Deep learning for human activity recognition: A resource efficient implementation on low-power devices
The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Human Activity Recognition provides valuable contextual information for wellbeing, healthcare, and sport applications. Over the past decades, many machine learning approaches have been proposed to identify activities from inertial sensor data for specific applications. Most methods, however, are designed for offline processing rather than processing on the sensor node. In this paper, a human activity recognition technique based on a deep learning methodology is designed to enable accurate and real-time classification for low-power wearable devices. To obtain invariance against changes in sensor orientation, sensor placement, and in sensor acquisition rates, we design a feature generation process that is applied to the spectral domain of the inertial data. Specifically, the proposed method uses sums of temporal convolutions of the transformed input. Accuracy of the proposed approach is evaluated against the current state-of-the-art methods using both laboratory and real world activity datasets. A systematic analysis of the feature generation parameters and a comparison of activity recognition computation times on mobile devices and sensor nodes are also presented.
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 proposed method results in an overall accuracy of 92.6%, outperforming other methods such as HMMs [23], DBNs [6], and CNNs [11], as shown in Figure 12b.”
From Deep Recurrent Neural Networks for Human Activity Recognition (2017) · cites this paper as [11]
In the citing paper
“Ravi et al. [170] used a shallow three-layer CNN network including a convolutional layer, a fully connected layer, and a softmax layer to perform on-device activity recognition on a resource-limited platform and shown its effectiveness and efficiency on public datasets.”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [170]
In the citing paper
“The main disadvantage of AIDS is the false alarm rate (FAR), making it difficult to distinguish between normal and abnormal intrusion detection patterns [197].”
From Comparative Analysis of Intrusion Detection Systems and Machine Learning Based Model Analysis through Decision Tree (2023) · cites this paper as [197]
Citations
Cites
The Design and Implementation of FFTW3
Frigo, M., & Johnson, S. G. (2005) · Proceedings of the IEEE · doi:10.1109/jproc.2004.840301 · Cited by 5,086 · cited 1×
“For both architectures, we use the FFTW3 library [17] to extract the spectrogram and the Torch framework [18] to implement the deep learning model.”
MethodActivity recognition using cell phone accelerometers
Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1964897.1964918 · Cited by 2,912 · cited 1×
“1 6 29 Front trouser pocket 20Hz 1,098,207 [19] (thigh) Daphnet FoG 2 10 Trunk, thigh, ankle 64Hz 1,917,887 [20] Skoda 10 1 Arms (20 positions) 98Hz ∼ 701, 440 [21]”
A Survey on Human Activity Recognition using Wearable Sensors
Lara, O. D., & Labrador, M. A. (2013) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2012.110112.00192 · Cited by 2,662 · cited 1×
“1) Raw inertial data is highly fluctuating over time, making classification impossible when using a single data point in time [15].”
BackgroundA symbolic representation of time series, with implications for streaming algorithms
Lin, J., Keogh, E., Lonardi, S., & Chiu, B. (2003) · Proceedings of the 8th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery · doi:10.1145/882082.882086 · Cited by 1,799 · cited 3×
“Features, such as mean [1], Fourier transforms [2], and symbols [3], are typically extracted from segments of data and then trained using classification methods [4]–[8].”
BackgroundMethodA tutorial on human activity recognition using body-worn inertial sensors
Bulling, A., Blanke, U., & Schiele, B. (2014) · ACM Computing Surveys · doi:10.1145/2499621 · Cited by 1,668 · cited 3×
“Features, such as mean [1], Fourier transforms [2], and symbols [3], are typically extracted from segments of data and then trained using classification methods [4]–[8].”
BackgroundMethod(2015) · Cited by 989
Convolutional Neural Networks for Human Activity Recognition using Mobile Sensors
Zeng, M., Nguyen, L. T., Yu, B., Mengshoel, O. J., Zhu, J., Wu, P., & Zhang, J. (2014) · Proceedings of the 6th International Conference on Mobile Computing, Applications and Services · doi:10.4108/icst.mobicase.2014.257786 · Cited by 876 · cited 2×
“In deep learning, features are abstracted automatically from the data instead of being handcrafted, which allows these machine learning methods to be more effectively used across a range of different classification tasks [10]– [13].”
MethodTime–frequency feature representation using energy concentration: An overview of recent advances
Sejdić, E., Djurović, I., & Jiang, J. (2009) · Digital Signal Processing · doi:10.1016/j.dsp.2007.12.004 · Cited by 756 · cited 1×
“STFT is used to determine the sinusoidal frequency and phase content of local sections of a signal as it changes over time [16].”
MethodWearable Assistant for Parkinson’s Disease Patients With the Freezing of Gait Symptom
Bachlin, M., Plotnik, M., Roggen, D., Maidan, I., Hausdorff, J. M., Giladi, N., & Troster, G. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2009.2036165 · Cited by 693 · cited 2×
“We obtain comparable accuracy results even against approaches that are more resource demanding [7], [13], [20], [21].”
Result(2006) · doi:10.1007/1-84628-484-8 · Cited by 667
Self-citation
Research works printed but not linked: 1
- walse, 2016, A study of human activity recognition using AdaBoost classifiers on WISDM dataset, The Institute of Integrative Omics and Applied Biotechnology Journal, 7, 68
Cited by
Items 201–300 of 311
Sensor placement determination for a wearable device in dual-arm manipulation tasks
Urukalo, D., Nates, F. M., & Blazevic, P. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109217 · Cited by 5
Personalized Federated Attention State Space Learning for Wearable Human Activity Recognition
Xiao, Z., Wan, Q., & Tong, H. (2026) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3820371 · Cited by 4
“Ravi et al. [42] utilized a convolutional model that incorporated temporal extraction to capture local features.”
Gu, Z., Guo, W., Li, C., Zhu, X., & Guo, T. (2018) · Sensors · doi:10.3390/s18030711 · Cited by 4
“Among these various methods, IBeacons are easier to be deployed with low cost, and can be used for many years due to low power consumption [13,14].”
Machine learning in translational bioinformatics
Ahmad, N., Mohanty, P., Kumar, N., & Gandotra, E. (2021) · Elsevier eBooks · doi:10.1016/b978-0-323-89824-9.00015-x · Cited by 4
Zhao, T., Chen, H., Bai, Y., Zhao, Y., & Zhao, S. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph191811706 · Cited by 4
“[13] collected activity data with low-power wearable devices.”
BackgroundHuman Activity Recognition Based on Wearable Devices and Feedforward Neural Networks
Hutabarat, J. P., Ahmadi, N., & Adiono, T. (2023) · doi:10.1109/iceei59426.2023.10346836 · Cited by 4
GNet-FHO: A Light Weight Deep Neural Network for Monitoring Human Health and Activities
Athota, R. K., & Sumathi, D. (2024) · IEEE Access · doi:10.1109/access.2024.3426075 · Cited by 4
“The authors of [18], suggested a DL method designed for accurate and immediate identification of human activities, optimized for use with low-power wearable devices.”
MethodKarasulu, B. (2018) · Bilişim Teknolojileri Dergisi · doi:10.17671/gazibtd.370281 · Cited by 4
Activity recognition using smartphones and wearable devices: Traditional approaches, New solutions
Iskanderov, J., & Guvensan, M. A. (2019) · Pamukkale University Journal of Engineering Sciences · doi:10.5505/pajes.2018.84758 · Cited by 4
Sansano‐Sansano, E. (2020) · Tesis Doctorals en Xarxa (Consorci de Serveis Universitaris de Catalunya) · doi:10.6035/14101.2020.180044 · Cited by 4
Machine Learning and Deep Learning Approaches for Healthcare Predictive Analytics
Charan, B. S. R., Jaswanth, D., Hemanth, E., & Naidu, M. S. (2024) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc60852.2024.10689833 · Cited by 3
“CNNs are excellent at extracting features from complicated datasets because they are built to automatically learn hierarchical representations [5].”
BackgroundDiffusion-Driven Inertial Generated Data for Smartphone Location Classification
Cohen, N., Dror, R., & Klein, I. (2025) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin66788.2025.11213024 · Cited by 3
“Beyond PDR, these technologies support healthcare monitoring [11], fitness tracking [12], and context-sensitive computing [13].”
Recognizing User Activity Using a Smartphone's Accelerometer and Deep Neural Network Classifier
Pranata, S., Mantoro, T., Ayu, M. A., Prabuwono, A. S., & Dewi, D. A. (2020) · IEEE International Conference on Computing, Engineering and Design (ICCED) · doi:10.1109/icced51276.2020.9415778 · Cited by 3
Wang, X., Zhang, L., Cheng, D., Tang, Y., Wang, S., Wu, H., & Song, A. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3481549 · Cited by 3
“Ravi et al. [27] report practical HAR implementation of deep learning algorithms on low energy sensing devices.”
BackgroundMethodDesenvolvimento de um modelo baseado em Machine Learning para rastreamento precoce do câncer bucal
Ivisson (2023) · Diversitas Journal · doi:10.48017/dj.v8i3.2532 · Cited by 3
Enhancing the Reliability of Wearable Cardiac Monitoring using Accelerometer Activity Data
Karhinoja, K., Panula, T., Leinonen, T., Airola, A., Stenholm, S., & Kaisti, M. (2023) · Wearable and Implantable Body Sensor Networks · doi:10.1109/bsn58485.2023.10331083 · Cited by 3
“[5] The aim of this research was to study whether recognizing the type of activity could improve the reliability of cardiac monitoring.”
BackgroundLim, J., Seong, J., Kim, C., & Choi, Y. (2018) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2018.8650392 · Cited by 3
“The next step involved generating data by using the sliding window, which is commonly used in the case of time-series data [8], [10]–[13].”
MethodTowards an Improvement of Fourier Transform
Aznag, K., Datsi, T., El, A., & Bachari, E. E. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0110188 · Cited by 3
“In [9], [10] and [11], [12] are implementations of the discrete Fourier transform (DFT).”
Multi-input 1-dimensional deep belief network: action and activity recognition as case study
Nickfarjam, A. M., & Ebrahimpour-Komleh, H. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-018-7076-0 · Cited by 3
“…the proposed method to state-of-the-art approaches on Skoda dataset Method Accuracy Zappi et al. (2008) [64] 86.0% Alsheikh et al. (2016) [5] 89.4% Ravi et al. (2016) [42] 91.7% Murad and Pyun (2017) [35] 92.6% Proposed M1DBN Method 93.28% Walking 0.98 0 0.02 0 0 0 Walking Upstairs 0.07 0.76 0.17…”
InfluentialVisualization as Intermediate Representations (VLAIR) for Human Activity Recognition
Jiang, A., Nacenta, M. A., Terzić, K., & Ye, J. (2020) · International Conference on Pervasive Computing Technologies for Healthcare · doi:10.1145/3421937.3422015 · Cited by 3
“, accelerometers, gyroscopes and magnetometers, and get better performance on common human activity recognition tasks [27, 29, 41].”
BackgroundA Method of Equipment Safety Certification Based on Daily Cycle Activity
Ye, N., Sun, C., Xu, R., & Sun, F. (2021) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd51990.2021.9458971 · Cited by 3
HabitAction: A Video Dataset for Human Habitual Behavior RecognitionPreprint
Li, H., Zhang, Z., & Wang, W. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.13463 · Cited by 3
“Particularly, with the exponential growth of video data on the Internet in recent years, the need for HAR has become even more pronounced [32].”
BackgroundNooruddin, S. (2023) · UWSpace (University of Waterloo) · Cited by 3
KAN-HAR: A Human activity recognition based on Kolmogorov-Arnold NetworkPreprint
Alikhani, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.11186 · Cited by 3
“[18] proposes a DL-based HAR technique for real-time classification on low-power wearable devices, using spectral-domain feature generation to achieve invariance to sensor orientation, placement, and acquisition rates.”
Mobile incident command dashboard (MIC-D)
Cai, Y., & Siegel, M. (2023) · Electronic Imaging · doi:10.2352/ei.2023.35.3.mobmu-358 · Cited by 2
Posturesense Intelligent Body Support Crutch Tool
Anushree, A., Darwin Nesakumar, A., Ajeet, R. J., Gopika, S., Haritha, V., & Pavithra, K. N. (2024) · doi:10.1109/iccds60734.2024.10560407 · Cited by 2
“It uses an Android app to wirelessly gather and analyze vital data, allowing users to adjust their activities in real-time [6] [15].”
BackgroundUnveiling Human Activity Patterns in Smart Cities Through a CNN-LSTM Approach
Ameur, I., Ameur, M. E. A., Ameur, M., & Degha, H. E. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-82112-7_4 · Cited by 2
A New Model for Assembly Task Recognition: A Case Study of Seru Production System
Torkul, O., Selvi, İ. H., Şişci, M., & Diren, D. D. (2024) · IEEE Access · doi:10.1109/access.2024.3484955 · Cited by 2
“Adding dropout to a network significantly reduces the possibility of overfitting and generalization error [86], [111].”
Backgroundde Souza, M. R. Q., Ruschel, R., Susin, A., Boeira, J. M., Guimares, L. V., & Parraga, A. (2018) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512361 · Cited by 2
“[11][12] shows that deep learning methods perform worse than a shallow network using a set of predefined features when limited resources are used, such as a small dataset.”
BackgroundPublicly Accessible Wearable Motion Databases for Human Gait Studies
Luo, Y. G., Ouyang, S., Lockwood, C. G., Ferraz, M. D., & Hu, B. (2020) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1071181320641417 · Cited by 2
“…and activity recognition models, automatic gait feature extraction approaches have been developed and combined with gait/activity classification via advanced machine learning technology (Zhang et al., 2016; Zhen et al., 2016; Dehzangi et al., 2017; Ravi et al., 2016; Gadaleta & Rossi., 2018).”
BackgroundMethodInfluentialMachine Learning for a Context Mining Facility
Rabah, N. B., Pinheiro, M. K., Grand, B. L., Jaffal, A., & Souveyet, C. (2020) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops48775.2020.9156134 · Cited by 2
“[41] CNN”
BackgroundIntroduction to Deep Learning in Health Informatics
Jyotiyana, M., & Kesswani, N. (2021) · Wiley eBooks · doi:10.1002/9781119711278.ch9 · Cited by 2
Polysomnography and Sleep Analysis
Sanei, S., Jarchi, D., & Constantinides, A. G. (2020) · Wiley eBooks · doi:10.1002/9781119390060.ch5 · Cited by 2
Recognition of Smartphone User Activity: From A Cyclical Perspective.Preprint
Mi, C., Xu, R., Lin, C., & Meng, R. Y. (2019) · arXiv (Cornell University) · Cited by 2
Contributions to Human Motion Modeling and Recognition using Non-intrusive Wearable Sensors
Martín, M. (2022) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.70493 · Cited by 2
Unified Contrastive Fusion Transformer for Multimodal Human Action RecognitionPreprint
Yang, K. O., Koh, J., & Choi, J. W. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.05032 · Cited by 2
“Second, using multiple sensor modalities can offer redundancy, which can improve the robustness of action recognition [18].”
BackgroundMethodZheng, N., Xia, H., Sun, Z., Li, W., & Zhou, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.10458 · Cited by 2
“In edge hardware, executing these continuous FP32 operations consumes approximately 4.6 pJ per step [14], rapidly draining micro-batteries and rendering always-on HAR highly impractical [35].”
InfluentialVision-Based Human Activity Recognition Uses A Deep Learning Approach
Sarkar, P. K., Hoque, M. E., & Nasir, M. K. (2025) · International Journal of Computer Applications · doi:10.5120/ijca2025924621 · Cited by 1
“Researchers have been studying activity categorization and pattern recognition methods for a long time [5,6], with an emphasis on the design and a few specific elements that are task-dependent.”
Meta-process-driven 3D skeleton feature learning for enhanced human action recognition
Chen, H., Wang, C., Duan, J., & Yang, Q. (2025) · The Visual Computer · doi:10.1007/s00371-025-03901-0 · Cited by 1
“Neverthe-less, single-frame image may not fully capture the whole motion, which could potentially compromise the classification accuracy [16].”
Wearable Device for Personalized Healthcare Monitoring for Sleep Monitoring and Analysis
Srivardhani, M., Vijayashree, J., Reddy, K. K., & Karthik, D. S. (2025) · International Conference on Data Science and Business Systems (ICDSBS) · doi:10.1109/icdsbs63635.2025.11032029 · Cited by 1
Cotugno, L., Pellegrino, S., & Siciliano, R. (2025) · Studies in classification, data analysis, and knowledge organization · doi:10.1007/978-3-032-03042-9_10 · Cited by 1
Susilo, R., Sudarsono, A., & Budi, T. (2025) · International Electronics Symposium (IES) · doi:10.1109/ies67184.2025.11161758 · Cited by 1
“The native C++ implementation further optimizes performance through hardware acceleration when available on the device [16].”
InfluentialAI-Augmented Computational Modeling of Human Behavior
Zhang, G., Zhang, S., & Wu, H. (2025) · Springer eBooks · doi:10.1007/978-981-97-8440-0_111-1 · Cited by 2
Sun, H., Zhang, F., Peng, J., Wang, H., & Zhang, H. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3659530 · Cited by 1
“Moreover, the large parameter counts in standard CNNs lead to high computational complexity, creating a bottleneck for deployment on resource-constrained edge devices [16], [17].”
Enhancing human activity recognition through GAN-augmented data and multi-branch CNN-LSTM networks
Shahid, A., Khan, M. H., Nisar, M. A., & Farid, M. S. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116783 · Cited by 1
Sowmiya, S., & Dharmaraj, M. (2024) · International Journal of Intelligent Systems and Applications in Engineering · Cited by 1
Human Activity Recognition Algorithm Based on One-Dimensional Convolutional Neural Network
Tang, D., Jin, M., Wang, Q., Wei, Z., & Zhang, J. (2020) · Revue d intelligence artificielle · doi:10.18280/ria.340110 · Cited by 1
“The research showed that the deep learning method can achieve improved performance compared with traditional machine learning methods in practical applications [7].”
MethodSENSOR-BASED HUMAN ACTIVITY RECOGNITION USING BIDIRECTIONAL LSTM FOR CLOSELY RELATED ACTIVITIES
Pavai, A. T. (2018) · CSUSB ScholarWorks (California State University, San Bernardino) · Cited by 1
Deep Neural Networks for Human Behavior Understanding
Singh, R. K., & Nigam, S. (2019) · Springer eBooks · doi:10.1007/978-3-030-15887-3_32 · Cited by 1
Ecg-based Stethoscope Tracking Using Transfer Learning
Yhdego, H. G., Kidane, N., McKenzie, F., & Audette, M. A. (2020) · Spring Simulation Multiconference · doi:10.22360/springsim.2020.msm.009 · Cited by 1
“Previous works have combined continuous wavelet transform (CWT) representation with CNN to address classification tasks of time-series data (Ravi et al. 2016) (Yhdego et al. 2019).”
Semi-supervised Adaptive Method for Human Activities Recognition (HAR)
Palechor, F. M., Vicario, E., Patara, F., Manotas, A. D. L. H., & Molina-Estren, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-10539-5_1 · Cited by 1
Indoor Intelligent IoT Datasets for Behavioral Learning and Autonomous Decision Making
Ye, H., & Luo, H. (2022) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom57177.2022.00115 · Cited by 1
“Among them, papers [12-13] are special in that both try to use mobile phones to collect relevant data for HAR.”
BackgroundAn Analysis about Federated Learning in Low-Powerful Devices
Flores-Martin, D., Galán–Jiménez, J., Berrocal, J., & Murillo, J. M. (2023) · doi:10.1145/3631309.3632833 · Cited by 1
Abdullayev, J., & Zingoni, A. (2023) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine58569.2023.10405616 · Cited by 1
“In [25], a resource-efficient implementation of DL for human activity recognition, such as walking, running, sitting, standing, and other common daily activities on low-power devices, is proposed.”
BackgroundMhalla, A., & Favreau, J.-M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-62488-9_4 · Cited by 1
A data fusion-based hybrid sensory system for older people’s daily activity recognition.
Wang, Y. (2019) · Bournemouth University Research Online (Bournemouth University) · Cited by 1
Hybrid deep neural network models for boosting Human Activity Recognition using IoT wearablesPreprint
Sowmiya, S., & Dharmaraj, M. (2022) · Research Square · doi:10.21203/rs.3.rs-2035081/v1 · Cited by 1
Li, J., Ding, R., Nie, L., Li, X., Si, X., Wang, L., Chu, D., & Zhan, D. (2018) · EAI International Conference on Mobile Multimedia Communications (MobiMedia) · doi:10.4108/eai.21-6-2018.2276633
“Currently, in the field of deep learning model, convolutional neural networks mainly rely on three important properties, including local connection, weight sharing and translation invariant[8][9] to extract complex features, so that convolutional neural networks have achieved good research results in the field of acti…”
BackgroundMethodDeep learning aiding Health Informatics in Drug discovery
Jasrotia, M., & Kaur, P. (2019) · International Journal of Computer Sciences and Engineering · doi:10.26438/ijcse/v7i5.315320
An active smartphone authentication method based on daily cyclical activityPreprint
Mi, C., Xu, R., Lin, C., & Meng, R. Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.00045
“During data collection, previous researches generally adopt low duty-cycled operations, which is switching the sensors between sleeping mode and working mode to save battery[28][32][33].”
MethodApplications of Deep Learning for Sequential Data: Music, Human Activity and Language
Brunner, G. (2020) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000450816
Machine Learning Vs Deep Learning: Which Is Better For Human Activity Recognition
Uddin, N., Singh, M. P., & Rakesh, M. V. (2020) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.c6310.049420
Machine Learning for Sensor Networks
Sanei, S., Jarchi, D., & Constantinides, A. G. (2020) · Wiley eBooks · doi:10.1002/9781119390060.ch9
Lee, U. H. (2022) · Deep Blue (University of Michigan) · doi:10.7302/6383
Detection of Human Behavior Using Swarm Technique and Neural Networks
Shankar, V. (2022) · Algorithms for intelligent systems · doi:10.1007/978-981-19-1669-4_22
Development of Fast Posture Classification System for Table Tennis Robot
Jin, S., Kwon, Y., Kim, Y., Park, M.-Y., An, J., Kang, H., Choi, J., & Lee, I. (2022) · The Journal of Korea Robotics Society · doi:10.7746/jkros.2022.17.4.463
DEEP LEARNING PROJECT BASED ON HUMAN ACTIVITY RECOGNITION
Sarumathi, G., Susmitha, T., Shivani, S., & Sathish, S. (2023) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem18015
Feature Selection and Energy Management in Wireless Sensor Networks using Deep Learning
Dora, S. S., & Swain, P. K. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i9s.7476
Villegas-Cortéz, J., Román-Alonso, G., de Vega, F. F., Flores-Morales, Y. A., & Cordero-Sánchez, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47765-2_24 · Cited by 1
Human activity recognition with machine learning
Kaushal, P., Gandhi, V., & Chahal, J. K. (2023) · AIP conference proceedings · doi:10.1063/5.0178130
Human Activity Recognition Using Hybrid Feature Extraction and Machine Learning
Jabade, V., Mane, S., & Khan, Z. (2023) · International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE) · doi:10.1109/aikiie60097.2023.10390534
“Its adaptability for a variety of activities and sensor setups is highlighted, and computation times are adequate for devices like smartphones [7].”
BackgroundData Based Framework for Sleep Medicine
Zovko, K., Šolić, P., Perković, T., Dodig, I. P., Kalcina, L. L., Pecotić, R., & Đogaš, Z. (2024) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech61897.2024.10612503
Visualizing and Analyzing Human Activity Patterns through Graph-Based Methods
Rahin, S. A., Hui, B., & Li, W. (2024) · International Conference on Machine Learning and Machine Intelligence (MLMI) · doi:10.1145/3696271.3696310
PhysioFit: A Inline Activity Recognition Leveraging Physiological Sensors
Subramanian, R. R., Gatikoppu, S. P. P. K., Chitikina, V. K., Jana, P., & Gollapalli, S. V. N. M. T. (2024) · International Conference on Automation, Computing and Renewable Systems (ICACRS) · doi:10.1109/icacrs62842.2024.10841482
Borty, S. C., Awan-Ur-Rahman, Ankolu, G., Quddus, S., Hasan, M. M., Chakravarty, S., Adewuyi, M. F., & Sakib, N. (2026) · SoftwareX · doi:10.1016/j.softx.2026.102901
Human Activity Recognition through ensemble Learning of Convulational neural network
-, M. B. (2025) · International Journal on Science and Technology · doi:10.71097/ijsat.v16.i2.5952
Subramanian, R. R., Dasharath, S., Dewi, D. A., & Gatikoppu, S. P. P. K. (2025) · International Conference on Computational Robotics, Testing and Engineering Evaluation (ICCRTEE) · doi:10.1109/iccrtee64519.2025.11053011
Human Activity Recognition Using Machine Learning
Kaushal, Y., Neha, & Kumar, K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4933-4_25
Sensor Based Human Activity Recognition using Machine Learning
Maurya, A., Mukherjee, C., Singh, P. K., Ali, D. I., & Pachauri, P. (. ). S. (2025) · Iconic Research and Engineering Journals · doi:10.64388/irev9i5-1712015
Artifact Correction Method for M-response using UNet1D Network
Zabrodin, K., Selivanova, K. G., & Geletka, O. (2025) · IEEE KhPI Week on Advanced Technology (KhPIWeek) · doi:10.1109/khpiweek61436.2025.11288400
“This makes areas like EEG, ECG, and EMG particularly interesting in the context of using this architecture due to its skip connections and efficient handling of local and global features [3], [8].”
Human activity recognition engineering
Konak, O. (2025) · publish.UP (University of Potsdam) · doi:10.25932/publishup-67015
The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms
Qendro, L., Chauhan, J., Ramos, A. G. C. P., & Mascolo, C. (2021) · Apollo (University of Cambridge) · doi:10.17863/cam.69890
Multi-modal Human Behavior Understanding
Chen, K. (2020) · UNSWorks (UNSW Sydney) · doi:10.26190/unsworks/21785
Detección de actividades humanas con sensores portables
Benages-Pardo, L., & Pérez, J. D. B. (2018) · Zaguan (University of Zaragoza Repository)
Time Series Classification of Sport Activities using Neural Networks : master's thesis
Мостафа, В. М. М., & Mostafa, W. M. M. (2024) · Electronic scientific archive of UrFU (Ural Federal University)
Smartwatch-based semantic learning of elements of human behaviour
Alevizaki, A. (2023) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.5287/ora-ovz6x06gr
Hybrid CNN-Based Models for Enhancing Human Activity Recognition Using Wearable Sensor Data
VUONG, T. H., ヴァン, テ. ホ., & VUONG, T. H. (2025) · SOKENDAI (Graduate University for Advanced Studies)
On-demand Crowdsourced Federated Learning over Edge Devices
Tahir, M. (2025) · Dublin City University Open Access Institutional Repository (Dublin City University)
Objective detection of Parkinson's disease motor states using Lasso-selected IMUs features
Memedi, M. (2026) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2026.101732
Pandian, G., & Kesavan, K. (2025) · International Conference on Smart Structures and Systems (ICSSS) · doi:10.1109/icsss66939.2025.11346260
“…on IoT-enabled fall detection systems that uses accelerometer and gyroscope sensors to identify unfortunate movement patterns in old individuals Deep learning algorithms like Convolutional Neural Networks (CNNs) have been used to enhance fall detection accuracy as stated by Ravi et al. [4].”
Optimizing feature selection in multilayer ensemble models for improved HAR accuracy
Jaiswal, D. P., & Shrivastava, A. K. (2026) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v15i1.10769
“Also, as previously mentioned, deep learning [16] models can be highly accurate but require high computation and are therefore generally not suitable for use in real-time or limited resource applications [17].”
(2026) · International Journal of Progressive Research in Engineering Management and Science · doi:10.58257/ijprems51628
Activity detection systems using infrared array sensors with deep learning (本文)
アルムガサミー, ム. ク., & Arumugasamy, M. K. (2022) · Institutional Repositories DataBase (IRDB)
Structured Motion Representation Learning for Robust Temporal Gesture Recognition
Vaishenaav, S., Iyengar, S. S., Akash, A. R., Kannah, R. V., Yajun, S., & Brindha, S. (2026) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem59590
Development of ML model for triboelectric nanogenerator based sign language detection system
Patel, M., Baro, B., Bayan, S., & Roy, M. (2026) · IEEE Guwahati Subsection Conference (GCON) · doi:10.1109/gcon69192.2026.11649240
“The frequency-domain representation, which has not yet been shown to be sensitive to changing timing implementation of the activity [10], was found to be popular in sensor-based activity recognition, and the MFCC features, which were initially designed to aid with speech recognition [14], have…”
Machine Learning for Sensor-Based Human Activity Recognition
Mukherjee, C., Singh, P. K., Pachauri, P. (. ). S., & Ali, D. I. (2026) · Iconic Research and Engineering Journals · doi:10.64388/irev9i10-1716485
STORM: Hardware-Aware Tiny Transformer Co-Design for Low-Power Inertial Human Activity Recognition
Varaldi, A., Genta, C., Manzone, A., & Vacca, M. (2026) · Electronics · doi:10.3390/electronics15091924
A Deep Attention-BLSTM Pipeline for Human Action Recognition
Yozbakee, A. A., Ghozzi, Y., Hamdani, T. M., & Alimi, A. M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-21585-7_3
Orfanos, S., Sanghan, T., Menychtas, A., Panagopoulos, C., Maglogiannis, I. G., & Chatpun, S. (2026) · Sensors · doi:10.3390/s26103143
“Studies thus far have used both machine and deep learning models such as support vector machines (SVMs), random forests (RFs), and convolutional neural networks (CNNs) to classify human movement patterns via IMU features [17,18].”
Metadata
- Authors
- Ravi, D., Wong, C., Lo, B., & Yang, G.-Z.
- Affiliations
- Imperial College London (GB)
- Venue
- 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 71-76
- ISSN
- 2376-8886 (ISSN-L)
- OpenAlex
- W2495920728
- Cited by
- 269
- References
- 22
- Citations by year
- 2026: 11 · 2025: 22 · 2024: 23 · 2023: 27 · 2022: 44 · 2021: 38 · 2020: 36 · 2019: 30 · 2018: 25 · 2017: 11 · 2016: 2
- FWCI
- 7.87
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Wearable and Implantable Body Sensor Networks (publishedVersion)
- Spiral (Imperial College London) (submittedVersion)
- Funders
- Engineering and Physical Sciences Research Council (EP/H009744/1, EP/L014149/1, EP/E044298/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Keywords
- human activity recognition, inertial data, wearable devices, real-time classification, temporal convolution, resource-efficient deep learning, mobile devices
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.