Dealing with Class Skew in Context Recognition
ICDCSW '06 Proceedings of the 26th IEEE International ConferenceWorkshops on Distributed Computing Systems
Structural Learning of Activities from Sparse Datasets
PERCOM '07 Proceedings of the Fifth IEEE International Conference on Pervasive Computing and Communications
SMOTE: synthetic minority over-sampling technique
Journal of Artificial Intelligence Research
A hybrid discriminative/generative approach for modeling human activities
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
SPO: Structure Preserving Oversampling for Imbalanced Time Series Classification
ICDM '11 Proceedings of the 2011 IEEE 11th International Conference on Data Mining
| Hi-index | 0.00 |
This poster presents an integrated framework to enable using standard non-sequential machine learning tools for accurate multi-modal activity recognition. Our framework contains simple pre- and post-classification strategies such as class-imbalance correction on the learning data using structure preserving oversampling, leveraging the sequential nature of sensory data using smoothing of the predicted label sequence and classifier fusion, respectively, for improved performance. Through evaluation on recent publicly-available OPPORTUNITY activity datasets comprising of a large amount of multi-dimensional, continuous-valued sensory data, we show that our proposed strategies are effective in improving the performance over common techniques such as One Nearest Neighbor (1NN) and Support Vector Machines (SVM). Our framework also shows better performance over sequential probabilistic models, such as Conditional Random Field (CRF) and Hidden Markov Models (HMM) and when these models are used as meta-learners.