“In-VM”模型的隐藏代码检测模型

Security tools are rapidly developed as network security threat is becoming more and more serious. To overcome the fundamental limitation of traditional host based anti malware system which is likely to be deceived and attacked by malicious codes, VMM based anti malware systems have recently become a hot research field. In this article, the existing malware hiding technique is analyzed, and a detecting model for hidden process based on “In VM” idea is also proposed. Based on this detecting model, a hidden process detection technology which is based on HOOK SwapContext on the VMM platform is also implemented successfully. This technology can guarantee the detecting method not to be attacked by malwares and also resist all the current process hiding technologies. In order to detect the malwares which use remote injection method to hide themselves, a method by hijacking sysenter instruction is also proposed. Experiments show that the proposed methods guarantee the isolation of virtual machines, can detect all malware samples, and just bring little performance loss.     

Classification‐Based Approach for Hybridizing Statistical and Rule‐Based Machine Translation

In this paper, we propose a classification‐based approach for hybridizing statistical machine translation and rule‐based machine translation. Both the training dataset used in the learning of our proposed classifier and our feature extraction method affect the hybridization quality. To create one such training dataset, a previous approach used auto‐evaluation metrics to determine from a set of component machine translation (MT) systems which gave the more accurate translation (by a comparative method). Once this had been determined, the most accurate translation was then labelled in such a way so as to indicate the MT system from which it came. In this previous approach, when the metric evaluation scores were low, there existed a high level of uncertainty as to which of the component MT systems was actually producing the better translation. To relax such uncertainty or error in classification, we propose an alternative approach to such labeling; that is, a cut‐off method. In our experiments, using the aforementioned cut‐off method in our proposed classifier, we managed to achieve a translation accuracy of 81.5% — a 5.0% improvement over existing methods.     

Enhancing optical properties of nanocrystalline silicon films with air exposure

We report the effect of air exposure and deposition temperatures, T_d, on the optical property of nanocrystalline silicon (nc-Si). The nc-Si thin films were investigated by photoluminescence (PL), optical absorption, X-ray diffraction (XRD), Fourier-transform infrared (FTIR) absorption and Raman scattering. Experimental results show the structural change from an amorphous to a nanocrystalline phase at T_d=80 °C. In addition, it suggests that T_d low condition leads to the increase in the density of SiH-related bonds and a decrease in the average grain size, δ. The oxygen absorption peak increases with the air-exposure time. The PL exhibited two peaks at around 1.75–1.78 and 2.1–2.3 eV. The PL increases and blue shifts consistently with the decrease of δ and increase of oxygen content. The first peak may be related to nanocrystallites in nc-Si films and the origin of another one may be due to defect-related oxygen. Thus, by the plasma-enhanced chemical vapor deposition (PECVD) technique at low T_d, we can produce the nc-Si films with different grain sizes, causing the corresponding luminescent properties. The new method processes advantages of low deposition temperature and effective oxidation of nc-Si on inexpensive substrates, thus making it more suitable for developing low-cost array or flexible nc-Si optoelectronic devices.     

基于模式间混淆关系自适应构建层次化分类器

为了解决层次化分类器的设计难点——子分类器的层属关系及其内部组成的确定,本文首先定义了模式间混淆关系,用于描述不同模式在判决域中的相互作用;进而提出了基于混淆矩阵度量模式间混淆关系的方法。设计并实现了多模式混淆关系分析机MPCRAM,将有师指派和无师自组两种常用的模式重组方法有机结合,遵循Fisher准则,自适应地产生层次化分类器结构。大量综合测试证实了该方法有效、实用,可显著提高分类器的识别性能和稳健性。     

A Capacitor Voltage Clamped Dual Half-Bridge Series-Resonant Inverter for Home Cooking Applications

An induction heating appliance used for cooking includes more than one inductor, each being controlled by a separate inverter system. The main aim of this paper is to control each coil separately at a different frequency and power output by using the same inverter system. A working coil of two parts has been designed practically and a computer simulation has been carried out, using practical coil parameters. Each part of the coil has been operated at a different frequency and power output, which allows the use of vessels of two different diameters while obtaining a high coupling factor for both conditions. This also increases the efficiency of the system and improves power quality. The proposed topology can be applied to induction hotplates made up of several inductors in which the power and frequency must be separately regulated.     

基于Gabor小波和支持向量机的人脸识别方法

基于Gabor小波在图像表征方面的优越性,提出了将Gabor小波和支持向量机(SVM)相结合用于人脸识别的方案。用Gabor小波对人脸图像进行特征提取,再利用SVM策略对特征向量进行分类识别,实验的仿真结果验证了本算法的有效性。     

Machine learning in vehicular networking: An overview

As vehicle complexity and road congestion increase, combined with the emergence of electric vehicles, the need for intelligent transportation systems to improve on-road safety and transportation efficiency using vehicular networks has become essential. The evolution of high mobility wireless networks will provide improved support for connected vehicles through highly dynamic heterogeneous networks. Particularly, 5G deployment introduces new features and technologies that enable operators to capitalize on emerging infrastructure capabilities. Machine Learning (ML), a powerful methodology for adaptive and predictive system development, has emerged in both vehicular and conventional wireless networks. Adopting data-centric methods enables ML to address highly dynamic vehicular network issues faced by conventional solutions, such as traditional control loop design and optimization techniques. This article provides a short survey of ML applications in vehicular networks from the networking aspect. Research topics covered in this article include network control containing handover management and routing decision making, resource management, and energy efficiency in vehicular networks. The findings of this paper suggest more attention should be paid to network forming/deforming decision making. ML applications in vehicular networks should focus on researching multi-agent cooperated oriented methods and overall complexity reduction while utilizing enabling technologies, such as mobile edge computing for real-world deployment. Research datasets, simulation environment standardization, and method interpretability also require more research attention.     

基于亮度检测检测和SVM的人脸表情识别算法

针对包含表情信息的静态图像,提出基于皮肤检测和SVM的人脸表情识别算法。首先根据先验知识,并使用皮肤检测和积分投影相结合定位眉毛眼睛区域和嘴巴区域,自动分割出表情子区域。接着,对分割出的表情子区域进行Gabor小波特征提取,在利用Fisher线性判别对特征进行降维,去除冗余和相关。最后利用支持向量机对人脸表情进行分类。用该算法在日本表情数据库上进行测试,获得了较高的识别准确率。证明了该算法的有效性。     

基于改进的蛙跳算法与支持向量机的实用语音情感识别

支持向量机是一种基于统计学习理论的新型机器学习算法,在高维特征空间中寻找最优分类超平面,具有很好的分类精度和泛化性能。支持向量机的训练需要求解一个带约束的二次规划问题,针对数据规模很大情况下经典训练方法变得很困难的缺点,提出一种基于改进混合蛙跳算法的支持向量机分类器参数优化方法,既提高了混合蛙跳算法的收敛速度和精度,又能借助混合蛙跳算法的全局随机搜索能力,为支持向量机参数的优化选择提供一条有效途径。本文提取情感语句的韵律特征、音质特征和混沌特征参数,提出一种基于改进蛙跳算法的数据融合方法,并利用基于改进蛙跳算法的支持向量机进行实用语音情感的识别研究。在实验中比较了PCA方法、BP神经网络和数据融合方法用于语音情感识别的识别率,研究结果表明本文所提的各项改进机制能有效提升情感识别率,为实用语音情感的识别提供一种新方法和新思路。      

量子粒子群和最小二乘支持向量机相结合的网络异常检测

为了提高网络安全性的异常入侵检测的准确率,提出一种量子粒子群算法（QPSO）优化最小二乘支持向量机（LSSVC）的网络异常检测方法（QPSO-LSSVC）.首先利用量子粒子群处算法对LSSVC模型参数进行搜索,选出最优参数,然后采用泛化性能力优异的LSSVC对网络入侵进行建模和检测.选取KDDCUP99数据对QPSO-LSSVC性能进行测试,实验结果表明,QPSO-LSSVC提高了网络异常检测准确率,降低了误报率,为网络安全提供了有效保证.