A-Wristocracy: Deep learning on wrist-worn sensing for recognition of user complex activities
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
In this work we present A-Wristocracy, a novel framework for recognizing very fine-grained and complex inhome activities of human users (particularly elderly people) with wrist-worn device sensing. Our designed A-Wristocracy system improves upon the state-of-the-art works on in-home activity recognition using wearables. These works are mostly able to detect coarse-grained ADLs (Activities of Daily Living) but not large number of fine-grained and complex IADLs (Instrumental Activities of Daily Living). These are also not able to distinguish similar activities but with different context (such as sit on floor vs. sit on bed vs. sit on sofa). Our solution helps accurate detection of in-home ADLs/ IADLs and contextual activities, which are all critically important for remote elderly care in tracking their physical and cognitive capabilities. A-Wristocracy makes it feasible to classify large number of fine-grained and complex activities, through Deep Learning based data analytics and exploiting multi-modal sensing on wrist-worn device. It exploits minimal functionality from very light additional infrastructure (through only few Bluetooth beacons), for coarse level location context. A-Wristocracy preserves direct user privacy by excluding camera/ video imaging on wearable or infrastructure. The classification procedure consists of practical feature set extraction from multi-modal wearable sensor suites, followed by Deep Learning based supervised fine-level classification algorithm. We have collected exhaustive home-based ADLs and IADLs data from multiple users. Our designed classifier is validated to be able to recognize very fine-grained complex 22 daily activities (much larger number than 6-12 activities detected by state-of-the-art works using wearable and no camera/ video) with high average test accuracies of 90% or more for two users in two different home environments.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“The results showed an excellent effect, but the model converged hardly, causing a lot of time to be wasted in the training stage.”
From LSTM-CNN Architecture for Human Activity Recognition (2020) · cites this paper as [29]
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
(2014) · Cited by 33,419
(2016) · Cited by 11,679
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239 · cited 8×
“In this work we have proposed and designed A-Wristocracy, an innovative multi-modal sensing and Deep Learning Neural Network based data analytics on wrist-worn wearable device, for fine-grained and complex in-home ADL/ IADL recognition.”
MethodInfluentialA systematic analysis of performance measures for classification tasks
Sokolova, M., & Lapalme, G. (2009) · Information Processing & Management · doi:10.1016/j.ipm.2009.03.002 · Cited by 7,515 · cited 1×
“performance measures for classification as defined in [11].”
BackgroundLearning Deep Architectures for AI
Bengio, Y. (2009) · now publishers, Inc. eBooks · doi:10.1561/9781601982957 · Cited by 4,941
Activity Recognition from User-Annotated Acceleration Data
Bao, L., & Intille, S. S. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24646-6_1 · Cited by 3,147 · cited 1×
“…the proposed and designed A-Wristocracy in-home activity classifier consists of pipeline of following phases: (i) sliding window based data pre-processing followed by feature extraction on each of the sensor datastreams; (ii) Deep Learning Neural Network based classification with parameter tuning.”
MethodDetecting activities of daily living in first-person camera views
Pirsiavash, H., & Ramanan, D. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248010 · Cited by 649 · cited 1×
“…the proposed and designed A-Wristocracy in-home activity classifier consists of pipeline of following phases: (i) sliding window based data pre-processing followed by feature extraction on each of the sensor datastreams; (ii) Deep Learning Neural Network based classification with parameter tuning.”
MethodHow smart are our environments? An updated look at the state of the art
Cook, D. J., & Das, S. K. (2007) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2006.12.001 · Cited by 589 · cited 1×
“Relevant works on multi-sensor fusion and context-awareness in Smart Environments include [10], [6].”
BackgroundSelf-citationSpector, W. D., Katz, S., Murphy, J. B., & Fulton, J. P. (1987) · Journal of Chronic Diseases · doi:10.1016/0021-9681(87)90004-x · Cited by 565 · cited 1×
“But the more important drawback is that most of the works are able to recognize only basic coarse-grained ADLs (Activities of Daily Living), while very few complex IADLs (instrumental activities of daily living) [14].”
Background
Research works printed but not linked: 1
- 0, H2o package in r
Cited by
Items 101–136 of 136
Particle Swarm Optimization of Convolutional Neural Networks for Human Activity Prediction
Devarakonda, P. G., & Božić, B. (2022) · IntechOpen eBooks · doi:10.5772/intechopen.97259 · Cited by 8
Multi-modal Atmospheric Sensing to Augment Wearable IMU-Based Hand Washing Detection
Burchard, R., & Laerhoven, K. V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-80856-2_4 · Cited by 7
“Similarly, the sensors are included in a work by Vepakomma et al. [14].”
MethodLeveraging dataset integration and continual learning for human activity recognition
Amrani, H., Micucci, D., Mobilio, M., & Napoletano, P. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02569-1 · Cited by 6
“Deep neural networks (DNNs) are a variation of the Artificial Neural Networks that contain more hidden layers enabling them to learn from large data [18–20].”
Elderly Behavior Prediction Using a Deep Learning Model in Smart Homes
Sridevi, U. K., Sudhir, S., & Palaniappan, S. (2020) · Advances in medical technologies and clinical practice book series · doi:10.4018/978-1-7998-2101-4.ch008 · Cited by 4
Chandrasekaran, K., Gerych, W., Buquicchio, L., Alajaji, A. S., Agu, E., & Rundensteiner, E. A. (2021) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp52413.2021.00026 · Cited by 4
Balancing Sampling Frequencies for Multi-modality IoT Systems: Smart Shoe as an Example
Deng, W., Chen, K., Ying, Q., & Cheng, J. (2022) · IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS) · doi:10.1109/iemtronics55184.2022.9795785 · Cited by 6
DeepLite: Real-Time Deep Learning Framework for Neighborhood Analysis
Ho, D. H., Marri, R., Rella, S., & Lee, Y. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9005651 · Cited by 3
“Successful HAR applications include home behavior analysis [9], video surveillance [10], gait analysis [11], and gesture recognition [12].”
BackgroundA New Motion Data Structuring for Human Activity Recognition Using Convolutional Neural Network
Alemayoh, T. T., Lee, J. H., & Okamoto, S. (2020) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob49111.2020.9224310 · Cited by 4
Context-Aware Complex Human Activity Recognition using Hybrid Deep Learning ModelsPreprint
Otebolaku, A., & Omolaja, A. (2022) · Preprints.org · doi:10.20944/preprints202203.0363.v1 · Cited by 3
Comparative Study of Ensemble Method vs Deep Learning on Human Activity Recognition for Elderly Care
Saudi, A. (2022) · Journal of Science and Mathematics Letters · doi:10.37134/jsml.vol10.1.4.2022 · Cited by 2
Luo, B., Qiu, Q., Zhu, T., & Liu, Z. (2024) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-57919-6_7 · Cited by 2
A Comprehensive Review of Deep Learning for Activity Recognition
Thakur, D., & Fortino, G. (2024) · Internet of things · doi:10.1007/978-3-031-60027-2_4 · Cited by 2
Shah, M., Nawaz, T. H., Nawaz, R., Rashid, N., & Ali, M. O. (2025) · PLoS ONE · doi:10.1371/journal.pone.0323314 · Cited by 2
“Non-vision-based methods rely on data from wearable sensors [3] or non-wearable sensors [4].”
A Low-Cost Cognitive Assistant
Costa, Â., Rincon, J. A., Julián, V., Nováis, P., & Carrascosa, C. (2020) · Electronics · doi:10.3390/electronics9020310 · Cited by 2
“[26] presented a framework that detected common home activities from wrist bracelets.”
BackgroundZhang, W., & Zhou, S. (2017) · Sensors · doi:10.3390/s17061214 · Cited by 2
“A first observation is that the classification accuracy is more or less improved by above methods through increasing features compared to single-length windows [13] for User 1 and User 2.”
BackgroundMethodInfluentialHuman Activity Recognition Using LDA And Stochastic Configuration Networks
Yuan, G., Zang, C., & Zeng, P. (2022) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei57409.2022.9950204 · Cited by 2
“Vepakomma et al. [12] manually extract features from the data obtained from the sensor and then input these features into a Deep Neural Networks (DNN) model.”
MethodT-WaveNet: Tree-Structured Wavelet Neural Network for Sensor-Based Time Series AnalysisPreprint
Liu, M., Zeng, A., Lai, Q., & Xu, Q. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.05456 · Cited by 6
Research on User Portrait Technology Based on Dynamic Graph Neural Network
Jiang, J., Zhou, T., Yang, H., & Xu, L. (2024) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia63733.2024.10808716
A Novel Spiking Neural Network for Wearable-Based Human Activity Recognition
Ren, Y., & Zhao, G. L. (2024) · IEEE International Conference on Frontiers Technology of Information and Computer (ICFTIC) · doi:10.1109/icftic64248.2024.10912869 · Cited by 2
“It is commonly employed in in human-computer interaction [2], behavior analysis [3], health monitoring [4], and smart device solutions [5].”
Energy-efficient activity and sleep recognition using edge computing and wearable devices
Rosa, M., Bürget, R., & Hubálek, J. (2025) · International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT) · doi:10.1109/icumt67815.2025.11268695 · Cited by 1
“In parallel, deep learning models such as feed-forward neural networks (FFNN) [7], convolutional neural networks (CNN) – both 1dCNN [8], [9] and 2dCNN [10], [11], long short-term memory networks (LSTM) [12], [13] , and autoencoders [14], [15] have been explored for their ability to learn complex…”
An affective personal trainer for elderly people
Rincon, J. A., Costa, Â., Nováis, P., Julián, V., & Carrascosa, C. (2019) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · Cited by 1
Wang, J., Chen, Y., & Hu, C. (2023) · Springer eBooks · doi:10.1007/978-3-031-24628-9_29 · Cited by 2
Human Activity Recognition in Free Living Using a Wearable Sensor: A Two-Stage Approach
Li, T., Zhou, X. M., Kokubun, K., & Chen, W. (2023) · International Conference on Awareness Science and Technology (iCAST) · doi:10.1109/icast57874.2023.10359305 · Cited by 2
“Their approach yielded average test accuracies of 90% for two participants [10].”
BackgroundTowards a Robotic Personal Trainer for the Elderly
Rincon, J. A., Costa, Â., Nováis, P., Julián, V., & Carrascosa, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33607-3_26 · Cited by 1
“While this specific work did not present a very high accuracy, newer works like [15] or [16] that using state of the art approaches, like Deep Learning methods, achieve over 90% accuracy in detecting physical activities, using just small wearable devices (like wristbands) with accelerometers and gyroscopes.”
BackgroundElderly Behavior Prediction Using a Deep Learning Model in Smart Homes
Sridevi, U. K., Sudhir, S., & Palaniappan, S. (2022) · IGI Global eBooks · doi:10.4018/978-1-6684-5295-0.ch025 · Cited by 1
A rehabilitation activity monitoring method based on Shallow-CNN
Wu, S., Huang, T., & Li, Y. (2022) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm55620.2022.9995387 · Cited by 1
“In sensor-based HAR, there are mainly two categories for their different features: one is the manually extracted features [10], and the other is the deeper features extracted from the original data in deep learning [16-27].”
BackgroundHuman Action Recognition Using Convolutional Neural Network and Depth Sensor DataPreprint
Khan, N., Ahmad, Z., Illanko, K., & Androutsos, D. (2023) · doi:10.32920/22734269.v1 · Cited by 1
Deep Neural Network for Human Activity Recognition
Khairy, D. (2018) · International Journal of Computer Applications · doi:10.5120/ijca2018916503
Research on Extraction Method of Time-Frequency Feature of Human Motion
Wang, T., Su, Z., Li, C., & Liu, N. (2019) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2019.8833050
“From now on, human motion recognition has become a key research field of human-computer interaction and pervasive computing [1], which is widely used in daily behavior analysis [2], gesture recognition and video monitoring.”
BackgroundChehab, M. (2019) · doi:10.26756/th.2020.168
Human Action Recognition Using Convolutional Neural Network and Depth Sensor DataPreprint
Khan, N., Ahmad, Z., Illanko, K., & Androutsos, D. (2023) · doi:10.32920/22734269
Boulemtafes, A., Derhab, A., & Challal, Y. (2023) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2023.103552
A Novel Deep Learning Model for Smartphone-Based Human Activity Recognition
Nadia, A., Sabri, L., Kazar, O., & Chibani, A. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-63992-0_15
Real-Time Adaptive STFT-CNN Fusion for EW Passive Guidance
Mondal, S., Johar, H. S., & Rao, S. S. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10725507
Burchard, R., Ali, H., & Laerhoven, K. V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-13312-0_18 · Cited by 2
Sah, S., Kumawat, S., & Jones, K. I. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-0148-9_15
Metadata
- Authors
- Vepakomma, P., De, D., Das, S. K., & Bhansali, S.
- Affiliations
- Motorola (United States) (US)
- Missouri University of Science and Technology (US)
- Florida International University (US)
- Venue
- 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)
- Publisher
- IEEE
- Published
- 2015-06
- Pages
- 1-6
- ISSN
- 2376-8886 (ISSN-L)
- OpenAlex
- W1923002919
- Cited by
- 136
- References
- 19
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 13 · 2023: 19 · 2022: 16 · 2021: 23 · 2020: 23 · 2019: 16 · 2018: 14 · 2017: 3 · 2016: 1
- FWCI
- 2.43
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Wearable and Implantable Body Sensor Networks (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Keywords
- instrumental activities of daily living, activities of daily living, elderly care, Bluetooth beacons, location context, feature extraction
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
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.