调研方向（算法相关）

来源1

：A Review of Accelerometry-Based Wearable Motion Detectors for Physical Activity Monitoring
都是基于加速度的，所以参考价值在算法本身上，解决的具体问题与自身课题有距离。

KNN

Detection of posture and motion by accelerometry: A validation study in ambulatory monitoring（1999）
Validity and reliability of measurements obtained with an activity monitor” in people with and without a transtibial amputation（1998）

SVM

Support vector machine for classification of walking conditions of persons after stroke with dropped foot(2009)
Fall detection by wearable sensor and one-class SVM algorithm(2006)

Naive Bayers

Towards less supervision in activity recognition from wearable sensors(2006)
Single-accelerometer-based daily physical activity classification(2009)

GMM

Classification of a known sequence of motions and postures from accelerometry data using adapted Gaussian mixture models(2006)

HMM

Machine learning methods for classifying human physical activity from On-Body Accelerometers(2010)
Development of novel techniques to classify physical activity mode using accelerometers(2006)

来源2:

直接调研算法
GMM
HMM，条件随机场，贝叶斯网络