1-17
Open AccessCharacterization of antibiotic resistance genes in drinking water sources of the Douhe Reservoir, Tangshan, northern China: the correlation with bacterial communities and environmental factors
Background: Antibiotics and antibiotic resistance genes (ARGs) threaten ecological sustainability and human health, especially the drinking water sources of the Douhe Reservoir, which have critical significance amid their direct use by people and the ecological hub of flora and fauna. Although antibiotics and ARGs pollution in reservoirs have been reported, it is of no practical significance to only study the changes (increase or decrease) of the abundance and diversity of ARGs, and it is more important to explore the mechanisms of the changes affecting ARGs. Thus, the occurrence and prevalence characterizations of the spatial and seasonal of the ARGs, mobile genetic elements (MGEs) and bacterial communities were comprehensively studied in present study. Results: 263 ARG (nine types of ARGs) and 51 MGE subtypes were detected in 56 samples, and the characteristics of the temporal and spatial distribution of ARGs, MGEs and the composition of bacterial communities were significantly different. Moreover, the correlation among the ARGs, bacterial communities, MGEs and environmental factors were defined, and the co-occurrence patterns associated with ARG subtypes, bacterial genera, and MGE subtypes between water and sediment of the Douhe Reservoir were different. Conclusions: In summary, ARGs were ubiquitous presence in water and sediment of the Douhe Reservoir, and the multidrug, aminoglycoside and macrolide–lincosamide–streptogramin B (MLSB) were main types of ARGs. Bacterial genera and the environmental factors [such as temperature (T), nitrate–nitrogen (NO– 3–N), total dissolved nitrogen (TDN), and total phosphorus (TP)] significantly affected the distribution pattern of ARGs. Overall, this research revealed the spatiotemporal change and transmission mechanisms of ARGs in the typical drinking water sources of reservoirs, which will supply clues to ensure the safety of water sources.