BHBohan Huang

Bohan Huang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bohan Huang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Regression study on fruit‐setting days of purple eggplant fruit based on in situ VIS‐NIRS and attention cycle neural network

    by Bohan Huang, Long Xue, Jie Yang, Chaoyang Yin, Keke Liao, Muhua Liu, Jing Li, Mengmeng Shang

    In the intelligent harvesting of eggplant, the lack of in situ identification technology makes it challenging to determine the maturity of purple eggplant fruit. The length of the fruit‐setting date can determine when the eggplant is ready to be harvested. This study uses deep learning techniques to predict the date of fruit maturity. First, we proposed a fruit‐setting days prediction method based on fruit spectroscopy and neural networks. Second, we collected the field in situ spectral data of purple eggplant fruit during 15–33 days of fruit setting using a portable spectrometer, covering 500–1000 nm. A fruit‐setting time regression network combining multi‐scale convolution, multi‐head attention mechanism, and long short‐term memory recurrent neural network was constructed using the collected in situ spectral data. The model demonstrated better fitting performance than traditional machine learning models such as backpropagation neural network, random forest, support vector machine, and partial least squares regression in the regression task of fruit‐setting days. After testing various spectral preprocessing methods, the best fitting effect was found on the standard normal variate–processed dataset, with R 2 of 0.876 and RMSE(root mean square error) of 2.148 days. Furthermore, the feasibility of each model module was analyzed in depth through ablation experiments, confirming each component's role in improving the model's performance. The network attention weight was also analyzed, and the model has strong detail mining ability in a specific spectral interval. In summary, the combination of visible and near‐infrared spectroscopy and attention cycle neural network is an effective method to predict the fruit‐setting days of purple eggplant fruit. Practical Application: A prediction method of fruit‐setting days based on fruit spectral characteristics and recurrent neural network regression was proposed. A novel approach to detecting and disclosing in situ surface VIS‐NIRS reflectance data of eggplant fruit during ripening is presented for the first time. A set of long‐term and short‐term memory networks based on multi‐scale convolution and multi‐head attention mechanisms was constructed for spectral data fitting. Through the ablation test method and attention weight analysis, the function of each module in the network and the interpretability of feature extraction are explored.

  • Feature area size prediction method of spherical fruit based on projection transformation

    by Bohan Huang, Long Xue, Chaoyang Yin, Jing Li, Muhua Liu

    With the development of machine vision and spectral detection technology, online sorting of fruit internal and external quality has been developed rapidly. However, for spherical fruits, it is difficult to obtain full surface images during sorting, so it is difficult to accurately calculate the size of the surface defects and the ratio of defects to the full surface. In this paper, a full surface line scanning image acquisition device for spherical fruit is proposed. Based on this device, the line scanning hyperspectral image of spherical fruit is collected, and the original image is extracted by feature extraction and background removal. Next, the isometric projection image and the equivalent projection image of the feature image is obtained through cartography projection transformation; The number of feature pixels in the original feature image, the isometric projection image, the equivalent projection image, and the width of the original feature image are used as input parameters to predict the actual defect area with the help of the shallow neural network. In this paper, the equipment and method are verified using three test balls with different diameters and pasting different sizes of identification blocks at different positions on their surfaces. The experimental results show that the prediction accuracy R of the test set of the model is 0.9937, and the RMSE is 0.3391 cm2. It can be seen that the method has good prediction accuracy, which can provide a reference for the hyperspectral on‐line sorting method of external quality of spherical fruit.Practical application: This method provides an effective solution for the quality sorting production line of spherical fruits. In addition to agricultural product quality testing and food quality testing, similar to the detection of industrial products such as ball balls, the scheme provided in this manuscript can also be used as one of the options.The method proposed in this manuscript is suitable for all kinds of line scanning equipment, including hyperspectral imager and laser profilometer.

  • Open Access

    nondestructive detection of kiwifruit textural characteristic based on near infrared hyperspectral imaging technology

    by Jing Li, Bohan Huang, Chenpeng Wu, Zheng Sun, Long Xue, Muhua Liu, Jinyin Chen

    The nondestructive detection of kiwifruit texture has become an important necessity that influences kiwifruit economic efficiency and consumer recognition of the kiwifruit. This study investigated the feasibility of using hyperspectral imaging technology to identify textural characteristics of kiwifruit, and to establish the model with best performance. Firstly, a near-infrared hyperspectral online grading system (1000–2500 nm) was constructed to acquire spectral images. Textural characteristics were measured via three different textural analysis tests: textural profile analysis, puncture test, and shear test. Then, samples were divided into a calibration set and a prediction set based on rank sampling at a ratio of 3:1. Mean centralization, standard normal variate, and multiplicative scatter correction methods were applied to pre-process obtained spectra. Finally, the partial least squares method was used to establish prediction models of kiwifruit textural characteristics. The models of hardness1, chewiness, resilience, peel hardness, average hardness, and corrected hardness achieved good performance. Both the correlation coefficients of calibration (rc) and prediction (rp) values exceeded 0.9. The difference between the root mean square error (RMSE) of calibration and prediction was small, and the ratio of prediction to deviation (RPD) value exceeded 2, which was used to predict kiwifruit quality. However, the model of average shear force had a low accuracy with an RPD of 1.680 and the model of shear force also had an RPD below 1.5 and a low RMSE. The results showed that near-infrared hyperspectral imaging technique can be used as a nondestructive method for the textural characteristics kiwifruit.