ABSTRACT
In this work, we provide motivation for a zero-effort crowdsensing task: auto-annotated ground truth collection for physical activity recognition. Data obtained through Smartphones for classification of human activities is prone to discrepancies, which reiterates the need for better and larger activity datasets. Artificial data generation algorithms fail to efficiently generate quality instances for minority data. In the proposed model, crowd-sourced sensor data is classified by a robust classifier built by researchers ground up. We nominate a Generic Classifier with ≥ 95% accuracy for this purpose. Data collection and distribution models which ensure that the crowd client receives non-skewed, quality data from locations with higher degree of activity occurrence are elucidated upon. Also integrated within our proposed model are Location-Specific Classifiers, which can be utilized by developers to optimize on location-specific tasks. Effective validation of classified activities using diverse sensor data streams improves the proposed classifier systems and boosts ground-truth accuracy.
- E. L. Allwein, R. E. Schapire, and Y. Singer. Reducing multiclass to binary: A unifying approach for margin classifiers. The Journal of Machine Learning Research, 1:113--141, 2001. Google ScholarDigital Library
- L. Bao and S. S. Intille. Activity recognition from user-annotated acceleration data. In Pervasive computing, pages 1--17. Springer, 2004.Google Scholar
- S. Bhattacharya, P. Nurmi, N. Hammerla, and T. Plötz. Using unlabeled data in a sparse-coding framework for human activity recognition. Pervasive and Mobile Computing, 15:242--262, 2014. Google ScholarDigital Library
- E. J. Bredensteiner and K. P. Bennett. Multicategory classification by support vector machines. In Computational Optimization, pages 53--79. Springer, 1999. Google ScholarDigital Library
- C. Bunkhumpornpat, K. Sinapiromsaran, and C. Lursinsap. Safe-level-smote: Safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem. In Advances in knowledge discovery and data mining, pages 475--482. Springer, 2009. Google ScholarDigital Library
- N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer. Smote: Synthetic minority over-sampling technique. J. Artif. Int. Res., 16(1):321--357, June 2002. Google ScholarDigital Library
- C. De Souza. Classification of imbalanced classes.Google Scholar
- H. Han, W.-Y. Wang, and B.-H. Mao. Borderline-smote: a new over-sampling method in imbalanced data sets learning. In Advances in intelligent computing, pages 878--887. Springer, 2005. Google ScholarDigital Library
- H. He, Y. Bai, E. A. Garcia, and S. Li. Adasyn: Adaptive synthetic sampling approach for imbalanced learning. In Neural Networks, 2008. IJCNN 2008.(IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on, pages 1322--1328. IEEE, 2008.Google Scholar
- S. Hemminki, P. Nurmi, and S. Tarkoma. Accelerometer-based transportation mode detection on smartphones. In Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems, page 13. ACM, 2013. Google ScholarDigital Library
- O. D. Incel. Analysis of movement, orientation and rotation-based sensing for phone placement recognition. Sensors, 15(10):25474--25506, 2015.Google ScholarCross Ref
- J. R. Kwapisz, G. M. Weiss, and S. A. Moore. Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter, 12(2):74--82, 2011. Google ScholarDigital Library
- N. D. Lane, Y. Chon, L. Zhou, Y. Zhang, F. Li, D. Kim, G. Ding, F. Zhao, and H. Cha. Piggyback crowdsensing (pcs): energy efficient crowdsourcing of mobile sensor data by exploiting smartphone app opportunities. In Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems, page 7. ACM, 2013. Google ScholarDigital Library
- S. L. Lau and K. David. Movement recognition using the accelerometer in smartphones. In Future Network and Mobile Summit, 2010, pages 1--9. IEEE, 2010.Google Scholar
- A. Rai, Z. Yan, D. Chakraborty, T. K. Wijaya, and K. Aberer. Mining complex activities in the wild via a single smartphone accelerometer. In Proceedings of the Sixth International Workshop on Knowledge Discovery from Sensor Data, pages 43--51. ACM, 2012. Google ScholarDigital Library
- N. Roy, A. Misra, and D. J. Cook. Ambient and smartphone sensor assisted ADL recognition in multi-inhabitant smart environments. J. Ambient Intelligence and Humanized Computing, 7(1):1--19, 2016.Google ScholarCross Ref
- B. P. Sarma, N. Li, C. Gates, R. Potharaju, C. Nita-Rotaru, and I. Molloy. Android permissions: a perspective combining risks and benefits. In Proceedings of the 17th ACM symposium on Access Control Models and Technologies, pages 13--22. ACM, 2012. Google ScholarDigital Library
- X. Sheng, J. Tang, X. Xiao, and G. Xue. Sensing as a service: Challenges, solutions and future directions. Sensors Journal, IEEE, 13(10):3733--3741, 2013.Google ScholarCross Ref
- Y. Shi, Y. Shi, and J. Liu. A rotation based method for detecting on-body positions of mobile devices. In Proceedings of the 13th international conference on Ubiquitous computing, pages 559--560. ACM, 2011. Google ScholarDigital Library
- Z. Zhu, U. Blanke, A. Calatroni, and G. Tröster. Prior knowledge of human activities from social data. In Proceedings of the 2013 International Symposium on Wearable Computers, pages 141--142. ACM, 2013. Google ScholarDigital Library
Index Terms
- AnnoTainted: Automating Physical Activity Ground Truth Collection Using Smartphones
Recommendations
Challenges in using wearable cameras and phone logs to generate ground truth of transportation activities
UbiComp/ISWC'15 Adjunct: Adjunct Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable ComputersResearchers have started recruiting users to record activity data with ground truth annotations in real-word settings. These annotations are considered "ground truth" because users who collected activity data probably know what happened during the ...
Using visual lifelogs to automatically characterize everyday activities
Visual lifelogging is the term used to describe recording our everyday lives using wearable cameras, for applications which are personal to us and do not involve sharing our recorded data. Current applications of visual lifelogging are built around ...
Activity classification using realistic data from wearable sensors
Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are ...
Comments