Al-Momani Orobah, Gharaibeh Khaled M
Yarmouk University, Irbid 21163, Jordan.
Int J Telemed Appl. 2014;2014:816369. doi: 10.1155/2014/816369. Epub 2014 Feb 10.
This paper aims to study the performance of support vector machine (SVM) classification in detecting asthma attacks in a wireless remote monitoring scenario. The effect of wireless channels on decision making of the SVM classifier is studied in order to determine the channel conditions under which transmission is not recommended from a clinical point of view. The simulation results show that the performance of the SVM classification algorithm in detecting asthma attacks is highly influenced by the mobility of the user where Doppler effects are manifested. The results also show that SVM classifiers outperform other methods used for classification of cough signals such as the hidden markov model (HMM) based classifier specially when wireless channel impairments are considered.
本文旨在研究支持向量机（SVM）分类在无线远程监测场景中检测哮喘发作的性能。研究无线信道对SVM分类器决策的影响，以便从临床角度确定不建议进行传输的信道条件。仿真结果表明，SVM分类算法在检测哮喘发作时的性能受用户移动性的影响很大，其中会表现出多普勒效应。结果还表明，SVM分类器优于其他用于咳嗽信号分类的方法，如基于隐马尔可夫模型（HMM）的分类器，特别是在考虑无线信道损伤的情况下。
