Using unlabeled acoustic data with locality-constrained linear coding for energy-related activity recognition in buildings

@article{Zhu2015UsingUA,
  title={Using unlabeled acoustic data with locality-constrained linear coding for energy-related activity recognition in buildings},
  author={Qingchang Zhu and Zhenghua Chen and Yeng Chai Soh},
  journal={2015 IEEE International Conference on Automation Science and Engineering (CASE)},
  year={2015},
  pages={174-179}
}
Behaviors of occupants can impact on the energy consumption of buildings. Human activity recognition using smartphones as sensor platform has proliferated in recent years. With the inertial measurement unit in smartphones, behaviors of occupants in terms of walking and running could be easily identified, but the obtained information is of the simple level. Thanks to the abundant functionalities of mobile gadgets, we can now achieve a better understanding of occupants' behaviors at a more… 

Figures and Tables from this paper

Online kernel dictionary learning for object recognition
  • Huaping Liu, F. Sun
  • Computer Science
    2016 IEEE International Conference on Automation Science and Engineering (CASE)
  • 2016
TLDR
A new optimization model to simultaneously perform prototype selection and kernel dictionary learning is proposed and a row-sparsity regularization term on the representation matrix is introduced to ensure that only a few samples are actually used to reconstruct the dictionary.

References

SHOWING 1-10 OF 24 REFERENCES
Smartphone-based Human Activity Recognition in buildings using Locality-constrained Linear Coding
TLDR
This work proposed an approach for HAR by using Locality-constrained Linear Coding (LLC) as a feature selector to improve the performance of HAR systems and showed that the LLC approach achieved an average accuracy of about 90% due to a better selected dictionary for feature representation.
Environmental sensing by wearable device for indoor activity and location estimation
TLDR
This study motivates a sensor fusion paradigm for learning individualized activity, location, and environmental preferences for energy management and user comfort and develops features for activity and location recognition based on environmental measurements.
Reduce the Number of Sensors: Sensing Acoustic Emissions to Estimate Appliance Energy Usage
TLDR
This novel personalized energy monitoring system shows people their personal energy consumption, while maintaining their user comfort and relinquishing the need for additional hardware.
Using unlabeled data in a sparse-coding framework for human activity recognition
PresenceSense: zero-training algorithm for individual presence detection based on power monitoring
TLDR
Non-intrusive presence detection of individuals in commercial buildings is much easier to implement than intrusive methods such as passive infrared, acoustic sensors, and camera, and popular models whose parameters are optimized over a large training set are evaluated.
Towards Using Unlabeled Data in a Sparse-coding Framework for Human Activity Recognition
TLDR
The practical potential of the new sparse-coding framework for activity recognition in ubiquitous and mobile computing is shown by successfully evaluating its generalization capabilities across both domain and sensor modalities by considering the popular Opportunity dataset.
Towards scalable activity recognition: adapting zero-effort crowdsourced acoustic models
TLDR
This work investigates two adapting approaches: a semi-supervised learning to combine crowd-sourced data and unlabeled user data, and an active-learning to query the user for labeling samples where the crowd- sourced based model fails to recognize.
Fusion of WiFi, Smartphone Sensors and Landmarks Using the Kalman Filter for Indoor Localization
TLDR
This work proposes a sensor fusion framework for combining WiFi, PDR and landmarks, and can provide an average localization accuracy of 1 m, which shows significant improvement using the proposed framework.
SoundSense: scalable sound sensing for people-centric applications on mobile phones
TLDR
This paper proposes SoundSense, a scalable framework for modeling sound events on mobile phones that represents the first general purpose sound sensing system specifically designed to work on resource limited phones and demonstrates that SoundSense is capable of recognizing meaningful sound events that occur in users' everyday lives.
Activity Recognition of Assembly Tasks Using Body-Worn Microphones and Accelerometers
TLDR
This work describes a method for the recognition of activities that are characterized by a hand motion and an accompanying sound using microphones and three-axis accelerometers mounted at two positions on the user's arms using on-body sensing.
...
1
2
3
...