Modelling Duration in Activity Recognition using Generative and Discriminative Models
نویسندگان
چکیده
Human activity recognition allows many applications in areas such as intelligent environments and health monitoring. Typically probabilistic models such as the hidden Markov model or conditional random fields are used to map the observed sensor data onto the hidden activity states. A weakness of these models, however, is their inaccurate modelling of state durations. Hidden semi-Markov models and semi-Markov conditional random fields model duration explicitly. Our experiments show that modelling duration accurately can lead to a significant increase in recognition performance, in real world activity recognition.
منابع مشابه
Voice-based Age and Gender Recognition using Training Generative Sparse Model
Abstract: Gender recognition and age detection are important problems in telephone speech processing to investigate the identity of an individual using voice characteristics. In this paper a new gender and age recognition system is introduced based on generative incoherent models learned using sparse non-negative matrix factorization and atom correction post-processing method. Similar to genera...
متن کاملVinod Nair A thesis submitted in conformity with the requirements for the degree of Doctor of Philosophy
Visual Object Recognition Using Generative Models of Images Vinod Nair Doctor of Philosophy Graduate Department of Computer Science University of Toronto 2010 Visual object recognition is one of the key human capabilities that we would like machines to have. The problem is the following: given an image of an object (e.g. someone’s face), predict its label (e.g. that person’s name) from a set of...
متن کاملExploiting Unlabelled Data for Hybrid Object Classification
We propose a semi-supervised learning algorithm for visual object categorization which utilizes statistical information from unlabelled data to increase classification performance. We build on an earlier hybrid generative-discriminative approach by Holub et al. [6] which extracts Fisher scores from generative models. The hybrid model allows us to combine the modelling power and flexibility of g...
متن کاملA Comparison of Generative and Discriminative Appliance Recognition Models for Load Monitoring
Appliance-level Load Monitoring (ALM) is essential not only to optimize energy utilization but also to promote energy awareness amongst consumers through real-time feedback mechanisms. Non-intrusive load monitoring is an attractive method to perform ALM that allows tracking of appliance states within the aggregated power measurements. It makes use of generative and discriminative machine learni...
متن کاملDiscriminative models for speech recognition
The discriminative approach to speech recognition offers several advantages over the generative, such as a simple introduction of additional dependencies and direct modelling of sentence posterior probabilities/decision boundaries. However, the number of sentences that can possibly be encoded into an observation sequence can be vast, which makes the application of models, such as support vector...
متن کامل