Classification of crop disease-pest questions based on BERT-BiGRU-CapsNet with attention pooling

Crop disease-pest question classification is an essential part of pest knowledge intelligent question answering system. A crop disease-pest question classification method is proposed on the basis of bidirectional encoder representations from transformers (BERT), bidirectional gated unit (BiGRU), capsule network (CapsNet), and BERT-BiGRU-CapsNet with attention pooling (BBGCAP). In BBGCAP, the unstructured text data are preprocessed vectorically using BERT, BiGRU is used to extract the deep features of the text, attention pooling is used to assign the corresponding weights to the extracted deep information, and CapsNet is used to route the right alternative. BBGCAP is a synthetic model by integrating the advantages of BERT, BiGRU, CapsNet, and attention pooling. The experimental results on the cucumber-pest question database show that the proposed method is superior to the methods based on traditional template matching, support vector machines (SVM), and convolutional neural network-long short-term memory (LSTM), and the accuracy rates of precision, recall, and F1 are all above 902.15%. This method provides technical support for intelligent question answering system of crop disease-pests.

Dilated convolution capsule network for apple leaf disease identification

Accurate and rapid identification of apple leaf diseases is the basis for preventing and treating apple diseases. However, it is challenging to identify apple leaf diseases due to their various symptoms, different colors, irregular shapes, uneven sizes, and complex backgrounds. To reduce computational cost and improve training results, a dilated convolution capsule network (DCCapsNet) is constructed for apple leaf disease identification based on a capsule network (CapsNet) and two dilated Inception modules with different dilation rates. The network can obtain multi-scale deep-level features to improve the classification capability of the model. The dynamic routing algorithm is used between the front and back layers of CapsNet to make the model converge quickly. In DCCapsNet, dilated Inception instead of traditional convolution is used to increase the convolution receptive fields and extract multi-scale features from disease leaf images, and CapsNet is used to capture the classification features of changeable disease leaves and overcome the overfitting problem in the training network. Extensive experiment results on the apple disease leaf image dataset demonstrate that the proposed method can effectively identify apple diseases. The method can realize the rapid and accurate identification of apple leaf disease.

Loop Closure Detection Based on Residual Network and Capsule Network for Mobile Robot

Loop closure detection based on a residual network (ResNet) and a capsule network (CapsNet) is proposed to address the problems of low accuracy and poor robustness for mobile robot simultaneous localization and mapping (SLAM) in complex scenes. First, the residual network of a feature coding strategy is introduced to extract the shallow geometric features and deep semantic features of images, reduce the amount of image noise information, accelerate the convergence speed of the model, and solve the problems of gradient disappearance and network degradation of deep neural networks. Then, the dynamic routing mechanism of the capsule network is optimized through the entropy peak density, and a vector is used to represent the spatial position relationship between features, which can improve the ability of image feature extraction and expression to optimize the overall performance of networks. Finally, the optimized residual network and capsule network are fused to retain the differences and correlations between features, and the global feature descriptors and feature vectors are combined to calculate the similarity of image features for loop closure detection. The experimental results show that the proposed method can achieve loop closure detection for mobile robots in complex scenes, such as view changes, illumination changes, and dynamic objects, and improve the accuracy and robustness of mobile robot SLAM.

A Novel LiDAR Data Classification Algorithm Combined CapsNet with ResNet

LiDAR data contain feature information such as the height and shape of the ground target and play an important role for land classification. The effect of convolutional neural network (CNN) for feature extraction on LiDAR data is very significant, however CNN cannot resolve the spatial relationship of features adequately. The capsule network (CapsNet) can identify the spatial variations of features and is widely used in supervised learning. In this article, the CapsNet is combined with the residual network (ResNet) to design a deep network-ResCapNet for improving the accuracy of LiDAR classification. The capsule network represents the features by vectors, which can account for the direction of the features and the relative position between the features. Therefore, more detailed feature information can be extracted. ResNet protects the integrity of information by passing input information to the output directly, which can solve the problem of network degradation caused by information loss in the traditional CNN propagation process to a certain extent. Two different LiDAR data sets and several classic machine learning algorithms are used for comparative experiments. The experimental results show that ResCapNet proposed in this article `improve the performance of LiDAR classification.

Accurate Reconstruction of Image Stimuli From Human Functional Magnetic Resonance Imaging Based on the Decoding Model With Capsule Network Architecture

In neuroscience, all kinds of computation models were designed to answer the open question of how sensory stimuli are encoded by neurons and conversely, how sensory stimuli can be decoded from neuronal activities. Especially, functional Magnetic Resonance Imaging (fMRI) studies have made many great achievements with the rapid development of deep network computation. However, comparing with the goal of decoding orientation, position and object category from human fMRI in visual cortex, accurate reconstruction of image stimuli is a still challenging work. Current prevailing methods were composed of two independent steps, (1) decoding intermediate features from human fMRI and (2) reconstruction using the decoded intermediate features. The new concept of 'capsule' and 'capsule' based neural network were proposed recently. The 'capsule' represented a kind of structure containing a group of neurons to perform better feature representation. Especially, the high-level capsule's features in the capsule network (CapsNet) contains various features of image stimuli such as semantic class, orientation, location, scale and so on, and these features can better represent the processed information inherited in the fMRI data collected in visual cortex. In this paper, a novel CapsNet architecture based visual reconstruction (CNAVR) computation model is developed to reconstruct image stimuli from human fMRI. The CNAVR is composed of linear encoding computation from capsule's features to fMRI data and inverse reconstruction computation. In the first part, we trained the CapsNet model to obtain the non-linear mappings from images to high-level capsule's features, and from high-level capsule's features to images again in an end-to-end manner. In the second part, we trained the non-linear mapping from fMRI data of selected voxels to high-level capsule's features. For a new image stimulus, we can use the method to predict the corresponding high-level capsule's features using fMRI data, and reconstruct image stimuli with the trained reconstruction part in the CapsNet. We evaluated the proposed CNAVR method on the open dataset of handwritten digital images, and exceeded about 10% than the accuracy of all existing state-of-the-art methods on the structural similarity index (SSIM). In addition, we explained the selected voxels in specific interpretable image features to prove the effectivity and generalization of the CNAVR method.