Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 169

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices

Open access
Rashid, Nafiul, Demirel, Berken Utku, Abdullah Al Faruque, Mohammad · 2022 · IEEE Internet of Things Journal

Abstract

Human activity recognition (HAR) is one of the key applications of health monitoring that requires continuous use of wearable devices to track daily activities. This article proposes an adaptive convolutional neural network for energy-efficient HAR (AHAR) suitable for low-power edge devices. Unlike traditional adaptive (early-exit) architecture that makes the early-exit decision based on classification confidence, AHAR proposes a novel adaptive architecture that uses an output block predictor to select a portion of the baseline architecture to use during the inference phase. The experimental results show that traditional adaptive architecture suffer from performance loss whereas our adaptive architecture provides similar or better performance as the baseline one while being energy efficient. We validate our methodology in classifying locomotion activities from two data sets—1) Opportunity and 2) w-HAR. Compared to the fog/cloud computing approaches for the Opportunity data set, our baseline and adaptive architectures show a comparable weighted F1 score of 91.79%, and 91.57%, respectively. For the w-HAR data set, our baseline and adaptive architectures outperform the state-of-the-art works with a weighted F1 score of 97.55%, and 97.64%, respectively. Evaluation on real hardware shows that our baseline architecture is significantly energy efficient ($422.38\times $less) and memory-efficient ($14.29\times $less) compared to the works on the Opportunity data set. For the w-HAR data set, our baseline architecture requires$2.04\times $less energy and$2.18\times $less memory compared to the state-of-the-art work. Moreover, experimental results show that our adaptive architecture is 12.32% (Opportunity) and 11.14% (w-HAR) energy efficient than our baseline while providing similar (Opportunity) or better (w-HAR) performance with no significant memory overhead.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1109/jiot.2022.3140465

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Self-check

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

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

Citations

Cites

Show all 14 references

Research works printed but not linked: 27

  1. 10.1109/ISLPED52811.2021.9502503 · DOI
  2. 10.1145/3394885.3431513 · DOI
  3. lu, 2019, On neural architecture search for resource-constrained hardware platforms, arXiv 1911 00105
  4. 10.1109/CVPR.2019.00881 · DOI · Paper page
  5. courbariaux, 2016, Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or ?1, arXiv 1602 02830 [cs]
  6. 10.1109/DAC18074.2021.9586259 · DOI
  7. 10.1109/TITB.2010.2051955 · DOI · Paper page
  8. 10.1186/s13673-017-0097-2 · DOI · Paper page
  9. 10.1109/JETCAS.2019.2910232 · DOI · Paper page
  10. 10.3390/s19173731 · DOI
  11. 10.1111/coin.12318 · DOI · Paper page
  12. 10.1109/TII.2020.2972628 · DOI
  13. 10.1109/JIOT.2020.3008842 · DOI
  14. 10.1109/JIOT.2020.3040713 · DOI
  15. 10.3390/s20185356 · DOI
  16. 10.1007/s12559-020-09734-4 · DOI
  17. abdel-basset, 2020, Deep learning for heterogeneous human activity recognition in complex IoT applications, IEEE Internet of Things Journal
  18. 10.3390/s150305163 · DOI
  19. 10.1016/j.medengphy.2006.12.001 · DOI · Paper page
  20. 10.1109/SURV.2012.110112.00192 · DOI · Paper page
  21. 10.1007/s40279-014-0142-5 · DOI · Paper page
  22. 10.1109/JIOT.2020.2989053 · DOI
  23. 10.1145/3358175 · DOI
  24. 10.1109/EMBC44109.2020.9175232 · DOI
  25. 2021, EFM$32^ TM $ Giant Gecko 32-Bit Microcontroller
  26. 10.3850/9783981537079_0819 · DOI
  27. 10.1109/EMBC46164.2021.9630576 · DOI

Cited by

See all 169

Metadata

Authors
Rashid, N., Demirel, B. U., & Abdullah Al Faruque, M.
Venue
IEEE Internet of Things Journal
Published
2022-08-01
Volume
9
Issue
15
Pages
13041-13051
ISSN
  • 2327-4662 (ISSN-L)
  • 2372-2541
OpenAlex
W3128348732
Cited by
169
References
14
FWCI
8.74
Type
journal article
Language
en
Open access
green
Funders
Graduate Assistance in Areas of National Need (GAANN) Award from the United States Department of Education

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices. https://app.cochat.ai/papers/10.1109/jiot.2022.3140465
The paper
Rashid, N., Demirel, B. U., & Abdullah Al Faruque, M. (2022). AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices. IEEE Internet of Things Journal. https://doi.org/10.1109/jiot.2022.3140465

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.