A Plant Disease Recognition Method Based on Fusion of Images and Graph Structure Text

The disease image recognition models based on deep learning have achieved relative success under limited and restricted conditions, but such models are generally subjected to the shortcoming of weak robustness. The model accuracy would decrease obviously when recognizing disease images with complex backgrounds under field conditions. Moreover, most of the models based on deep learning only involve characterization learning on visual information in the image form, while the expression of other modal information rather than the image form is often ignored. The present study targeted the main invasive diseases in tomato and cucumber as the research object. Firstly, in response to the problem of weak robustness, a feature decomposition and recombination method was proposed to allow the model to learn image features at different granularities so as to accurately recognize different test images. Secondly, by extracting the disease feature words from the disease text description information composed of continuous vectors and recombining them into the disease graph structure text, the graph convolutional neural network (GCN) was then applied for feature learning. Finally, a vegetable disease recognition model based on the fusion of images and graph structure text was constructed. The results show that the recognition accuracy, precision, sensitivity, and specificity of the proposed model were 97.62, 92.81, 98.54, and 93.57%, respectively. This study improved the model robustness to a certain extent, and provides ideas and references for the research on the fusion method of image information and graph structure information in disease recognition.

Review: The evolution of chemometrics coupled with near infrared spectroscopy for fruit quality evaluation

Short wave near infrared (NIR) spectroscopy operated in a partial or full transmission geometry and a point spectroscopy mode has been increasingly adopted for evaluation of quality of intact fruit, both on-tree and on-packing lines. The evolution in hardware has been paralleled by an evolution in the modelling techniques employed. This review documents the range of spectral pre-treatments and modelling techniques employed for this application. Over the last three decades, there has been a shift from use of multiple linear regression to partial least squares regression. Attention to model robustness across seasons and instruments has driven a shift to machine learning methods such as artificial neural networks and deep learning in recent years, with this shift enabled by the availability of large and diverse training and test sets.

Technical note: PMR – a proxy metric to assess hydrological model robustness in a changing climate

The ability of hydrological models to perform in climatic conditions different from those encountered in calibration is crucial to ensure a reliable assessment of the impact of climate change on river regimes and water availability. However, most evaluation studies based on the differential split-sample test (DSST) endorsed the consensus that rainfall–runoff models lack climatic robustness. Models applied under climatologically different conditions typically exhibit substantial errors in streamflow volumes. In this technical note, we propose a new performance metric to evaluate model robustness without applying the DSST, and it can be performed with a single hydrological model calibration. The proxy for model robustness (PMR) is based on the systematic computation of model error on sliding sub-periods of the whole streamflow time series. We demonstrate that the PMR metric shows patterns similar to those obtained with the DSST for a conceptual model on a set of 377 French catchments. An analysis of the sensitivity to the length of the sub-periods shows that this length influences the values of the PMR and its equivalency with DSST biases. We recommend a range of a few years for the choice of sub-period lengths, although this should be context dependent. Our work makes it possible to evaluate the temporal transferability of any hydrological model, including uncalibrated models, at a very low computational cost.

Combining data augmentation and domain information with TENER model for Clinical Event Detection

Background In recent years, with the development of artificial intelligence, the use of deep learning technology for clinical information extraction has become a new trend. Clinical Event Detection (CED) as its subtask has attracted the attention from academia and industry. However, directly applying the advancements in deep learning to CED task often yields unsatisfactory results. The main reasons are due to the following two points: (1) A great number of obscure professional terms in the electronic medical record leads to poor recognition performance of model. (2) The scarcity of datasets required for the task leads to poor model robustness. Therefore, it is urgent to solve these two problems to improve model performance. Methods This paper proposes a combining data augmentation and domain information with TENER Model for Clinical Event Detection. Results We use two evaluation metrics to compare the overall performance of the proposed model with the existing model on the 2012 i2b2 challenge dataset. Experimental results demonstrate that our proposed model achieves the best F1-score of 80.26%, type accuracy of 93% and Span F1-score of 90.33%, and outperforms the state-of-the-art approaches. Conclusions This paper proposes a multi-granularity information fusion encoder-decoder framework, which applies the TENER model to the CED task for the first time. It uses the pre-trained language model (BioBERT) to generate word-level features, solving the problem of a great number of obscure professional terms in the electronic medical record lead to poor recognition performance of model. In addition, this paper proposes a new data augmentation method for sequence labeling tasks, solving the problem of the scarcity of datasets required for the task leads to poor model robustness.

A study of real-world micrograph data quality and machine learning model robustness

Machine-learning (ML) techniques hold the potential of enabling efficient quantitative micrograph analysis, but the robustness of ML models with respect to real-world micrograph quality variations has not been carefully evaluated. We collected thousands of scanning electron microscopy (SEM) micrographs for molecular solid materials, in which image pixel intensities vary due to both the microstructure content and microscope instrument conditions. We then built ML models to predict the ultimate compressive strength (UCS) of consolidated molecular solids, by encoding micrographs with different image feature descriptors and training a random forest regressor, and by training an end-to-end deep-learning (DL) model. Results show that instrument-induced pixel intensity signals can affect ML model predictions in a consistently negative way. As a remedy, we explored intensity normalization techniques. It is seen that intensity normalization helps to improve micrograph data quality and ML model robustness, but microscope-induced intensity variations can be difficult to eliminate.

Generating adversarial images to monitor the training state of a CNN model

Deep neural networks have shown effectiveness in many applications, however, in regulated applications like automotive or medicine, quality guarantees are required. Thus, it is important to understand the robustness of the solutions to perturbations in the input space. In order to identify the vulnerability of a trained classification model and evaluate the effect of different perturbations in the input on the output class, two different methods to generate adversarial examples were implemented. The adversarial images created were developed into a robustness index to monitor the training state and safety of a convolutional neural network model. In the future work, some generated adversarial images will be included into the training phase to improve the model robustness.

Enhancing the robustness of the convolutional neural networks for traffic sign detection

The detection of traffic signs in clean and noise-free images has been investigated by numerous researchers; however, very few of these works have focused on noisy environments. While in the real world, for different reasons (e.g. the speed and acceleration of a vehicle and the roughness around it), the input images of the convolutional neural networks (CNNs) could be extremely noisy. Contrary to other research works, in this paper, we investigate the robustness of the deep learning models against the synthetically modeled noises in the detection of small objects. To this end, the state-of-the-art architectures of Faster-RCNN Resnet101, R-FCN Resnet101, and Faster-RCNN Inception Resnet V2 are trained by means of the Tsinghua-Tencent 100K database, and the performances of the trained models on noisy data are evaluated. After verifying the robustness of these models, different training scenarios (1 – Modeling various climatic conditions, 2 – Style randomization, and 3 – Augmix augmentation) are used to enhance the model robustness. The findings indicate that these scenarios result in up to 13.09%, 12%, and 13.61% gains in the mentioned three networks by means of the mPC metric. They also result in 11.74%, 8.89%, and 7.27% gains in the rPC metric, demonstrating that improvement in robustness does not lead to performance drop on the clean data.

Multi-view Feature Augmentation with Adaptive Class Activation Mapping

We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance. Different from using global average pooling (GAP) to extract vectorized features from only the global view, we propose to sample and ensemble diverse multi-view local features to improve model robustness. To sample class-representative local features, we incorporate a simple auxiliary classifier head (comprising only one 1x1 convolutional layer) which efficiently and adaptively attends to class-discriminative local regions of feature maps via our proposed AdaCAM (Adaptive Class Activation Mapping). Extensive experiments demonstrate consistent and noticeable performance gains achieved by our multi-view feature augmentation module.