ABSTRACT
Human activity recognition (AR) has begun to mature as a field, but for AR research to thrive, large, diverse, high quality, AR data sets must be publically available and AR methodology must be clearly documented and standardized. In the process of comparing our AR research to other efforts, however, we found that most AR data sets are sufficiently limited as to impact the reliability of existing research results, and that many AR research papers do not clearly document their experimental methodology and often make unrealistic assumptions. In this paper we outline problems and limitations with AR data sets and describe the methodology problems we noticed, in the hope that this will lead to the creation of improved and better documented data sets and improved AR experimental methodology. Although we cover a broad array of methodological issues, our primary focus is on an often overlooked factor, model type, which determines how AR training and test data are partitioned---and how AR models are evaluated. Our prior research indicates that personal, hybrid, and impersonal/universal models yield dramatically different performance [30], yet many research studies do not highlight or even identify this factor. We make concrete recommendations to address these issues and also describe our own publically available AR data sets.
- actitracker.comGoogle Scholar
- Abdallah, Z. S., Gaber, M. M., Srinivasan, B., and Krishnaswamy, S. CBARS: Cluster based classification for activity recognition systems. In Proc. 1st Int. Conference on Advances Machine Learning Technologies (2012).Google ScholarCross Ref
- Abdallah, Z. S., Gaber, M. M., Srinivasan, B., and Krishnaswamy, S., StreamAR: incremental and active learning with evolving sensory data for activity recognition. In Proc. 24th IEEE Int. Conf. on Tools with AI (2012). Google ScholarDigital Library
- Anguita, D., Ghio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J. Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. In Proc. Int. Workshop of Ambient Assisted Living (2012). Google ScholarDigital Library
- Anguita, D., Ghio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J. L. A public domain dataset for human activity recognition using smartphones. In Proc. European Symposium on Artificial Neural Networks, Comp. Intelligence, and Machine Learning (2013), 437--442.Google Scholar
- Anguita, D., Ghio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J. L. Energy efficient smartphone-based activity recognition using fixed-point arithmatic, Journal of Universal Comp. Science, 19, 9 (2013), 1295--1314.Google Scholar
- Bao, L., and Intille, S. Activity recognition from user-annotated acceleration data. Lecture Notes Computer Science 3001 (2004), 1--17.Google ScholarCross Ref
- Brezmes, T., Gorricho, J. L., and Cotrina, J. Activity recognition from accelerometer data on mobile phones. In Proc. 10th International Work-Conference on Artificial Neural Networks (2009), 796--799. Google ScholarDigital Library
- Cho, Y., Nam, Y., Choi, Y-J, and Cho, W-D. Smart-Buckle: human activity recognition using a 3-axis accelerometer and wearable camera. HealthNet (2008). Google ScholarDigital Library
- Derawi, M., and Bours, P. Gait and activity recognition using commercial phones. Computers and Security, 39 (2013): 137--144. Google ScholarDigital Library
- Dernbach, S., Das, B., Krishnan, N. C., Thomas, B. L., and Cook, D. J. Simple and complex activity recognition through smart phones. In Proc. 8th Int. Conference on Intelligent Environments (2012), 214--221. Google ScholarDigital Library
- Do, T. M., Loke, S. W., and Liu, F. HealthyLife: An activity recognition system with smartphone using logic-based stream reasoning. Mobile and Ubiquitous Systems: Computing, Networking, and Services, Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 120 (2013), 188--199.Google Scholar
- Fahim, M. Evolutionary learning models for indoor and outdoor human activity recognition. PhD Thesis, Kyung Hee University (2014).Google Scholar
- Fahim, M., Fatima, I., and Lee, S. EFM: Evolutionary fuzzy model for dynamic activities recognition using a smartphone accelerometer. Applied Intelligence, 39, 3, (2013), 475--488. Google ScholarDigital Library
- Gomes, J. B., Krishnaswamy S., Gaber, M. M., Sousa, A. C., and Menasalvas, E. Mobile activity recognition using ubiquitous data stream mining. In Proc. 14th Int. Conf. on Data Warehousing and Knowledge Discovery (2012). Google ScholarDigital Library
- Gyorbiro, N., Fabian, A., and Homanyi, G. An activity recognition system for mobile phones. Mobile Networks and Applications 14, 1 (2008), 82--91. Google ScholarDigital Library
- M. Han, An intergativ Human Activity Recognition Framework based on Smartphone Multimodal Sensors, Doctoral Thesis, Kyung Hee University, 2013.Google Scholar
- Han, M., Bang, J-H, Nugent, C., McClean, S., and Lee, S. HARF: A hierarchical activity recognition framework using smartphone sensors, Ubiquitous Computing and Ambient Intelligence, Lecture Notes in Computer Science, 8276 (2013), 159--166.Google ScholarCross Ref
- He, Z., and Jin, L. Activity recognition from acceleration data based on discrete cosine transform and SVM. In. Proc. IEEE International Conference on Systems, Man, and Cybernetics (2009).Google Scholar
- He, Y., and Li, Y. Physical activity recognition utilizing the built-in kinematic sensors of a smartphone. Int. Journal of Distributed Sensor Networks (2013).Google ScholarCross Ref
- Kastner, M., Strickert, M., and Villmann, T. A sparse kernelized matrix learning vector quantization model for human activity recognition. In Proc. European Symposium on Artificial Neural Networks, Comp. Intelligence, and Machine Learning (2013).Google Scholar
- Kawaguchi, N., et al. HASC Challenge: gathering large scale human activity corpus for the real-world activity understandings. In Proc. 2nd Augmented Human International Conference (2011). Google ScholarDigital Library
- Khan, A. M., Lee, Y. K., Lee, S. Y., and Kim, T. S. Human activity recognition via an accelerometer-enabled-smartphone using kernel discriminant analysis. In Proc. 5th Int. Conf. on Future Information Technology (2010), 1--6.Google ScholarCross Ref
- Khan, A. M., Siddiqi, M. H., and Lee, S-W. Exploratory data analysis of acceleration signals to select light-weight and accurate features for real-time activity recognition on smartphones. Sensors 13 (2013), 13099--13122.Google ScholarCross Ref
- Kwapisz, J. R., Weiss, G. M., and Moore, S. A. Activity recognition using cell phone accelerometers, SIGKDD Explorations, 12 2 (2010), 74--82. Google ScholarDigital Library
- Lane, N. D., Xu, Y., Lu, H., Hu, S., Choudhury, T., Campbell, A. T., and Zhao, F., Enabling large-scale human activity inference on smartphones using community similarity networks (CSN). In Proc. 13th International Conference on Ubiquitous Computing (2011), 355--364. Google ScholarDigital Library
- Lane, N. D., Xu, Y., Lu, H. Hu, S., Choudhury, T. Campbell, A. T., and Zhao, F. Community similarity networks. Personal Ubiquitous Computing, 18, 2 (2014), 355--358. Google ScholarDigital Library
- Lee, Y., and Cho, S. Activity recognition using hierarchical hidden Markov models on a smartphone with 3D accelerometer. In Proc. 6th Int. Conf. on Hybrid Artificial Intelligent Systems (2011), 460--467. Google ScholarDigital Library
- Lee, Y., and Cho, S. Activity recognition with Android phone using mixture-of-experts co-trained with labeled and unlabeled data. Neurocomputing, 126 (2014), 106--115. Google ScholarDigital Library
- Lockhart, J. W., and Weiss, G. M. The benefits of personalized smartphone-based activity recognition models. In Proc. SIAM International Conference on Data Mining (SDM) (2014), 614--622.Google ScholarCross Ref
- Lockhart, J. W. The Benefits of Personalized Data Mining Approaches to Human Activity Recognition with Smartphone Sensor Data. Master's Thesis, Dept. of Computer & Info. Science, Fordham University (2014). {http://www.cis.fordham.edu/wisdm/Lockhart-MS-thesis.pdf}Google Scholar
- Miluzzo, E., Lane, N. D., Fodor, K., Peterson, R., Lu, H., Musolesi, M., Eisenman, S. B., Zheng, X., and Campbell, A. T. Sensing meets mobile social networks: the design, implementation and evaluation of the CenceMe application. In Proc. 6th ACM Conference on Embedded Networked Sensor Systems (2008), 337--350. Google ScholarDigital Library
- Qi, X. Keally, M., Zhou, G., Li, Y., Ren, Z. AdaSense: adapting sampling rates for activity recognition in body sensor networks. In Proc. IEEE 19th Real-Time and Embedded Technology and Applications Symposium (2013), 163--172. Google ScholarDigital Library
- Reiss, A., Hendeby, G., and Stricker, D. A competitive approach for human activity recognition on smartphones. In Proc. European Symposium on Artificial Neural Networks, Computational Intelligence, and Machine Learning (2013), 455--460.Google Scholar
- Riboni, D., and Bettini, C. COSAR: hybrid reasoning for context-aware activity recognition. Personal and Ubiquitous Computing, 15, 3 (2011), 271--289. Google ScholarDigital Library
- Roggen, D. et al. Opportunity: towards opportunistic activity and context recognition systems. In Proc. 3rd IEEE Workshop on Autononomic and Opportunistic Communications (2009).Google Scholar
- Roy, N., Misra, A., and Cook, D. Infrastructure-assisted smartphone-based ADL recognition in multi-Inhabitant smart environments. In Proc. IEEE Int. Conf. on Pervasive Computing and Communications (2013), 38--46.Google ScholarCross Ref
- Shoaib, M., Scholten, H., and Havinga, P. J. M. Towards physical activity recognition using smartphone sensors. In Proc. 10th International Conference on Ubiquitous Intelligence & Computing (2013), 80--87. Google ScholarDigital Library
- Siirtola, P., and Roning, J. Ready-to-use activity recognition for smartphones, In Proc. IEEE Symposium on Comp. Intelligence and Data Mining (2013), 59--64.Google ScholarCross Ref
- Tapia, E., Intille, S., Haskell, W., Larson, K., Wright, J., King, A., and Friedman, R. Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart rate monitor. In Proc. 11th IEEE Int. Symp. on Wearable Computers (2007), 37--40. Google ScholarDigital Library
- www.cis.fordham.edu/wisdm/dataset.phpGoogle Scholar
- Wu, W., Dasgupta, S., Ramirez, E. E., Peterson, C., and Norman, G. J. Classification accuracies of physical activities using smartphone motion sensors. Journal of Medical Internet Research, 14, 5 (2012).Google ScholarCross Ref
- Yan, Z., Chakraborty, D., Mittal, S., Misra, A., and Aberer, K. An exploration with online complex activity recognition using cellphone accelerometer. UbiComp Adjunct (2013), 199--202. Google ScholarDigital Library
- Yang, J. Toward physical activity diary: motion recognition using simple acceleration features with mobile phones. In Proc. 1st Int. Workshop on Interactive Multimedia for Consumer Electronics (2009). Google ScholarDigital Library
- Yuan, B., Herbert, J., and Emamian, Y. Smartphone-based activity recognition using hybrid classifier utilizing cloud infrastructure for data analysis. In Proc. of the 4th Int. Conference on Pervasive and Embedded Computing & Comm. Systems. 2014.Google Scholar
Index Terms
- Limitations with activity recognition methodology & data sets
Recommendations
Archetype modeling methodology
Graphical abstractDisplay Omitted
Highlights- An archetype modeling methodology is proposed.
- Composed by 5 phases: analysis, ...
AbstractClinical Information Models (CIMs) expressed as archetypes play an essential role in the design and development of current Electronic Health Record (EHR) information structures. Although there exist many experiences about using ...
A comprehensive data quality methodology for web and structured data
Measuring and improving data quality in an organisation or in a group of interacting organisations is a complex task. Several methodologies have been developed in the past, providing a basis for the definition of a data quality programme that guarantees ...
A Methodology for Supporting Collaborative Exploratory Analysis of Massive Data Sets in Tele-Immersive Environments
HPDC '99: Proceedings of the 8th IEEE International Symposium on High Performance Distributed ComputingThis paper proposes a methodology for employing collaborative, immersive virtual environments as a high-end visualization interface for massive data-sets. The methodology employs feature detection, partitioning, summarization and decimation to ...
Comments