Accelerometer-based measurement of exercise and mobility for pulmonary rehabilitation

@inproceedings{citeulike:758463, abstract = {The aim of this study is to develop a wearable sensor system to remotely monitor the exercise activity of chronic obstructive pulmonary disease (COPD) patients. Data were collected and analyzed from 8 COPD patients who wore accelerometers on the arms and legs while performing a series of aerobic exercises. Exercise identification was based on the output of a neural network trained with examples from each of the exercise conditions. Sensitivity (\% correct classifications) of the neural network was high, ranging from 93 to 98\%, and specificity (100\% - \% errors where one exercise classified as another) was above 97.5\% in all cases. In addition, 3 patients followed an expanded protocol that included activities representing mobility in daily life in addition to the original aerobic exercise set. Planar projections of the multidimensional feature sets derived from accelerometer signals show well-defined clusters for most activities, indicating that these signals contain sufficient information to reliably discriminate among the various activities.}, author = {Sherrill, D. M. and Bonato, P. and Moy, M. L. and Reilly, J. J. }, citeulike-article-id = {758463}, comment = {左右の足と前腕に装着したアクセラロメータから、方向、動き、周波数などを特徴としてANNを学習、その出力により動き等の検出。PCAによりクラスタリング。精度も擬陽性も高い。}, journal = {Bioengineering Conference, 2004. Proceedings of the IEEE 30th Annual Northeast}, keywords = {2004, acc, cite000, datamining}, pages = {237--238}, posted-at = {2006-07-14 01:23:09}, priority = {0}, title = {Accelerometer-based measurement of exercise and mobility for pulmonary rehabilitation}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1300082}, year = {2004} }

TY - CONF ID - citeulike:758463 L3 - citeulike-article-id:758463 TI - Accelerometer-based measurement of exercise and mobility for pulmonary rehabilitation JF - Bioengineering Conference, 2004. Proceedings of the IEEE 30th Annual Northeast SP - 237 EP - 238 N2 - The aim of this study is to develop a wearable sensor system to remotely monitor the exercise activity of chronic obstructive pulmonary disease (COPD) patients. Data were collected and analyzed from 8 COPD patients who wore accelerometers on the arms and legs while performing a series of aerobic exercises. Exercise identification was based on the output of a neural network trained with examples from each of the exercise conditions. Sensitivity (% correct classifications) of the neural network was high, ranging from 93 to 98%, and specificity (100% - % errors where one exercise classified as another) was above 97.5% in all cases. In addition, 3 patients followed an expanded protocol that included activities representing mobility in daily life in addition to the original aerobic exercise set. Planar projections of the multidimensional feature sets derived from accelerometer signals show well-defined clusters for most activities, indicating that these signals contain sufficient information to reliably discriminate among the various activities. KW - 2004 KW - acc KW - cite000 KW - datamining N1 - 左右の足と前腕に装着したアクセラロメータから、方向、動き、周波数などを特徴としてANNを学習、その出力により動き等の検出。PCAによりクラスタリング。精度も擬陽性も高い。 AU - Sherrill, DM AU - Bonato, P AU - Moy, ML AU - Reilly, JJ PY - 2004/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1300082 ER -