Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Information Theory, Inference & Learning Algorithms
Information Theory, Inference & Learning Algorithms
Mining physiological conditions from heart rate variability analysis
IEEE Computational Intelligence Magazine
| Hi-index | 0.00 |
Nuclear Magnetic Resonance (NMR) Spectroscopy is a rapidly developing technique that measures chemicals within the brain without removing tissue or blood samples. Furthermore, it is an important tool for performing non-invasive quantitative assessments of brain tumour glucose metabolism. The principles underlying this technique have been successfully used to produce high quality images of neuroanatomy and disease processes. Unfortunately, current diagnosis techniques ignore the dynamic aspects of these signals. It is largely believed that temporal variations of NMR Spectra are simply due to noise or do not carry enough information to be exploited by any reliable diagnosis procedure. In this paper, we investigate the underlying characteristics of these signals using some complexity measures in combination with information theoretic concepts. The dynamics of these signals are further analyzed using elements from the theory of nonlinear dynamical systems. Furthermore, we show that they exhibit rich chaotic dynamics suggesting the encoding of metabolic pathway information.