The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Deep learning for human activity recognition: A resource efficient implementation on low-power devices
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
Deep learning for sensor-based activity recognition: A survey
Wang, J., Chen, Y., Hao, S., Peng, X., & Hu, L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.02.010 · Cited by 2,014
“For multi-modal signals, it is better to use CNN since (Bhattacharya and Lane, 2016) Body-worn, ambiemt RBM Gesture, ADL, transportation Self, D01 (Chen and Xue, 2015) Body-worn CNN ADL Self (Chen et al., 2016b) Body-worn CNN ADL D06 (Edel and K¨oppe, 2016) Body-worn RNN ADL D01, D04, Self (Fang and Hu, 2014) Object,…”
MethodInfluentialDeep Learning for Health Informatics
Ravì, D., Wong, C., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B., & Yang, G.-Z. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2636665 · Cited by 2,000
“[96] proposed data preprocessing techniques to standardize and reduce variations in the input data caused by differences in sensor properties, such as placement and orientation.”
MethodSelf-citationA State-of-the-Art Survey on Deep Learning Theory and Architectures
Alom, M. Z., Taha, T. M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M. S., Hasan, M., Van Essen, B. C., Awwal, A. A. S., & Asari, V. K. (2019) · Electronics · doi:10.3390/electronics8030292 · Cited by 1,620
Network Intrusion Detection for IoT Security Based on Learning Techniques
Chaabouni, N., Mosbah, M., Zemmari, A., Sauvignac, C., & Faruki, P. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2896380 · Cited by 940
“in [158] where they presented an optimization approach to enable the use of real-time deep learning in low-power devices.”
BackgroundNweke, H. F., Teh, Y. W., Al-garadi, M. A., & Alo, U. R. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.03.056 · Cited by 930
Deep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690
“Considering deep neural networks are more effective in feature extraction than shallow ones, a combination of human-crafted and deep features is a potential solution to lowering computation cost. In [119], the authors incorporated the spectrogram features with only one CNN layer and two fully-connected layers for huma…”
BackgroundDeep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022) · Sensors · doi:10.3390/s22041476 · Cited by 625
Deep Recurrent Neural Networks for Human Activity Recognition
Murad, A., & Pyun, J.-Y. (2017) · Sensors · doi:10.3390/s17112556 · Cited by 524
“The proposed method achieved better overall accuracy than other methods, such as CNNs [28], least squares support vector machine (LS-SVM) [30], and random forest [31], as shown in Figure 9b.”
BackgroundMethodInfluentialBianchi, V., Bassoli, M., Lombardo, G., Fornacciari, P., Mordonini, M., & De Munari, I. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2920283 · Cited by 466
“Finally, in [32] the hardware is a smartphone: this is a good solution when a shortterm monitoring has to be done (e.”
BackgroundMethodA deep learning approach to on-node sensor data analytics for mobile or wearable devices
Ravi, D., Wong, C., Lo, B., & Yang, G.-Z. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2633287 · Cited by 439
Self-citationA survey on wearable sensor modality centred human activity recognition in health care
Wang, Y., Cang, S., & Yu, H. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.04.057 · Cited by 409
Nweke, H. F., Teh, Y. W., Mujtaba, G., & Al-garadi, M. A. (2019) · Information Fusion · doi:10.1016/j.inffus.2018.06.002 · Cited by 394
Human activity recognition in artificial intelligence framework: a narrative review
Gupta, N., Gupta, S. K., Pathak, R. K., Jain, V., Rashidi, P., & Suri, J. S. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10116-x · Cited by 337
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314
“Considering deep neural networks are more effective in feature extraction than shallow ones, a combination of human-crafted and deep features is a potential solution to lowering computation cost. In [119], the authors incorporated the spectrogram features with only one CNN layer and two fully-connected layers for huma…”
BackgroundYadav, S. K., Tiwari, K., Pandey, H. M., & Akbar, S. A. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.106970 · Cited by 311
Recent trends in machine learning for human activity recognition—A survey
Ramasamy Ramamurthy, S., & Roy, N. (2018) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1254 · Cited by 299
“Ravi, Wong, Lo, and Yang (2016) validated their accuracy with real-life datasets such as OPPORTUNITY (Roggen et al., 2009), Transportation & Physical (Bhattacharya & Lane, 2016), and Indoor/Outdoor (Radu et al., 2014) datasets with different state-of-the-art classifiers for each of the activities.”
BackgroundAzam, Z., Islam, M. M., & Huda, M. N. (2023) · IEEE Access · doi:10.1109/access.2023.3296444 · Cited by 265
A Multi-View Deep Learning Framework for EEG Seizure Detection
Yuan, Y., Xun, G., Jia, K., & Zhang, A. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2871678 · Cited by 258
“the time domain [22], [50], [71].”
Human Activity Recognition Using Inertial Sensors in a Smartphone: An Overview
Sousa Lima, W., Souto, E., El-Khatib, K., Jalali, R., & Gama, J. (2019) · Sensors · doi:10.3390/s19143213 · Cited by 256
A federated learning system with enhanced feature extraction for human activity recognition
Xiao, Z., Xu, X., Xing, H., Song, F., Wang, X., & Zhao, B. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107338 · Cited by 251
Multiscale Deep Feature Learning for Human Activity Recognition Using Wearable Sensors
Tang, Y., Zhang, L., Min, F., & He, J. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3161812 · Cited by 224
“…the proposed method is also able to provide a consistent performance improvement, beating several state-of-the-art algorithms, e.g., Ravi et al. ’s [29] method combining features learned by CNN together with a set of shallow features by 0.82%, Alsheikh et al. ’s [30] method using deep belief…”
MethodInfluentialNano-enabled biosensing systems for intelligent healthcare: towards COVID-19 management
Mujawar, M. A., Gohel, H., Bhardwaj, S. K., Srinivasan, S., Hickman, N., & Kaushik, A. (2020) · Materials Today Chemistry · doi:10.1016/j.mtchem.2020.100306 · Cited by 223
Islam, M. M., Nooruddin, S., Karray, F., & Muhammad, G. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106060 · Cited by 217
“The system developed in [62] used just one CNN layer and two fully connected layers where the spectrogram features are fed into the network for activity recognition.”
MethodDanHAR: Dual Attention Network for multimodal human activity recognition using wearable sensors
Gao, W., Zhang, L., Teng, Q., He, J., & Wu, H. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107728 · Cited by 214
Kumar, P., Chauhan, S., & Awasthi, L. K. (2024) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-09986-x · Cited by 206
“The authors of [133] have proven that a shallow three-layer CNN network can successfully recognise activities occurring locally on a device running on a limited amount of system resources.”
Convolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors
Moya Rueda, F., Grzeszick, R., Fink, G. A., Feldhorst, S., & Ten Hompel, M. (2018) · Informatics · doi:10.3390/informatics5020026 · Cited by 196
“In theory, this abstraction should also allow for more robustness against the IMUs being slightly asynchronous or having different characteristics [10,23].”
BackgroundMethodTeng, Q., Wang, K., Zhang, L., & He, J. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2978772 · Cited by 183
“We evaluate our method on five public benchmark datasets, namely UCI HAR dataset [7], Opportunity dataset [17], UniMib-SHAR dataset [18], PAMAP2 dataset [19] and WISDM dataset [20].”
BackgroundMethodInfluentialXiao, Z., Tong, H., Qu, R., Xing, H., Luo, S., Zhu, Z., Song, F., & Feng, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3344294 · Cited by 172
“This section reviews the existing studies on wearable HAR, CapNet, CL, and KD.”
Algarni, M., Saeed, F., Al-Hadhrami, T., Ghabban, F. M., & Al-Sarem, M. (2022) · Sensors · doi:10.3390/s22082976 · Cited by 170
“In the study by [10], a smartphone was used as a sensor to measure, say, the output/data collected from accelerometers and gyroscopes to study human activity.”
MethodA review of machine learning-based human activity recognition for diverse applications
Kulsoom, F., Narejo, S., Mehmood, Z., Chaudhry, H. N., Butt, A., & Bashir, A. K. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07665-9 · Cited by 167
Tang, Y., Teng, Q., Zhang, L., Min, F., & He, J. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3015521 · Cited by 166
“al, 2016 [41]; Alsheikh et al, 2015 [42]).”
MethodInfluentialTriple Cross-Domain Attention on Human Activity Recognition Using Wearable Sensors
Tang, Y., Zhang, L., Teng, Q., Min, F., & Song, A. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2021.3136642 · Cited by 139
A database of human gait performance on irregular and uneven surfaces collected by wearable sensors
Luo, Y. G., Coppola, S. M., Dixon, P. C., Li, S., Dennerlein, J. T., & Hu, B. (2020) · Scientific Data · doi:10.1038/s41597-020-0563-y · Cited by 137
Multi-Sensor Fusion for Activity Recognition—A Survey
Aguileta, A. A., Brena, R., Mayora, O., Minero, E. M., & Trejo, L. A. (2019) · Sensors · doi:10.3390/s19173808 · Cited by 133
An effective deep autoencoder approach for online smartphone-based human activity recognition
Almaslukh, B., Artoli, A. M., & Al-Muhtadi, J. F. (2017) · Cited by 132
Zhao, T., Xie, Y., Wang, Y., Cheng, J., Guo, X., Hu, B., & Chen, Y. J. (2022) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3153408 · Cited by 129
Qi, W., Su, H., Yang, C., Ferrigno, G., Momi, E. D., & Aliverti, A. (2019) · Sensors · doi:10.3390/s19173731 · Cited by 126
“In other words, the performance of the designed FE algorithms decided the recognition rate and computational speed of the classifier [24], for example, k-NN, SVM, DT, and ANN methods [25] only worked well under the premise of extracting perfect features from the collected signals.”
MethodA Novel Deep Learning Bi-GRU-I Model for Real-Time Human Activity Recognition Using Inertial Sensors
Tong, L., Ma, H., Lin, Q., He, J., & Peng, L. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3148431 · Cited by 126
Physical activity recognition by smartphones, a survey
Morales, J., & Akopian, D. (2017) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2017.04.004 · Cited by 122
Zebin, T., Scully, P., Peek, N. B., Casson, A. J., & Ozanyan, K. B. (2019) · IEEE Access · doi:10.1109/access.2019.2941836 · Cited by 119
“A detailed review of few other deep learning methods are available in [1], [13], [14].”
BackgroundRecognition and Repetition Counting for Complex Physical Exercises with Deep Learning
Soro, A., Brunner, G., Tanner, S., & Wattenhofer, R. P. (2019) · Sensors · doi:10.3390/s19030714 · Cited by 110
Zebin, T., Sperrin, M., Peek, N., & Casson, A. J. (2018) · 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8513115 · Cited by 107
“[5] and [10] used Long-Short Term Memory (LSTM) RNNs to better exploit the temporal correlations between input data samples by having memory cells and controlling gates embedded in the architecture.”
MethodCheng, X., Zhang, L., Tang, Y., Liu, Y., Wu, H., & He, J. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3149337 · Cited by 99
Smartphone-Based Activity Recognition for Indoor Localization Using a Convolutional Neural Network
Zhou, B., Yang, J., & Li, Q. (2019) · Sensors · doi:10.3390/s19030621 · Cited by 99
“Ravi et al. [37] propose a deep learning method for human activity recognition using low-power devices.”
MethodSurvey on Human Activity Recognition based on Acceleration Data
Slim, S. O., Atia, A., Marwa, M. A., & Mostafa, M.-S. M. (2019) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2019.0100311 · Cited by 96
“Transportation Riding a bus, Cycling, Driving [24][28][38][40][47][53][5556][58][61][63-64][67]”
MethodInfluentialWang, J., Chen, Y., Gu, Y., Xiao, Y., & Pan, H. (2018) · 2018 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489106 · Cited by 92
“Deep learning models with automatic feature extraction are also widely adapted to this community[14].”
BackgroundExtending the battery lifetime of wearable sensors with embedded machine learning
Fafoutis, X., Marchegiani, L., Elsts, A., Pope, J., Piechocki, R. J., & Craddock, I. J. (2018) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot.2018.8355116 · Cited by 87
“Examples can be found for Support Vector Machines (SVM) [14], artificial neural networks [15] and deep learning [16].”
BackgroundIss2Image: A Novel Signal-Encoding Technique for CNN-Based Human Activity Recognition
Hur, T., Bang, J., Huynh‐The, T., Lee, J., Kim, J., & Lee, S. (2018) · Sensors · doi:10.3390/s18113910 · Cited by 87
“[25] changed ACC signals into spectrograms, a three-dimensional representation of changes in the acceleration energy content of a signal as a function of frequency and time.”
BackgroundIncreasing Robustness in the Detection of Freezing of Gait in Parkinson’s Disease
San-Segundo, R., Navarro-Hellín, H., Torres-Sánchez, R., Hodgins, J., & De la Torre, F. (2019) · Electronics · doi:10.3390/electronics8020119 · Cited by 86
“[23] used a convolutional neural network (CNN) with one convolutional layer for feature extraction and one fully connected layer for classification.”
MethodFederated Contrastive Learning With Feature-Based Distillation for Human Activity Recognition
Xiao, Z., & Tong, H. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3510428 · Cited by 86
“Ravi et al. [46] introduced a convolutional model with temporal extraction to capture local features in HAR data.”
Yoosefzadeh-Najafabadi, M., Tulpan, D., & Eskandari, M. (2021) · Remote Sensing · doi:10.3390/rs13132555 · Cited by 86
Sung, C., & Park, J. Y. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10809-z · Cited by 82
“[8] 2015 Railway track inspection Ravi et al. [33] 2016 Human activity recognition Cheng et al. [6] 2016 Recommendation systems Hung et al. [11] 2017 Biological image data.”
BackgroundAttention-Based Deep Learning Framework for Human Activity Recognition With User Adaptation
Buffelli, D., & Vandin, F. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3067690 · Cited by 81
“On the other hand, Model Driven approaches [e.g. 21, 31, 39] first preprocess the data to get a grid-like structure, and then use CNNs.”
MethodDeep transfer learning in sheep activity recognition using accelerometer data
Kleanthous, N., Hussain, A. J., Khan, W., Sneddon, J. C., & Liatsis, P. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117925 · Cited by 76
Heterogeneous Mutual Knowledge Distillation for Wearable Human Activity Recognition
Xiao, Z., Xing, H., Qu, R., Li, H., Cheng, X., Xu, L., Li, F., & Wan, Q. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3556317 · Cited by 75
Aiello, G., Catania, P., Vallone, M., & Venticinque, M. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106637 · Cited by 74
A study of deep neural networks for human activity recognition
Sansano, E., Montoliu, R., & Belmonte Fernández, Ó. (2020) · Computational Intelligence · doi:10.1111/coin.12318 · Cited by 73
DeepMI: Deep multi-lead ECG fusion for identifying myocardial infarction and its occurrence-time
Tadesse, G. A., Javed, H. A., Weldemariam, K., Liu, Y., Liu, J., Chen, J., & Zhu, T. (2021) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102192 · Cited by 73
CarePre: An Intelligent Clinical Decision Assistance System
Jin, Z., Cui, S., Guo, S., Gotz, D., Sun, J., & Cao, N. (2020) · ACM Transactions on Computing for Healthcare · doi:10.1145/3344258 · Cited by 70
“Some deep learning techniques have been developed to assess risk for specific conditions, such as the diagnosis of heart disease [1, 40, 51], cancer [10, 14, 53], and mental health [2, 22, 41].”
BackgroundA Survey of Deep Learning Based Models for Human Activity Recognition
Khan, N. S., & Ghani, M. S. (2021) · Wireless Personal Communications · doi:10.1007/s11277-021-08525-w · Cited by 69
“For such cases, other measures are used such as precision, recall [61], f-measure [80, 85, 86, 88, 92, 94–96], and specificity [61] which are more appropriate.”
BackgroundMethodInfluentialDeep learning-based cattle behaviour classification using joint time-frequency data representation
Hosseininoorbin, S., Layeghy, S., Kusý, B., Jurdak, R., Bishop-Hurley, G. J., Greenwood, P. L., & Portmann, M. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106241 · Cited by 69
“the case for animals [21], accelerometry signals of human fetal activity [23], and human activity signals more generally [22, 24, 25].”
BackgroundInfluentialA perspective on human activity recognition from inertial motion data
Gomaa, W. E., & Khamis, M. A. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08863-9 · Cited by 69
DeXAR: Deep Explainable Sensor-Based Activity Recognition in Smart-Home Environments
Arrotta, L., Civitarese, G., & Bettini, C. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3517224 · Cited by 68
A survey on deep learning for challenged networks: Applications and trends
Bochie, K., Gilbert, M. S., Gantert, L., Barbosa, M. S. M., Medeiros, D. S. V., & Campista, M. E. M. (2021) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2021.103213 · Cited by 66
“observe that classification complexity is reduced when producing a spectrogram of the input data before passing it on to the neural network [81].”
How Validation Methodology Influences Human Activity Recognition Mobile Systems
Bragança, H. L. D. S., Colonna, J. G., Oliveira, H. A. B. F., & Souto, E. (2022) · Sensors · doi:10.3390/s22062360 · Cited by 65
“For HAR, the most common solutions found in the literature are based on Convolutional Neural Networks (CNN) and Long-Short-Term Memory Recurrent (LSTMs) [28,36,38,39].”
BackgroundMethodPSDRNN: An Efficient and Effective HAR Scheme Based on Feature Extraction and Deep Learning
Xiao, L., Wang, Y., Zhang, B., & Ma, J. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2968920 · Cited by 62
“Targeting at low-ability devices, tri-PSD-Con similarly combined the shallow feature PSD and deep learning based recognition model [19].”
BackgroundMethodIMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition
Leng, Z., Bhattacharjee, A., Rajasekhar, H., Zhang, L., Bruda, E., Kwon, H., & Plötz, T. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3678545 · Cited by 61
“The effectiveness of these methods relies heavily on the availability of accurately annotated datasets.”
Hoelzemann, A., Romero, J., Bock, M., Laerhoven, K. V., & Lv, Q. (2023) · Sensors · doi:10.3390/s23135879 · Cited by 61
“ActiveMiles is limited to simple locomotion activities, and Leisure Activities consists of six participants’ wrist-worn inertial data over a week where each of them performed one specific leisure activity daily.”
BackgroundApplying Deep Learning to Individual and Community Health Monitoring Data: A Survey
Yao, Z., Bi, J., & Chen, Y. (2018) · Machine Intelligence Research · doi:10.1007/s11633-018-1136-9 · Cited by 61
Mahmud, T., Sazzad Sayyed, A. Q. M., Fattah, S. A., & Kung, S.-Y. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3015781 · Cited by 58
Comprehensive machine and deep learning analysis of sensor-based human activity recognition
Balaha, H. M., & Hassan, A. E.-S. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08374-7 · Cited by 58
“For basic activity, SVM was mainly used for recognition.”
MethodInfluentialDargazany, A. R., Stegagno, P., & Mankodiya, K. (2018) · Mobile Information Systems · doi:10.1155/2018/8125126 · Cited by 57
“Embedding DL in low-power devices for healthcare Survey(2016) [122], Ravi(2016,2017) [123], [124], [124]–[127] Survey(2016) [122] Survey(2016) [122]”
Huang, W., Zhang, L., Teng, Q., Song, C., & He, J. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3092396 · Cited by 56
“4) WISDM dataset[44]: The WISDM group collected the WISDM dataset.”
MethodCheng, D., Zhang, L., Bu, C., Wu, H., & Song, A. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110789 · Cited by 55
Sound of guns: digital forensics of gun audio samples meets artificial intelligence
Raponi, S., Oligeri, G., & Ali, I. M. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12612-w · Cited by 55
“the context of audio classification [10], sound event classification [11], emotion recognition [12], human activity recognition [9], cross-modality feature learning [13], and gunshot classification [14].”
BackgroundAugmenting Dementia Cognitive Assessment With Instruction-Less Eye-Tracking Tests
Mengoudi, K., Ravì, D., Yong, K. X. X., Primativo, S., Pavisic, I. M., Brotherhood, E., Lu, K., Schott, J. M., Crutch, S. J., & Alexander, D. C. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3004686 · Cited by 55
“arrhythmia from electroencephalogram (EEG) and electrocardiogram (ECG), respectively [14]–[16].”
BackgroundWearables, Artificial intelligence, and the Future of Healthcare
El-Gayar, O., Ambati, L. S., & Nawar, N. (2019) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-5225-9687-5.ch005 · Cited by 54
Deep Ensemble Learning for Human Activity Recognition Using Wearable Sensors via Filter Activation
Huang, W., Zhang, L., Wang, S., Wu, H., & Song, A. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3551486 · Cited by 53
Towards a Secure Internet of Things: A Comprehensive Study of Second Line Defense Mechanisms
Kamaldeep, Dutta, M., & Granjal, J. (2020) · IEEE Access · doi:10.1109/access.2020.3005643 · Cited by 53
“In this regards, researchers can take inspirations from [181], [182].”
BackgroundReal-Time Physical Activity Recognition on Smart Mobile Devices Using Convolutional Neural Networks
Peppas, K. P., Tsolakis, A. C., Krinidis, S., & Tzovaras, D. K. (2020) · Applied Sciences · doi:10.3390/app10238482 · Cited by 53
“[56,57] achieved high performance on both datasets, 98.”
BackgroundRecent Advances in Pedestrian Navigation Activity Recognition: A Review
Wang, Q., Luo, H., Wang, Q., Sun, L., Ma, Z., Zhang, C., Fu, M., & Zhao, F. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3153610 · Cited by 50
Activity Monitoring of Islamic Prayer (Salat) Postures using Deep Learning
Koubâa, A., Ammar, A., Benjdira, B., Al-Hadid, A., Kawaf, B., Al-Yahri, S. A., Babiker, A., Assaf, K., & Ras, M. B. (2020) · International Conference on Data Science and Machine Learning Applications (CDMA) · doi:10.1109/cdma47397.2020.00024 · Cited by 49
“In [16], the authors proposed a human activity recognition technique based on a deep learning model designed for low power devices.”
BackgroundBruinsma, J., & Carloni, R. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3086843 · Cited by 49
“subjects in [16], on raw-data from multiple IMUs on the lower limbs to recognize both the locomotion modes and the transitions of healthy subjects and transtibial amputees in [17], on raw-data from multiple IMUs on the lower-limbs and/or torso to recognize locomotion modes of healthy subjects in [18], on IMU features…”
BackgroundShen, Q., Yang, X. S., Zou, L., Wei, K., Wang, C., & Liu, G. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3195777 · Cited by 47
A survey on intelligent human action recognition techniques
Kumar, R., & Kumar, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17529-6 · Cited by 46
Organizing egocentric videos of daily living activities
Ortis, A., Farinella, G. M., D’Amico, V., Addesso, L., Torrisi, G., & Battiato, S. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.07.010 · Cited by 44
Yhdego, H. G., Li, J., Morrison, S., Audette, M. A., Paolini, C. P., Sarkar, M., & Okhravi, H. R. (2019) · Spring Simulation Multiconference · doi:10.23919/springsim.2019.8732857 · Cited by 44
“Ravi et al (Ravi et al. 2016) show the importance of using a suitable domain when a deep learning methodology is applied to time-series data.”
BackgroundMekruksavanich, S., & Jitpattanakul, A. (2024) · Applied Sciences · doi:10.3390/app14052107 · Cited by 42
“Ravi et al. [29] introduced CNN models with three distinct regularizations, achieving high accuracy in classifying four datasets—ActivMiles, WISDM v1.”
BackgroundHu, B., Li, S., Chen, Y., Kavi, R. R., & Coppola, S. M. (2021) · Applied Ergonomics · doi:10.1016/j.apergo.2021.103414 · Cited by 42
Real-Time Activity Recognition With Instantaneous Characteristic Features of Thigh Kinematics
Cheng, S., Bolívar-Nieto, E., & Gregg, R. D. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3107780 · Cited by 42
Adversarial Patch Attacks and Defences in Vision-Based Tasks: A SurveyPreprint
Sharma, A., Bian, Y., Munz, P., & Narayan, A. (2022) · doi:10.36227/techrxiv.20085902.v1 · Cited by 42
A time-efficient convolutional neural network model in human activity recognition
Gholamrezaii, M., & Almodarresi, S. M. T. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10435-1 · Cited by 40
“In [24], the spectrogram features with one CNN layer and two fully-connected layers for human activity recognition has been used.”
BackgroundMethodActivity Recognition in Sensor Data Streams for Active and Assisted Living Environments
Machot, F. A., Mosa, A. H., Ali, M., & Kyamakya, K. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2764868 · Cited by 40
“Other works like in [45] proposed a technique based on a deep learning methodology to offer real-time activity recognition to be applied on limited power devices.”
BackgroundZebin, T., Scully, P., & Ozanyan, K. B. (2017) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/icsens.2017.8234222 · Cited by 40
“the recognition of activities using a number of classifiers by processing the data collected from a single subject in multiple settings [9, 10] They concluded that activities like standing, walking, running, going up and downstairs, can be recognized with accuracy up to 90.”
BackgroundDeep Learning for Clinical Decision Support Systems: A Review from the Panorama of Smart Healthcare
Kumar, E. S., & Jayadev, P. S. (2019) · Studies in big data · doi:10.1007/978-3-030-33966-1_5 · Cited by 40
Applications of Deep Learning in Healthcare and Biomedicine
Mittal, S., & Hasija, Y. (2019) · Studies in big data · doi:10.1007/978-3-030-33966-1_4 · Cited by 39
Progress of Human Action Recognition Research in the Last Ten Years: A Comprehensive Survey
Singh, P. K., Kundu, S., Adhikary, T., Sarkar, R., & Bhattacharjee, D. (2021) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-021-09681-9 · Cited by 36
“Ravi et al. [182]used temporal convolutions on input from low-power, wearable devices to recognize action classes.”
BackgroundLee, U. H., Bi, J., Patel, R., Fouhey, D. F., & Rouse, E. J. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3007455 · Cited by 35
“Inspired by [15], we modified this approach to be suitable for our tasks by developing an analysis pipeline composed of a lightweight neural network architecture and a mel-scaled spectrogram.”
BackgroundMethodInfluentialDetection and prediction of freezing of gait with wearable sensors in Parkinson’s disease
Zhang, W., Sun, H., Huang, D., Zhang, Z., Li, J., Wu, C., Sun, Y., Gong, M., Wang, Z., Sun, C., et al. (2023) · Neurological Sciences · doi:10.1007/s10072-023-07017-y · Cited by 36
Liang, J., Zhang, L., Bu, C., Cheng, D., Wu, H., & Song, A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122180 · Cited by 35
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.