Data compression of the exercise ECG using a Kohonen neural network

The goal for any data compression scheme is to maximize compression while minimizing distortion. This is particularly true for measurement sensitive electrocardiographic data. Many different approaches have been taken to achieve this goal. One common technique used in image and speech data compression, vector quantization, was selected for this study. Central to vector quantization is the creation of a codebook of vectors. Creating the best possible codebook will enable the best possible data compression. A neural network was used to create a codebook of vectors that attempt to span the low-frequency data space. Since these vectors are potentially the less critical areas of the electrocardiographic signal, less important information will be subjected to increases in distortion. The Kohonen paradigm used in this study is an unsupervised neural network that adapts the codebook vectors based on distance measurements and controls the scope of the changes based on time. This network has been shown to work well with image and speech data, but to the author's knowledge has not been used on electrocardiographic data. The compression of the signal comes from inserting the address of the codebook vector that best represents the original vector in place of the vector. A test is first performed to determine if the distortion between the original and the replacement vector is within a present limit. If it is, the address is inserted. If the distortion is too large the original vector will be retained. Typically, the QRS segment and possibly the T segment will be preserved. The new compressed file can be further reduced by lossless techniques to increase the compression ratio.(ABSTRACT TRUNCATED AT 250 WORDS)