skip to main content
research-article
Public Access

RDeepSense: Reliable Deep Mobile Computing Models with Uncertainty Estimations

Published: 08 January 2018 Publication History

Abstract

Recent advances in deep learning have led various applications to unprecedented achievements, which could potentially bring higher intelligence to a broad spectrum of mobile and ubiquitous applications. Although existing studies have demonstrated the effectiveness and feasibility of running deep neural network inference operations on mobile and embedded devices, they overlooked the reliability of mobile computing models. Reliability measurements such as predictive uncertainty estimations are key factors for improving the decision accuracy and user experience. In this work, we propose RDeepSense, the first deep learning model that provides well-calibrated uncertainty estimations for resource-constrained mobile and embedded devices. RDeepSense enables the predictive uncertainty by adopting a tunable proper scoring rule as the training criterion and dropout as the implicit Bayesian approximation, which theoretically proves its correctness. To reduce the computational complexity, RDeepSense employs efficient dropout and predictive distribution estimation instead of the model ensemble or sampling-based method for inference operations. We evaluate RDeepSense with four mobile sensing applications using Intel Edison devices. Results show that RDeepSense can reduce around 90% of the energy consumption while producing superior uncertainty estimations and preserving at least the same model accuracy compared with other state-of-the-art methods.

References

[1]
Intel edison compute module. http://www.intel.com/content/dam/support/us/en/documents/edison/sb/edison-module_HG_331189.pdf.
[2]
P. Baldi and P. J. Sadowski. Understanding dropout. In Advances in Neural Information Processing Systems, pages 2814--2822, 2013.
[3]
J. S. Bauer, S. Consolvo, B. Greenstein, J. Schooler, E. Wu, N. F. Watson, and J. Kientz. Shuteye: encouraging awareness of healthy sleep recommendations with a mobile, peripheral display. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pages 1401--1410. ACM, 2012.
[4]
P. Baumann, M. Langheinrich, A. Dey, and S. Santini. Quantifying the uncertainty of next-place predictions. In Proceedings of the 8th EAI International Conference on Mobile Computing, Applications and Services, pages 74--85. ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering), 2016.
[5]
F. R. Bentley, Y.-Y. Chen, and C. Holz. Reducing the stress of coordination: sharing travel time information between contacts on mobile phones. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, pages 967--970. ACM, 2015.
[6]
D. M. Blei, A. Kucukelbir, and J. D. McAuliffe. Variational inference: A review for statisticians. Journal of the American Statistical Association, (just-accepted), 2017.
[7]
N. Boukhelifa, M.-E. Perrin, S. Huron, and J. Eagan. How data workers cope with uncertainty: A task characterisation study. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pages 3645--3656. ACM, 2017.
[8]
K.-Y. Chen, D. Ashbrook, M. Goel, S.-H. Lee, and S. Patel. Airlink: sharing files between multiple devices using in-air gestures. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pages 565--569. ACM, 2014.
[9]
T. Choudhury, S. Consolvo, B. Harrison, J. Hightower, A. LaMarca, L. LeGrand, A. Rahimi, A. Rea, G. Bordello, B. Hemingway, et al. The mobile sensing platform: An embedded activity recognition system. IEEE Pervasive Computing, 7(2), 2008.
[10]
J. Chung, M. Donahoe, C. Schmandt, I.-J. Kim, P. Razavai, and M. Wiseman. Indoor location sensing using geo-magnetism. In Proceedings of the 9th international conference on Mobile systems, applications, and services, pages 141--154. ACM, 2011.
[11]
M. Clyde and E. I. George. Model uncertainty. Statistical science, pages 81--94, 2004.
[12]
A. Damianou and N. Lawrence. Deep gaussian processes. In Artificial Intelligence and Statistics, pages 207--215, 2013.
[13]
V. B. E. T. G. A. H. C. Daniel Castro, Steven Hickson and I. Essa. Predicting daily activities from egocentric images using deep learning. ISWC, 2015.
[14]
M. Faurholt-Jepsen, M. Vinberg, M. Frost, S. Debel, E. Margrethe Christensen, J. E. Bardram, and L. V. Kessing. Behavioral activities collected through smartphones and the association with illness activity in bipolar disorder. International journal of methods in psychiatric research, 25(4):309--323, 2016.
[15]
J. Fonollosa, S. Sheik, R. Huerta, and S. Marco. Reservoir computing compensates slow response of chemosensor arrays exposed to fast varying gas concentrations in continuous monitoring. Sensors and Actuators B: Chemical, 215:618--629, 2015.
[16]
Y. Gal and Z. Ghahramani. Bayesian convolutional neural networks with bernoulli approximate variational inference. arXiv preprint arXiv:1506.02158, 2015.
[17]
Y. Gal and Z. Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In ICML, 2016.
[18]
Y. Gal and Z. Ghahramani. A theoretically grounded application of dropout in recurrent neural networks. In Advances in Neural Information Processing Systems, pages 1019--1027, 2016.
[19]
Z. Ghahramani. Probabilistic machine learning and artificial intelligence. Nature, 521(7553):452--459, 2015.
[20]
T. Gneiting and A. E. Raftery. Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102(477):359--378, 2007.
[21]
A. L. Goldberger, L. A. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C.-K. Peng, and H. E. Stanley. Physiobank, physiotoolkit, and physionet. Circulation, 101(23):e215--e220, 2000.
[22]
D. Gordon, J. Czerny, T. Miyaki, and M. Beigl. Energy-efficient activity recognition using prediction. In Wearable Computers (ISWC), 2012 16th International Symposium on, pages 29--36. IEEE, 2012.
[23]
E. Griffiths, T. S. Saponas, and A. Brush. Health chair: implicitly sensing heart and respiratory rate. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pages 661--671. ACM, 2014.
[24]
T. Grosse-Puppendahl, X. Dellangnol, C. Hatzfeld, B. Fu, M. Kupnik, A. Kuijper, M. R. Hastall, J. Scott, and M. Gruteser. Platypus: Indoor localization and identification through sensing of electric potential changes in human bodies. In Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services, pages 17--30. ACM, 2016.
[25]
Y. Guan and T. Ploetz. Ensembles of deep lstm learners for activity recognition using wearables. arXiv preprint arXiv:1703.09370, 2017.
[26]
Y. Jiang, X. Pan, K. Li, Q. Lv, R. P. Dick, M. Hannigan, and L. Shang. Ariel: Automatic wi-fi based room fingerprinting for indoor localization. In Proceedings of the 2012 ACM Conference on Ubiquitous Computing, pages 441--450. ACM, 2012.
[27]
M. Kachuee, M. M. Kiani, H. Mohammadzade, and M. Shabany. Cuff-less high-accuracy calibration-free blood pressure estimation using pulse transit time. In Circuits and Systems (ISCAS), 2015 IEEE International Symposium on, pages 1006--1009. IEEE, 2015.
[28]
S. Kaiser, A. Parks, P. Leopard, C. Albright, J. Carlson, M. Goel, D. Nassehi, and E. C. Larson. Design and learnability of vortex whistles for managing chronic lung function via smartphones. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pages 569--580. ACM, 2016.
[29]
M. Kay, T. Kola, J. R. Hullman, and S. A. Munson. When (ish) is my bus?: User-centered visualizations of uncertainty in everyday, mobile predictive systems. In Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, pages 5092--5103. ACM, 2016.
[30]
M. Kay, S. N. Patel, and J. A. Kientz. How good is 85%?: A survey tool to connect classifier evaluation to acceptability of accuracy. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, pages 347--356. ACM, 2015.
[31]
C. Koehler, N. Banovic, I. Oakley, J. Mankoff, and A. K. Dey. Indoor-alps: an adaptive indoor location prediction system. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pages 171--181. ACM, 2014.
[32]
D. Koller and N. Friedman. Probabilistic graphical models: principles and techniques. MIT press, 2009.
[33]
M. Krzywinski and N. Altman. Points of significance: importance of being uncertain. Nature methods, 10(9):809, 2013.
[34]
B. Lakshminarayanan, A. Pritzel, and C. Blundell. Simple and scalable predictive uncertainty estimation using deep ensembles. arXiv preprint arXiv:1612.01474, 2016.
[35]
N. D. Lane, P. Georgiev, and L. Qendro. Deepear: robust smartphone audio sensing in unconstrained acoustic environments using deep learning. In Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pages 283--294. ACM, 2015.
[36]
B. Y. Lim and A. K. Dey. Investigating intelligibility for uncertain context-aware applications. In Proceedings of the 13th international conference on Ubiquitous computing, pages 415--424. ACM, 2011.
[37]
Z. C. Lipton. The mythos of model interpretability. arXiv preprint arXiv:1606.03490, 2016.
[38]
A. Mannini, S. S. Intille, M. Rosenberger, A. M. Sabatini, and W. Haskell. Activity recognition using a single accelerometer placed at the wrist or ankle. Medicine and science in sports and exercise, 45(11):2193, 2013.
[39]
P. Melgarejo, X. Zhang, P. Ramanathan, and D. Chu. Leveraging directional antenna capabilities for fine-grained gesture recognition. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pages 541--551. ACM, 2014.
[40]
T. Park, J. Lee, I. Hwang, C. Yoo, L. Nachman, and J. Song. E-gesture: a collaborative architecture for energy-efficient gesture recognition with hand-worn sensor and mobile devices. In Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems, pages 260--273. ACM, 2011.
[41]
G. Pirkl and P. Lukowicz. Robust, low cost indoor positioning using magnetic resonant coupling. In Proceedings of the 2012 ACM Conference on Ubiquitous Computing, pages 431--440. ACM, 2012.
[42]
Q. Pu, S. Gupta, S. Gollakota, and S. Patel. Whole-home gesture recognition using wireless signals. In Proceedings of the 19th annual international conference on Mobile computing 8 networking, pages 27--38. ACM, 2013.
[43]
J. Quinonero-Candela, C. E. Rasmussen, F. Sinz, O. Bousquet, and B. Schölkopf. Evaluating predictive uncertainty challenge. In Machine Learning Challenges. Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Tectual Entailment, pages 1--27. Springer, 2006.
[44]
V. Radu, N. D. Lane, S. Bhattacharya, C. Mascolo, M. K. Marina, and F. Kawsar. Towards multimodal deep learning for activity recognition on mobile devices. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct, pages 185--188. ACM, 2016.
[45]
C. E. Rasmussen. Gaussian processes for machine learning. 2006.
[46]
N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1):1929--1958, 2014.
[47]
A. Stisen, H. Blunck, S. Bhattacharya, T. S. Prentow, M. B. Kjærgaard, A. Dey, T. Sonne, and M. M. Jensen. Smart devices are different: Assessing and mitigatingmobile sensing heterogeneities for activity recognition. In Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems, pages 127--140. ACM, 2015.
[48]
T. Toscos, K. Connelly, and Y. Rogers. Best intentions: health monitoring technology and children. In Proceedings of the SIGCHI conference on Human Factors in Computing Systems, pages 1431--1440. ACM, 2012.
[49]
E. J. Wang, W. Li, D. Hawkins, T. Gernsheimer, C. Norby-Slycord, and S. N. Patel. Hemaapp: noninvasive blood screening of hemoglobin using smartphone cameras. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pages 593--604. ACM, 2016.
[50]
H. Wang, Y.-H. Kuo, D. Kifer, and Z. Li. A simple baseline for travel time estimation using large-scale trip data. In Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, page 61. ACM, 2016.
[51]
J. Weppner, B. Bischke, and P. Lukowicz. Monitoring crowd condition in public spaces by tracking mobile consumer devices with wifi interface. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct, pages 1363--1371. ACM, 2016.
[52]
L. Yao, F. Nie, Q. Z. Sheng, T. Gu, X. Li, and S. Wang. Learning from less for better: semi-supervised activity recognition via shared structure discovery. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pages 13--24. ACM, 2016.
[53]
S. Yao, M. T. Amin, L. Su, S. Hu, S. Li, S. Wang, Y. Zhao, T. Abdelzaher, L. Kaplan, C. Aggarwal, et al. Recursive ground truth estimator for social data streams. In Information Processing in Sensor Networks (IPSN), 2016 15th ACM/IEEE International Conference on, pages 1--12. IEEE, 2016.
[54]
S. Yao, S. Hu, S. Li, Y. Zhao, L. Su, L. Kaplan, A. Yener, and T. Abdelzaher. On source dependency models for reliable social sensing: Algorithms and fundamental error bounds. In Distributed Computing Systems (ICDCS), 2016 IEEE 36th International Conference on, pages 467--476. IEEE, 2016.
[55]
S. Yao, S. Hu, Y. Zhao, A. Zhang, and T. Abdelzaher. Deepsense: a unified deep learning framework for time-series mobile sensing data processing. In Proceedings of the 26th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 2017.
[56]
S. Yao, Y. Zhao, A. Zhang, L. Su, and T. Abdelzaher. Deepiot: Compressing deep neural network structures for sensing systems with a compressor-critic framework. In Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems. ACM, 2017.
[57]
H.-S. Yeo, J. Lee, A. Bianchi, and A. Quigley. Watchmi: pressure touch, twist and pan gesture input on unmodified smartwatches. In Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services, pages 394--399. ACM, 2016.
[58]
C. Zhang, L. Liu, D. Lei, Q. Yuan, H. Zhuang, T. Hanratty, and J. Han. Triovecevent: Embedding-based online local event detection in geo-tagged tweet streams. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 595--604. ACM, 2017.
[59]
C. Zhang, K. Zhang, Q. Yuan, H. Peng, Y. Zheng, T. Hanratty, S. Wang, and J. Han. Regions, periods, activities: Uncovering urban dynamics via cross-modal representation learning. In Proceedings of the 26th International Conference on World Wide Web, pages 361--370. International World Wide Web Conferences Steering Committee, 2017.
[60]
Y. Zhang, M. K. Chong, J. Müller, A. Bulling, and H. Gellersen. Eye tracking for public displays in the wild. Personal and Ubiquitous Computing, 19(5-6):967--981, 2015.
[61]
Y. Zhao, S. Li, S. Hu, L. Su, S. Yao, H. Shao, H. Wang, and T. Abdelzaher. Greendrive: A smartphone-based intelligent speed adaptation system with real-time traffic signal prediction. In Proceedings of the 8th International Conference on Cyber-Physical Systems, pages 229--238. ACM, 2017.
[62]
Y. Zhao, S. Yao, S. Li, S. Hu, H. Shao, and T. F. Abdelzaher. Vibebin: A vibration-based waste bin level detection system. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 1(3):122, 2017.
[63]
Y. Zhao, Y. Zhang, T. Yu, T. Liu, X. Wang, X. Tian, and X. Liu. Citydrive: A map-generating and speed-optimizing driving system. In INFOCOM, 2014 Proceedings IEEE, pages 1986--1994. IEEE, 2014.

Cited By

View all
  • (2024)Deep Heterogeneous Contrastive Hyper-Graph Learning for In-the-Wild Context-Aware Human Activity RecognitionProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/36314447:4(1-23)Online publication date: 12-Jan-2024
  • (2024)RTDeepEnsemble: Real-Time DNN Ensemble Method for Machine Perception Systems2024 IEEE 42nd International Conference on Computer Design (ICCD)10.1109/ICCD63220.2024.00037(191-198)Online publication date: 18-Nov-2024
  • (2023)ScaleFlow: Efficient Deep Vision Pipeline with Closed-Loop Scale-Adaptive InferenceProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3612412(1698-1706)Online publication date: 26-Oct-2023
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies  Volume 1, Issue 4
December 2017
1298 pages
EISSN:2474-9567
DOI:10.1145/3178157
Issue’s Table of Contents
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 January 2018
Accepted: 01 October 2017
Revised: 01 August 2017
Received: 01 May 2017
Published in IMWUT Volume 1, Issue 4

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Deep Learning
  2. Internet-of-Things
  3. Mobile Computing
  4. Reliability
  5. Uncertainty Estimation

Qualifiers

  • Research-article
  • Research
  • Refereed

Funding Sources

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)112
  • Downloads (Last 6 weeks)27
Reflects downloads up to 17 Jan 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Deep Heterogeneous Contrastive Hyper-Graph Learning for In-the-Wild Context-Aware Human Activity RecognitionProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/36314447:4(1-23)Online publication date: 12-Jan-2024
  • (2024)RTDeepEnsemble: Real-Time DNN Ensemble Method for Machine Perception Systems2024 IEEE 42nd International Conference on Computer Design (ICCD)10.1109/ICCD63220.2024.00037(191-198)Online publication date: 18-Nov-2024
  • (2023)ScaleFlow: Efficient Deep Vision Pipeline with Closed-Loop Scale-Adaptive InferenceProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3612412(1698-1706)Online publication date: 26-Oct-2023
  • (2023)Transforming Large-Size to Lightweight Deep Neural Networks for IoT ApplicationsACM Computing Surveys10.1145/357095555:11(1-35)Online publication date: 9-Feb-2023
  • (2023)A Bayesian Approach for Quantifying Data Scarcity when Modeling Human Behavior via Inverse Reinforcement LearningACM Transactions on Computer-Human Interaction10.1145/355138830:1(1-27)Online publication date: 7-Mar-2023
  • (2022)PrivacyEye: A Privacy-Preserving and Computationally Efficient Deep Learning-Based Mobile Video Analytics SystemIEEE Transactions on Mobile Computing10.1109/TMC.2021.305045821:9(3263-3279)Online publication date: 1-Sep-2022
  • (2022)Enabling Real-time AI Inference on Mobile Devices via GPU-CPU Collaborative Execution2022 IEEE 28th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)10.1109/RTCSA55878.2022.00027(195-204)Online publication date: Aug-2022
  • (2022)IoBT-OS: Optimizing the Sensing-to-Decision Loop for the Internet of Battlefield Things2022 International Conference on Computer Communications and Networks (ICCCN)10.1109/ICCCN54977.2022.9868920(1-10)Online publication date: Jul-2022
  • (2022)DeepPulse: An Uncertainty-aware Deep Neural Network for Heart Rate Estimations from Wrist-worn Photoplethysmography2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)10.1109/EMBC48229.2022.9871813(1651-1654)Online publication date: 11-Jul-2022
  • (2022)Probabilistic electrical load forecasting for buildings using Bayesian deep neural networksJournal of Building Engineering10.1016/j.jobe.2021.10385346(103853)Online publication date: Apr-2022
  • Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Full Access

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media