基于改进的BP算法的舰载C4I威胁判断模型

为解决传统舰载C4I威胁判断模型的不足,寻求适应信息化作战要求的舰载C4I威胁判断模型,将神经网络引入舰载C4I系统,提出了基于BP神经网络的威胁判断模型,并对BP算法进行了改进;通过Matlab仿真计算,结果表明该方法计算速度快、精度高.     

Real-time prediction of projectile penetration to laminates by training machine learning models withfinite element solver as the trainer

Studies on ballistic penetration to laminates is complicated, but important for design effective protection of structures. Experimental means of study is expensive and can often be dangerous. Numerical simu-lation has been an excellent supplement, but the computation is time-consuming. Main aim of this thesis was to develop and test an effective tool for real-time prediction of projectile penetrations to laminates by training a neural network and a decision tree regression model. A large number of finite element models were developed;the residual velocities of projectiles fromfinite element simulations were used as the target data and processed to produce sufficient number of training samples. Study focused on steel 4340tpolyurea laminates with various configurations. Four different 3D shapes of the projectiles were modeled and used in the training. The trained neural network and decision tree model was tested using independently generated test samples using finite element models. The predicted projectile velocity values using the trained machine learning models are then compared with thefinite element simulation to verify the effectiveness of the models. Additionally, both models were trained using a published experimental data of projectile impacts to predict residual velocity of projectiles for the unseen samples. Performance of both the models was evaluated and compared. Models trained with Finite element simulation data samples were found capable to give more accurate predication, compared to the models trained with experimental data, becausefinite element modeling can generate much larger training set, and thus finite element solvers can serve as an excellent teacher. This study also showed that neural network model performs better with small experimental dataset compared to decision tree regression model.     

神经计算机并行模拟结构

神经网络实现技术是神经网络研究的一个极重要的领域。本文首先分析了神经网络模拟对并行计算机系统的要求,认为影响神经网络计算机速度和容量提高的主要因素是单个处理单元的速度、单个处理单元的局部存储器的容量以及互连网络的通信带宽。要提高模拟神经计算机的速度和容量,就要有相应的并行结构来支持。在定量的需求分析的基础上,本文还提出了一种模拟神经计算机的并行结构。     

神经网络能力研究

文献[1]～[3]中研究了神经网络的能力—存储能力。但我们认为神经网络的能力应包括存储能力和计算能力两个方面。本文对神经网络的存储能力和计算能力进行定量分析,并得出了许多有益的结论。     

污水处理过程软测量系统辅助变量的选择方法

辅助变量的选择包括变量类型、数量及检测点的选择,是软测量建模的第一步,直接关系到软测量质量的好坏.针对活性污泥法,从微生物生长繁殖的角度出发,探讨了各要素对于微生物生长活动能力的影响及其相互关系,通过影响力大小及相互间耦合性的复杂程度选取辅助变量的原则,完成了污水处理辅助变量类型的初选,并对辅助变量的精选进行了讨论.     

External security determinants of Greek military expenditure: An empirical investigation using Neural networks

Greece has regularly ranked as the country with the highest defence burden in NATO and the European Union. Over the past decades she has allocated an averatge 6% of GDP to defence yearly. This study using neural networks examines the external security determinants of Greek military expenditure in the context of the ongoing Greek‐Turkish conflict.     

论智能控制（IC）在水面兵器中的应用

对智能控制的应用情况、控制特点、基本型式及其在应用中有待解决的若干问题进行了论述。     

The SSA-BP-based potential threat prediction for aerial target considering commander emotion

The target's threat prediction is an essential procedure for the situation analysis in an aerial defense system. However, the traditional threat prediction methods mostly ignore the effect of commander's emotion. They only predict a target's present threat from the target's features itself, which leads to their poor ability in a complex situation. To aerial targets, this paper proposes a method for its potential threat prediction considering commander emotion (PTP-CE) that uses the Bi-directional LSTM (BiLSTM) network and the backpropagation neural network (BP) optimized by the sparrow search algorithm (SSA). Furthermore, we use the BiLSTM to predict the target's future state from real-time series data, and then adopt the SSA-BP to combine the target's state with the commander's emotion to establish a threat prediction model. Therefore, the target's potential threat level can be obtained by this threat prediction model from the predicted future state and the recognized emotion. The experimental results show that the PTP-CE is efficient for aerial target's state prediction and threat prediction, regardless of commander's emotional effect.     

一种基于模糊竞争网络的主动声纳目标分类器

提出了一种基于模糊竞争网络的主动声纳目标分类器。该分类器结构简单,学习速度快,仅用少量样本进行训练便可获得良好的推广性能．便于实时学习和应用。通过对模式属于各类别的隶属度的分析,可以知道判决的可靠性,具有较好的应用价值。     

Multi-scale traffic vehicle detection based on faster R-CNN with NAS optimization and feature enrichment

It well known that vehicle detection is an important component of the field of object detection. However, the environment of vehicle detection is particularly sophisticated in practical processes. It is compara-tively difficult to detect vehicles of various scales in traffic scene images, because the vehicles partially obscured by green belts, roadblocks or other vehicles, as well as influence of some low illumination weather. In this paper, we present a model based on Faster R-CNN with NAS optimization and feature enrichment to realize the effective detection of multi-scale vehicle targets in traffic scenes. First, we proposed a Retinex-based image adaptive correction algorithm (RIAC) to enhance the traffic images in the dataset to reduce the influence of shadow and illumination, and improve the image quality. Second, in order to improve the feature expression of the backbone network, we conducted Neural Architecture Search (NAS) on the backbone network used for feature extraction of Faster R-CNN to generate the optimal cross-layer connection to extract multi-layer features more effectively. Third, we used the object Feature Enrichment that combines the multi-layer feature information and the context information of the last layer after cross-layer connection to enrich the information of vehicle targets, and improve the robustness of the model for challenging targets such as small scale and severe occlusion. In the imple-mentation of the model, K-means clustering algorithm was used to select the suitable anchor size for our dataset to improve the convergence speed of the model. Our model has been trained and tested on the UN-DETRAC dataset, and the obtained results indicate that our method has art-of-state detection performance.