ABSTRACT
Machine learning models are bounded by the credibility of ground truth data used for both training and testing. Regardless of the problem domain, this ground truth annotation is objectively manual and tedious as it needs considerable amount of human intervention. With the advent of Active Learning with multiple annotators, the burden can be somewhat mitigated by actively acquiring labels of most informative data instances. However, multiple annotators with varying degrees of expertise poses new set of challenges in terms of quality of the label received and availability of the annotator. Due to limited amount of ground truth information addressing the variabilities of Activity of Daily Living (ADLs), activity recognition models using wearable and mobile devices are still not robust enough for real-world deployment. In this paper, we first propose an active learning combined deep model which updates its network parameters based on the optimization of a joint loss function. We then propose a novel annotator selection model by exploiting the relationships among the users while considering their heterogeneity with respect to their expertise, physical and spatial context. Our proposed model leverages model-free deep reinforcement learning in a partially observable environment setting to capture the action-reward interaction among multiple annotators. Our experiments in real-world settings exhibit that our active deep model converges to optimal accuracy with fewer labeled instances and achieves ~8% improvement in accuracy in fewer iterations.
- Mohammad Arif Ul Alam and Nirmalya Roy. 2017. Unseen Activity Recognitions: A Hierarchical Active Transfer Learning Approach. In 37th IEEE International Conference on Distributed Computing Systems, ICDCS 2017, Atlanta, GA, USA, June 5--8, 2017. 436--446.Google Scholar
- Hande Ö zgü r Alemdar, T. L. M. van Kasteren, and Cem Ersoy. 2017. Active learning with uncertainty sampling for large scale activity recognition in smart homes. JAISE , Vol. 9, 2 (2017), 209--223.Google Scholar
- Mohammad Abu Alsheikh, Ahmed Selim, Dusit Niyato, Linda Doyle, Shaowei Lin, and Hwee-Pink Tan. 2016. Deep Activity Recognition Models with Triaxial Accelerometers. In Artificial Intelligence Applied to Assistive Technologies and Smart Environments, Papers from the 2016 AAAI Workshop .Google Scholar
- Liming Chen, Jesse Hoey, Chris D. Nugent, Diane J. Cook, and Zhiwen Yu. 2012. Sensor-Based Activity Recognition. Trans. Sys. Man Cyber Part C, Vol. 42, 6 (2012), 790--808. Google ScholarDigital Library
- Gabriele Civitarese, Claudio Bettini, Timo Sztyler, Daniele Riboni, and Heiner Stuckenschmidt. 2018. NECTAR: Knowledge-based Collaborative Active Learning for Activity Recognition. In 2018 IEEE International Conference on Pervasive Computing and Communications, PerCom 2018, Athens, Greece, March 19--23, 2018. 1--10.Google Scholar
- Pinar Donmez and Jaime G. Carbonell. 2008. Proactive learning: cost-sensitive active learning with multiple imperfect oracles. In Proceedings of the 17th ACM Conference on Information and Knowledge Management, CIKM 2008, Napa Valley, California, USA, October 26--30, 2008 . 619--628. Google ScholarDigital Library
- Pinar Donmez, Jaime G. Carbonell, and Jeff G. Schneider. 2010. A Probabilistic Framework to Learn from Multiple Annotators with Time-Varying Accuracy. In Proceedings of the SIAM International Conference on Data Mining, SDM 2010, April 29 - May 1, 2010, Columbus, Ohio, USA. 826--837.Google ScholarCross Ref
- Yu Guan and Thomas Plö tz. 2017. Ensembles of Deep LS™ Learners for Activity Recognition using Wearables. IMWUT, Vol. 1, 2 (2017), 11:1--11:28. Google ScholarDigital Library
- Mahmudul Hasan and Amit K. Roy-Chowdhury. 2015. Context Aware Active Learning of Activity Recognition Models. In 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, December 7--13, 2015. 4543--4551. Google ScholarDigital Library
- H. M. Sajjad Hossain, Md Abdullah Al Hafiz Khan, and Nirmalya Roy. 2017. Active learning enabled activity recognition. Pervasive and Mobile Computing , Vol. 38 (2017), 312--330.Google ScholarCross Ref
- H. M. Sajjad Hossain, M. D. Abdullah Al Haiz Khan, and Nirmalya Roy. 2018. DeActive: Scaling Activity Recognition with Active Deep Learning. IMWUT , Vol. 2, 2 (2018), 66:1--66:23. Google ScholarDigital Library
- H. M. Sajjad Hossain and Nirmalya Roy. 2018. SocialAnnotator: Annotator Selection Using Activity and Social Context. In Proceedings of the AAAI Fall Symposium on Reasoning and Learning in Real-World Systems for Long-Term Autonomy. 30--37.Google Scholar
- Md Abdullah Al Hafiz Khan and Nirmalya Roy. 2017. TransAct: Transfer learning enabled activity recognition. In 2017 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2017, Kona, Big Island, HI, USA, March 13--17, 2017 . 545--550.Google ScholarCross Ref
- Md Abdullah Al Hafiz Khan, Nirmalya Roy, and Archan Misra. 2018. Scaling Human Activity Recognition via Deep Learning-based Domain Adaptation. In 2018 IEEE International Conference on Pervasive Computing and Communications, PerCom 2018, Athens, Greece, March 19--23, 2018. 1--9.Google ScholarCross Ref
- Kundan Krishna, Deepali Jain, Sanket V. Mehta, and Sunav Choudhary. 2017. An LS™ Based System for Prediction of Human Activities with Durations. IMWUT , Vol. 1, 4 (2017), 147:1--147:31. Google ScholarDigital Library
- Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. CoRR (2015).Google Scholar
- Akhil Mathur, Tianlin Zhang, Sourav Bhattacharya, Petar Velickovic, Leonid Joffe, Nicholas D. Lane, Fahim Kawsar, and Pietro Liò. 2018. Using deep data augmentation training to address software and hardware heterogeneities in wearable and smartphone sensing devices. In Proceedings of the 17th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2018, Porto, Portugal, April 11--13, 2018. 200--211. Google ScholarDigital Library
- Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin A. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. CoRR , Vol. abs/1312.5602 (2013).Google Scholar
- Francisco Javier Ordó n ez Morales and Daniel Roggen. 2016. Deep Convolutional and LS™ Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors , Vol. 16, 1 (2016), 115.Google ScholarCross Ref
- Sebastian Mü nzner, Philip Schmidt, Attila Reiss, Michael Hanselmann, Rainer Stiefelhagen, and Robert Dü richen. 2017. CNN-based sensor fusion techniques for multimodal human activity recognition. In Proceedings of the 2017 ACM International Symposium on Wearable Computers, ISWC 2017, Maui, HI, USA, September 11--15, 2017. 158--165. Google ScholarDigital Library
- Henry Friday Nweke, Ying Wah Teh, Mohammed Ali Al-garadi, and Uzoma Rita Alo. 2018. Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: State of the art and research challenges. Expert Syst. Appl. , Vol. 105 (2018), 233--261.Google ScholarCross Ref
- Liangying Peng, Ling Chen, Zhenan Ye, and Yi Zhang. 2018. AROMA: A Deep Multi-Task Learning Based Simple and Complex Human Activity Recognition Method Using Wearable Sensors. IMWUT , Vol. 2, 2 (2018), 74:1--74:16. Google ScholarDigital Library
- Valentin Radu, Catherine Tong, Sourav Bhattacharya, Nicholas D. Lane, Cecilia Mascolo, Mahesh K. Marina, and Fahim Kawsar. 2017. Multimodal Deep Learning for Activity and Context Recognition. IMWUT , Vol. 1, 4 (2017), 157:1--157:27. Google ScholarDigital Library
- Sreenivasan Ramasamy Ramamurthy and Nirmalya Roy. 2018. Recent trends in machine learning for human activity recognition - A survey. Wiley Interdisc. Rew.: Data Mining and Knowledge Discovery , Vol. 8, 4 (2018).Google ScholarCross Ref
- Daniele Riboni, Timo Sztyler, Gabriele Civitarese, and Heiner Stuckenschmidt. 2016. Unsupervised recognition of interleaved activities of daily living through ontological and probabilistic reasoning. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016, Heidelberg, Germany, September 12--16, 2016. 1--12. Google ScholarDigital Library
- Seyed Ali Rokni, Marjan Nourollahi, and Hassan Ghasemzadeh. 2018. Personalized Human Activity Recognition Using Convolutional Neural Networks. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, February 2--7, 2018 .Google Scholar
- Sadiq Sani, Nirmalie Wiratunga, Stewart Massie, and Kay Cooper. 2018. Matching networks for personalised human activity recognition. In Proceedings of the First Joint Workshop on AI in Health organized as part of the Federated AI Meeting (FAIM 2018). 61--64.Google ScholarCross Ref
- Burr Settles. 2012. Active Learning .Morgan & Claypool Publishers. Google Scholar
- Farhad Shahmohammadi, Anahita Hosseini, Christine E. King, and Majid Sarrafzadeh. 2017. Smartwatch Based Activity Recognition Using Active Learning. In Proceedings of the Second IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2017, Philadelphia, PA, USA, July 17--19, 2017. 321--329. Google ScholarDigital Library
- David Silver, Guy Lever, Nicolas Heess, Thomas Degris, Daan Wierstra, and Martin Riedmiller. 2014. Deterministic Policy Gradient Algorithms. In Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32 (ICML'14). Google ScholarDigital Library
- Richard S. Sutton and Andrew G. Barto. 1998. Reinforcement learning - an introduction .MIT Press. Google ScholarDigital Library
- Jindong Wang, Yiqiang Chen, Lisha Hu, Xiaohui Peng, and Philip S. Yu. 2018. Stratified Transfer Learning for Cross-domain Activity Recognition. In 2018 IEEE International Conference on Pervasive Computing and Communications, PerCom 2018, Athens, Greece, March 19--23, 2018. 1--10.Google Scholar
- Chirine Wolley and Mohamed Quafafou. 2012. Learning from Multiple Annotators: When Data is Hard and Annotators are Unreliable. In 12th IEEE International Conference on Data Mining Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012. 514--521. Google ScholarDigital Library
- Ou Wu, Weiming Hu, and Jun Gao. 2011. Learning to Rank under Multiple Annotators. In IJCAI 2011, Proceedings of the 22nd International Joint Conference on Artificial Intelligence, Barcelona, Catalonia, Spain, July 16--22, 2011. 1571--1576. Google ScholarDigital Library
- Ming Zeng, Le T. Nguyen, Bo Yu, Ole J. Mengshoel, Jiang Zhu, Pang Wu, and Joy Zhang. 2014. Convolutional Neural Networks for human activity recognition using mobile sensors. In 6th International Conference on Mobile Computing, Applications and Services, MobiCASE. 197--205.Google ScholarCross Ref
Index Terms
- Active Deep Learning for Activity Recognition with Context Aware Annotator Selection
Recommendations
A Survey on Deep Learning for Human Activity Recognition
Human activity recognition is a key to a lot of applications such as healthcare and smart home. In this study, we provide a comprehensive survey on recent advances and challenges in human activity recognition (HAR) with deep learning. Although there are ...
Smartwatch based activity recognition using active learning
CHASE '17: Proceedings of the Second IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering TechnologiesHuman activity monitoring has become widely popular in recent years, and has been utilized in a vast number of fields and applications. Most of the activity recognition algorithms proposed have emphasized the use of inertial sensors in smartphone ...
Annotating smart environment sensor data for activity learning
Smart Environments: Technology to Support HealthcareThe pervasive sensing technologies found in smart homes offer unprecedented opportunities for providing health monitoring and assistance to individuals experiencing difficulties living independently at home. In order to monitor the functional health of ...
Comments