Zheng Zhang

Prof. Zheng Zhang

Shanghai Ocean University, Shanghai, China
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
4 March 2021 in IEEE Access
Verified
Journal Article
Open access
SCShouqi Cao
Shouqi Cao
LZLixin Zhou
Lixin Zhou
ZZZheng Zhang
Zheng Zhang
In the aquaculture industry, dissolved oxygen is an important water quality parameter index. The prediction of dissolved oxygen can reduce the operation cost of aquatic product management to a certain extent. In this paper, a hybrid method is proposed to predict the change of dissolved oxygen from the perspective of time series in aquaculture, which based on k-means clustering and improved Softplus extreme learning machine (SELM) with particle swarm optimization (PSO). We use k-means algorithm to divide the dataset into several clusters by calculating the similarity among variables, to find the periodic change rule and trend of variables. Softplus is employed as the activation function of ELM to make the model closer to the biological activation model. Meanwhile, partial least square (PLS) method is utilized to solve the strong collinearity among variables. In addition, we introduce PSO algorithm to optimize the model parameters. The experimental results show that our model can achieve better prediction performance and accuracy of prediction compared with other single models. Compared with the counterpart model, the improved model can tolerate some data loss and uncertain outliers of sensor time series. Our work provides an accurate predictive model framework for researchers to track dissolved oxygen.

9 June 2023 in Sensors
Verified
Journal Article
Open access
PDF file
LCLiling Cao
Liling Cao
CSChangFu Shao
ChangFu Shao
ZZZheng Zhang
Zheng Zhang
SCShouqi Cao
Shouqi Cao
The lithium-ion battery is the power source of an electric vehicle, so it is of great significance to estimate the state of charge (SOC) of lithium-ion batteries accurately to ensure vehicle safety. To improve the accuracy of the parameters of the equivalent circuit model for batteries, a second-order RC model for ternary Li-ion batteries is established, and the model parameters are identified online based on the forgetting factor recursive least squares (FFRLS) estimator. To improve the accuracy of SOC estimation, a novel fusion method, IGA-BP-AEKF, is proposed. Firstly, an adaptive extended Kalman filter (AEKF) is used to predict the SOC. Then, an optimization method for BP neural networks (BPNNs) based on an improved genetic algorithm (IGA) is proposed, in which pertinent parameters affecting AEKF estimation are utilized for BPNN training. Furthermore, a method with evaluation error compensation for AEKF based on such a trained BPNN is proposed to enhance SOC evaluation precision. The excellent accuracy and stability of the suggested method are confirmed by the experimental data under FUDS working conditions, which indicates that the proposed IGA-BP-EKF algorithm is superior, with the highest error of 0.0119, MAE of 0.0083, and RMSE of 0.0088.

17 August 2019 in Electronics
Verified
Journal Article
Open access
PDF file
ZZZheng Zhang
Zheng Zhang
SCShouqi Cao
Shouqi Cao
YWYuntengyao Wang
Yuntengyao Wang
Wireless communications for applications of inshore fishery and large area aquatic environmental monitoring are really challenging, due to the characteristics of a long monitoring period, large coverage area, and adverse transmission conditions. Recently, LPWAN (low-power wide-area network) became the new solution to address these challenges, due to its long transmission distance and low power consumption of end-nodes. In this paper, we designed a novel network system for aquatic environmental monitoring, based on long-range 2.4G technology, which consisted of a low cost dual-channel gateway and end-nodes. A DMSF (dual-channel multiple spreading factors)–TDMA (time division multiple access) MAC (medium access control) scheme for this system was proposed, which largely reduces the channel collision probability, and improves the real-time for urgent data and the average lifetime of end-nodes. We verified the applicability of the long-range 2.4G technology in an aquatic environment, by point-to-point communication experiments over lake water. The performance evaluation and analysis of DMSF–TDMA is presented through simulations, and comparison with other existing schemes. The results demonstrated the benefit of our proposed scheme, in terms of the packet delivery rate, delay, and energy consumption.

15 July 2022 in Drones
Verified
Journal Article
Open access
PDF file
ZZZheng Zhang
Zheng Zhang
CZChun Zhou
Chun Zhou
LSLiangcai Sheng
Liangcai Sheng
SCShouqi Cao
Shouqi Cao
Recently, the use of unmanned aerial vehicles (UAVs) and LPWANs (low-power wide-area networks) has been a good solution to the problem of data collection for environmental monitoring in remote areas without infrastructure, and there are many valuable research works in this field. UAV data collection for sensor nodes is becoming a challenge, that is, the amount of data will affect the UAV’s communication time and flight status, especially in LPWAN systems. In this paper, the optimization schemes are proposed to improve the efficiency of UAV for collecting data in LoRa network monitoring systems. Firstly, an improved clustering algorithm for the LoRa network is proposed, which considers the influence of distance between the cluster heads and the UAV take-off point. Secondly, we present an improved Genetic Algorithm for path planning to reduce the UAV flight distance, which introduces the Teaching–Learning-based Optimization (TLBO) and local search optimization algorithms to improve convergence speed and the path solution. Then, a LoRa 2.4 GHz adaptive data rate strategy with a dual channel is designed based on distance and link quality, to reduce the data transmitting time between the UAV and the cluster head nodes. Finally, we carry out the simulations and experiments. The results show the performance of the proposed schemes, which means that these can improve the efficiency of UAV data collection with low cost LoRa networks in remote areas without infrastructure.

25 January 2021 in IEEE Access
Verified
Journal Article
Open access
ZZZheng Zhang
Zheng Zhang
JHJunjun Huang
Junjun Huang
SCShouqi Cao
Shouqi Cao
Recently, the research of the internet of vessels system is a hotspot in the marine engineering area. In this article, the Internet of Vessels based on Beidou satellite navigation system (IoV-BDS) architecture is proposed for marine cold chain transportation monitoring and scheduling. An improved communication method using Beidou short-message communication (SMC) is designed to ensure the reliability of ship-shore data transmission. Additionally, based on the IoV-BDS, we proposed a novel route scheduling optimization model which considers the key costs for marine cold chain transportation, such as fuel, catches damage, and refrigeration energy consumption, and designed a speed selection mechanism. Furthermore, an improved ant colony optimization (IACO) algorithm was utilized to optimize the whole fleet transportation routes, which takes advantage of the A-star algorithm to speed up the convergence of ant colony algorithm (ACO), a novel state transition rule was used to prevent falling into a locally optimal solution. The applicability of IoV-BDS was verified by the shipboard data acquisition and Beidou SMC experiments. The performance evaluation and analysis of route optimization schemes were presented by simulations and comparison with other schemes. The results demonstrated the benefit of our proposed schemes, in terms of solution quality and convergence of the algorithm.

1 January 2024 in Mathematical Biosciences and Engineering
Verified
Journal Article
Open access
PDF file
ZZZheng Zhang
Zheng Zhang
XLXiang Lu
Xiang Lu
SCShouqi Cao
Shouqi Cao
Detecting abnormal surface features is an important method for identifying abnormal fish. However, existing methods face challenges in excessive subjectivity, limited accuracy, and poor real-time performance. To solve these challenges, a real-time and accurate detection model of abnormal surface features of in-water fish is proposed, based on improved YOLOv5s. The specific enhancements include: 1) We optimize the complete intersection over union and non-maximum suppression through the normalized Gaussian Wasserstein distance metric to improve the model's ability to detect tiny targets. 2) We design the DenseOne module to enhance the reusability of abnormal surface features, and introduce MobileViTv2 to improve detection speed, which are integrated into the feature extraction network. 3) According to the ACmix principle, we fuse the omni-dimensional dynamic convolution and convolutional block attention module to solve the challenge of extracting deep features within complex backgrounds. We carried out comparative experiments on 160 validation sets of in-water abnormal fish, achieving precision, recall, mAP50, mAP50:95 and frames per second (FPS) of 99.5, 99.1, 99.1, 73.9% and 88 FPS, respectively. The results of our model surpass the baseline by 1.4, 1.2, 3.2, 8.2% and 1 FPS. Moreover, the improved model outperforms other state-of-the-art models regarding comprehensive evaluation indexes.