**Classifying and Predicting Respiratory Function Based on Gait Analysis**

Yu Sheng Chan, Wen Te Liu and Ching Te Chiu

Additional information is available at the end of the chapter

http://dx.doi.org/10.5772/63917

#### **Abstract**

Epilepsy, which has to be considered a severe neurological condition, is characterized by recurrent seizures. In the past, it was assumed that these epileptic events are generated by a single focus and spread from there to other brain regions. Recent findings in neurological and epilepsy research indicate that a seizure is rather an abnormal activity and response of the whole network neuronal network involved. Chapter 4 presents a new network analysis approach, which uses neurophysiological data recorded prior to surgical epilepsy treatment to identify the affected brain regions and their interconnections activated during an epileptic

In the twentieth century, the DNA was identified to control all functions of individual cells, tissues, organs, and the whole body. Even though already available since the past century only very recently reasonably fast and accurate methods to read the DNA and analyze its structure have been developed. With this development, it became possible to use the infor‐ mation stored in the DNA for diagnostic purpose. Alterations in the structure of the DNA, for example, introduced when it is copied to generate proteins or when it is repaired after one of its strands or both broke, can severely affect the function of the cell. A large number of so-called copy number alterations (CNA) can be used to characterize cancer cells. A new method to assess and validate the CNA in the DNA of single cells is presented in Chapter 5. This book only covers a small selection of new and advanced biosignal processing and diag‐ nostic methods. As an editor, I thank all the authors for their contributions. I also thank all researchers whose work could not be included in this book for various reasons. All your great work is an important contribution to the field of biosignal processing with respect to

the development of new and improved diagnostic tools, therapies, and treatments.

**Dr. Christoph Hintermüller** Guger Technologies OG Schiedlberg, Austria

event.

VIII Preface

The human walking behaviour can express the physiological information of human body, and gait analysis methods can be used to access the human body condition. In addition, the respiratory parameters from pulmonary spirometer are the standard of accessing the body condition of the subjects. Therefore, we want to show the correla‐ tion between gait analysis method and the respiratory parameters. We propose a vision sensor-based gait analysis method without wearing any sensors. Our method proposed features such as *D* ′ *<sup>p</sup>*, *V* ′ *<sup>p</sup>* and *γυ* to prove the correlation by classification and prediction experiment. In our experiment, the subjects are divided into three levels depending on the respiratory index. We run classifying and predicting experiment with the extract‐ ed features: *V* ′ *<sup>p</sup>* and *γυ*. In the classifying experiment, the accuracy result is 75%. In predicting experiment, the correlations of predicting the forced expiratory volume in 1 s (FEV1) and forced vital capacity (FVC) are 0.69 and 0.67, respectively. Therefore, there is a correlation between the pulmonary spirometer and our method. The radar system is a tool using impulse to record the moving of the subjects' chest. Combining the features of radar system with our features improves the classification result from 75 to 81%. In predicting FEV1/FVC, the correlation also improves from 25 to 42%. There‐ fore, cooperating with radar system improves the correlation.

**Keywords:** gait analysis, classification, prediction, pattern recognition, feature extrac‐ tion
