TY - JOUR

T1 - Using unlabeled data in a sparse-coding framework for human activity recognition

AU - Bhattacharya, Sourav

AU - Nurmi, Petteri

AU - Hammerla, Nils

AU - Plötz, Thomas

N1 - Special Issue on Information Management in Mobile Applications Special Issue on Data Mining in Pervasive Environments

PY - 2014/12

Y1 - 2014/12

N2 - We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It automatically derives a compact, sparse and meaningful feature representation of sensor data that does not rely on prior expert knowledge and generalizes well across domain boundaries. (ii) It exploits unlabeled sample data for bootstrapping effective activity recognizers, i.e., substantially reduces the amount of ground truth annotation required for model estimation. Such unlabeled data is easy to obtain, e.g., through contemporary smartphones carried by users as they go about their everyday activities.Based on the self-taught learning paradigm we automatically derive an over-complete set of basis vectors from unlabeled data that captures inherent patterns present within activity data. Through projecting raw sensor data onto the feature space defined by such over-complete sets of basis vectors effective feature extraction is pursued. Given these learned feature representations, classification backends are then trained using small amounts of labeled training data.We study the new approach in detail using two datasets which differ in terms of the recognition tasks and sensor modalities. Primarily we focus on a transportation mode analysis task, a popular task in mobile-phone based sensing. The sparse-coding framework demonstrates better performance than the state-of-the-art in supervised learning approaches. More importantly, we show the practical potential of the new approach by successfully evaluating its generalization capabilities across both domain and sensor modalities by considering the popular Opportunity dataset. Our feature learning approach outperforms state-of-the-art approaches to analyzing activities of daily living.

AB - We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It automatically derives a compact, sparse and meaningful feature representation of sensor data that does not rely on prior expert knowledge and generalizes well across domain boundaries. (ii) It exploits unlabeled sample data for bootstrapping effective activity recognizers, i.e., substantially reduces the amount of ground truth annotation required for model estimation. Such unlabeled data is easy to obtain, e.g., through contemporary smartphones carried by users as they go about their everyday activities.Based on the self-taught learning paradigm we automatically derive an over-complete set of basis vectors from unlabeled data that captures inherent patterns present within activity data. Through projecting raw sensor data onto the feature space defined by such over-complete sets of basis vectors effective feature extraction is pursued. Given these learned feature representations, classification backends are then trained using small amounts of labeled training data.We study the new approach in detail using two datasets which differ in terms of the recognition tasks and sensor modalities. Primarily we focus on a transportation mode analysis task, a popular task in mobile-phone based sensing. The sparse-coding framework demonstrates better performance than the state-of-the-art in supervised learning approaches. More importantly, we show the practical potential of the new approach by successfully evaluating its generalization capabilities across both domain and sensor modalities by considering the popular Opportunity dataset. Our feature learning approach outperforms state-of-the-art approaches to analyzing activities of daily living.

KW - Activity recognition

KW - Sparse-coding

KW - Machine learning

KW - Unsupervised learning

U2 - 10.1016/j.pmcj.2014.05.006

DO - 10.1016/j.pmcj.2014.05.006

M3 - Journal article

VL - 15

SP - 242

EP - 262

JO - Pervasive and Mobile Computing

JF - Pervasive and Mobile Computing

SN - 1574-1192

ER -