Chengyun Zhang

Prof. Dr. Chengyun Zhang

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 January 2023 in Forests
Verified
Journal Article
Open access
PDF file
CZChengyun Zhang
Chengyun Zhang
HZHaisong Zhan
Haisong Zhan
zezhou haozezhou hao
zezhou hao
XGxinghui Gao
xinghui Gao
The use of passive acoustic monitoring (PAM) can compensate for the shortcomings of traditional survey methods on spatial and temporal scales and achieve all-weather and wide-scale assessment and prediction of environmental dynamics. Assessing the impact of human activities on biodiversity by analyzing the characteristics of acoustic scenes in the environment is a frontier hotspot in urban forestry. However, with the accumulation of monitoring data, the selection and parameter setting of the deep learning model greatly affect the content and efficiency of sound scene classification. This study compared and evaluated the performance of different deep learning models for acoustic scene classification based on the recorded sound data from Guangzhou urban forest. There are seven categories of acoustic scenes for classification: human sound, insect sound, bird sound, bird–human sound, insect–human sound, bird–insect sound, and silence. A dataset containing seven acoustic scenes was constructed, with 1000 samples for each scene. The requirements of the deep learning models on the training data volume and training epochs in the acoustic scene classification were evaluated through several sets of comparison experiments, and it was found that the models were able to achieve satisfactory accuracy when the training sample data volume for a single category was 600 and the training epochs were 100. To evaluate the generalization performance of different models to new data, a small test dataset was constructed, and multiple trained models were used to make predictions on the test dataset. All experimental results showed that the DenseNet_BC_34 model performs best among the comparison models, with an overall accuracy of 93.81% for the seven acoustic scenes on the validation dataset. This study provides practical experience for the application of deep learning techniques in urban sound monitoring and provides new perspectives and technical support for further exploring the relationship between human activities and biodiversity.

29 January 2021 in IEEE Access
Verified
Journal Article
Open access
LFLiyun Fu
Liyun Fu
HZHouyao Zhu
Houyao Zhu
CZChengyun Zhang
Chengyun Zhang
HOHaibin Ouyang
Haibin Ouyang
SLSteven Li
Steven Li
Differential evolution (DE) algorithm has some excellent attributes including strong exploration capability. However, it cannot balance the exploitation with exploration ability in the search process. To enhance the performance of the DE algorithm, this paper proposes a new algorithm named hybrid harmony differential evolution algorithm (HHSDE). The key features of HHSDE algorithm are as follows. First, a new mutation operation is developed for improving the efficiency of mutation, in which the New Harmony generation mechanics of the harmony algorithm (HS) is employed. Second, the harmony memory size is updated with the iteration. Third, a self-adaptive parameter adjustment strategy is presented to control scaling factor. Fourth, a new evaluation method is proposed to effectively assess the algorithm convergence performance. Two classical DE algorithms, HS algorithm, improvement Differential evolution algorithm(ISDE) and Hybrid Artificial Bee Colony algorithm with Differential Evolution(HABCDE) have been tested against HHSDE based on 25 benchmark functions of CEC2005 and the results reveal that the proposed algorithm is better than the other algorithms under consideration.

11 November 2022 in Animals
Verified
Journal Article
Open access
PDF file
CZChengyun Zhang
Chengyun Zhang
YCYonghuan Chen
Yonghuan Chen
zezhou haozezhou hao
zezhou hao
XGxinghui Gao
xinghui Gao
Bird sounds have obvious characteristics per species, and they are an important way for birds to communicate and transmit information. However, the recorded bird sounds in the field are usually mixed, which making it challenging to identify different bird species and to perform associated tasks. In this study, based on the supervised learning framework, we propose a bird sound separation network, a dual-path tiny transformer network, to directly perform end-to-end mixed species bird sound separation in the time-domain. This separation network is mainly composed of the dual-path network and the simplified transformer structure, which greatly reduces the computational resources required of the network. Experimental results show that our proposed separation network has good separation performance (SI-SNRi reaches 19.3 dB and SDRi reaches 20.1 dB), but compared with DPRNN and DPTNet, its parameters and floating point operations are greatly reduced, which means a higher separation efficiency and faster separation speed. The good separation performance and high separation efficiency indicate that our proposed separation network is valuable for distinguishing individual birds and studying the interaction between individual birds, as well as for realizing the automatic identification of bird species on a variety of mobile devices or edge computing devices.

3 October 2026 in Journal of Applied Ecology
Verified
Journal Article
Closed access
YCYuhao Chen
Yuhao Chen
ZHZezhou Hao
Zezhou Hao
CZChengyun Zhang
Chengyun Zhang
ZCZihao Chen
Zihao Chen
LLLe Li
Le Li
YLYang Liu
Yang Liu

1 January 2026 in Biodiversity Science
Verified
Journal Article
Closed access
PDF file
HZHao Zezhou
Hao Zezhou
SXShen Xiaoli
Shen Xiaoli
SXSi Xingfeng
Si Xingfeng
ZYZhao Yanyan
Zhao Yanyan
WCWei Chentao
Wei Chentao
YLYang Liu
Yang Liu

1 January 2024 in Biodiversity Science
Verified
Journal Article
Closed access
PDF file
WHWantao Huang
Wantao Huang
ZHZezhou Hao
Zezhou Hao
ZZZixin Zhang
Zixin Zhang
ZXZhishu Xiao
Zhishu Xiao
CZChengyun Zhang
Chengyun Zhang