Emotion-cause pair extraction (ECPE), which aims at simultaneously extracting emotion-cause pairs that express emotions and their corresponding causes in a document, plays a vital role in understanding natural languages. Considering that a cause usually appears around its corresponding emotion, we construct a pair graph and a Pair Graph Convolutional Network (PairGCN) to model dependency relations among local neighborhood candidate pairs. Moreover, in our proposed graph, there are three types of dependency relations and each type of dependency relations has its own way to propagate contextual information. Experiments on a benchmark Chinese emotion-cause pair extraction corpus demonstrate the effectiveness of the proposed model.
Uncertainty extremely interferes with the execution of farm machinery operation. Treating uncertainties is especially important for machinery cooperatives providing social service since they face more uncertain influence factors (UIFs) than family farms. Under social service circumstance, uncertainties may arise from participants and environments. Classification and evaluation of UIFs were studied in this research. According to the production system, 32 UIFs are defined and classified into six categories, which include supply, demand, interactivity, nature, society and others. Uncertainty composite index (UCI) is defined to evaluate the importance of UIFs, which is the square root of the product of occurrence frequency (OF) and impact degree (ID) calculated from the well-designed questionnaire responded by farm machinery operators. UCI is divided into five ranks based on normalization distribution test to illustrate the level of importance. Results from questionnaire showed that natural UIFs have an extreme impact on farm operation, UIFs of the demand and the supply have a serious influence on farm operation, UIFs of interactivity cannot be ignored, and social UIFs have a weak impact on farm operations. This study discovered the uncertainty problems under the specific circumstance of farm machinery service, which may provide a theoretical basis and potential methods for risk management of machinery cooperatives.
With advances in precision agriculture, autonomous agricultural machines can reduce human labor, optimize workflow, and increase productivity. Accurate and reliable obstacle-detection and avoidance systems are essential for ensuring the safety of automated agricultural machines. Existing LiDAR-based obstacle detection methods for the farmland environment process the point clouds via manually designed features, which is time-consuming, labor-intensive, and weak in terms of generalization. In contrast, deep learning has a powerful ability to learn features autonomously. In this study, we attempted to apply deep learning in LiDAR-based 3D obstacle detection for the farmland environment. In terms of perception hardware, we established a data acquisition platform including LiDAR, a camera, and a GNSS/INS on the agricultural machine. In terms of perception method, considering the different agricultural conditions, we used our datasets to train an effective 3D obstacle detector, known as Focal Voxel R-CNN. We used focal sparse convolution to replace the original 3D sparse convolution because of its adaptable ability to extract effective features from sparse point cloud data. Specifically, a branch of submanifold sparse convolution was added to the upstream of the backbone convolution network; this adds weight to the foreground point and retains more valuable information. In comparison with Voxel R-CNN, the proposed Focal Voxel R-CNN significantly improves the detection performance for small objects, and the AP in the pedestrian class increased from 89.04% to 92.89%. The results show that our model obtains an mAP of 91.43%, which is 3.36% higher than the base model. The detection speed is 28.57 FPS, which is 4.18 FPS faster than the base model. The experiments show the effectiveness of our model, which can provide a more reliable obstacle detection model for autonomous agricultural machines.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.