跨模态医学图像预测综述

医学影像技术与设备的进步在生物医学领域的各项研究中发挥着重要作用.跨模态医学图像预测旨在由一种模态图像预测另一种模态图像.本文详细综述了由MRI预测CT图像、7T-Like图像重构、PET预测及其他医学模态预测研究,阐述了各类模态预测的必要性及存在的挑战,说明各类预测方法的特点并进行性能比较,最终得出结论：基于深度学习的跨模态预测在预测精度和预测时间两方面更具优势.     

基于霾层学习的单幅图像去雾算法

针对传统去雾算法出现色彩失真、去雾不完全、出现光晕等现象,本文提出了一种基于霾层学习的卷积神经网络的单幅图像去雾算法.首先,依据大气散射物理模型进行理论推导,本文设计了一种能够直接学习和估计有雾图像和霾层图像之间的映射关系的网络模型.采用有雾图像作为输入,并输出有雾图像与无雾图像之间的残差图像,随后直接从有雾图像中去除此霾层图像,即可恢复出无雾图像.残差学习的引入,使得网络来直接估计初始霾层,利用相对大的学习率,减少计算量,加快收敛过程.再利用引导滤波进行细化,使得恢复出的无雾图像更接近真实场景.本文对不同雾浓度的有雾图片的去雾效果进行测试,并与当前主流深度学习去雾算法及其他经典算法进行对比.实验结果显示,本文设计的卷积神经网络模型在图像去雾的应用,不论在主观效果还是客观指标上,都有优势.     

具有双重稀疏机制的在线学习算法

针对大数据背景下数据分类问题,已有的在线学习算法通常引入L₁范数正则化增强预测模型的稀疏性,但单一的正则化约束不能高效的获取稀疏模型.基于此,提出了一种具有双重稀疏机制的在线学习算法（an online learning algorithm with dual sparse mechanisms,DSOL）.在DSOL算法中,一方面利用L_1/2正则化项约束目标函数以增强预测模型的稀疏性,提高算法的泛化性能.另一方面用改进的梯度截取法对数据特征进行选择,有效稀疏化预测模型.通过L_1/2正则化与改进的梯度截取策略的有机融合,有效利用了历史数据信息,提高了算法分类数据的性能.通过与另4种代表性稀疏在线学习算法在9个公开数据集的实验对比表明DSOL算法对数据分类的准确性更高.     

Deep reinforcement learning based resource allocation algorithm in cellular networks

In order to solve multi-objective optimization problem,a resource allocation algorithm based on deep reinforcement learning in cellular networks was proposed.Firstly,deep neural network (DNN) was built to optimize the transmission rate of cellular system and to complete the forward transmission process of the algorithm.Then,the Q-learning mechanism was utilized to construct the error function,which used energy efficiency as the rewards.The gradient descent method was used to train the weights of DNN,and the reverse training process of the algorithm was completed.The simulation results show that the proposed algorithm can determine optimization extent of optimal resource allocation scheme with rapid convergence ability,it is obviously superior to the other algorithms in terms of transmission rate and system energy consumption optimization.     

视觉注意力检测技术研究综述

近年来,为实现服务机器人智能人性化的人机交互、用户认知障碍诊断等,视觉注意力(Visual Focus of Attention,VFOA)检测技术已成为国内外的热点研究课题。重点分析了该技术的流程及相关方法实施细节,给出了目前VFOA检测研究时使用到的数据集情况,并对视觉注意力检测技术的应用场景进行了梳理。通过对当前视觉注意力检测系统优缺点的分析,指出了该技术的研究难点与未来研究方向。     

Bidirectional authentication key agreement protocol supporting identity’s privacy preservation based on RLWE

In order to solve the problem of identity privacy preservation between two participants involved when implementing authenticated key agreement protocol,a bidirectional authenticated key agreement protocol against quantum attack based on C commitment scheme was proposed.Through the design of C commitment function,the real identity information of two participants involved was hidden.Based on RLWE difficult problem,under the premise to ensure identity anonymity,this protocol not only completed two-way identity authentication,but also ensured the integrity of the transmitted message,furthermore,the shared session key was negotiated.After been analyzed,in terms of protocol’s execution efficiency,only two rounds of message transmission were needed to complete anonymous two-way authentication and key agreement in the proposed scheme.Compared with Ding’s protocol,the length of public key was reduced by nearly 50%.With regard to security,the protocol could resist forgery,replay,key-copy,and man-in-the-middle attacks.It is proved that the proposed protocol satisfies the provable security under the eCK model.At the same time,the protocol is based on the RLWE problem of lattices,and can resist quantum computing attacks.     

主动学习半监督聚类入侵检测算法

针对聚类的入侵检测算法误报率高的问题,提出一种主动学习半监督聚类入侵检测算法.在半监督聚类过程中应用主动学习策略,主动查询网络中未标记数据与标记数据的约束关系,利用少量的标记数据生成正确的样本模型来指导大量的未标记数据聚类,对聚类后仍未能标记的数据采用改进的K-近邻法进一步确定未标记数据的类型,实现对新攻击类型的检测.实验结果表明了算法的可行性及有效性.     

三合板半圆筒激光切割机动态特性分析

针对三合板半圆筒激光切割机,对其θ轴系的机电传动装置进行了详细的分析,将其机械传动系统中各轴及相应齿轮的转动惯量、阻尼系数、扭转刚度折算到电机主轴上,在机电耦合基础上,建立了θ轴系动态特性的数学模型。采用MATLAB软件的SIMULINK仿真模块进．行θ轴系动态特性的仿真,分析了θ轴系传动比、电感系数、扭转刚度等参数对...     

高速网络环境下的P2P流媒体业务分析和识别方法

The growing P2P streaming traffic brings a variety of problems and challenges to ISP networks and service providers.A P2P streaming traffic classification method based on sampling technology is presented in this paper.By analyzing traffic statistical features and network behavior of P2P streaming,a group of flow characteristics were found,which can make P2P streaming more recognizable among other applications.Attributes from Netflow and those proposed by us are compared in terms of classification accuracy,a...     

投影光刻机中PDP-11主控制计算机系统的替换

介绍了针对早期的投影光刻机存在PDP-11计算机速度慢,控制系统难操作的问题,利用普通PC机通过GPIB卡替换了PDP-11计算机,使用VB语言编写的程序替换了主控制系统程序。