Search

Relation extraction (RE) is a crucial step for knowledge graph construction, which aims to extract meaningful relations between entity pairs in plain texts. Very few works have been studied on Chinese relation extraction (CRE) in the military field. Moreover, recent deep neural network-based methods have achieved considerable performance but still suffer from three inherent limitations, including overlapping of entities, imbalanced data and the ambiguity. Therefore, this work investigates a novel Multi-Grained Lattice Transformer (MGLT), which leverages external information of lexicon and word sense tailored for CRE. In MGLT, self-matched lexicon words and related word senses are fused through a cross-transformer mechanism to alleviate the ambiguity in texts. The finally enriched sequence representation in MGLT captures the relatedness between the head entity and the tail one, which is helpful to alleviate the overlapping of entities. Experimental results on two benchmark datasets and a self-developed dataset constructed from online military news show that the proposed MGLT achieves state-of-the-art (SOTA) performance. Compared with other typical baselines, MGLT achieves better area under curve (AUC) and F 1 -score by up to 10.46% and 6.90%, respectively. We further demonstrate the effectiveness of using ensemble learning to fully exploit complementary information from multiple MGLT-based base learners to improve the overall performance for imbalanced data classification on the military dataset. Such results indicate that the proposed ensemble learning model is effective and robust to be applied in practical applications. [ABSTRACT FROM AUTHOR]

The traditional generation of combat simulation scenarios often requires a manual understanding of conceptual scenarios and transformation into simulation scenarios. This method has the problems of long development time and high development threshold. Conceptual scenarios are usually visual Unified Modeling Language (UML) diagrams, so we can use artificial intelligence technology to extract key semantics from them, and automatically map the extracted semantics to simulation scenarios. This method is called the intelligent generation of combat simulation scenarios. To extract the key semantics from conceptual scenarios in UML form, we propose the UML diagram recognition method based on Keypoint Region-based Convolutional Neural Network (R-CNN). This method includes three parts: image character recognizer, primitive object detector, and image semantic extractor. First, we use optical character recognition (OCR) technology to achieve image character recognition. Second, we manually annotate the primitive target-detection dataset and propose a new primitive target-detection model—Keypoint R-CNN. This model considers the direction of connecting lines and realizes the detection of symbols and connecting lines. Third, we propose a targeted combined primitive detection and primitive relationship extraction method to extract the high-level semantics of UML diagrams. Then, we carried out experiments and evaluations on the self-made dataset. Compared with other methods, the F1 score of our method is improved by about 7%, and the Jaccard coefficient is improved by about 10%. Finally, we use a case study to implement the intelligent generation process of combat simulation scenarios using the UML recognition method we proposed. This case shows the operability and efficiency of our method. Our method greatly reduces the labor cost and development threshold of combat simulation scenario generation and improves the development efficiency of the combat simulation system. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) reconstruction of a human head with high precision has promising applications in scientific research, product design and other fields. However, it still faces resistance from two factors. One is inaccurate registration caused by symmetrical distribution of head feature points, and the other is economic burden due to high-accuracy sensors. Research on 3D reconstruction with portable consumer RGB-D sensors such as the Microsoft Kinect has been highlighted in recent years. Based on our multi-Kinect system, a precise and low-cost three-dimensional modeling method and its system implementation are introduced in this paper. A registration method for multi-source point clouds is provided, which can reduce the fusion differences and reconstruct the head model accurately. In addition, a template-based texture generation algorithm is presented to generate a fine texture. The comparison and analysis of our experiments show that our method can reconstruct a head model in an acceptable time with less memory and better effect. [ABSTRACT FROM AUTHOR]

To decode the pilot's behavioral awareness, an experiment is designed to use an aircraft simulator obtaining the pilot's physiological behavior data. Existing pilot behavior studies such as behavior modeling methods based on domain experts and behavior modeling methods based on knowledge discovery do not proceed from the characteristics of the pilots themselves. The experiment starts directly from the multimodal physiological characteristics to explore pilots' behavior. Electroencephalography, electrocardiogram, and eye movement were recorded simultaneously. Extracted multimodal features of ground missions, air missions, and cruise mission were trained to generate support vector machine behavior model based on supervised learning. The results showed that different behaviors affects different multiple rhythm features, which are power spectra of the 𝜃 waves of EEG, standard deviation of normal to normal, root mean square of standard deviation and average gaze duration. The different physiological characteristics of the pilots could also be distinguished using an SVM model. Therefore, the multimodal physiological data can contribute to future research on the behavior activities of pilots. The result can be used to design and improve pilot training programs and automation interfaces. [ABSTRACT FROM AUTHOR]

Technology of brain-computer interface (BCI) provides a new way of communication and control without language or physical action. Brain signal tracking and positioning is the basis of BCI research, while brain modeling affects the treatment analysis of (EEG) and functional magnetic resonance imaging (fMRI) directly. This paper proposes human ellipsoid brain modeling method. Then, we use non-parametric spectral estimation method of time-frequency analysis to deal with simulation and real EEG of epilepsy patients, which utilizes both the high spatial and the high time resolution to improve the doctor's diagnostic efficiency. [ABSTRACT FROM AUTHOR]

This paper improves the algorithm of point cloud filtering and registration in 3D modeling, aiming for smaller sampling error and shorter processing time of point cloud data. Based on collaborative sampling among several Kinect devices, we analyze the deficiency of current filtering algorithm, and use a novel method of point cloud filtering. Meanwhile, we use Fast Point Feature Histogram (FPFH) algorithm for feature extraction and point cloud registration. Compared with the aligning process using Point Feature Histograms (PFH), it only takes 9min when the number of points is about 500,000, shortening the aligning time by 47.1%. To measure the accuracy of the registration, we propose an algorithm which calculates the average distance of the corresponding coincident parts of two point clouds, and we improve the accuracy to an average distance of 0.7mm. In the surface reconstruction section, we adopt Ball Pivoting algorithm for surface reconstruction, obtaining image with higher accuracy in a shorter time. [ABSTRACT FROM AUTHOR]

Deep neural networks have achieved state-of-the-art performance on many object recognition tasks, but they are vulnerable to small adversarial perturbations. In this paper, several extensions of generative stochastic networks (GSNs) are proposed to improve the robustness of neural networks to random noise and adversarial perturbations. Experimental results show that compared to normal GSN method, the extensions using adversarial examples, lateral connections and feedforward networks can improve the performance of GSNs by making the models more resistant to overfitting and noise. [ABSTRACT FROM AUTHOR]

Value function approximation plays an important role in reinforcement learning (RL) with continuous state space, which is widely used to build decision models in practice. Many traditional approaches require experienced designers to manually specify the formulization of the approximating function, leading to the rigid, non-adaptive representation of the value function. To address this problem, a novel Q-value function approximation method named 'Hierarchical fuzzy Adaptive Resonance Theory' (HiART) is proposed in this paper. HiART is based on the Fuzzy ART method and is an adaptive classification network that learns to segment the state space by classifying the training input automatically. HiART begins with a highly generalized structure where the number of the category nodes is limited, which is beneficial to speed up the learning process at the early stage. Then, the network is refined gradually by creating the attached sub-networks, and a layered network structure is formed during this process. Based on this adaptive structure, HiART alleviates the dependence on expert experience to design the network parameter. The effectiveness and adaptivity of HiART are demonstrated in the Mountain Car benchmark problem with both fast learning speed and low computation time. Finally, a simulation application example of the one versus one air combat decision problem illustrates the applicability of HiART. [ABSTRACT FROM AUTHOR]

With the development of computer technique, performance evaluation of complex products is playing an increasingly critical role in ensuring product quality and improving development process. An extensible comprehensive performance evaluation framework with the integration of effective group decision-making algorithms could be a supporting tool to achieve an efficient evaluation process and reduce comprehensive evaluation difficulty. This paper aims to provide a evaluation framework with friendly interactive operation and extensive expansibility, which adopts a multi-expert evaluation approach based on fuzzy, analytical hierarchy process (FAHP) and Dempstere-Shafer (DS) theory (FADS) in order to consider experts' relative importance degree. In addition, an extensible evaluation process and related auxiliary functions are implemented in the framework, including the establishment of an assessment index system, integration and calls of multiple types of testing data preprocessing methods and index assessment methods suitable for small sample data, graphical result display and data analysis, etc. Finally, performance evaluation cases of two models of airborne radar anti-jamming are presented to verify the feasibility and expansibility of our assessment framework. The group decision-making method shows its effectiveness compared with the experimental evaluation results by the FAHP researched method. [ABSTRACT FROM AUTHOR]

The original restricted Boltzmann machines (RBMs) are extended by replacing the binary visible and hidden variables with clusters of binary units, and a new learning algorithm for training deep Boltzmann machine of this new variant is proposed. The sum of binary units of each cluster is approximated by a Gaussian distribution. Experiments demonstrate that the proposed Boltzmann machines can achieve good performance in the MNIST handwritten digital recognition task. [ABSTRACT FROM AUTHOR]