CoChat
Sign Up
Cited by 21IoT and Edge/Fog ComputingInternet of Things and AIContext-Aware Activity Recognition Systems

Optimizing computational resources for edge intelligence through model cascade strategies

Open access
Gomez-Carmona, Oihane, Casado-Mansilla, Diego, Lopez-de-Ipina, Diego, Garcia-Zubia, Javier·2022·IEEE Internet of Things Journal
DOI 10.1109/jiot.2021.3118845
Open this paper in CoChat — free accountOpen PDF

Abstract

As the number of interconnected devices increases and more artificial intelligence (AI) applications upon the Internet of Things (IoT) start to flourish, so does the environmental cost of the computational resources needed to send and process all the generated data. Therefore, promoting the optimization of AI applications is a key factor for the sustainable development of IoT solutions. Paradigms such as Edge Computing are progressively proposed as a solution in the IoT field, becoming an alternative to delegate all the computation to the Cloud. However, bringing the computation to the local stage is limited by the resources’ availability of the devices hosted at the Edge of the network. For this reason, this work presents an approach that simplifies the complexity of supervised learning algorithms at the Edge. Specifically, it separates complex models into multiple simpler classifiers forming a cascade of discriminative models. The suitability of this proposal in a human activity recognition (HAR) context is assessed by comparing the performance of three different variations of this strategy. Furthermore, its computational cost is analyzed in several resource-constrained Edge devices in terms of processing time. The experimental results show the viability of this approach to outperform other ensemble methods, i.e., the Stacking technique. Moreover, it substantially reduces the computational cost of the classification tasks by more than 60% without a significant accuracy loss (around 3.5%). This highlights the potential of this strategy to reduce resource and energy requirements in IoT architectures and promote more efficient and sustainable classification solutions.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/jiot.2021.3118845

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Despite the rapid progress of ML methods, there are several potential flaws, including data bias, overfitting, resource-intensive training, and limited transfer learning.

    “Despite the rapid progress of ML methods, there are several potential flaws, including data bias,27 overfitting,28 resource-intensive training,29 and limited transfer learning.30”

    From Artificial intelligence in diabetes management: Advancements, opportunities, and challenges (2023) · cites this paper as [29]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 48

  1. J. Wang, M. K. Lim, C. Wang, and M.-L. Tseng, "The evolution of the Internet of Things (IoT) over the past 20 years," Comput. Ind. Eng., vol. 155, May 2021, Art. no. 107174.
  2. M. Asif-Ur-Rahman et al., "Toward a heterogeneous mist, fog, and cloud-based framework for the Internet of Healthcare Things," IEEE Internet Things J., vol. 6, no. 3, pp. 4049-4062, Jun. 2019.
  3. L. Hou et al., "Internet of Things cloud: Architecture and implementa- tion," IEEE Commun. Mag., vol. 54, no. 12, pp. 32-39, Dec. 2016.
  4. B. Rana, Y. Singh, and P. K. Singh, "A systematic survey on Internet of Things: Energy efficiency and interoperability perspective," Trans. Emerg. Telecommun. Technol., to be published.
  5. A. J. Ferrer, J. M. Marquès, and J. Jorba, "Towards the decentralised cloud: Survey on approaches and challenges for mobile, ad hoc, and edge computing," ACM Comput. Surveys, vol. 51, no. 6, pp. 1-36, 2019.
  6. S. Yu, X. Chen, L. Yang, D. Wu, M. Bennis, and J. Zhang, "Intelligent edge: Leveraging deep imitation learning for mobile edge computa- tion offloading," IEEE Wireless Commun., vol. 27, no. 1, pp. 92-99, Feb. 2020.
  7. S. Yu, X. Chen, Z. Zhou, X. Gong, and D. Wu, "When deep rein- forcement learning meets federated learning: Intelligent multitimescale resource management for multiaccess edge computing in 5G ultra- dense network," IEEE Internet Things J., vol. 8, no. 4, pp. 2238-2251, Feb. 2021.
  8. S. Dhar, J. Guo, J. Liu, S. Tripathi, U. Kurup, and M. Shah, "On-device machine learning: An algorithms and learning theory perspective," 2019. [Online]. Available: arXiv:1911.00623. · arXiv
  9. S. Deng, H. Zhao, W. Fang, J. Yin, S. Dustdar, and A. Y. Zomaya, "Edge intelligence: The confluence of edge computing and artificial intelligence," IEEE Internet Things J., vol. 7, no. 8, pp. 7457-7469, Aug. 2020.
  10. O. Gómez-Carmona, D. Casado-Mansilla, F. A. Kraemer, D. L. Ipiña, and J. García-Zubia, "Exploring the computational cost of machine learning at the edge for human-centric Internet of Things," Future Gener. Comput. Syst., vol. 112, pp. 670-683, Nov. 2020.
  11. L. Breiman, "Bagging predictors," Mach. Learn., vol. 24, no. 2, pp. 123-140, 1996.
  12. D. H. Wolpert, "Stacked generalization," Neural Netw., vol. 5, no. 2, pp. 241-259, 1992.
  13. C. Zhang and Y. Ma, Ensemble Machine Learning: Methods and Applications. New York, NY, USA: Springer, 2012.
  14. P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR), vol. 1, 2001, p. 1.
  15. S. Xu, Q. Tang, L. Jin, and Z. Pan, "A cascade ensemble learning model for human activity recognition with smartphones," Sensors, vol. 19, no. 10, p. 2307, 2019.
  16. J. Wu, J. M. Rehg, and M. D. Mullin, "Learning a rare event detection cascade by direct feature selection," in Proc. 16th Int. Conf. Neural Inf. Process. Syst. (NIPS), Whistler, BC, Canada, 2003, pp. 1523-1530.
  17. O. Sagi and L. Rokach, "Ensemble learning: A survey," Interdiscipl. Rev. Data Min. Knowl. Disc., vol. 8, no. 4, 2018, Art. no. e1249.
  18. M. Rokicki and M. Drozda, "Evaluating trade-offs in energy-efficient error detection," Int. J. Commun. Syst., vol. 30, no. 7, 2017, Art. no. e3028.
  19. C. Kaynak and E. Alpaydin, "Multistage cascading of multiple classi- fiers: One man's noise is another man's data," in Proc. ICML, 2000, pp. 455-462.
  20. E. J. Silva, A. S. Britto, L. S. Oliveira, F. Enembreck, R. Sabourin, and A. L. Koerich, "A two-step cascade classification method," in Proc. IEEE Int. Joint Conf. Neural Netw. (IJCNN), 2017, pp. 573-580.
  21. Z. Xu, M. J. Kusner, K. Q. Weinberger, M. Chen, and O. Chapelle, "Classifier cascades and trees for minimizing feature evaluation cost," J. Mach. Learn. Res., vol. 15, no. 1, pp. 2113-2144, 2014.
  22. M. Chen, Z. Xu, K. Weinberger, O. Chapelle, and D. Kedem, "Classifier cascade for minimizing feature evaluation cost," in Proc. Artif. Intell. Stat., 2012, pp. 218-226.
  23. G. Fumera, F. Roli, and G. Giacinto, "Reject option with multiple thresholds," Pattern Recognit., vol. 33, no. 12, pp. 2099-2101, 2000.
  24. L. S. Oliveira, A. Britto, and R. Sabourin, "Improving cascading clas- sifiers with particle swarm optimization," in Proc. IEEE 8th Int. Conf. Doc. Anal. Recognit. (ICDAR), 2005, pp. 570-574.
  25. P. Zhang, T. D. Bui, and C. Y. Suen, "A novel cascade ensemble classi- fier system with a high recognition performance on handwritten digits," Pattern Recognit., vol. 40, no. 12, pp. 3415-3429, 2007.
  26. X. Wang, D. Kondratyuk, K. M. Kitani, Y. Movshovitz-Attias, and E. Eban, "Multiple networks are more efficient than one: Fast and accu- rate models via ensembles and cascades," 2020. [Online]. Available: arXiv:2012.01988. · arXiv
  27. E. Park et al., "Big/little deep neural network for ultra low power infer- ence," in Proc. IEEE Int. Conf. Hardw. Softw. Codesign Syst. Synth. (CODES+ISSS), 2015, pp. 124-132.
  28. S. Leroux et al., "The cascading neural network: Building the Internet of Smart Things," Knowl. Inf. Syst., vol. 52, no. 3, pp. 791-814, 2017.
  29. L. Lefakis and F. Fleuret, "Joint cascade optimization using a product of boosted classifiers," in Proc. Adv. Neural Inf. Process. Syst., 2010, pp. 1315-1323.
  30. O. Gómez-Carmona, D. Casado-Mansilla, D. L. Ipiña, and J. García- Zubia, "Simplicity is best: Addressing the computational cost of machine learning classifiers in constrained edge devices," in Proc. 9th Int. Conf. Internet Things, 2019, pp. 1-8.
  31. B. Bruno, F. Mastrogiovanni, and A. Sgorbissa, "A public domain dataset for ADL recognition using wrist-placed accelerometers," in Proc. 23rd IEEE Int. Symp. Robot Human Interact. Commun., 2014, pp. 738-743.
  32. D. Anguita, A. Ghio, L. Oneto, X. Parra, and J. L. Reyes-Ortiz, "A public domain dataset for human activity recognition using smartphones," in Proc. ESANN, vol. 3, 2013, p. 3.
  33. K. Altun, B. Barshan, and O. Tunçel, "Comparative study on classifying human activities with miniature inertial and magnetic sensors," Pattern Recognit., vol. 43, no. 10, pp. 3605-3620, 2010.
  34. C. R. Banbury et al., "Benchmarking TinyML systems: Challenges and direction," 2020. [Online]. Available: arXiv:2003.04821. · arXiv
  35. F. Pedregosa et al., "Scikit-learn: Machine learning in python," J. Mach. Learn. Res., vol. 12, no. 85, pp. 2825-2830, 2011. [Online]. Available: http://jmlr.org/papers/v12/pedregosa11a.html
  36. H. Liu and R. Setiono, "CHI2: Feature selection and discretization of numeric attributes," in Proc. 7th IEEE Int. Conf. Tools Artif. Intell., 1995, pp. 388-391.
  37. G. Chandrashekar and F. Sahin, "A survey on feature selection methods," Comput. Elect. Eng., vol. 40, no. 1, pp. 16-28, 2014.
  38. C. Qian, Y. Yu, and Z.-H. Zhou, "Subset selection by pareto optimization," in Proc. Adv. Neural Inf. Process. Syst., 2015, pp. 1774-1782.
  39. K. P. Bennett and E. Parrado-Hernández, "The interplay of optimization and machine learning research," J. Mach. Learn. Res., vol. 7, pp. 1265-1281, Jan. 2006.
  40. R. Sánchez-Corcuera et al., "Smart cities survey: Technologies, applica- tion domains and challenges for the cities of the future," Int. J. Distrib. Sensor Netw., vol. 15, no. 6, pp. 1-19, 2019.
  41. O. Gómez-Carmona, D. Casado-Mansilla, and J. García-Zubia, "Opportunities and challenges of technology-based interventions to increase health-awareness in the workplace," Transf. Ergon. Pers. Health Intell. Workplaces, vol. 25, p. 33, Sep. 2019.
  42. B. L. R. Stojkoska and K. V. Trivodaliev, "A review of Internet of Things for smart home: Challenges and solutions," J. Cleaner Prod., vol. 140, pp. 1454-1464, Jan. 2017.
  43. H. H. Nguyen, F. Mirza, M. A. Naeem, and M. Nguyen, "A review on IoT healthcare monitoring applications and a vision for transform- ing sensor data into real-time clinical feedback," in Proc. IEEE 21st Int. Conf. Comput. Supported Cooperat. Work Design (CSCWD), 2017, pp. 257-262.
  44. A. Irizar-Arrieta, O. Gómez-Carmona, A. Bilbao-Jayo, D. Casado- Mansilla, D. López-De-Ipiña, and A. Almeida, "Addressing behavioural technologies through the human factor: A review," IEEE Access, vol. 8, pp. 52306-52322, 2020.
  45. M. A. Goralski and T. K. Tan, "Artificial intelligence and sustain- able development," Int. J. Manag. Educ., vol. 18, no. 1, 2020, Art. no. 100330.
  46. Y. Zhang, X. Bai, F. P. Mills, and J. C. Pezzey, "Rethinking the role of occupant behavior in building energy performance: A review," Energy Build., vol. 172, pp. 279-294, Aug. 2018.
  47. E. Strubell, A. Ganesh, and A. McCallum, "Energy and policy con- siderations for deep learning in NLP," 2019. [Online]. Available: arXiv:1906.02243. · arXiv
  48. A. de Vries, "Bitcoin's energy consumption is underestimated: A mar- ket dynamics approach," Energy Res. Soc. Sci., vol. 70, Dec. 2020, Art. no. 101721.

Cited by

Sorted by citations

Authors
Gomez-Carmona, O., Casado-Mansilla, D., Lopez-de-Ipina, D., & Garcia-Zubia, J.
Affiliations
  • DeustoTech, University of Deusto, Bilbao, Spain
  • Faculty of Engineering, University of Deusto, Bilbao, Spain
ORCID
Venue
IEEE Internet of Things Journal
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2022-05-15
Volume
9
Issue
10
Pages
7404-7417
ISSN
  • 2327-4662 (ISSN-L)
  • 2372-2541
DOI
10.1109/jiot.2021.3118845
OpenAlex
W3205944598
Cited by
21
References
5
Citations by year
2026: 1 · 2025: 6 · 2024: 5 · 2023: 6 · 2022: 3
FWCI
1.57
Type
journal article
Language
en
Open access
Licence
Locations
IEEE Internet of Things Journal (publishedVersion, cc-by)
Funders
  • European Commission through the AURORAL Project (101016854)
  • Ministry of Economy, Industry and Competitiveness of Spain for IoP (PID2020-119682RB-I00)
Topics
  • Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
  • Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
Keywords
edge computing, human activity recognition, Internet of Things, resource-constrained devices, computational complexity reduction, energy efficiency, ensemble methods, stacking, supervised learning, sustainable AI

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review