Text summarization aims to offer a highly condensed and valuable information that expresses the main ideas of the text. Most previous researches focus on extractive models. In this work, we put forward a new generative model based on convolutional seq2seq architecture. A hierarchical CNN framework is much more efficient than the conventional RNN seq2seq models. We also equip our model with a copying mechanism to deal with the rare or unseen words. Additionally, we incorporate a hierarchical attention mechanism to model the keywords and key sentences simultaneously. Finally we verify our model on two real-life datasets, GigaWord and DUC corpus. The experiment results verify the effectiveness of our model as it outperforms state-of-the-art alternatives consistently and statistical significantly.

Precise 3D hand pose estimation can be used to improve the performance of human–computer interaction (HCI). Specifically, computer-vision-based hand pose estimation can make this process more natural. Most traditional computer-vision-based hand pose estimation methods use depth images as the input, which requires complicated and expensive acquisition equipment. Estimation through a single RGB image is more convenient and less expensive. Previous methods based on RGB images utilize only 2D keypoint score maps to recover 3D hand poses but ignore the hand texture features and the underlying spatial information in the RGB image, which leads to a relatively low accuracy. To address this issue, we propose a channel fusion attention mechanism that combines 2D keypoint features and RGB image features at the channel level. In particular, the proposed method replans weights by using cascading RGB images and 2D keypoint features, which enables rational planning and the utilization of various features. Moreover, our method improves the fusion performance of different types of feature maps. Multiple contrast experiments on public datasets demonstrate that the accuracy of our proposed method is comparable to the state-of-the-art accuracy.

Since there has been growing concern about the damage that atmospheric leakage and dispersion accidents may have done to human beings, researchers are dedicated to study effective and feasible source estimation methods in chemical plant clusters. In this paper, the safety monitoring of chemical production process is conducted via an unmanned aerial vehicle (UAV) monitoring system. Based on the observed data from this system, a source estimation method incorporating Bayesian inference and Particle Swarm Optimization (PSO) is proposed. Furthermore, the method is extended to discuss the source tracing algorithm using game theory in the UAV system. Finally, a practical case study is carried out to verify the feasibility and credibility of the proposed method. Results show that the method and system are helpful for safety monitoring and risk assessment in a chemical plant cluster.

Modeling of emergency response plan is the basis for reducing the harm and adverse effects of sudden disasters on society. Multi-entity (unit) participate in emergency response plan has high synergy in workers and entities, strong logical relationship, etc. In this paper, the natural disaster emergency response plan is the research object, and the emergency rescue mission is directive, and rescue time is the main line, and model is builded by using the network diagram. This method aims to express all kinds of emergency response plans more flexibly and accurately, and the complex relationship between internal working rooms and the expression of structural networks. At the same time, this paper establishes a task which completion probability model to comprehensively evaluate emergency response capabilities based on time. The emergency response network diagram established in this paper has the characteristics of the network and can be combined with complex network theory for in-depth research.