The rapid popularity of smartphones has led to a growing research interest in human
activity recognition (HAR) with the mobile devices. Accelerometer is the most commonly used
sensor of smartphone for HAR. Most supervised HAR methods have been developed. However, it
is very difficult to collect the annotated or labeled training data for HAR. So, developing of
effective unsupervised methods for HAR is very necessary. The accuracy of the unsupervised
activity recognition can be greatly affected by feature extraction methods and distance measures.
Although Euclidean distance measure is commonly used in activity recognition, it is not suitable
for measuring distance when the number of features is very large, which is usually the case in HAR.
Jaccard distance is a distance measure based on mutual information theory and can better represent
the differences between nonnegative feature vectors than Euclidean distance. In this work, the
Jaccard distance measure is applied to HAR for the first time. In the experiments, the results of the
Jaccard distance measure and the Eucildean distance measure are compared, using three different
feature extraction methods. Two different evaluation methods are used to comprehensively analyze
the final results: (a) C-Index before clustering, (b) FM-index after using five different clustering
methods which are Spectral Cluster, Single-Linkage, Ward-Linkage, Average-Linkage, and
K-Medoids. Experiments show that, almost for every combination of the feature extraction
methods and the evaluation methods, the Jaccard distance is consistently better than the Euclidean
distance for unsupervised HAR.
|Name||Lecture Notes in Computer Science|
|Conference||Asia Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data|
|Period||07/07/2017 → 09/07/2017|