采用预处理的心电信号数据压缩的神经网络方法

根据心电图特征的变化，本文首先对采样数据进行了必要的预处理，较大幅度地减少了冗余信息。在保留心电信号主要特征的前提下，缩小了神经网络输入、输出数据规模，从而减少了网络训练所需的时间，使得基于人工神经网络的心电信号数据压缩方法更适应实时数据压缩的需要。模拟结果表明，本文所采用的数据压缩方法具有较高的压缩比和压缩精度。     

基于能量特征的脑电信号上肢运动意图智能识别

传统的对运动员上肢运动意图识别方法,没有对采集获得的大量脑电信号进行平滑滤波,存在较多毛刺干扰,导致识别准确率和识别率不高。我们提出一种基于能量特征的脑电信号上肢运动意图智能识别方法,采用快速傅里叶变换方法对采集获得的运动障碍患者脑电信号进行频率分析,获得患者脑电信号中的μ波和β波频率分布规律,找到脑电信号噪声所在频段;并采用Daubechies小波将患者脑电信号进行3阶分解,将患者脑电信号中低频部分的小波系数进行归零处理后,再进行脑电信号重构,即可消除低频脑电信号中的噪声干扰;在此基础上,采用小波包系数分析患者脑电能量,实现患者脑电信号能量特征提取;基于脑电信号能量特征,采用马氏距离判别方法对上肢运动意图进行智能识别。实验结果显示,所提方法能够去除原始脑电信号中的"毛刺"干扰,平均识别率结果为88. 6%,识别准确率和识别率较高。     

基于抗交叉串扰自适应噪声抵消的诱发脑电信号提取研究

由于诱发脑电信号比自发脑电信号的幅度小得多 ,传统的叠加平均方法提取诱发脑电信号需要大量的重复刺激 ,如何通过少量的刺激次数来获取诱发脑电信号是一个重要的研究课题。本文提出了一种抗交叉串扰自适应噪声抵消方法来提取诱发脑电信号 ,同时引进滤波技术并结合常用的叠加技术 ,使提取诱发脑电信号所需的重复刺激次数大幅减少 ,仿真实验说明 ,该方法只需数次甚至单次刺激便可提取相当完好的诱发脑电信号     

快速提取脑电信号的谱分量参数

本文利用现代谱分析技术,提出一种新的快速算法来提取脑电信号的谱分量参数。并围绕现代谱估计在脑电信号分析中可能会遇到的一些问题,在理论分析和大量实验的基础上,分别提出新的见解和解决方法。新算法较常规算法要快十几倍,而且能充分保证现代谱分析技术性能的高效性,可以在短数据场合下对脑电信号进行谱分析和特征参数提取,从而有利于把脑电信号分析,向定量化、精确化方向推进一步。     

脑电信号的分形截距特征分析及在癫痫检测中的应用

脑电信号的非线性特征会随癫痫发作而改变,脑电信号的特征分析和检测对癫痫的诊断和治疗具有重要意义。提出对癫痫脑电信号进行毯子维和分形截距的特征分析,并将分形截距应用于癫痫脑电信号的检测。首先提取脑电信号的分形截距和毯子维特征,并对两种特征的均值和方差进行比较,最后使用支持向量机分类器,实现脑电信号的分类检测。发现癫痫发作时脑电信号的分形截距显著高于发作间期,而脑电信号的毯子维在发作前后变化规律则不明显。将分形截距作为分类特征,能有效地区分癫痫脑电与间歇期脑电,具有较强的癫痫脑电检测性能,分类检测的准确率达到96%以上。     

一种脑电效应计算机分析系统的设计及其应用

建立了一种新的用于记录和分析脑电信号计算机软硬件技术。首先通过模数转换技术将脑电的膜拟信号转换为数字信号，数字中直接存放于计算机硬盘，只要计算机硬盘允许可以长时间记录脑电信号，记录在计算机上的脑电信号可再进一步用于脑电效应分析，通过对用药后每秒脑电波数和脑电压的变化分析，采用１２－３０Ｈｚ之间每秒脑电波数或脑电压的变化可有效地反映受试者用药后的脑电效应变化情况，从而为进一步进行中枢神经系统药物的药     

运动想象脑电信号的特征提取和分类进展

运动想象脑电信号是指想象肢体运动而没有实际的肢体动作所产生的脑电信号.信号处理和模式分类方法是运动想象脑电信号以及整个BC1系统的核心技术.本文对基于运动想象的脑电信号的识别算法进行了综述.阐述了运动想象脑电特征提取和分类的方法,比较了各种方法的特点,分析了几种典型的特征提取和识别算法的组合,并且总结了运动想象脑电信号的特征提取和分类的发展现状和前景.     

基于异方差混合转移分布模型和支持向量机的脑电分类研究

为解决线性分析和单一非线性动力学指标方法无法准确描述脑电信号的问题,本研究提出基于异方差混合转移分布模型脑电特征提取方法。首先对采集到的脑电信号依据条件期望最大化(ECM)算法建立异方差混合转移分布模型,求得模型条件方差序列的均值及方差作为脑电信号的特征,将得到的脑电信号特征采用支持向量机进行分类。通过对6个人的正常脑电信号和带有眼电伪迹脑电信号进行分类仿真实验,其结果表明该方法能很好地拟合出脑电信号,且分类精确度能达到99.166 7%,说明此方法可有效提取脑电特征并准确识别出眼电伪迹。     

经验模式分解与代价敏感支持向量机在癫痫脑电信号分类中的应用

提取出脑电信号中微弱征兆信息,可以更好地了解脑电信号的特征,但由于各类外界信号的相互混叠,信号呈现出非线性、非平稳性,因此脑电信号的提取是个难题。为此本研究提出了优于小波分解的经验模式分解(EMD)算法对脑电信号进行分解,提取主要IMF分量的特征值,随后采取代价敏感支持向量机(CSVM)进行分类,并对参数进行寻优。在对癫痫患者脑电信号研究的实验中,分类准确率均达到90%以上,验证了本方法的可行性。     

非线性脑电分析技术及其临床应用

传统的脑电信号分析方法有频域（frequency domain）和时域（timedomain）分析两大类。频域分析是把幅度随时间变化的脑电波变换为脑电功率随频率变化的谱图;时域分析主要是分析脑电图（EEG）波形的几何性质,如幅值、波形的持续时间等。由于脑电信号是时变、非平稳信号,不同时刻有不同的频率成分,单纯的时域或频域分析都无法准确地表达脑电信号,所以如何对脑电信号进行精确的分析已引起诸多学者的重视。随着技术的进步,     

Telephone transmission of 20-channel digital electroencephalogram using lossless data compression.

BACKGROUND: The use of telecommunications for computer-assisted transmission of neurophysiological signals is a relatively new practice. With the development of digital technology, it is now possible to record electroencephalograms (EEGs) in digital form. Previous reports have demonstrated the possibility of real-time telephone transmission of a limited number of EEG channels. OBJECTIVES: To assess the effectiveness of specific data-compression software to improve the transmission of digital 20-channel EEG records over ordinary public telephone lines. METHODS: A prototype system was built to transmit digital EEG signals from one computer to another using two 14.4-kbps modems and proprietary lossless data-compression software. RESULTS: Forty compressed digital EEG records of 20 channels each were sent from different locations at variable distances using "plain old telephone service" (POTS). The mean compression ratio was 2.2 to 2.8:1 using a sampling frequency of 128 Hz and 2.8:1 at a sampling rate of 256 Hz. Transmission time was reduced proportionately. CONCLUSION: Although this study used a store-and-forward approach, the results suggest that it may be possible to transmit a large number of compressed EEG channels in real time using data compression.     

Watermark Compression in Medical Image Watermarking Using Lempel-Ziv-Welch (LZW) Lossless Compression Technique

In teleradiology, image contents may be altered due to noisy communication channels and hacker manipulation. Medical image data is very sensitive and can not tolerate any illegal change. Illegally changed image-based analysis could result in wrong medical decision. Digital watermarking technique can be used to authenticate images and detect as well as recover illegal changes made to teleradiology images. Watermarking of medical images with heavy payload watermarks causes image perceptual degradation. The image perceptual degradation directly affects medical diagnosis. To maintain the image perceptual and diagnostic qualities standard during watermarking, the watermark should be lossless compressed. This paper focuses on watermarking of ultrasound medical images with Lempel-Ziv-Welch (LZW) lossless-compressed watermarks. The watermark lossless compression reduces watermark payload without data loss. In this research work, watermark is the combination of defined region of interest (ROI) and image watermarking secret key. The performance of the LZW compression technique was compared with other conventional compression methods based on compression ratio. LZW was found better and used for watermark lossless compression in ultrasound medical images watermarking. Tabulated results show the watermark bits reduction, image watermarking with effective tamper detection and lossless recovery.     

Signal processing and quality of displaying waveform at digital EEG machine

With great advances in computer technology, the digital EEG machine was developed and has become widely used. In this paper, signal processing and quality of display of waveform at digital EEG machine were discussed to confirm its advantages and drawbacks. Signal processing on a digital EEG machine is summarized in 3 parts as follows: i) A/D conversion(sampling) of EEG signals in the head box, ii) Digital signal processing to obtain mathematically reconstructed EEG on the computer, iii) Displaying EEG on a monitor. For sampling, it was recommended that sampling rate was 200 or 256 Hz, and resolution in 12 bits or preferably 16 bits per sample. A high amplitude artifact caused EEG flattening called DC build up saturation. Montage reformatting had a clinical advantage. However, re-filtering using 15 Hz high cut filter influenced the EEG interpretation. The maximal resolution of digital EEG machine with a 17-inch CRT display using 1600 x 1200 dots was about 22 Hz. The performance of paper used for conventional EEG surpassed the performance of CRT display using digital EEG machine. It seemed that understanding the characteristics of digital EEG machine and realization of data processing were important for utilizing its functions effectively.     

The application of delta modulation to EEG waveforms for database reduction and real-time signal processing

The large volume of digital data and the demanding processing task involved in electroencephalogram (EEG) analysis place stringent requirements on computer resources in terms of data transfer, computation speed, and temporary or permanent storage. The reduction of the database to a manageable size is therefore necessary for economical use of transmission channels and the storage media. The two criteria, waveform reproducibility and processing applications, must be analyzed and optimized in terms of signal-to-noise ratio (SNR) using the various factors affecting the coding. This analysis and optimization can become cumbersome, and a specialized workstation has been developed specifically for analysis of digital coding. Our interest in data compression stems from the study of the feasibility of predicting pilots' acceleration (G_z) tolerance during flight by processing both their uncoded and coded EEG.     

Retained energy-based coding for EEG signals

The recent use of long-term records in electroencephalography is becoming more frequent due to its diagnostic potential and the growth of novel signal processing methods that deal with these types of recordings. In these cases, the considerable volume of data to be managed makes compression necessary to reduce the bit rate for transmission and storage applications. In this paper, a new compression algorithm specifically designed to encode electroencephalographic (EEG) signals is proposed. Cosine modulated filter banks are used to decompose the EEG signal into a set of subbands well adapted to the frequency bands characteristic of the EEG. Given that no regular pattern may be easily extracted from the signal in time domain, a thresholding-based method is applied for quantizing samples. The method of retained energy is designed for efficiently computing the threshold in the decomposition domain which, at the same time, allows the quality of the reconstructed EEG to be controlled. The experiments are conducted over a large set of signals taken from two public databases available at Physionet and the results show that the compression scheme yields better compression than other reported methods.     

A Review of Medical Image Watermarking Requirements for Teleradiology

Teleradiology allows medical images to be transmitted over electronic networks for clinical interpretation and for improved healthcare access, delivery, and standards. Although such remote transmission of the images is raising various new and complex legal and ethical issues, including image retention and fraud, privacy, malpractice liability, etc., considerations of the security measures used in teleradiology remain unchanged. Addressing this problem naturally warrants investigations on the security measures for their relative functional limitations and for the scope of considering them further. In this paper, starting with various security and privacy standards, the security requirements of medical images as well as expected threats in teleradiology are reviewed. This will make it possible to determine the limitations of the conventional measures used against the expected threats. Furthermore, we thoroughly study the utilization of digital watermarking for teleradiology. Following the key attributes and roles of various watermarking parameters, justification for watermarking over conventional security measures is made in terms of their various objectives, properties, and requirements. We also outline the main objectives of medical image watermarking for teleradiology and provide recommendations on suitable watermarking techniques and their characterization. Finally, concluding remarks and directions for future research are presented.     

脑电记录中数据压缩的研究

近年内脑电压缩的研究很少见,而心电压缩技术有很大的进展。脑电在频率范围和波形特征上和心电有相近之处。故作者从心电压缩算法中选择合适的、较好的扇形算法作为脑电压缩研究的起点,实验结果表明其效果不佳。分析该算法的缺点后,提出一种新的算法:四选一算法。对脑电数据压缩得到比较满意的结果。在压缩比和百分均方根误差方面,明显地优越。处理速度快,能对16道脑电的数据进行实时处理。本文叙述新算法的原理和实验结果。     

Data compression methods for EEG.

Modem brain research experiments require the recording of large amounts of high-accuracy EEG data. Sampling frequency, bit resolution and number of channels are significantly larger than in routine clinical measurements. Because of this, the need of efficient signal compression has emerged. This paper presents a survey of available methods and explores some techniques, both lossy and lossless, for compressing EEG signals.     

Watermarking Techniques used in Medical Images: a Survey

The ever-growing numbers of medical digital images and the need to share them among specialists and hospitals for better and more accurate diagnosis require that patients’ privacy be protected. As a result of this, there is a need for medical image watermarking (MIW). However, MIW needs to be performed with special care for two reasons. Firstly, the watermarking procedure cannot compromise the quality of the image. Secondly, confidential patient information embedded within the image should be flawlessly retrievable without risk of error after image decompressing. Despite extensive research undertaken in this area, there is still no method available to fulfill all the requirements of MIW. This paper aims to provide a useful survey on watermarking and offer a clear perspective for interested researchers by analyzing the strengths and weaknesses of different existing methods.     

Lossless Watermarking for Verifying the Integrity of Medical Images with Tamper Localization

Given the ease of alteration of digital data, integrity verification and tamper detection for medical images are becoming ever more important. In this paper, instead of using the conventional irreversible block-based watermarking approach to achieve tamper localization, we propose to incorporate such functionality into the region-based lossless watermarking scheme. This is achieved by partitioning an image into certain non-overlapping regions and appending the associated local authentication information directly into the watermark payload. A region of authentication, which can be flexibly specified by the user, is partitioned into small regions in a multilevel hierarchical manner. Such hierarchical structure allows the user to easily adjust the localization accuracy, and makes the tamper detection efficient. Experimental results demonstrate the effectiveness of tamper localization.