Analysis of human gait to detect walking abnormality has recently gained growing interest. It carries profound impact in medical diagnosis and rehabilitation engineering. In this study we have explored different regression modeling techniques to detect pathological gait. Inexpensive Microsoft Kinect (V2) sensor was used for data acquisition. Comparative analysis was performed between logistic regression, SVM and multiple adaptive regression splines (MARS) models. Kinematic time series, extracted from different lower limb joints, were fed into the models and used to detect the abnormal pattern. Feature vectors were constructed from 6 joint angles (hip, knee and ankle angles of both sides) and merged on the range of multiple time instance for greater accuracy. An attempt was also made to investigate the statistical significance of the feature vectors. MARS model was found to be comparatively better than others with 88.3% of detection accuracy.

分析人的步态以检测步行异常最近已引起越来越多的兴趣。它对医学诊断和康复工程具有深远的影响。在这项研究中，我们探索了不同的回归建模技术来检测病理步态。廉价的Microsoft Kinect（V2）传感器用于数据采集。在逻辑回归，支持向量机和多个自适应回归样条（MARS）模型之间进行了比较分析。从不同的下肢关节提取的运动时间序列被输入到模型中，并用于检测异常模式。从6个关节角度（两侧的臀部，膝盖和脚踝角度）构建特征向量，并在多个时间范围内合并以提高准确性。还尝试研究特征向量的统计意义。发现MARS模型比其他模型具有更好的检测精度，检测精度为88.3％。