Integrating prior Knowledge in Weighted SVM for Human Activity Recognition in Smart Home

M 'Hamed Bilal Abidine (1) , Belkacem Fergani (1) , Anthony Fleury (2, 3, 4)

1 USTHB - Université des Sciences et de la Technologie Houari Boumediene = University of Sciences and Technology Houari Boumediene [Alger]
2 CERI SN - IMT Nord Europe - Centre for Digital Systems
3 IMT Lille Douai - Ecole nationale supérieure Mines-Télécom Lille Douai
4 Université de Lille

Feature extraction and classification are two key steps for activity recognition in a smart home environment. In this work, we performed a new hybrid model using Temporal or Spatial Features (TF or SF) with the PCA-LDA-WSVM classifier. The last method combines two methods for feature extraction: Principal Component Analysis (PCA), and Linear Discriminant Analysis (LDA) followed by Weighted SVM Classifier. This classifier is used to handle the problem of imbalanced activity data from sensor readings. The experiments that were implemented on multiple real-world datasets, showed the effectiveness of TF and SF attributes combined with PCA-LDA-WSVM in activity recognition.

Mots clés: Activity recognition; Feature extraction; PCA; LDA; Weighted SVM

Domaines: Traitement du signal et de l'image [eess.SP]

M 'Hamed Bilal Abidine, Belkacem Fergani, Anthony Fleury. Integrating prior Knowledge in Weighted SVM for Human Activity Recognition in Smart Home. ICOST 2017 -- 15th International Conference On Smart homes and health Telematics. IoT for Enhanced Quality of Life and Smart Living, Aug 2017, Marne la vallée, France. ⟨hal-01855154⟩