基于区域结构特征的城区LiDAR数据快速分类

机载激光雷达能够及时准确地获取大量具有精确三维位置信息的三维点云数据,在数字城市、森林防火、智能交通等领域有着广泛的应用。城市中心区域的三维点云数据往往会因为高大树木或植被的遮挡,造成建筑物等人造目标识别特别困难。本文通过直接的二次多项式拟合方式提取高大树木等植被与建筑物目标典型局部区域的区域信息,构建区域目标敏感的结构特征,进而,通过模糊逻辑即可完成三维点云数据的建筑物目标敏感的分类任务。实验结果表明,该方法能够快速有效地实现较大尺度范围内LiDAR点云数据的分类,具有较好的应用前景和推广能力。     

An improved model training method for residual convolutional neural networks in deep learning

Multimedia Tools and Applications - Residual convolutional neural network (R-CNN) has become a promising method for image recognition in deep learning applications. The application accuracy, as a...     

LogGAN: a Log-level Generative Adversarial Network for Anomaly Detection using Permutation Event Modeling

Information Systems Frontiers - System logs that trace system states and record valuable events comprise a significant component of any computer system in our daily life. Each log contains...     

A Performance Evaluation of Classic Convolutional Neural Networks for 2D and 3D Palmprint and Palm Vein Recognition

Palmprint recognition and palm vein recognition are two emerging biometrics technologies. In the past two decades, many traditional methods have been proposed for palmprint recognition and palm vein recognition, and have achieved impressive results. However, the research on deep learning-based palmprint recognition and palm vein recognition is still very preliminary. In this paper, in order to investigate the problem of deep learning based 2D and 3D palmprint recognition and palm vein recognition in-depth, we conduct performance evaluation of seventeen representative and classic convolutional neural networks (CNNs) on one 3D palmprint database, five 2D palmprint databases and two palm vein databases. A lot of experiments have been carried out in the conditions of different network structures, different learning rates, and different numbers of network layers. We have also conducted experiments on both separate data mode and mixed data mode. Experimental results show that these classic CNNs can achieve promising recognition results, and the recognition performance of recently proposed CNNs is better. Particularly, among classic CNNs, one of the recently proposed classic CNNs, i.e., EfficientNet achieves the best recognition accuracy. However, the recognition performance of classic CNNs is still slightly worse than that of some traditional recognition methods.

     

TP-FER：基于优化卷积神经网络的三通道人脸表情识别方法

针对人脸五官在表达不同情绪时所起的作用不同,利用单一的卷积神经网络对人脸面部特征进行特征提取和表情识别可能会导致提取表情关键特征信息时聚焦性不够,而仅对眼部或者嘴部等重点部位进行特征提取,又有可能造成特征提取不够充分的问题,提出了一种基于优化卷积神经网络的三通道人脸表情识别方法TP-FER(tri-path networks for facial expression recognition).该方法基于构建的卷积神经网络训练,采用三个输入渠道,分别聚焦面部、眼部和嘴部区域进行特征提取和表情判别,最后采用基于决策层的融合技术将三个渠道的识别结果进行相对多数投票决策,获取整体最优识别率.将此方法应用于JCK+数据集和自建数据集上进行了实验判别分析,结果表明该方法在两个数据集上均提高了整体表情识别率.该方法既考虑了脸部整体特征的提取,又兼顾了某些表情主要聚焦在眼部、嘴部表达的特性,相互辅助,整体提高了表情的识别率;该方法也能对神经心理学研究提供数据支持.     

优化强化学习路径特征分类的脉象识别法

脉象识别是中医诊断的重要手段之一。长期以来,依据个人经验进行的脉诊制约了中医的推广与发展。因此,利用传感设备进行脉象识别的研究正在逐步展开。针对神经网络识别脉象的相关研究中,存在需要大量训练数据集,以及存在处理“黑箱”和时间花销较大等问题,在强化学习的框架下,提出了一种采用马尔可夫决策和蒙特卡罗搜索的脉象图分析法。首先依据中医理论对特定的脉象进行路径分类,然后在此基础上为不同的路径选择代表性特征,最终通过对代表性特征的阈值对比完成对脉象的识别。实验结果表明,所提方法可缩减训练时间和所需资源,并可保留完整的经验轨迹;且在提高脉象识别的准确率的同时,还可解决数据处理过程中的“黑箱”问题。     

基于行波函数的仿蠕虫移动机器人驱动信号统一表征方法

提出了基于行波函数的仿蠕虫移动机器人驱动信号统一表征方法.首先,针对连续型仿蠕虫移动机器人,推导了基于行波函数的驱动信号表达式,并提出了驱动信号波形生成函数的构造方法.然后,针对多单元仿蠕虫移动机器人,修正了基于行波函数的驱动信号表达式,并证明了多单元机器人的驱动信号表达式可以转化为连续型机器人的驱动信号表达式.最后,简单介绍了当存在以不同波速传播的驱动信号时和当不同部分上的驱动信号波形生成函数不相同时的驱动信号表达式.将本文提出的方法应用于一个连续型仿蠕虫移动机器人和两个多单元仿蠕虫移动机器人,新驱动信号表征方法和原驱动信号表征方法得到了相同的结果,表明本文方法具有很强的适用性.     

基于Attention-DenseNet-BC的恶意软件家族分类方法

恶意软件是互联网最严重的威胁之一.现存的恶意软件数据庞大,特征多样.卷积神经网络具有自主学习的特点,可以用来解决恶意软件特征提取复杂、特征选择困难的问题.但卷积神经网络连续增加网络层数会引起梯度消失,导致网络性能退化、分类准确率较低.针对此问题,提出了一种适用于恶意软件图像检测的Attention-DenseNet-BC模型.首先结合DenseNet-BC网络和注意力机制(attention mechanism)构建了Attention-DenseNet-BC模型,然后将恶意软件图像作为模型的输入,通过对模型进行训练和测试得到检测结果.实验结果表明,相比其他深度学习模型,Attention-DenseNet-BC模型可以取得更好的分类结果.在Malimg公开数据集上该模型取得了较高的分类精确率.     

New Robust Stability Criteria for Lur’e Systems with Time-varying Delays and Sector-bounded Nonlinearities

This paper deals with a robust stability problem for uncertain Lur’e systems with time-varying delays and sector-bounded nonlinearities. An improved delay-dependent robust stability criterion is proposed via a modified Lyapunov-Krasovskii functional (LKF) approach. Firstly, a modified LKF consisting of delay-dependent matrices and double-integral items under two delay subintervals is constructed, thereby making full use of the delay and its derivative information. Secondly, the stability criteria can be expressed as convex linear matrix inequality (LMI) via the properties of quadratic function application. Thirdly, to further reduce the conservatism of stability criteria, the quadratic generalized free-weighting matrix inequality (QGFMI) is used. Finally, some numerical examples, including the Lur’e system and the general linear time-delayed system, are presented to show the improvement of the proposed approach.

     

Modeling and Control of Hybrid-driven Gliding Motion for an Underwater Gliding Snake-like Robot

International Journal of Control, Automation and Systems - An underwater gliding snake-like robot (UGSR) combines the advantages of an underwater glider (UG) and an underwater snake-like robot...