目标视场角对P300-RSVP目标检测系统的影响分析

为了提高P300-RSVP目标检测系统的准确率，研究目标视场角对目标检测系统的影响。对5位被试者采用4种不同视场角的目标作为靶刺激进行实验；对被试者大脑产生的脑电波进行预处理，将目标图片对应的脑电信号进行50次叠加平均，发现目标所占视场角为8°左右时P300的峰值最高；采用结构化判别成分分析（HDCA）对单试次脑电信号进行分类，目标所占视场角为8°左右时的目标探测率平均达到82%以上，高于其他目标视场角对应的目标探测率。     

Functional brain network and multichannel analysis for the P300-based brain computer interface system of lying detection

Deception is a complex cognition process which involves activities in different brain regions. However, most of the ERP based lie detection systems focus on the features of ERPs from few channels. In this study, we designed a multi-channel ERP based brain computer interface (BCI) system for lie detection. Based on this, two new EEG feature selection approaches, bootstrapped geometric difference (BGD) and network analysis were proposed and applied to feature recognition and classification system. Unlike other methods, our approaches focus on the changes of EEGs from different brain regions and the correlation between them. For the test, we focus on visual and auditory stimuli, two groups of subjects went through the test and their EEGs were recorded. For all subjects, BGD of the P300 for all the scalp electrodes combined with SVM classifier showed the average rate of recognition accuracy was 84.4% and 82.2% for visual and auditory modality respectively. Statistical analysis of network features indicated the difference in the two groups were significant and the average accuracy rate reached 88.7% and 83.5% respectively, and the guilty group showed more obvious small-world property than innocent group. The results suggest the BGD and network analysis based approaches combined with SVM are efficient for ERP based expert and intelligent system for detection and evaluation of deception. The combination of these methods and other feature selection approaches can promote the development and application of ERP based lie detection system.     

基于Kmean和ELM的乳腺肿块检测方法

肿块是乳腺癌在X线图像上的一个主要表现。提出了一种肿块自动检测算法。该方法包括四个步骤：在图像预处理阶段,去除背景、标记、胸肌和噪声,图像分割和图像增强;利用Kmean方法找到感兴趣区域（ROI）;提取能够表征肿块的特征;利用极限学习机（Extreme Learning Machine,ELM）分类器去除假阳性,将图像中的肿块和非肿块分离开来。通过对MIAS数据库中乳腺X线图像的测试实验,得到的检测肿块的准确率为93.5%。     

基于单试次脑电解码的类自举法谎言预测研究

基于脑电(Electroencephalogram, EEG)的谎言检测技术依赖于对事件相关电位(Event-related potential, ERP)的有效解码, 当前主要采用手工设计特征进行脑电分析. 近年来, 单试次脑电分类方法取得了长足进步, 其中端到端的脑电分类方法能够实现对脑电的自动特征提取和分类, 但在谎言检测中缺乏研究和应用, 同时存在无法在测谎场景下直接应用的问题. 本研究设计基于复合反应范式(Complex trial protocol, CTP)进行自我面孔信息识别任务的实验, 采集了18 名被试的脑电数据. 研究了不同端到端的单试次ERP分类方法在谎言检测中的应用, 同时针对单试次脑电解码方法无法直接实际应用的问题, 提出了一种类自举算法. 算法基于数据分布假设, 通过对比各类刺激图像被视为探针刺激时所训练模型的性能, 来推断真正的探针刺激. 实验结果表明, 在基于自我面孔信息的CTP的谎言预测中, 所提出的类自举法性能优于传统探针预测方法, 在仅使用少量脑电数据情况下, 可实现准确的谎言预测.     

基于改进原型网络的P300脑电信号检测

从脑电信号中检测P300电位是实现P300脑机接口的关键. 由于不同个体间的脑电信号存在较大差异, 现有的基于深度学习的P300检测方法均需要大量的脑电数据来训练模型. 对于小样本的患者数据, 至今仍没有令人满意的解决方案. 本文提出了一种改进的适用于小样本P300脑电信号检测的原型网络方法. 该模型通过卷积神经网络提...     

基于事件相关电位的脑－机接口系统微弱信号分析方法研究

脑－机接口(BCI,brain computer interface)技术作为一种新型的人机交互方式,近年来受到越来越多的关注。基于听觉刺激模式诱发的事件相关电位P300建立了脑－机接口系统,主要研究微弱P300信号的单导联小样本数据的特征提取和模式识别方法。首先经过预处理和小波变换对脑电信号中的P300成分进行特征提取,建立特征向量,然后使用支持向量机的方法对特征提取结果进行模式分类。对7名受试者进行事件相关电位P300诱发实验,结果表明,系统的分类正确率可达到85％以上,且支持向量机的训练时间都在0.05 s以内。该方法可为脑－机接口的进一步应用奠定基础。     

基于粗糙集的入侵检测方法研究

为了改善入侵检测系统的性能,常采用特征提取的方法精简初始数据,以减轻系统的处理负荷,提高检测速度。本文首先采用粗糙集理论对入侵检测系统进行了形式化描述,以信息熵作为测度对连续数值属性进行离散化,使用知识约简对入侵检测的属性特征进行提取,通过信息增益控制属性特征的约简过程,有效剔除了冗余特征,减少了系统的处理负荷,提高了系统的检测时效。实验证实所提出的方法使系统对于PROBING、DoS等典型攻击的训练时间分别缩短2.8和3.2倍,而检测速度分别提高3.3和3.8倍。     

基于粒子群算法优化支持向量机的模拟电路诊断

为了提高支持向量机网络(SVM)进行模拟电路诊断的准确率,提出了一种基于粒子群(PSO)算法和支持向量机的诊断方法。该方法首先对被测电路的响应信号进行多小波变换,通过归一化处理得到分类能力强的最优故障特征;然后用粒子群算法优化支持向量机的结构参数,实现对不同故障模式分类识别。仿真结果表明,此方法能有效提高模拟电路故障诊断准确率。     

Quantifying target spotting performances with complex geoscientific imagery using ERP P300 responses

Geoscientific data interpretation is a challenging task, which requires the detection and synthesis of complex patterns within data. As a first step towards better understanding this interpretation process, our research focuses on quantitative monitoring of interpreters' brain responses associated with geoscientific target spotting. This paper presents a method that profiles brain responses using electroencephalography (EEG) to detect P300-like responses that are associated with target spotting for complex geoscientific data. In our experiment, eight interpreters with varying levels of expertise and experience were asked to detect features, which are likely to be copper–gold rich porphyry systems within magnetic geophysical data. The target features appear in noisy background and often have incomplete shape. Magnetic images with targets and without targets were shown to participants using the “oddball” paradigm. Event related potentials were obtained by averaging the EEG epochs across multiple trials and the results show delayed P3 response to the targets, likely due to the complexity of the task. EEG epochs were classified and the results show reliable single trial classification of EEG responses with an average accuracy of 83%. The result demonstrated the usability of the P300-like responses to quantify the geoscientific target spotting performances.     

基于退化四元小波变换的纸币识别

针对如何提取纸币图像特征和提高识别率的问题,综合利用退化四元小波变换具有的相位特性,提出一种基于退化四元小波变换的纸币识别方法.该方法首先对采集的纸币图像进行倾斜校正和边缘检测,然后运用退化四元小波对纸币图像进行分解操作,并对分解系数进行统计分析,将每个分解子带系数的能量和标准差作为该纸币图像的特征向量,最后将支持向量机作为分类器对纸币图像进行识别.本文方法在资源约束的嵌入式清分系统上实现,实验结果表明采用本文提出的算法突破了传统纸币识别系统识别率很难再提高的瓶颈,同时能够满足清分系统的实时性要求.     

Remarks on Colquhoun's: “ The Effect of ‘ unwanted ’ Signals on Performance in a Vigilance Task ”

Colquhoun's 1961 experiment is interpreted as emphasizing the discrimination phase of a complex task in which the detection of a signal is followed by the discrimination of one of its features. His conclusion that signal probability determines vigilance performance is supported by research from this laboratory with a simple detection task. In our research the probability is redefined as the ratio of signals to attention-eliciting stimuli, and the latter stimuli must be presented at high rates (15 or more times per minute). His results with the complex task suggest an effect of signal probability on search and scanning patterns during prolonged visual work.     

High resolution time-frequency representation for chirp signals using an adaptive system based on duffing oscillators

This paper presents a novel methodology to estimate the frequency shift in chirp signals with SNRs as low as −17 dB through the use of an adaptive array of Duffing oscillators. The system used here is an array of five Duffing oscillators with each oscillator's response enhanced through a correlation with the reference signal. As a final result, a time-frequency depiction is provided by the Duffing array for further analysis of chirp signals.Using computer simulated experiments, it is found that the analysis of chirp signals with low SNR by means of the Duffing oscillator shows a markedly better performance than the conventional methods of time-frequency analysis. To this end, the results obtained from the proposed Duffing method are compared against some recent techniques in time-frequency analysis.Furthermore, to strengthen the proposed representation, Monte Carlo simulation is used.     

基于方位特征的听觉选择性注意计算模型研究

经典的听觉注意计算模型主要针对声音强度、频率、时间等初级听觉特征进行研究,这些特征不能较好地模拟听觉注意指向性,必须寻求更高级的听觉特征来区分不同声音.根据听觉感知机制,本文基于声源方位特征和神经网络提出了一种双通路信息处理的自下而上听觉选择性注意计算模型.模型首先对双耳信号进行预处理和频谱分析;然后,将其分别送入where通路和what通路,其中where通路用于提取方位特征参数,并利用神经网络提取声源的局部方位特征,接着通过局部特征聚合和全局优化法得到方位特征显著图;最后,根据方位特征显著图提取主导方位并作用于what通路,采用时频掩蔽法分离出相应的主导音.仿真结果表明：该模型引入方位特征作为聚类线索,利用多级神经网络自动筛选出值得注意的声音对象,实时提取复杂声学环境中的主导音,较好地模拟了人类听觉的方位分类机制、注意选择机制和注意转移机制.     

A vague set approach for identifying shot transition in videos using multiple feature amalgamation

Shot boundary detection (SBD) is the preliminary and most significant step in Content Based Video Retrieval (CBVR). As such the effectiveness of a CBVR system depends heavily on reliable detection of shot boundaries. In this work, a simple yet effective technique for amalgamating several distance features extracted from video frames has been proposed. The aim here is to develop a technique which is able to produce a better distance feature from the existing ones by hybridizing several distance metrics. In the proposed model, any number of distance features can be incorporated and fused together. The resultant feature is not only more robust but also immune to features which are inefficient. Robustness of the proposed method is tested by combining several low performing features with the more efficient ones. Several statistical amalgamation functions are also tested for determining the most efficient one in terms of F1 score. The power of vague sets has been harnessed to detect the shot boundaries effectively using the resultant distance feature. The proposed method is proved to be effective by means of the results obtained, which show that multiple feature amalgamation can lead to a hybrid distance feature which performs better than the best feature incorporated for SBD. The proposed technique is analyzed using ANOVA. A comparison with the other existing methods portray the efficacy of the proposed approach. This method can also be applied for other research problems where several features are to be fused together for producing superior results than the ones obtained by individual methods.     

Decision-level fusion based on wavelet decomposition for induction motor fault diagnosis using transient current signal

In this paper, we propose and implement a decision-level fusion model by combining the information of multi-level wavelet decomposition for fault diagnosis of induction motor using transient stator current signal. Firstly, the start-up transient current signals are collected from different faulty motors. Then signal preprocessing is conducted containing smoothing and subtracting to reduce the influence of line frequency in transient current signals. Next, we employ discrete wavelet transform technique to decompose the preprocessed signals into different frequency ranges of products, and then features are extracted from decomposed detail components. Finally, two decision-level fusion strategies, Bayesian belief fusion and multi-agent fusion, are employed. That is, fault features are classified using several classifiers and generated decisions are fused using a specific fusion algorithm. The proposed approach is evaluated by an experiment of fault diagnosis for induction motors. Experiment results show that excellent diagnosis performance can be obtained.     

Robust decentralized actuator fault detection and estimation for large-scale systems using a sliding mode observer

In this paper, robust decentralized actuator fault detection and estimation is considered for a class of non-linear large-scale systems. A sliding mode observer is proposed together with an appropriate coordinate transformation to find the sliding mode dynamics. Then, based on the features of the observer, a decentralized fault estimation strategy is proposed using an equivalent output error injection, and a decentralized reconstruction scheme follows by further exploiting the structure of the uncertainty which is allowed to have non-linear bounds. The estimation and reconstruction signals only depend on the available measured information and thus the proposed strategy can work on-line. The theoretical results which have been obtained are applied to an automated highway system. Simulation shows the feasibility and effectiveness of the proposed scheme.     

基于自相关平方函数与小波变换的基音检测

在背景噪声干扰条件下,研究语音信号的基音周期,提出了一种基于自相关平方函数与小波变换结合的基音检测算法。该算法先用小波变换对带噪语音去噪,然后再求语音的自相关平方函数以突出真实基音周期的峰值,以获取较精确的基音周期。实验结果表明,与传统的自相关法相比,该算法鲁棒性好,具有更高的准确性,且计算复杂度低,利于语音合成和编码的实时处理。     

Detection of Parkinson's disease by Shifted One Dimensional Local Binary Patterns from gait

The Parkinson's disease (PD) is one of the most common diseases, especially in elderly people. Although the previous studies showed that the PD can be diagnosed by expert systems through its cardinal symptoms such as the tremor, muscular rigidity, disorders of movements and voice, it was reported that the presented approaches, which utilize simple motor tasks, were limited and lack of standardization. To achieve a standard approach in PD detection, an approach, which is built on shifted one-dimensional local binary patterns (Shifted 1D-LBP) and machine learning methods, was proposed. Shifted 1D-LBP is built on 1D-LBP, which is sensitive to local changes in a signal. In 1D-LBP the positions of neighbors around center data are constant and therefore, the number of patterns that can be exacted by it is limited. This drawback was solved by Shifted 1D-LBP by changeable positions of neighbors. In evaluation and validation stages, the Gait in Parkinson's Disease (gaitpdb) dataset, which consists of three gait datasets that were recorded in different tasks or experiment protocols, were employed. Statistical features were exacted from formed histograms of gait signals transformed by Shifted 1D-LBP. Whole features and selected features were classified by machine learning methods. Obtained results were compared with statistical features exacted from signals in both time and frequency domains and results reported in the literature. Achieved results showed that the proposed approach can be successfully employed in PD detection from gait. This work is not only an attempt to develop a PD detection method, but also a general-purpose approach that is based on detecting local changes in time ordered signals.     

高分辨率遥感图像投影分析的靠岸舰船检测

目的 高分辨率遥感图像中,靠岸舰船检测有着广泛的应用前景,其主要难点在于舰船与港口陆地在空间上紧邻,在颜色和纹理特征上相似,舰船与港口陆地难以分割。针对这种情况,利用港口岸线平直的几何特点和靠岸舰船多为舷靠的停泊特点,提出一种基于投影分析的靠岸舰船检测方法。方法 首先,对原始图像进行预处理,利用K-means聚类算法与区域生长算法相结合的方式得到海陆分割图像,利用Sobel算子与Otsu分割结合的方式获取边缘图像;然后,通过改进的Hough变换提取直线特征,结合港岸几何特性定位港口岸线;再将海陆分割后的二值图像向沿岸线和垂直岸线两个方向进行投影,根据沿岸线方向投影形态确定和分离并靠舰船,根据垂直岸线方向的投影形态定位舰船目标;最后,利用舰船尺寸、长宽比、最小外接矩形占空比特征去除虚警。结果 在15个港口场景不同分辨率的遥感图像测试集上,本文方法整体检测率达到85.4%,虚警率达17.2%;限定分辨率范围在24 m的情形下,检测率提高到93.5%,虚警率降低至5.3%。结论 本文方法简单有效,无需港口先验信息,适用于多尺度和多方向的靠岸舰船目标检测任务,对不同类型舰船形态差异具有鲁棒性,且能够分离并靠舰船。