نویسندگان
1 گروه بیوالکتریک-دانشکده مهندسی پزشکی-دانشگاه صنعتی سهند-تبریز- ایران
2 عضو هیات علمی/گروه بیوالکتریک، دانشکده مهندسی پزشکی، دانشگاه صنعتی سهند
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Stroke patients generally exhibit trouble walking and moving, which affects their quality of life. Hence, an accurate diagnosis of stroke is important for providing an effective treatment and rehabilitation strategy. However, the development of a cost-effective and non-invasive diagnostic tool is a big challenge for clinical applications. To address this challenge, in this study, a new ischemic stroke detection has been proposed based on structural features of foot plantar pressure signals and support vector machine classifier. A local uniform binary pattern extracted from the time-frequency representation of pressure signals has been used to capture the local structure over two-dimensional space and quantify the stability of this pattern. The proposed method has been evaluated using the pressure signals recorded during normal walking tasks from 36 healthy controls and 46 Ischemic stroke patients. The classification has also been performed for different plantar channels to offer regional analysis. The obtained results have achieved a high average accuracy rate of 99.66% for stroke detection. Furthermore, the robustness of the proposed method against different plantar regions as well as technical parameters of the local binary pattern approach has been demonstrated in an experimental comparative study. The performance has confirmed that the local binary pattern analysis discriminates effectively stroke patients and healthy controls when foot plantar pressure signals are used.
کلیدواژهها [English]