基于二阶C0复杂度的癫痫发作预测

癫痫发作的预测是近年来在临床医学和神经系统科学研究领域中备受关注的问题。如果癫痫发作能够被可靠地预测,则可以提前采取有效的临床预防措施,从而能较大程度地改善癫痫患者的生活质量。文章提出了一种基于二阶C0复杂度的预测算法用于预测癫痫发作。该算法通过分析癫痫患者颅内脑电信号的二阶C0复杂度,利用发作前期复杂度曲线的变化特征预测癫痫发作。作者运用该算法对21组癫痫病人87次发作的临床颅内脑电数据和4组大鼠4次发作的颅内脑电数据进行分析计算,预测准确率分别为94.3%和100%。实验结果表明该算法可以有效地预测癫痫发作,具有潜在的重要临床应用价值。     

一种基于支持向量机技术的癫痫脑电棘尖波识别方法

支持向量机是一种基于统计学习理论的新型学习机。文章提出一种基于支持向量机的癫痫脑电特征提取与识别方法,充分发挥其泛化能力强的特点,在与神经网络方法的比较中,表现出较低的漏检率和较好的鲁棒性,有深入研究的价值和良好的应用前景。     

基于脑电信号识别采集的假肢控制系统

本文介绍了脑电信号（EEG）的模式识别和步骤,分析了EEG采集领域的发展和医学原理。通过研究脑电信号和假肢运动的联系,总结脑电控制假肢的可行性结论。设计出从头皮电极到模／数转换器的基于脑电信号识别采集的假肢控制系统,能够满足脑电假肢的各种要求。     

非线性动力学在脑电信号分析中的应用

EEG是由大脑产生的非线性时间序列,体现出混沌行为。近年来迅速发展的非线性动力学理论为脑电信号分析开创了一个新的领域。本文综述了近年来非线性动力学在脑电信号研究中（睡眠阶段,麻醉深度,认知过程,精神分裂,痴呆及癫痫）的进展,以期对脑神经动力学有更好的理解。     

基于思维脑电信号的假手的研究

本文主要研究利用思维脑电信号来控制假手动作。采用小波变换对思维脑电信号进行分解,选取合适的子带信号并提取相应能量特征,组成特征向量输入BP神经网络进行分类识别。整个信号处理过程在LabVIEW软件平台上实现,并利用其串口通信模块输出控制指令来控制假手的张开和闭合。     

基于EEG信号分析处理的癫痫预测研究

癫痫是神经系统的常见病,特点是大脑神经细胞群反复超同步放电,从而引起突发性的脑功能紊乱.由于癫痫发作具有突然性,发作时患者常伴有意识丧失,癫痫的发作常造成患者意外的伤害.如能对癫痫发作进行有效的预测,就可在发作前对患者采取必要的保护措施,从而减少患者受到伤害的风险.癫痫预测的研究也对认识癫痫的发病机制及开发新的治疗方法提供依据.本文介绍了癫痫发作预测常用的方法,研究现状和存在的问题.     

基于多特征融合的多分类运动想象脑电信号识别研究

针对目前多分类运动想象脑电识别存在特征提取单一、分类准确率低等问题,提出一种多特征融合的四分类运动想象脑电识别方法来提高识别率。对预处理后的脑电信号分别使用希尔伯特-黄变换、一对多共空间模式、近似熵、模糊熵、样本熵提取结合时频—空域—非线性动力学的初始特征向量,用主成分分析降维,最后使用粒子群优化支持向量机分类。该算法通过对国际标准数据集BCI2005 Data set IIIa中的k3b受试者数据经MATLAB仿真处理后获得93.30%的识别率,均高于单一特征和其它组合特征下的识别率。分别对四名实验者实验采集运动想象脑电数据,使用本研究提出的方法处理获得了72.96%的平均识别率。结果表明多特征融合的特征提取方法能更好的表征运动想象脑电信号,使用粒子群支持向量机可取得较高的识别准确率,为人脑的认知活动提供了一种新的识别方法。     

癫痫病人发作时及术前术后护理

癫痫是神经系统发作性疾病。约80％患者得不到正确诊断及治疗,使大部分患者长期反复发作,给患者及家庭造成严重的精神负担和经济负担。     

基于PSoC的脑电信号采集系统的设计

脑电信号是一种很重要的生物医学信号,它是临床医学诊断和脑科学研究的一种重要手段。本文介绍了基于Cypress PSoC~(TM)可编程片上系统的脑电信号采集系统的整个设计过程,包括硬件组成和软件设计方法。通过PSoC芯片特有的可编程模拟系统和数字系统,可以把大量的外围器件集成到芯片的内部,从而提高了硬件系统的集成度和可靠性;加上功能强大的PSOC Designer集成开发环境,提高了开发效率,而且系统的软硬件升级也更加容易了。     

I131内放射治疗对成人恶性脑胶质瘤癫痫发作的影响

目的:探讨内放射治疗对胶质瘤引起的癫痫的影响.方法:回顾性分析2004年后利用I131内放射治疗的成人幕上恶性脑胶质瘤合并有癫痫发作的患者23例,统计其在治疗前1月及治疗后1月、2月时的癫痫发作频率和类型,并分析肿瘤体积变化与发作频率变化的关系.结果:治疗后1月癫痫发作无明显改变,治疗后2个月癫痫发作明显减少,13例无癫痫发作,另外10例有发作患者频率也明显下降,其中肿瘤缩小超过1/2者78％无癫痫发作.结论:I131内放射治疗的成人幕上恶性脑胶质瘤可以明显减少患者的癫痫发作.     

Complexity measures of brain wave dynamics

To understand the nature of brain dynamics as well as to develop novel methods for the diagnosis of brain pathologies, recently, a number of complexity measures from information theory, chaos theory, and random fractal theory have been applied to analyze the EEG data. These measures are crucial in quantifying the key notions of neurodynamics, including determinism, stochasticity, causation, and correlations. Finding and understanding the relations among these complexity measures is thus an important issue. However, this is a difficult task, since the foundations of information theory, chaos theory, and random fractal theory are very different. To gain significant insights into this issue, we carry out a comprehensive comparison study of major complexity measures for EEG signals. We find that the variations of commonly used complexity measures with time are either similar or reciprocal. While many of these relations are difficult to explain intuitively, all of them can be readily understood by relating these measures to the values of a multiscale complexity measure, the scale-dependent Lyapunov exponent, at specific scales. We further discuss how better indicators for epileptic seizures can be constructed.     

A distance-based dynamical transition analysis of time series signals and application to biological systems

This study demonstrates an application of distance-based numerical measures to the phase space of time series signals, in order to obtain a temporal analysis of complex dynamical systems. This method is capable of detecting alterations appearing in the characters of the deterministic dynamical systems and provides a simple tool for the real-time analysis of time series data obtained from a complex dynamical system even with black box functionality. The study presents a possible application of the method in the dynamical transition analysis of real EEG records from epilepsy patients.     

Linear and Nonlinear Measures and Seizure Anticipation in Temporal Lobe Epilepsy

In a recent paper, we showed that the value of a nonlinear quantity computed from scalp electrode data was correlated with the time to a seizure in patients with temporal lobe epilepsy. In this paper we study the relationship between the linear and nonlinear content and analyses of the scalp data. We do this in two ways. First, using surrogate data methods, we show that there is important nonlinear structure in the scalp electrode data to which our methods are sensitive. Second, we study the behavior of some simple linear metrics on the same set of scalp data to see whether the nonlinear metrics contain additional information not carried by the linear measures. We find that, while the nonlinear measures are correlated with time to seizure, the linear measures are not, over the time scales we have defined. The linear and nonlinear measures are themselves apparently linearly correlated, but that correlation can be ascribed to the influence of a small set of outliers, associated with muscle artifact. A remaining, more subtle relation between the variance of the values of a nonlinear measure and the expectation value of a linear measure persists. Implications of our observations are discussed.     

Prediction of linear B-cell epitopes

The use of antigenicity scales based on physicochemical properties and the sliding window method in combination with an averaging algorithm and subsequent search for the maximum value is the classical method for B-cell epitope prediction. However, recent studies have demonstrated that the best classical methods provide a poor correlation with experimental data. We review both classical and novel algorithms and present our own implementation of the algorithms. The AAPPred software is available at http://www.bioinf.ru/aappred/.     

人源microRNA前体的全基因组预测

microRNA（miRNA）是一类不编码蛋白的调控小分子RNA,在真核生物中发挥着广泛而重要的调控功能.由于miRNA的表达具有时空特异性,因而通过计算方法预测miRNA而后有针对性的实验验证是miRNA发现的一条重要途径.降低假阳性率是miRNA预测方法面临的重要挑战.本研究采用集成学习方法构建预测miRNA前体的分类器SVMbagging,对训练集、测试集和独立测试集的结果表明,本研究的方法性能稳健、假阳性率低,具有很好的泛化能力,尤其是当阈值取0.9时,特异性高达99.90%,敏感性在26%以上,适合于全基因组预测.采用SVMbagging在人全基因组中预测miRNA前体,当取阈值0.9时,得到14933个可能的miRNA前体.通过与高通量小RNA测序数据的比较,发现其中4481个miRNA前体具有完全匹配的小RNA序列,与理论估计的真阳性数值非常接近.最后,对32个可能的miRNA进行实验验证,确定其中2条为真实的miRNA.     

面向蛋白质功能位点识别的机器学习平台构建

有关蛋白质功能的研究是解析生命奥秘的基础,机器学习技术在该领域已有广泛应用。利用支持向量机(support vectormachine,SVM)方法,构建一个预测蛋白质功能位点的通用平台。该平台先提取非同源蛋白质序列,再对这些序列进行特征编码(包括序列的基本信息、物化特征、结构信息及序列保守性特征等),以编码好的样本作为训练数据,利用SVM进行训练,得到敏感性、特异性、Matthew相关系数、准确率及ROC曲线等评价指标,反复测试,得到评价指标最优的SVM模型后,便可以用来预测蛋白质序列上的功能位点。该平台除了应用在预测蛋白质功能位点之外,还可以应用于疾病相关单核苷酸多态性(SNP)预测分析、预测蛋白质结构域分析、生物分子间的相互作用等。     

Elimination of zinc-65 from the brain under kainate-induced seizures

On the basis of the previous evidence that 65Zn concentrations in the brain of EL (epilepsy) mice was affected by induction of seizures, 65Zn movement in the brain was quantitatively evaluated in ddY mice treated with kainate. Six days after intravenous injection of 65ZnCl2, mice were intraperitoneally injected with kainate (10 mg/kg x 6 times in 2 weeks). Myoclonic jerks were observed during treatment with kainate. Twenty days after 65Zn injection, 65Zn distribution in the brain was compared between the kainite-treated and control mice. 65Zn distribution in the brain of the kainate-treated mice was overall lower than in the control mice. 65Zn concentration was significantly decreased in the frontal cortex, hippocampal CA1, thalamus and hypothalamus by treatment with kainate. These results demonstrate that kainate-induced seizures are linked to decreased zinc concentrations in the brain.