A tutorial on human activity recognition using body-worn inertial sensors
The DOI matches its Crossref record; 131 of the 132 references it cites were found in a registry or an index.
Abstract
The last 20 years have seen ever-increasing research activity in the field of human activity recognition. With activity recognition having considerably matured, so has the number of challenges in designing, implementing, and evaluating activity recognition systems. This tutorial aims to provide a comprehensive hands-on introduction for newcomers to the field of human activity recognition. It specifically focuses on activity recognition using on-body inertial sensors. We first discuss the key research challenges that human activity recognition shares with general pattern recognition and identify those challenges that are specific to human activity recognition. We then describe the concept of an Activity Recognition Chain (ARC) as a general-purpose framework for designing and evaluating activity recognition systems. We detail each component of the framework, provide references to related research, and introduce the best practice methods developed by the activity recognition research community. We conclude with the educational example problem of recognizing different hand gestures from inertial sensors attached to the upper and lower arm. We illustrate how each component of this framework can be implemented for this specific activity recognition problem and demonstrate how different implementations compare and how they impact overall recognition performance.
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 promising results delivered in these works without the use of labels have resulted in a general direction of integrating unsupervised learning as-is into conventional activity recognition chains (ARC) [8] in the feature extraction step.”
From Contrastive Predictive Coding for Human Activity Recognition (2021) · cites this paper as [8]
In the citing paper
“The comparative studies using our evaluation framework are novel, because such an analysis has in particular been missing in most survey papers of sensor-based HAR [1,2,3].”
From Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors (2018) · cites this paper as [3]
In the citing paper
“In [3], the authors carried out extensive experiments to assess the effectiveness of several approaches, but only considered simple hand-crafted features and classifiers using a small self-produced dataset.”
From Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors (2018) · cites this paper as [3]
In the citing paper
“While the HAR problem seeks to find a perfect segmentation of activities, this task is difficult to achieve since humans perform activities in a fluent way and the segmentation of time series into intervals that represent single activities is not straightforward (Bulling et al. 2014).”
From Advanced Sensing and Human Activity Recognition in Early Intervention and Rehabilitation of Elderly People (2020) · cites this paper as Bulling et al. 2014
In the citing paper
“The second aspect that goes along with this is that human activity is highly diverse and the recognition of specific activities therefore requires an accurate selection of sensors and their placement (Bulling et al. 2014).”
From Advanced Sensing and Human Activity Recognition in Early Intervention and Rehabilitation of Elderly People (2020) · cites this paper as Bulling et al. 2014
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
A tutorial on hidden Markov models and selected applications in speech recognition
Rabiner, L. R. (1989) · Proceedings of the IEEE · doi:10.1109/5.18626 · Cited by 22,743 · cited 2×
“Given the training data T and an initial guess of the parameters ., a separate model is trained for each class using expectation maximization [Rabiner 1989; Fink 2008].”
MethodAn introduction to ROC analysis
Fawcett, T. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.10.010 · Cited by 21,879 · cited 1×
“Therefore, a common strategy is to sweep the threshold on the score for each individual class (one vs. all) and analyze the behavior in so-called Receiver Operating Characteristic (ROC) or Precision-Recall (PR) curves [Fawcett 2006].”
MethodPeng, H., Long, F., & Ding, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.159 · Cited by 10,544 · cited 2×
“These can be categorized into wrapper [Kohavi and John 1997], filter [Peng et al. 2005], or hybrid [Somol et al.”
BackgroundMethodWrappers for feature subset selection
Kohavi, R., & John, G. H. (1997) · Artificial Intelligence · doi:10.1016/s0004-3702(97)00043-x · Cited by 8,947 · cited 2×
“A large number of researchers investigated machine recognition of gestures and activities from still images and video in constrained environments or stationary settings (see Mitra and Acharya [2007], Turaga et al.”
BackgroundAn introduction to variable and feature selection
GuyonIsabelle, & ElisseeffAndré (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944968 · Cited by 7,715
The Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139
Friedman, J., Hastie, T., & Tibshirani, R. (2000) · The Annals of Statistics · doi:10.1214/aos/1016218223 · Cited by 6,884 · cited 2×
“Introduced in machine learning and computer vision [Friedman et al. 2000; Torralba et al. 2007], boosting as a variant of decision fusion has been successfully applied to activity recognition as well [Lester et al. 2005; Blanke and Schiele 2009; Zinnen et al. 2009b].”
Method2011 Compendium of Physical Activities: A Second Update of Codes and MET Values
AINSWORTH, B. E., HASKELL, W. L., HERRMANN, S. D., MECKES, N., BASSETT, D. R., TUDOR-LOCKE, C., GREER, J. L., VEZINA, J., WHITT-GLOVER, M. C., & LEON, A. S. (2011) · Medicine & Science in Sports & Exercise · doi:10.1249/mss.0b013e31821ece12 · Cited by 6,317 · cited 2×
“Other resources include the comprehensive compendium of physical activity [Ainsworth et al. 2011].”
BackgroundProceedings of the 19th International Joint Conference on Artificial Intelligence
Pujol, J. M., Delgado, J., Ramon Sangüesa, A., & Flache, A. (2005) · International Joint Conference on Artificial Intelligence · Cited by 5,771
Kittler, J., Hatef, M., Duin, R. P. W., & Matas, J. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.667881 · Cited by 5,290 · cited 3×
“J. Kittler et al. 1998.”
Background
Research works printed but not linked: 7
- 10.5555/2015035.2015320 · doi:10.5555/2015035.2015320
- 10.5555/1642293.1642416 · doi:10.5555/1642293.1642416
- 10.5555/1642293.1642417 · doi:10.5555/1642293.1642417
- 10.5555/2283516.2283683 · doi:10.5555/2283516.2283683
- 10.5555/1460232.1460248 · doi:10.5555/1460232.1460248
- 10.5555/2021975.2022004 · doi:10.5555/2021975.2022004
- 10.5555/862896.881089 · doi:10.5555/862896.881089
Cited by
Items 801–900 of 1,007
Ahmad, N., & Leung, H.-F. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3643511 · Cited by 13
“The reader is referred to the survey papers [11, 29] for details on handcrafted feature extraction approaches based on HAR studies.”
MethodFerguson, E. F., Spackman, E. K., Cai, R. Y., Hardan, A. Y., & Uljarević, M. (2024) · Autism Research · doi:10.1002/aur.3207 · Cited by 13
“…measurement units, are needed to capture the multifaceted origins of RRBs in ID and non-speaking samples in a time and context-sensitive manner (Bulling et al., 2014; Cantin-Garside et al., 2020; Gilchrist et al., 2018; Goodwin et al., 2011; Großekathöfer et al., 2017; Nguyen et al., 2021).”
Encoding human activities using multimodal wearable sensory data
Khan, M. H., Shafiq, H., Farid, M. S., & Grzegorzek, M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125564 · Cited by 13
Transformer-Based Contrastive Meta-Learning For Low-Resource Generalizable Activity Recognition
Wang, J., & Faruque, M. A. A. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889848 · Cited by 13
“Deep neural networks have been widely adopted for time-series data processing [2]– [4] and notably improved HAR over traditional methods [5], [6].”
WaveHAR: Learning Wavelet Representation for Wearable Human Activity Recognition
Yao, M., Zhang, L., Cheng, D., Wu, H., & Song, A. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3571487 · Cited by 13
“Current HAR studies can be categorized into two main research lines: video-based HAR and sensor-based HAR [4], [5].”
Measurement of Heel-Rise Test Results using a Mobile Device
Pires, I. M., de Andrade, M. S., García, N. M., Crisóstomo, R. S. D. S., & Flórez‐Revuelta, F. (2015) · Research Repository (Kingston University London) · Cited by 13
From Lens to Prism: Device-Free Modeling and Recognition of Multi-Part Activities
Wenyuan, L., Siyang, W., Wang, L., Binbin, L., Su, X., & Jing, N. (2018) · IEEE Access · doi:10.1109/access.2018.2850534 · Cited by 13
“Based on the Fresnel zone model [24], it is impossible to know which subcarriers are sensitive or insensitive to activity when the relative position is uncertain between the target and the antennas.”
BackgroundSecured healthcare monitoring system in wireless body area network using polynomial based technique
Shanthapriya, R., & Vaithianathan, V. (2019) · Polish Journal of Medical Physics And Engineering · doi:10.2478/pjmpe-2019-0023 · Cited by 13
Identification of Walker Identity Using Smartphone Sensors: An Experiment Using Ensemble Learning
Angrisano, A., Bernardi, M. L., Cimitile, M., Gaglione, S., & Vultaggio, M. (2020) · IEEE Access · doi:10.1109/access.2020.2971693 · Cited by 13
“These approaches are largely applied to recognize human activities from a set of data extracted by using sensors [35].”
BackgroundUzunhisarcıklı, E., Kavuncuoğlu, E., & Özdemir, A. T. (2022) · Computational Intelligence · doi:10.1111/coin.12517 · Cited by 13
“24 In other words, the same activities can be carried out differently by different subjects, and similarities can be found in different activities.”
BackgroundSensor-Based Activity Recognition and Performance Assessment in Climbing: A Review
Andrić, M., Ricci⋆, F., & Zini, F. (2022) · IEEE Access · doi:10.1109/access.2022.3213683 · Cited by 13
Smart Suspenders With Sensors and Machine Learning for Human Activity Monitoring
Mani, N., Haridoss, P., & George, B. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3263231 · Cited by 13
“Most HAR time segments recognize the activity in the transition window, as it is challenging to achieve a fluent segmentation restricted to a single activity [24].”
BackgroundMethodALAE-TAE-CutMix+: Beyond the State-of-the-Art for Human Activity Recognition Using Wearable Sensors
Ahmad, N., & Leung, H.-F. (2023) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom56429.2023.10099138 · Cited by 13
“The traditional sensor-based human activity recognition (HAR) process requires segmentation using sliding windows, manual feature extraction, and machine learning classification [3].”
MethodZhang, Y., Cheng, A., Chen, B., Wang, Y., & Jia, L. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3296987 · Cited by 13
Multimodal Sensor Data Fusion and Ensemble Modeling for Human Locomotion Activity Recognition
Oh, S. W., Jeong, H., Chung, S., Lim, J., & Noh, K. J. (2023) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3594739.3610753 · Cited by 13
“There has already been a lot of research showing that sensor data fusion can improve recognition performance[1, 3, 6, 8, 9, 14].”
BackgroundTransition-Aware Housekeeping Task Monitoring Using Single Wrist-Worn Sensor
Liu, K.-C., Hsieh, C.-Y., & Chan, C.-T. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2868278 · Cited by 13
“The proposed approach constitutes a significant improvement compared to using typical approach while the ability of using typical approach [17] to identify fine-grained transitional activity is limited.”
BackgroundMethodInfluentialAdar: Adversarial Activity Recognition in Wearables
Sah, R. K., & Ghasemzadeh, H. G. (2019) · doi:10.1109/iccad45719.2019.8942124 · Cited by 13
“, ”Is this an image of a dog?” or ”Is the word Harry present in this sentence?”), HAR algorithms need to deal with new challenges due to (1) complexity of human movements captured from individual body joints and observed partially with wearable sensors; and (2) lack of concrete definitions, languages or structure of h…”
BackgroundRodado, D. N., Nugent, C., Cleland, I., Rodríguez, J. V., & Viloria, A. (2020) · Sensors · doi:10.3390/s20071858 · Cited by 13
“This approach has allowed researchers to gain robustness, and reliability, in the process of recognizing human activities [23].”
BackgroundedgeTrans - Edge transport mode detection
Ferreira, P., Zavgorodnii, C., & Veiga, L. (2020) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2020.101268 · Cited by 13
Convolutional Neural Network for Human Activity Recognition and Identification
Gamble, J. A., & Huang, J. (2020) · IEEE International Systems Conference (SysCon) · doi:10.1109/syscon47679.2020.9275924 · Cited by 13
Requirements on Delay of VRU Context Detection for Cooperative Collision Avoidance
Morold, M., Nguyen, Q.-H., Bachmann, M., David, K., & Dressler, F. (2020) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2020-fall49728.2020.9348627 · Cited by 13
“The detection of a pedestrian’s current activity usually comprises different stages within the Activity Recognition Chain for (1) data acquisition (2) preprocessing and segmentation, (3) feature extraction, and (4) classification [13].”
MethodBorz, S. A. (2021) · Forests · doi:10.3390/f12040406 · Cited by 13
Estimation of Fine-Grained Foot Strike Patterns with Wearable Smartwatch Devices
Joo, H., Kim, H., Ryu, J.-K., Ryu, S., Lee, K., & Kim, S.-C. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph19031279 · Cited by 13
“…approaches [31], we mainly focus on body-worn sensors throughout this study because these wearable sensors are ubiquitous (e.g., smartphones [6,8,9,32,33], smartwatch/band [32,34,35], and generic embedded devices [12,36–38]), and, thus, are unobtrusively applicable to users who exercise.”
BackgroundBorz, S. A., Cheţa, M., Bîrda, M., & Proto, A. R. (2022) · Bulletin of the Transilvania University of Brasov Series II Forestry • Wood Industry • Agricultural Food Engineering · doi:10.31926/but.fwiafe.2022.15.64.1.2 · Cited by 13
Bi-STAN: bilinear spatial-temporal attention network for wearable human activity recognition
Gao, C., Chen, Y., Jiang, X., Hu, L., Zhao, Z., & Zhang, Y. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01781-1 · Cited by 13
“Nowadays, wearable-based human activity recognition (HAR) is an active research area of ubiquitous computing and humancomputer interaction [1].”
BackgroundEvaluating Low-cost Activity Trackers for Use in Large-scale Data Gathering of Forestry Workers
Bowen, J., Hinze, A., Cunningham, S. J., & Parker, R. (2015) · Australian Conference on Computer-Human Interaction (OzCHI) · doi:10.1145/2838739.2838741 · Cited by 13
Detection of human respiration patterns using deep convolution neural networks
Petrenko, A., Kyslyi, R., & Pysmennyi, I. (2018) · Eastern-European Journal of Enterprise Technologies · doi:10.15587/1729-4061.2018.139997 · Cited by 13
Ankle torque estimation during locomotion from surface electromyography and accelerometry
Siu, H. C., Sloboda, J., McKindles, R. J., & Stirling, L. (2020) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob49111.2020.9224286 · Cited by 13
“The use of IMUs to estimate human movement has gained popularity in the recent decades due to increasing ubiquity of “smart” devices (phones, watches, etc), which typically contain such sensors and are carried close to the body [5].”
BackgroundPersonalizing Activity Recognition With a Clustering Based Semi-Population Approach
Cruciani, F., Nugent, C., Medina-Quero, J., Cleland, I., McCullagh, P. J., Synnes, K., & Hallberg, J. (2020) · IEEE Access · doi:10.1109/access.2020.3038084 · Cited by 13
“While recent automated Machine Learning (ML) approaches have been proposed (automating part of training process in presence of labeled data) [1], [13], human supervision/intervention is still required to generate reliable labeled datasets [8], [14]–[16].”
BackgroundCina: Suppressing the Detection of Unstable Context Inconsistency
Xu, C., Xi, W., Cheung, S.-C., Ma, X., Cao, C., & Lü, J. (2015) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2015.2418760 · Cited by 13
Smart assisted diagnosis solution with multi-sensor Holter
Bie, R., Zhang, G., Sun, Y., Xu, S., Li, Z., & Song, H. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.06.074 · Cited by 13
Human Activity Recognition With Two Body-Worn Accelerometer Sensors
Hessen, H.-O., & Tessem, A. J. (2016) · NVA (Nasjonalt vitenarkiv) · Cited by 13
Bian, S., Rey, V. F., Yuan, S., & Lukowicz, P. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.14794 · Cited by 13
“, [39, 40] for an overview of IMU-based methods).”
BackgroundMAC-Gaze: Motion-Aware Continual Calibration for Mobile Gaze TrackingPreprint
Lei, Y., Zhao, M., Wang, Y., He, S., Sugano, Y., Khamis, M., & Ye, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.22769 · Cited by 13
“HAR has evolved from traditional feature engineering with classical machine learning algorithms [8] to deep learning architectures, including CNNs [67], RNNs, hybrid CNN-LSTM models [69], attention mechanisms [49, 21], and transformers [45].”
Liu, C.-P., Lu, T.-Y., Wang, H.-C., Chang, C.-Y., Hsieh, C.-Y., & Chan, C.-T. (2024) · Sensors · doi:10.3390/s24206656 · Cited by 12
“Feature Description”
Fu, Z., Cheng, D., Zhang, L., Huang, W., Chen, Z., & Wu, H. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i1.36990 · Cited by 12
“Earlier works often relied on traditional machine learning algorithms such as SVM, KNN, and Random Forests (Bulling, Blanke, and Schiele 2014), requiring manual feature engineering.”
Detecting changes of transportation-mode by using classification data
Lopez, A. J., Ochoa, D., & Gautama, S. (2015) · Ghent University Academic Bibliography (Ghent University) · Cited by 12
Human Activity Recognition: Challenges and Process Stages
Alzahrani, M. S., & Kammoun, S. (2016) · International Journal of Innovative Research in Computer and Communication Engineering · Cited by 12
Leddy, C., Bolger, R., Byrne, P. J., Kinsella, S., & Zambrano, L. (2024) · Int. J. Comput. Sci. Sport · doi:10.2478/ijcss-2024-0007 · Cited by 12
Adaptive model fusion for wearable sensors based human activity recognition
Koskimäki, H., & Siirtola, P. (2016) · Cited by 12
Seeking Optimum System Settings for Physical Activity Recognition on Smartwatches
Ahmad, M. I., Khan, A., Mazzara, M., & Distefano, S. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-17798-0_19 · Cited by 12
Multiple Object Activity Identification Using RFIDs: A Multipath-Aware Deep Learning Solution
Fan, X., Wang, F., Gong, W., Zhang, L., & Liu, J. (2018) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2018.00060 · Cited by 12
“It has attracted significant attention from both academia and industry, with a wide range of solutions based on cameras [1], radars [2], and/or various inertial sensors [3].”
BackgroundStarting Movement Detection of Cyclists Using Smart Devices
Bieshaar, M., Depping, M., Schneegans, J., & Sick, B. (2018) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2018.00042 · Cited by 12
Transfer Learning and Data Fusion Approach to Recognize Activities of Daily Life
Hernandez-Cruz, N., Razzaq, M. A., Nugent, C., McChesney, I., & Zhang, S. (2018) · International Conference on Pervasive Computing Technologies for Healthcare · doi:10.1145/3240925.3240949 · Cited by 12
“Transfer learning has been successfully applied in many application areas such as natural language processing [11], sign language recognition [12], adaptive updating of land-cover maps [13], and activity recognition [14].”
BackgroundDinarević, E. C., Husić, J. B., & Baraković, S. (2019) · Sensors · doi:10.3390/s19235206 · Cited by 12
Ahmed, M., Antar, A. D., & Ahad, M. A. R. (2021) · Pattern Recognition Letters · doi:10.1016/j.patrec.2021.04.001 · Cited by 12
Human Activity and Gesture Recognition Based on WiFi Using Deep Convolutional Neural Networks
Jawad, S. K., & Alaziz, M. (2022) · Iraqi Journal for Electrical And Electronic Engineering · doi:10.37917/ijeee.18.2.14 · Cited by 12
Activities of daily living recognition using optimal trajectories from motion boundaries
Avgerinakis, K., Briassouli, A., & Kompatsiaris, I. Y. (2015) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-150347 · Cited by 12
“The advantage of wearable sensors, e.g. inertial sensors (accelerometers), is that they can be deployed in various environments and can provide information in unconstrained real life conditions [9], while less complicated sensors like accelerometers also entail a lower computational cost.”
Liu, K.-C., & Chan, C.-T. (2017) · Sensors · doi:10.3390/s17010187 · Cited by 12
“Considering the computational complexity, classification performance, target activity, and type of application, the selection of appropriate machine learning-based approaches is a critical component [48,49].”
BackgroundMultimodal Sensor Data Fusion for Activity Recognition Using Filtered Classifier
Razzaq, M. A., Cleland, I., Nugent, C., & Lee, S. (2018) · International Conference on Ubiquitous Computing and Ambient Intelligence (UCAmI) · doi:10.3390/proceedings2191262 · Cited by 12
“A sliding window segmentation technique [19] with the step size of 1-s was chosen in order to keep the maximum number of instances [20] and better performance [21].”
MethodHybrid and Convolutional Neural Networks for Locomotion Recognition
Osmani, A., & Hamidi, M. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3267520 · Cited by 12
“Current approaches gathered under the field of human activity recognition, rely on the well-known processing pipeline [2] which starts by a segmentation step responsible of dividing the data streams coming from sensors into small chunks with a typical granularity being in the order of seconds or…”
BackgroundA More Reliable Step Counter using Built-in Accelerometer in Smartphone
Myo, W. W., Wettayaprasit, W., & Aiyarak, P. (2018) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v12.i2.pp775-782 · Cited by 12
“…in training and testing stages to get the accurate results[2] ISSN: 2502-4752 Indonesian J Elec Eng & Comp Sci, Vol. 12, No. 2, November 2018 : 775 – 782 776 7) Data collection: Necessity of the realistic condition for collecting data[4], [5] These challenges support our decision to do this work.”
BackgroundVirtual Sensors for Optimal Integration of Human Activity Data
Aguileta, A. A., Brena, R., Mayora, O., Minero, E. M., & Trejo, L. A. (2019) · Sensors · doi:10.3390/s19092017 · Cited by 12
“During training, the parameters of these algorithms are learned by reducing the classification error [49].”
BackgroundMethodInfluentialFeasibility of human activity recognition using wearable depth cameras
Voigt, P., Budde, M., Pescara, E., Fujimoto, M., Yasumoto, K., & Beigl, M. (2018) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3267242.3267276 · Cited by 12
“Our results clearly show the potential of wearable depth cameras for HAR.”
MethodInfluentialKhatiwada, P., Chatterjee, A., & Subedi, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03324 · Cited by 12
Jangir, M. K., & Singh, K. (2019) · Journal of Discrete Mathematical Sciences and Cryptography · doi:10.1080/09720529.2019.1696552 · Cited by 11
“In some applications, to describe the time series data, we have a set of shallow features viz. statistical parameters [6], basis transform coding [7], and symbolic representation [8].”
BackgroundDeriving Effective Human Activity Recognition Systems through Objective Task Complexity Assessment
Hiremath, S. K., & Plötz, T. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3432227 · Cited by 11
“The core of our automated guidance is–indirectly–based on the state-of-the-art in human activity recognition, the standard activity recognition chain (ARC) [6], which is used for pre-processing the pilot data.”
BackgroundMethodInfluentialWu, J., & Liu, Q. (2023) · Neural Processing Letters · doi:10.1007/s11063-023-11385-z · Cited by 11
“HAR is a part of traditional pattern recognition, therefore, machine learning methods are widely used to work with human action including time-frequency transformations [12], statistical methods [13], and symbolic representations [14].”
MethodPosture and Body Movement Effects on Behavioral Biometrics for Continuous Smartphone Authentication
Cariello, N., Eslinger, R., Gallagher, R., Kurtzer, I. L., Gasti, P., & Balagani, K. S. (2024) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2024.3409349 · Cited by 11
Pearce, J., Chang, Y., Xia, D., & Abeyesinghe, S. M. (2024) · Animals · doi:10.3390/ani14131957 · Cited by 11
Gravity‐Driven Air‐Liquid Interface Flexible Sensor for Human Motion Detection
Zhuang, Z., Ding, K., Zhong, H., Shen, L., & Zhang, Z. (2025) · Small · doi:10.1002/smll.202412022 · Cited by 11
A survey for wearable sensors empowering smart healthcare in the era of large language models
Liu, Y., Li, J., Lian, C., Zhang, X., Gong, J., Wang, Y., & Zhao, Y. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103409 · Cited by 11
Mapping the Important Sensor Limitations to Design Robust Occupant Sensing Systems
Das, A., Sangogboye, F. C., & Kjærgaard, M. B. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3274761 · Cited by 11
“For example: To eliminate the cost issues, if cheap motes are used then they are more prone to errors than a sensor with a refined granularity and range [1].”
BackgroundYang, Q., Zhang, Y., Dai, W., & Pan, S. J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781139061773.016 · Cited by 12
Chiu, Y., Lin, C.-Y., & Hong, H.-C. (2022) · Frontiers in Mechanical Engineering · doi:10.3389/fmech.2022.876714 · Cited by 11
Ren, Y., Liu, M., Yang, Y., Mao, L., & Chen, K. (2024) · Digital Health · doi:10.1177/20552076231223804 · Cited by 11
Inertia Based Recognition of Daily Activities with ANNs and Spectrotemporal Features
Kilinc, O., Dalzell, A., Uluturk, I., & Uysal, I. (2015) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2015.220 · Cited by 11
“…have investigated this problem in the recent past using a wide variety of signal processing algorithms for feature extraction and classifiers ranging from nearest class centroids [6] to Gaussian mixture models [7] as well as looking at different combination of sensors to improve accuracy [8].”
BackgroundOAFPM: optimized ANFIS using frequent pattern mining for activity recognition
Marimuthu, P., Perumal, V., & Vijayakumar, V. (2019) · The Journal of Supercomputing · doi:10.1007/s11227-019-02802-z · Cited by 11
Automatic Detection of Urban Features from Wheelchair Users’ Movements
Civitarese, G., Mascetti, S., Butifar, A., & Bettini, C. (2019) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2019.8767422 · Cited by 11
“A common technique for data cleaning is data smoothing, which aims at reducing the intrinsic noise of inertial sensor measurements [6].”
MethodAutomatic Classification of Locomotion in Sport: A Case Study from Elite Netball.
Smith, P. D., & Bedford, A. (2020) · Int. J. Comput. Sci. Sport · doi:10.2478/ijcss-2020-0007 · Cited by 11
“…cycle of walking cadence, but short enough to minimise the chance of including multiple movement categories that would be expected in normal match play (Bailey, Gastin, Mackey, & Dwyer, 2017; Bulling et al., 2014; Fox, Spittle, Otago, & Saunders, 2013; Karantonis et al., 2006; Mathie et al., 2003).”
BackgroundMethodTowards Stroke Patients’ Upper-Limb Automatic Motor Assessment Using Smartwatches
Bensalah, A., Chen, J., Fornés, A., Carmona-Duarte, C., Lladós, J., & Ferrer, M. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68763-2_36 · Cited by 11
Issues and Challenges in Various Sensor-Based Modalities in Human Activity Recognition System
Kolkar, R., & Geetha, V. (2021) · Algorithms for intelligent systems · doi:10.1007/978-981-33-4862-2_18 · Cited by 11
Rahman, A., Hassan, I., & Ahad, M. A. R. (2021) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3460418.3479389 · Cited by 11
“Human activity recognition technology has been studied utilizing mobile sensors such as smartphones [2].”
BackgroundHuman Activity Recognition based on LSTM Neural Network Optimized by PSO Algorithm
Gajjala, K. S., & Chakraborty, B. (2021) · IEEE International Conference on Knowledge Innovation and Invention (ICKII) · doi:10.1109/ickii51822.2021.9574788 · Cited by 11
Device-Free Indoor Tracking via Joint Estimation of DFS and AoA using CSI Amplitude
Tian, Z., Ye, C., & Jin, Y. (2021) · International Conference on Microwave and Millimeter Wave Technology (ICMMT) · doi:10.1109/icmmt52847.2021.9618601 · Cited by 11
Mușat, E.-C., & Borz, S. A. (2022) · Healthcare · doi:10.3390/healthcare10050916 · Cited by 11
“The lower performance in the testing phase was less likely to come from the class imbalance issues, which is one of the main challenges in applications of human activity recognition [21].”
BackgroundInfluentialFeedback-based handwriting recognition from inertial sensor data for wearable devices
Li, Y., Yao, K., & Zweig, G. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178375 · Cited by 11
“In our case, letters are clearly segmented, and the only type of errors that need to be considered are substitutions.”
BackgroundLong-term gait pattern assessment using a tri-axial accelerometer
Cillis, F. D., Simio, F. D., & Setola, R. (2017) · Journal of Medical Engineering & Technology · doi:10.1080/03091902.2017.1293741 · Cited by 11
“The DETECT follows the typical pipeline structure commonly used in the inertial-based HAR field, the socalled activity recognition chain (ARC) [28,29].”
MethodJing, L., & Cheng, Z. (2017) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2017.8122979 · Cited by 11
“Human Activity Recognition (HAR) refers to automatic recognition of physical activities to allow computing systems to provide proactive service [2].”
BackgroundEvaluation of Transfer Learning for Human Activity Recognition Among Different Datasets
Islam, M. S., Okita, T., & Inoue, S. (2019) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/cbdcom/cyberscitech.2019.00155 · Cited by 11
“In pervasive computing [14] human activity recognition is a popular research area.”
BackgroundNurse care activity recognition based on convolution neural network for accelerometer data
Rasul, M. G., Khan, M. H., & Lota, L. N. (2020) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3410530.3414335 · Cited by 11
“However, with the advancement of Deep Learning (DL) methods, it is concluded that deep learning algorithms are more suitable to solve HAR problems [3] .”
BackgroundFrom Human Pose to On-Body Devices for Human-Activity Recognition
Rueda, F. M., & Fink, G. A. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412283 · Cited by 11
“These features are, for example, the mean, variance, and correlation for the time domain, or the entropy, energy, and coherence extracted from the Fourier Transform in the frequency domain [1], [10], [13], [23].”
BackgroundMethodInfluentialHoettinger, H., Mally, F., & Sabo, A. (2016) · Procedia Engineering · doi:10.1016/j.proeng.2016.06.279 · Cited by 11
Mogeste: A Mobile Tool for In-Situ Motion Gesture Design
Parnami, A., Gupta, A., Reyes, G., Sadana, R., Yang, L., & Abowd, G. D. (2016) · Indian Conference on Human-Computer Interaction (IndiaHCI) · doi:10.1145/3014362.3014365 · Cited by 11
“Although inertial sensors are commonly employed for activity recognition [6], their use for gestural interaction on commodity devices is limited to specialized functions (e.g., checking the time by rotating the wrist) or gaming (e.g., Wii).”
BackgroundKhatiwada, P., Subedi, M., Chatterjee, A., & Gerdes, M. W. (2020) · Preprints.org · doi:10.20944/preprints202010.0367.v1 · Cited by 11
Human Activity Recognition using Attribute-Based Neural Networks and Context InformationPreprint
L\"udtke, S., Rueda, F. M., Ahmed, W., Fink, G. A., & Kirste, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.04564 · Cited by 11
Reddy, L., Anand, K., Kaushik, S., Rodrigo, C. J., McKay, J. L., Kesar, T. M., & Kwon, H. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0001004 · Cited by 10
Gong, J., Asare, P., Lach, J., & Qi, Y. (2014) · International Conference on Body Area Networks · doi:10.4108/icst.bodynets.2014.257043 · Cited by 10
“BACKGROUND Typical action extraction or activity recognition systems follow the process illustrated in Figure 2 (adapted from Bulling et al [6]).”
BackgroundMethodInfluentialShen, N., Feng, Z., Li, J., You, H., & Xia, C. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-14123-0 · Cited by 10
“The most critical parameter of sliding window method is the window size which depends on the specific requirements of action recognition system and thus is usually determined empirically [2].”
BackgroundMulti-Framework Evidential Association Rule Fusion for Wearable Human Activity Recognition
Geng, X., Chen, X., Ma, Z., & Song, L. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3363908 · Cited by 10
“Moreover, due to the widespread of smart devices such as smartphone or smartwatch that are convenient to carry, the wearable sensor-based techniques have been widely used in more and more HAR applications [18], [19].”
MethodSensor and feature selection for an emergency first responders activity recognition system
Scheurer, S., Tedesco, S. A., Brown, K. N., & O’Flynn, B. (2017) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/icsens.2017.8234090 · Cited by 10
“or k-Nearest Neighbours (kNN), to discriminate among the activities of interest [2].”
BackgroundStudent Knowledge and Misconceptions
Lewis, C. M., Clancy, M. J., & Vahrenhold, J. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.028 · Cited by 10
Shapiro, R. B., & Tissenbaum, M. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.021 · Cited by 10
Poli, A., Spinsante, S., Nugent, C., & Cleland, I. (2019) · Computer communications and networks · doi:10.1007/978-3-030-25590-9_7 · Cited by 10
Performance Analysis of Inception-v2 and Yolov3-Based Human Activity Recognition in Videos
Mustafa, T., Dhavale, S., & Kuber, M. (2020) · SN Computer Science · doi:10.1007/s42979-020-00143-w · Cited by 10
Towards a Complete Set of Gym Exercises Detection Using Smartphone Sensors
Khan, U. A., Khan, I. A., Din, A., Jadoon, W., Jadoon, R. N., Khan, M. A., Khan, F. G., & Khan, A. N. (2020) · Scientific Programming · doi:10.1155/2020/6471438 · Cited by 10
“/e data is preprocessed and segmented and the features are extracted and classified as the last step [11, 46].”
MethodZiaeetabar, F., Pomp, J., Pfeiffer, S., El-Sourani, N., Schubotz, R. I., Tamošiūnaitė, M., & Wörgötter, F. (2020) · PLoS ONE · doi:10.1371/journal.pone.0243829 · Cited by 10
“see [41], thus it is not the best source for action prediction, while contextual information in the current study we consider as distractors as explained above.”
BackgroundArtificial intelligence technologies for more flexible recommendation in uniforms
Wen, C.-H., Cheng, C.-C., & Shih, Y.-C. (2022) · Data Technologies and Applications · doi:10.1108/dta-09-2021-0230 · Cited by 10
Robinson, M. A., Lü, L., Tan, Y., Oetomo, D., & Manzie, C. G. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2022.3199025 · Cited by 10
“47%, using a 75/25 train test split [19].”
BackgroundMethodInfluentialZhou, B., Wang, C., Huan, Z., Li, Z., Chen, Y., Gao, G., Li, H., Dong, C., & Liang, J. (2022) · Sensors · doi:10.3390/s22197446 · Cited by 10
“…and recognition of different kinds of activities such as walking, running, eating, lying down, sitting, etc. Recently, numerous research works on HAR have been conducted, and most of the works are on healthcare [1,2], surveillance activities [3,4], context-aware computing [5,6], and smart home [7].”
Background
Metadata
- Authors
- Bulling, A., Blanke, U., & Schiele, B.
- Affiliations
- Max Planck Institute for Informatics (DE)
- ETH Zurich (CH)
- Venue
- ACM Computing Surveys
- Published
- 2014-01
- Volume
- 46
- Issue
- 3
- Pages
- 1-33
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W2023302299
- Cited by
- 1,668
- References
- 132
- Citations by year
- 2026: 114 · 2025: 105 · 2024: 104 · 2023: 125 · 2022: 158 · 2021: 153 · 2020: 201 · 2019: 213 · 2018: 164 · 2017: 118 · 2016: 115 · 2015: 75 · 2014: 22
- FWCI
- 98.29
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Computing Surveys (publishedVersion)
- Max Planck Digital Library (submittedVersion)
- MPG.PuRe (Max Planck Society) (submittedVersion)
- 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, wearable sensors, hand gesture recognition
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.