Object detection based on the multiscale location Enhancement network

For the target detection task,there are two problems in the one-stage network structure of the deep neural network model.First,whether the design of the anchor box hyperparameter is suitable or not will affect the training results of the whole network;second,a large down sampling factor will affect the positioning ability of the target.To solve these problems,this paper proposes a multi-location enhancement network.The structure of the one-stage network model is redesigned,and a better scheme for selecting the super parameters of the anchor frame is proposed.So the efficiency of the first stage network is ensured and the positioning accuracy is better than the previous one.A large number of experiments show that the multi-location enhancement network can achieve a higher positioning accuracy while ensuring real-time performance.The average accuracy of 82.5 is achieved on the public dataset (Pascal VOC 2007).     

Two-Phase Bidirectional Dual-Relay Selection Strategy for Wireless Relay Networks

In this article, we introduce a new bi-directional dual-relay selection strategy with its bit error rate (BER) performance analysis. During the first step of the proposed strategy, two relays out of a set of N relay-nodes are selected in a way to optimize the system performance in terms of BER, based on the suggested algorithm which checks if the selected relays using the max-min criterion are the best ones. In the second step, the chosen relay-nodes perform an orthogonal space-time coding scheme using the two-phase relaying protocol to establish a bi-directional communication between the communicating terminals, leading to a significant improvement in the achievable coding and diversity gain. To further improve the overall system performance, the selected relay-nodes apply also a digital network coding scheme. Furthermore, this paper discusses the analytical approximation of the BER performance of the proposed strategy, where we prove that the analytical results match almost perfectly the simulated ones. Finally, our simulation results show that the proposed strategy outperforms the current state-of-the-art ones.     

A 360-Degree Panoramic Image Inpainting Network Using a Cube Map

Inpainting has been continuously studied in the field of computer vision. As artificial intelligence technology developed, deep learning technology was introduced in inpainting research, helping to improve performance. Currently, the input target of an inpainting algorithm using deep learning has been studied from a single image to a video. However, deep learning-based inpainting technology for panoramic images has not been actively studied. We propose a 360-degree panoramic image inpainting method using generative adversarial networks (GANs). The proposed network inputs a 360-degree equirectangular format panoramic image converts it into a cube map format, which has relatively little distortion and uses it as a training network. Since the cube map format is used, the correlation of the six sides of the cube map should be considered. Therefore, all faces of the cube map are used as input for the whole discriminative network, and each face of the cube map is used as input for the slice discriminative network to determine the authenticity of the generated image. The proposed network performed qualitatively better than existing single-image inpainting algorithms and baseline algorithms.     

Parameter identification of proton exchange membrane fuel cell via Levenberg-Marquardt backpropagation algorithm

It is essential to develop an accurate model of proton exchange membrane fuel cell (PEMFC) for a reliable operation and analysis, in which unknown parameters usually need to be determined. The inherent nonlinear, strong coupling, and diversification of PEMFC model seriously hinder traditional methods to identify the parameters. For the sake of overcoming these thorny obstacles, Levenberg-Marquardt backpropagation (LMBP) algorithm based on artificial neural networks (ANNs) is proposed for PEMFC parameter identification. Furthermore, the performance of LMBP is thoroughly evaluated and compared with four typical meta-heuristic algorithms under three cases. Simulation results indicate that LMBP performs a higher accuracy and faster speed for parameter identification. In particular, accuracy and convergence speed can achieve as much as 99.8% and 95.9% growth via LMBP, respectively.     

A Dynamic Memory Allocation Optimization Mechanism Based on Spark

Spark is a distributed data processing framework based on memory. Memory allocation is a focus question of Spark research. A good memory allocation scheme can effectively improve the efficiency of task execution and memory resource utilization of the Spark. Aiming at the memory allocation problem in the Spark2.x version, this paper optimizes the memory allocation strategy by analyzing the Spark memory model, the existing cache replacement algorithms and the memory allocation methods, which is on the basis of minimizing the storage area and allocating the execution area according to the demand. It mainly including two parts: cache replacement optimization and memory allocation optimization. Firstly, in the storage area, the cache replacement algorithm is optimized according to the characteristics of RDD Partition, which is combined with PCA dimension. In this section, the four features of RDD Partition are selected. When the RDD cache is replaced, only two most important features are selected by PCA dimension reduction method each time, thereby ensuring the generalization of the cache replacement strategy. Secondly, the memory allocation strategy of the execution area is optimized according to the memory requirement of Task and the memory space of storage area. In this paper, a series of experiments in Spark on Yarn mode are carried out to verify the effectiveness of the optimization algorithm and improve the cluster performance.     

基于联合节点行为策略的WSN覆盖控制算法

针对无线传感器网络在对移动目标节点覆盖过程中出现网络能量快速消耗问题，提出了一种基于联合节点行为策略的覆盖算法。根据网络模型建立传感器节点与目标节点从属关系，确定覆盖关联模型；利用概率理论求解邻居节点冗余覆盖度，确定最少传感器节点数量；给出了邻居节点覆盖期望值的求解方法；仿真实验表明，该算法与其他算法在网络覆盖率和网络生存周期两个性能指标上均提升了12.39%和15.01%，从而验证了算法的有效性。     

Distributed two‐stage state estimation with event‐triggered strategy for multirate sensor networks

This paper investigates the state estimation issue for a class of wireless sensor networks (WSNs) with the consideration of limited energy resources. First, a multirate estimation model is established, and then, a new event‐triggered two‐stage information fusion algorithm is developed based on the optimal fusion criterion weighted by matrices. Compared with the existing methods, the presented fusion algorithm can significantly reduce the communication cost in WSNs and save energy resources of sensors efficiently. Furthermore, by presetting a desired containment probability over the interval [0,1] with the developed event‐triggered mechanism, one can obtain a suitable compromise between the communication cost and the estimation accuracy. Finally, a numerical simulation for the WSN tracking system is given to demonstrate the effectiveness of the proposed method.     

一种基于雷达图表示的数值型数据的CNN分类方法

卷积神经网络（convolutional neural networks， CNN）是一种广泛用于分析视觉图像的分类方法.由于数值数据存在着非线性、耦合性等复杂的空间关系，因此基于CNN的数值型数据的研究较少.本文的目的是找到一种可行的方法，将CNN的应用领域扩展到数值数据.于是提出了一种基于雷达图表示的数值型数据的CNN分类方法（Radar-CNN）.该算法首先将数值数据表示成雷达图形式，然后将其输入CNN中构建分类模型.为了进一步研究特征尺度和序列对性能的影响，提出了两种改进算法Rank Radar-CNN和SFS Radar-CNN.为了验证所提算法的有效性，引入TE化工过程数据集进行实验测试并比较，实验结果表明Radar-CNN及其改进算法具有优异的性能.     

基于深度残差学习的自动驾驶道路场景理解

随着道路场景理解技术的快速发展，自主驾驶领域取得了长足的进步。在相关任务中，包括道路分割、分类和车辆检测的实时性和准确性是安全性的一个关键问题。为此，提出了一个具有编/解码器网络结构的基于深度残差学习的方法。一方面，编码器网络结构使用不同层次的残差网络来提取高维中的抽象特征，这些特征在接下来的三个任务中共享使用；另一方面，解码器网络结构采用一种子任务的并行计算机制，即道路分割、车辆检测和道路分类任务同时执行。此外，全卷积神经网络用于对提取的图像特征进行上采样以解决道路分割问题。最终，实验结果表明在保证高精度的前提下处理帧率可达到15 fps以上。