Search

BACKGROUND: In the contemporary food industry, accurate and rapid differentiation of oolong tea varieties holds paramount importance for traceability and quality control. However, achieving this remains a formidable challenge. This study addresses this lacuna by employing machine learning algorithms – namely support vector machines (SVMs) and convolutional neural networks (CNNs) – alongside computer vision techniques for the automated classification of oolong tea leaves based on visual attributes. RESULTS: An array of 13 distinct characteristics, encompassing color and texture, were identified from five unique oolong tea varieties. To fortify the robustness of the predictive models, data augmentation and image cropping methods were employed. A comparative analysis of SVM‐ and CNN‐based models revealed that the ResNet50 model achieved a high Top‐1 accuracy rate exceeding 93%. This robust performance substantiates the efficacy of the implemented methodology for rapid and precise oolong tea classification. CONCLUSION: The study elucidates that the integration of computer vision with machine learning algorithms constitutes a promising, non‐invasive approach for the quick and accurate categorization of oolong tea varieties. The findings have significant ramifications for process monitoring, quality assurance, authenticity validation and adulteration detection within the tea industry. © 2023 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

Event Causality Identification (ECI) aims at detecting the causal relation between 2 events, which is a challenging task due to the complexity of causal expressions and the background knowledge needed for identifying certain causal relations. Considerable work has been done on the learning of context and the incorporation of external knowledge. However, none of the work incorporates both explicit and implicit causal knowledge. To this end, we propose an integrative model for event causality identification, integrating both explicit causal indicators and implicit causal knowledge with the data-oriented model. For the data-oriented model, an event pair graph is constructed and Relational Graph Convolutional Network (R-GCN) is employed to better capture interactions between individual pairs. Regarding the explicit causal indicators, their word embeddings are used to initialize the filters of convolutional neural network so as to capture the clues indicating causal relation. We further introduce a cause–effect matching mechanism to better leverage implicit causal knowledge. It measures the possibility of causal relation holding between 2 events based on the possible causes and effects generated by COMET. The proposed method is evaluated on 3 datasets, and experimental results demonstrate the effectiveness and superiority of the proposed method. • Propose a novel method integrating RGCN and explicit and implicit causal knowledge. • Propose a cause–effect matching mechanism to leverage implicit causal knowledge. • Achieve the best performance on 3 widely adopted datasets. [ABSTRACT FROM AUTHOR]

Imaging of a subwavelength microstructure made of a periodic grid-like finite set of circular rods is carried out from transient scattered field data in different configurations of sources and receivers. The goal is to identify the position of possibly missing rods. Time reversal is confirmed as a cheap yet efficient first-order diagnostic method even in the demanding context of a subwavelength microstructure. Tools of deep learning, expected to be valid in general circumstances if data acquired in sufficient numbers, are in parallel developed to image the microstructure. To that effect, recurrent neural networks (RNN) and convolutional neural networks (CNN) are both used. Pros and cons of all approaches are illustrated by comprehensive simulations from synthetic data computed via a finite difference time domain method (FD-TD) software carefully tailored to the microstructure model and used also to make the networks learn the microstructures. The analysis is completed from examples of laboratory-controlled data acquired on a microstructure prototype set within a microwave anechoic chamber. These examples confirm the good promises of neural networks even with rather scarce data as exemplified in a forward scattering case—fixed source and receiver antennas face each other and the microstructure is rotated between them. [ABSTRACT FROM AUTHOR]

Most existing Web service recommendation models based on machine learning do not fully consider the high-order features interaction between users and services and with poor interpretability. In this paper, an Interpretable Web Service Recommendation model based on Disentangled Representation Learning (WSR-DRL) is proposed. First of all, to make full use of the service description information to improve the accuracy of Web service recommendation, the features representation of service name is obtained by using BERT model, and the local and global features representation of service description information is further obtained by combining 2-D CNN and Bi-LSTM. Then the disentangled convolution neural network is used to generate the high-order interaction features between users and services, and the neighborhood routing algorithm is used to mine the latent factors in these features. That improves the accuracy of Web service recommendation and make it interpretable. Finally, in order to verify the effectiveness of the model, several groups of experiments are carried out on real data sets. The experimental results show that compared with latest models such as DMF, DeepFM, DKN, GCMC, NDCG model and WSR-MGAT model, the WSR-DRL model proposed in this paper shows better performance on Precision@10, Recall@10, F1@10 and NDCG@10 evaluation metrics. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) are widely used for hyperspectral image (HSI) classification due to their better ability to model the local details of HSI. However, CNNs tends to ignore the global information of HSI, and thus lack the ability to establish remote dependencies, which leads to computational cost consumption and remains challenging. To address this problem, we propose an end-to-end Inception Transformer network (IFormer) that can efficiently generate rich feature maps from HSI data and extract high- and low-frequency information from the feature maps. First, spectral features are extracted using batch normalization (BN) and 1D-CNN, while the Ghost Module generates more feature maps via low-cost operations to fully exploit the intrinsic information in HSI features, thus improving the computational speed. Second, the feature maps are transferred to Inception Transformer through a channel splitting mechanism, which effectively learns the combined features of high- and low-frequency information in the feature maps and allows for the flexible modeling of discriminative information scattered in different frequency ranges. Finally, the HSI features are classified via pooling and linear layers. The IFormer algorithm is compared with other mainstream algorithms in experiments on four publicly available hyperspectral datasets, and the results demonstrate that the proposed method algorithm is significantly competitive among the HSI classification algorithms. [ABSTRACT FROM AUTHOR]