Shuai Wang’s research while affiliated with Zhejiang University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (11)


Figure 4 Spectra profile of raw data and preprocessing with SNV in different batches
Figure 5 Monte Carlo Sampling (MCS) outlier detection of the in-line detection set
Figure 8 Results of wavelength selection by CARS-PLSR of in-line data.
Descriptive statistics of the pomelo datasets in three years
Model performance of PLSR with different wavelength selection methods in the range of 500-1000 nm
Modeling method for SSC prediction in pomelo using Vis-NIRS with wavelength selection and latent variable updating
  • Article
  • Full-text available

March 2024

·

6 Reads

International Journal of Agricultural and Biological Engineering

Hao Tian

·

Shuai Wang

·

Huirong Xu

·

Yibin Ying
Download


Vis/NIR model development and robustness in prediction of potato dry matter content with influence of cultivar and season

March 2023

·

20 Reads

·

13 Citations

Postharvest Biology and Technology

Visible/Near-infrared (Vis/NIR) spectroscopy is widely used in the detection of dry matter content (DMC) of potatoes. However, biological variability (e.g., cultivar and season) will affect the potato DMC and spectral features, and will further cause the DMC prediction model ineffective. This study aimed to develop robust Vis/NIR models for predicting potato DMC with influence of cultivar and season. The local and global models were developed to explore the influence of cultivar and season. The Mahalanobis distance and concentration gradient (MD-CG) method was developed to select representative samples, and the combinations of different variable selection methods (CARS, SPA and CSMW) and model updating methods (SBC and recalibration) were investigated for model enhancement. The results indicated that 10 new samples selected by MD-CG method, combined with variable selection and model updating, were sufficient to improve the performance of the local (RPDp>1.7) and global (RPDp>2) models. In the local models, for the datasets with different cultivars (EG-2021, XS-2021 and AT-2021), the optimal results were obtained using CSMW combined with recalibration, and the RMSEp was decreased from 4.18%, 1.14%, 2.54–1.05%, 0.72%, 0.79%, respectively. For the datasets with different seasons (FA-2022), the optimal result was obtained by using SPA combined with recalibration, and the RMSEp was decreased from 3.70% to 0.91%. For the global model, CSMW combined with recalibration and SPA combined with SBC obtained better results, with RMSEp decreasing from 0.83% to 0.52% and 0.51%, respectively. The MD-CG method and the combinations of variable selection and model updating proposed in this study are important to reduce the influence of external conditions and enhance the model robustness to biological variability.


Evaluation of dry matter content in intact potatoes using different optical sensing modes

December 2022

·

186 Reads

·

5 Citations

Journal of Food Measurement and Characterization

Potatoes are generally consumed directly as a staple food or used for processing, depending on the quality of raw materials. Dry matter content (DMC) is the most critical characteristic of potatoes, as it determines the processing and the final product quality. This study aimed to investigate the potential of different optical sensing systems in predicting the DMC of intact potato tubers, and the efficacy of classifying potatoes based on dry matter levels. The whole tubers were scanned using three optical sensing modes (transmittance spectra, interactance spectra and hyperspectral imaging). PLSR and different classifiers (PLSDA, SVM and ANN) were utilized to build the prediction and classification models, respectively. To extract the most influential wavelengths related to the prediction of DMC, the CARS and CSMW techniques were applied. The results indicated that the DMC of two sections on the equator of the potato tuber belly can well represent the DMC of the intact potato, and together with the spectral detection at the equatorial position, it provided good performance. The CARS-PLSR prediction model in transmittance mode showed stronger correlations than other systems, with Rp and RMSEP values of 0.968 and 0.413%, respectively. The CARS-SVM-Linear classification model exhibited the best performance with classification rates of 100% and 97.62% in the training and testing sets, respectively. Moreover, the spectra preferred by CARS and CSMW variable selection methods in transmittance mode overlapped near the absorption peak at 980 nm, indicating the importance of this band for predicting DMC. This study presented the feasible application of using spectroscopy to evaluate the DMC of intact potatoes and classify potatoes based on thresholds that are crucial to consumers and food processors. Graphical abstract


Paddy moisture on-line detection based on ensemble preprocessing and modeling for combine harvester

July 2022

·

22 Reads

·

5 Citations

Computers and Electronics in Agriculture

The on-line detection of paddy moisture content (MC) during harvest has gained increasing interest recently due to its unique role for the control of combine harvester, yield evaluation and post-harvest grain handling operations. However, it is very difficult to achieve good performance under the complex and changeable situation during field harvest. In this study, paddy varieties, paddy flow, feeding types and algorithms were comprehensively considered to optimize the MC detection method. Firstly, an on-line near-infrared sensing system supplemented for grain tank of combine harvester was designed, and spectra were collected under the most common and essential detecting conditions, which including paddy varieties, feeding types and straw effect. Then, ensemble preprocessing, parameter optimization and accuracy test were performed. The best result of all conditions was extreme learning machine (ELM) coupled with the ensemble preprocessing of orthogonal signal correction with savitzky-golay (OSC + SG). The root mean standard error of prediction (RMSEPV) of this method after validation on unknown sample was as low as 1.0791% w.b, and the residual predictive deviation (RPDV) was higher than 3.5646. Stability tests were carried out under conditions of varying feeding types and straw quantities. The results showed that ELM had enough robustness to cope with complex detecting conditions and maintain proper accuracy as the mean value of repeatability, conditions and reproducibility were calculated as 0.0213%, 0.4471% and 0.6868% w.b, respectively. Despite the preliminary feasibility for on-line MC measurement of paddy, the on-line near-infrared sensing system needs to be verified on combine harvester during harvest.


Apple stem/calyx real-time recognition using YOLO-v5 algorithm for fruit automatic loading system

March 2022

·

869 Reads

·

176 Citations

Postharvest Biology and Technology

Fruit loading and packaging are still labor-intensive tasks during postharvest commercialization, of which the key issues is to realize the real-time detection and adjustment of fruit posture. However, fruit stem/calyx position is a key structural characteristic for fruit posture and will also affect fruit internal quality detection. In this paper, an image acquisition system based on fruit posture adjustment equipment was set up, and the YOLO-v5 algorithm based on deep learning was used to study the real-time recognition of stem/calyx of apples. First, hyperparameters were determined, and the training method of transfer learning was used to obtain better detection performance; then the networks with different widths and depths were trained to find the best baseline detection net; finally, the YOLO-v5 algorithm was optimized for this task by using detection head searching, layer pruning and channel pruning. The results showed that under the same setting conditions, YOLO-v5s had a more superior usability and could be selected as the baseline network considering detection performance, model weight size, and detection speed. After optimization, the complexity of the algorithm was further reduced. The model parameters and weight volume were decreased by about 71 %, while mean Average Precision (mAP) and F1-score (F1) were only decreased by 1.57 % and 2.52 %, respectively. The optimized algorithm could achieve real-time detection under CPU condition at a speed of 25.51 frames per second (FPS). In comparison with other deep learning target detection algorithms, the algorithm used in this paper was similar to other lightweight networks in complexity. Its mAP and F1 were 0.880 and 0.851, respectively. This was better than other one-stage object detection algorithms in detection ability, only lower than that of Faster R-CNN. The optimized YOLO-v5s achieved 93.89 % accuracy in fruit stem/calyx detection for different cultivars of apples. This research could lay the foundation for the automation of fruit loading and packing systems.


Early detection of freezing damage in oranges by online Vis/NIR transmission coupled with diameter correction method and deep 1D-CNN

February 2022

·

36 Reads

·

69 Citations

Computers and Electronics in Agriculture

Realizing online detection of early freezing damage of citrus fruits is meaningful and profitable in the existing postharvest sorting system of fruits and vegetables. Transmission spectra of 114 oranges in the range of 644–900 nm were obtained using a self-designed online spectral measurement system in this study. Fruit size seriously affected the intensity of transmission spectra and thus reduced the detection accuracy of the model for early freezing damage. To solve this problem, a new diameter correction method (DCM) was proposed. The results showed that DCM could eliminate the effect of fruit size on transmission spectra more effectively than multiplicative scattering correction (MSC) and standard normal variable (SNV), and partial least squares discrimination analysis (PLSDA) and support vector machine (SVM) models based on DCM pretreated spectra had better performance. To eliminate the collinearity variables in the original spectra and simplify the model, competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were used to extract effective wavelengths (EWs). The accuracy of DCM-CARS-SPA-PLSDA model established by 15 EWs for early freezing damage identification met the requirement of online detection. A one-dimensional Convolutional Neural Network (1D-CNN) architecture was proposed in this study to further improve the detection accuracy. The model established by combining DCM and 1D-CNN had the best performance. In the prediction set, the recall of the optimal model for the early freeze-damaged oranges and unfrozen oranges was 95.15 % and 88.54 %, and the overall accuracy was 91.96 %. Therefore, the DCM and 1D-CNN method proposed in this study can effectively eliminate the effect of fruit size on transmission spectra, and enable the model to effectively identify freezing damage.


Simulation and Experimental Study of Potato Conveyor Trajectory for Optimization Design of Belt-Fed Potato Sorter

January 2022

·

38 Reads

·

1 Citation

Journal of the ASABE

Highlights Potatoes of different mass had significantly different moving times and trajectories during unloading. Moving time and trajectory length increased with the increase in mass level of potatoes at different initial speeds. The belt-fed potato sorter developed by investigating potato moving trajectories had high accuracy and low damage. Abstract . Belt conveyors are one of the main transport methods in potato sorting equipment. Generally, potatoes are detected and sorted while being discharged from the end of the loading conveyor. Therefore, the moving time and trajectory of potatoes are critical to determining the detection and sorting positions. In this study, the detection and sorting locations were optimized by investigating the influence of different mass levels of potatoes on their moving time and trajectories at different initial speeds by using a high-speed camera. In addition, a dynamic simulation model of potato movement was established using ADAMS software for further comparison. It was found that the potato trajectories and moving times were significantly influenced by the potato mass levels in a practical experiment. At the same initial speed, the moving time and trajectory length increased with the increase in mass level. Calculation methods for the optimal size and position of the rod ejectors and the unloading conveyor are proposed. When the initial speed was 1 m s-1, the length of the rod ejectors was 218.77 mm with a falling height of 250 mm, and the vertical and horizontal distances between the loading and unloading conveyors were 450 and 216.7 mm, respectively. Finally, a sorting experiment was performed to verify the design, and a classification accuracy of 98.95% and damage rate of 1.26% were obtained. This study provides a theoretical reference for the optimization design of belt-fed potato sorters. Keywords: Optimization design, Potato, Simulation, Trajectory tracking.


Intact Macadamia Nut Quality Assessment Using Near-Infrared Spectroscopy and Multivariate Analysis

June 2021

·

36 Reads

·

12 Citations

Journal of Food Composition and Analysis

As production and demand for high quality Macadamia nuts rise worldwide, rapid and accurate in-situ methods for monitoring internal nut quality will need to be developed. Therefore, purpose of this study was to determine the quality (internal nut defects and oil content) of intact macadamia nuts by combining near-infrared spectroscopy with variable selection algorithms and calibration models. Transmission spectra in the ranges of 1,000-1,650 nm from a total of 345 macadamia nuts were acquired. Partial least square-discriminant analysis (PLS-DA) and partial least square-regression (PLS-R) models with three different spectral preprocessing techniques were then evaluated using the full spectra to classify nut defects and predict oil content. A Savitzky-Golay (S-G) first derivatives preprocessing technique was selected as the best one. Then, competitive adaptive reweighted sampling (CARS), random frog (RF), and variable importance projection (VIP) algorithms were used to select effective wavelengths (EWs) to build simpler and more robust models for classification of intact macadamia nut defects and prediction of oil content. The PLS-DA-CARS with S-G first derivatives preprocessing based model provided the best nut defect classification with a 91.4% accuracy, whilst a PLS-R-CARS with S-G second derivatives preprocessing model for oil content prediction had a coefficient of determination (R²pred) of 0.88 and standard error of prediction (SEP) of 1.15%.



Citations (9)


... To validate the performance of the candy defect recognition detection method proposed in this paper, we trained five advanced object recognition detection algorithms under the same dataset and parameter settings conditions, including Faster R-CNN, YOLOv5, YOLOX, YOLOv7, and the improved YOLOv7 proposed in this paper [33][34][35][36]. During the training phase, the parameters of these models were uniform and are shown in Table 2. ...

Reference:

A Candy Defect Detection Method Based on StyleGAN2 and Improved YOLOv7 for Imbalanced Data
MSDD-YOLOX: An enhanced YOLOX for real-time surface defect detection of oranges by type
  • Citing Article
  • September 2023

European Journal of Agronomy

... It serves as a fundamental dietary component in numerous developed and developing nations, contributing to its status as a staple food. Potatoes are ingested in their uncooked state as a fundamental sustenance or vegetable, transformed into French fries, crisps, and additional culinary enhancements, and employed in the production of potato flour, starch, and alcohol [1]. According to the data provided by the Food and Agriculture Organization (FAO), the global production of potatoes amounted to a significant quantity of 376 million metric tons. ...

Evaluation of dry matter content in intact potatoes using different optical sensing modes

Journal of Food Measurement and Characterization

... These methods are often time-consuming, costly in terms of equipment and reagents, prone to human error, have a limited throughput, and are laborious and limited in obtaining real-time data, hindering rapid and efficient research analysis [4]. Additionally, conventional techniques usually entail destructive sampling, which makes it difficult to study the same sample again or to monitor changes over time [5]. ...

Vis/NIR model development and robustness in prediction of potato dry matter content with influence of cultivar and season
  • Citing Article
  • March 2023

Postharvest Biology and Technology

... They integrated Yolov5 and EfficientDet models and observed a performance increase of 2.5% to 10.9% in fire detection accuracy. An ensemble pre-processing approach was proposed for paddy-moisture online detection in [31]. In [32], authors have proposed a robust Deep Ensemble Convolutional Neural Network (DECNN) model that can accurately diagnose rice nutrient deficiency. ...

Paddy moisture on-line detection based on ensemble preprocessing and modeling for combine harvester
  • Citing Article
  • July 2022

Computers and Electronics in Agriculture

... IR spectroscopy is widely used to analyze various components in Citrus fruits, such as SSC [63], acidity [11], vitamin content [64], and flavonoids [65], providing essential data for the quality grading and classification of Citrus. Additionally, changes in infrared spectral absorption and scattering can help detect defects [66] and identify biochemical changes caused by diseases. This capability offers crucial technical support for early disease detection, enabling timely intervention to reduce losses and improve disease management strategies [67]. ...

Early detection of freezing damage in oranges by online Vis/NIR transmission coupled with diameter correction method and deep 1D-CNN
  • Citing Article
  • February 2022

Computers and Electronics in Agriculture

... The optimization involved integrating the Swin Transformer attention mechanism and refining the Focal Loss function, resulting in an AP of 88.5%, marking a 7% improvement compared to the original model. Wang et al. [17] presented a YOLOv5-based object detection algorithm for real-time detection of apple stems and sepals, achieving a mAP of 88%. Bhattarai et al. [18] proposed a deep regression-based network, AgRegNet, capable of estimating the density, quantity, and location of flowers and fruits in tree crowns. ...

Apple stem/calyx real-time recognition using YOLO-v5 algorithm for fruit automatic loading system
  • Citing Article
  • March 2022

Postharvest Biology and Technology

... Recently, imaging and spectroscopic methods have been employed as an alternative to destructive and subjective methods of assessing various quality and safety traits of tree nuts [24,25]. Indeed, among various spectroscopic techniques, visible and near-infrared spectroscopy (VNIRS) has garnered considerable attention as a potent tool for evaluating nut quality [25,26]. ...

Intact Macadamia Nut Quality Assessment Using Near-Infrared Spectroscopy and Multivariate Analysis
  • Citing Article
  • June 2021

Journal of Food Composition and Analysis

... The second stage consists of the screening and conveyance of potatoes to the collection unit. The third stage involves the transportation of potatoes to the storage facility via a transport vehicle [115]. Compared to the digging and soil separation processes, the transportation process inflicts lower mechanical damage and bruising on the potatoes. ...

Influence of initial orientations on potato conveyor trajectories by machine vision
  • Citing Article
  • August 2019

Computers and Electronics in Agriculture

... Best-fit classification models (100%) were developed using all wavelengths and spectra from images of face-up kernels and were marginally more accurate than models developed using images of kernels in face-down (98%), or pooled image (98%) orientations. The best-fit model using VNIR face-down images was more accurate than another study using the NIR region (980-1680 nm) that reported 88.2% accuracy [60]. This may be attributed to the hyperspectral images in this study collecting both spectral and spatial data and, therefore, allowing inspection of a greater kernel surface area in comparison with the NIR point method. ...

Assessment of Intact Macadamia Nut Internal Defects Using Near-Infrared Spectroscopy
  • Citing Conference Paper
  • January 2020