张浙亮 吕维雪 张浙亮(中国科学院模式识别开放实验室，北京 100080)；吕维雪(浙江大学生命科学与医学工程学系，杭州 310027) 中国生物医学工程学报 1999 0 18 1


    关键词：心电信号(ECG)；自组织特征映射(SOFM)；矢量量化(VQ)；数据压缩 期刊 zgswyxgcxb 0 生物医学信息 fur -->


    

矢量量化(Vector Quantization)是一种重要的数据编码方法，其关键是码本设计和检索方法。然而，通常的码本聚类生成算法所用的局部信息，不能很好表现信号特征。由Kohonen提出的自组织特征映射(Self-OrganizingFeature Map, SOFM)具有自组织聚类特性，可直接用于码本设计，并较著名的LBG算法有许多良好特性。本文在简略描述自组织特征映射网络特点后，主要论述一种新改进算法并将其运用于心电信号压缩。从压缩结果来看，SOFM法适用于多种心电波形压缩任务；对于基线波动严重的波形，效果可较好；对规则波形如T100等却不很理想，S波处有失真。

    分类号： R318.04; R540.42

ECG DATA COMPRESSION USING

    SELF-ORGANIZING FEATURE MAP

Zhang Zheliang, Lu Weixue

(Department of Life Science &Biomedical Engineering, Zhejiang University, 310027)

(National Laboratory of PatternRecognition Institute of Automation Chinese Academy of Sciences, Beijing, 100080)

ABSTRACT Vector quantization (VQ) is animportant method for data compression. Now vector quantization using Neural Networksmethods received much attention in data compression techniques, especially using Kohonen'sselforgamizing feature map (SOFM) in the design of codebook, whose result were super tothe LBG algorithm. After discribed the SOFM algorithm and its change forms, this paperpresented a new SOFM algorithm and used it to compress ECG data. Experiments showed thatthis method was better than the traditional SOFM algorithm in ECG data compression, itcould be used for various ECG waveforms. The accuracy of reconstruction could be improvedif the number of codeword was increased.

     ......