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 701–800 of 1,007
Statistical Database of Human Motion Recognition Using Wearable IoT—A Review
Asl, E. F., Ebadollahi, S., Vahidnia, R., & Jalali, A. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3282171 · Cited by 18
“In general, joint boosting is very similar to boosting in terms of performance and structure [51] and is not considered separately in the statistical analysis.”
BackgroundMethodInfluentialLayered hidden Markov models to recognize activity with built-in sensors on Android smartphone
Lee, Y.-S., & Cho, S. (2016) · Pattern Analysis and Applications · doi:10.1007/s10044-016-0549-8 · Cited by 18
“presented a semi-supervised learning method to train a classifier for monitoring patients [3].”
BackgroundMethodInfluentialWiseFi: Activity Localization and Recognition on Commodity Off-the-Shelf WiFi Devices
Zhu, D., Pang, N., Li, G., & Liu, S. (2016) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-smartcity-dss.2016.0085 · Cited by 18
“[16].”
Using a Smartwatch to Detect Stereotyped Movements in Children With Developmental Disabilities
Lee, Y., & Song, M. (2017) · IEEE Access · doi:10.1109/access.2017.2689067 · Cited by 18
“RELATED WORK There are two well-known approaches to the recognition of human physical activity, involving external and wearable sensors [10].”
BackgroundMethodFeature selection for physical activity recognition using genetic algorithms
Baldominos, A., Isasi, P., & Sáez, Y. (2017) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2017.7969569 · Cited by 18
Clapés, A., Pardo, À., Pujol, O., & Escalera, S. (2018) · Machine Vision and Applications · doi:10.1007/s00138-018-0931-1 · Cited by 18
Using Domain Knowledge for Interpretable and Competitive Multi-Class Human Activity Recognition
Scheurer, S., Tedesco, S. A., Brown, K. N., & O’Flynn, B. (2020) · Sensors · doi:10.3390/s20041208 · Cited by 18
“is to extract a set of features from inertial data along a sliding window, and use the resulting matrix—whose rows and columns correspond to windows and features, respectively—as inputs to the machine learning algorithm [4,5].”
MethodGIFT: Glove for Indoor Fitness Tracking System
Hippocrate, A. A. E., Fujiwara, M., Arakawa, Y., Suwa, H., & Yasumoto, K. (2018) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2018.8480211 · Cited by 18
“them have been intensively investigated in previous studies and proved to be effective for activity recognition [19] [20].”
BackgroundA Survey on Multimodal Wearable Sensor-based Human Action Recognition
Ni, J., Guo, B., Haque, S. T., Ngu, A. H. H., & Ding, C. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3716688 · Cited by 17
Skill Level Classification in Basketball Free-Throws Using a Single Inertial Sensor
Guo, X., Brown, E., Chan, P. P. K., Chan, R. H. M., & Cheung, R. T. H. (2023) · Applied Sciences · doi:10.3390/app13095401 · Cited by 17
“Emerging evidence has shown that machine learning algorithms based on data from wearable sensors can be applied in sports movements classification [17–20], which may form the basis of biofeedback systems for sports performance enhancement [30].”
BackgroundResultNisar, M. A., Shirahama, K., Irshad, M. T., Huang, X., & Grzegorzek, M. (2023) · Sensors · doi:10.3390/s23198234 · Cited by 17
ProCAVIAR: Hybrid Data-Driven and Probabilistic Knowledge-Based Activity Recognition
Bettini, C., Civitarese, G., Giancane, D., & Presotto, R. (2020) · IEEE Access · doi:10.1109/access.2020.3015091 · Cited by 17
“Activity recognition using mobile devices has been mainly addressed with supervised machine learning methods [1], [2], [9].”
Analysis of Human Activity Recognition using Deep Learning
Khattar, L., Kapoor, C., & Aggarwal, G. (2021) · International Conference on Cloud Computing, Data Science & Engineering (Confluence) · doi:10.1109/confluence51648.2021.9377114 · Cited by 17
“A paper by Blanke et al. [12] focused on recognizing human activity by using on-body sensors.”
BackgroundHulaMove: Using Commodity IMU for Waist Interaction
Xu, X., Li, J., Yuan, T., He, L., Liu, X., Yan, Y., Wang, Y., Shi, Y., Mankoff, J. C., & Dey, A. K. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445182 · Cited by 17
“We refer readers to a few good survey and tutorial papers for more details: [10, 44, 59].”
MethodHuman Activity Recognition: A Dynamic Inductive Bias Selection Perspective
Hamidi, M., & Osmani, A. (2021) · Sensors · doi:10.3390/s21217278 · Cited by 17
“Figure 2 illustrates the steps of the activity recognition chain as defined in [16].”
BackgroundMethodInfluentialMachine Learning approach towards real time assessment of hand-arm vibration risk
Aiello, G., Certa, A., Abusohyon, I. A. S., Longo, F., & Padovano, A. (2021) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2021.08.140 · Cited by 17
Affinity Propagation Clustering for Older Adults Daily Routine Estimation
Jiménez-Martín, A., Gordo, I. M., Dominguez, J. J. G., Torres-Sospedra, J., Plaza, S. L., & Gualda, D. (2021) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin51156.2021.9662579 · Cited by 17
Morshed, M. B., Haresamudram, H., Bandaru, D., Abowd, G. D., & Plötz, T. (2022) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3544794.3558469 · Cited by 17
“We adopted a sliding window approach [10] with the window size of 1 second and 50 percent overlap, which is an established choice for modeling IMU data [17].”
MethodReenvisioning Patient Education with Smart Hospital Patient Rooms
Dawson, J., Phanich, K. J., & Wiese, J. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3631419 · Cited by 17
“The SPR’s ability to sense activity could build of other research on human activity recognition [11, 29, 49].”
BackgroundRobust Human Activity Recognition via Wearable Sensors Using Dynamic Gaussian Kernel Learning
Wang, S., Sun, Y., Sha, Y., Yang, G., Cheng, D., Zhang, L., Wu, H., & Song, A. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3355704 · Cited by 17
“Traditional machine learning (ML) algorithms [6], [7], such as k -nearest neighbors (KNNs) and support vector machines (SVMs) [8], [9], have been widely employed in predicting human activities and have shown notable progress in inferring activity details.”
BackgroundWe hear your activities through Wi-Fi signals
Wu, F.-J., & Solmaz, G. (2016) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot.2016.7845478 · Cited by 17
“Some of these studies are focused on using body-worn sensors [2], [3] or smartphones [4] while most literature can be found in the computer vision field [5], [6].”
BackgroundQualitative assessment of recurrent human motion
Ebert, A., Beck, M., Mattausch, A., Belzner, L., & Linnhoff-Popien, C. (2017) · European Signal Processing Conference · doi:10.23919/eusipco.2017.8081218 · Cited by 13
“Bulling et al. name (1) sliding windows, (2) energy-based segmentation, (3) rest-position based segmentation, and (4) the use of additional sensors or context resources as applicable procedures [4].”
MethodHierarchical modeling for first-person vision activity recognition
Abebe, G., & Cavallaro, A. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.06.015 · Cited by 17
“In addition to using SVM and LR, we test the proposed feature groups on different classifiers, namely KNN, decision tree (DT) [47] and HMM.”
MethodDistribution-Based Semi-Supervised Learning for Activity Recognition
Qian, H., Pan, S. J., & Miao, C. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33017699 · Cited by 17
“…has spurred a great deal of interest with a wide spectrum of real-world applications, such as security, personalized health monitoring and assisted living (Janidarmian et al. 2017; Bulling, Blanke, and Schiele 2014; Lara and Labrador 2013; Frank, Mannor, and Precup 2010; Avci et al. 2010).”
BackgroundEngineering Education Research
Loui, M. C., & Borrego, M. J. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.012 · Cited by 17
Recognizing Multi-Agent Plans When Action Models and Team Plans Are Both Incomplete
Zhuo, H. H. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3319403 · Cited by 17
If only we had more data!: Sensor-Based Human Activity Recognition in Challenging Scenarios
Plötz, T. (2023) · 2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) · doi:10.1109/percomworkshops56833.2023.10150267 · Cited by 16
“1a and summarized in [9].”
MethodSepahvand, M., & Abdali-Mohammadi, F. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2877360 · Cited by 16
“Some of these applications also need simultaneous inputs from multiple sensors, each with multiple degrees of freedom [9]–[11].”
BackgroundLattanzi, E., Calisti, L., & Capellacci, P. (2023) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2023.101848 · Cited by 16
Too Good To Be True: accuracy overestimation in (re)current practices for Human Activity Recognition
Tello, A., Degeler, V., & Lazovik, A. (2024) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops59983.2024.10503465 · Cited by 16
Hoelzemann, A., & Laerhoven, K. V. (2024) · Frontiers in Computer Science · doi:10.3389/fcomp.2024.1379788 · Cited by 16
“Furthermore, due to the in-the-wild recording setup, the intra-class differences [22] for comparatively simple activities, walking or running can be significant.”
BackgroundRoad Sensing: Personal Sensing and Machine Learning for Development of Large Scale Accessibility Map
Iwasawa, Y., Nagamine, K., Matsuo, Y., & Yairi, I. E. (2015) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/2700648.2811366 · Cited by 16
“In this paper, referring activity recognition research [1] and our pre-experiments’ result, FEX were de signed to calculate mean, standard deviation, max, and min of following six channels: x, y, z of the three-axis accelerom eter and difference sequences of x, y, z.”
MethodA Hybrid Accuracy- and Energy-Aware Human Activity Recognition Model in IoT Environment
Jha, D. N., Chen, Z., Liu, S., Wu, M., Zhang, J., Morgan, G., Ranjan, R. K., & Li, X. (2022) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2022.3209086 · Cited by 16
“The application of smart healthcare ranges from clinical facility, fitness tracking, elderly monitoring, assisted living, diet planning to name a few [3], [4], [5], [6].”
BackgroundComplex Human Activity Recognition Using a Local Weighted Approach
Aşuroğlu, T. (2022) · IEEE Access · doi:10.1109/access.2022.3208686 · Cited by 16
“[ 29], [30].”
Human Activity Recognition using Deep Learning
Moola, R., & Hossain, A. (2022) · URSI Regional Conference on Radio Science (URSI-RCRS) · doi:10.23919/ursi-rcrs56822.2022.10118525 · Cited by 16
Jia, Q., Guo, J. M., Yang, P., & Yang, Y. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01218-w · Cited by 16
“In recent years, the spotlight has been on HAR [31], which can learn advanced information about human activities from raw sensor input [32].”
Strengthening and Sustaining Health-Related Outcomes Through Digital Health Interventions
Goel, R. K., & Vishnoi, S. (2023) · Journal of Engineering Science and Technology Review · doi:10.25103/jestr.162.02 · Cited by 16
“It can be used to monitor and analyse activity patterns over time, identify changes or abnormalities that may indicate health or behavioural issues, and provide personalized feedback and recommendations to improve health [47,48].”
BackgroundChildren’s Rehabilitation with Humanoid Robots and Wearable Inertial Measurement Units
Özgür, A. G., Bert Arnrich, A., & Ersoy, C. (2015) · International Conference on Pervasive Computing Technologies for Healthcare · doi:10.4108/icst.pervasivehealth.2015.259273 · Cited by 16
“provide high performance across a variety of activity recognition problems [7].”
BackgroundHaescher, M., Trimpop, J., Matthies, D. J. C., Bieber, G., Urban, B., & Kirste, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-20916-6_68 · Cited by 16
“Moreover, the temperature and decibel values can be used to differentiate places and inside and outside locations, respectively [6].”
BackgroundMethodInfluentialA movement activity recognition pervasive system for patient monitoring in ambient assisted living
Pereira, J. D., Silva, F. J. D. S. E., Coutinho, L., Gomes, B. D. T. P., & Endler, M. (2016) · ACM Symposium on Applied Computing · doi:10.1145/2851613.2851689 · Cited by 16
Egocentric activity recognition by leveraging multiple mid-level representations
Hsieh, P.-J., Lin, Y.-L., Chen, Y., & Hsu, W. H. (2016) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2016.7552937 · Cited by 16
“In addition, there is a rising trend in analyzing accelerometers [6] on activity recognition since they can record data directly related to subjects’ motion patterns with the advantages of low-power requirement, compact size, low cost and non-intrusiveness.”
BackgroundInfluentialACTIVITY RECOGNITION ON SMART DEVICES: Dealing with diversity in the wild
Blunck, H., Bhattacharya, S., Stisen, A., Prentow, T. S., Kjærgaard, M. B., Dey, A. K., Jensen, M. M., & Sonne, T. (2016) · GetMobile Mobile Computing and Communications · doi:10.1145/2972413.2972425 · Cited by 16
Towards Self-Improving Activity Recognition Systems Based on Probabilistic, Generative Models
Janicke, M., Tomforde, S., & Sick, B. (2016) · IEEE International Conference on Autonomic Computing (ICAC) · doi:10.1109/icac.2016.22 · Cited by 16
“is actively pursued at the moment [20], [21].”
BackgroundActivity Recognition from Mobile Phone using Deep CNN
Wu, W., & Zhang, Y. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8865142 · Cited by 16
“In most sensor-based HAR methods, users had to attach multiple dedicated motion sensors [5, 6] to various parts of the body such as legs, arms, and waist.”
MethodDesign and Analysis for Fall Detection System Simplification
Martínez-Villaseñor, L., & Ponce-Espinosa, H. (2020) · Journal of Visualized Experiments · doi:10.3791/60361 · Cited by 16
“9 , which consists of stages for data acquisition, signal preprocessing and segmentation, feature extraction and selection, training and classification.”
BackgroundChang, C.-Y., Hsieh, C.-Y., Huang, H.-Y., Wu, Y., Chen, L., Chan, C.-T., & Liu, K.-C. (2020) · Sensors · doi:10.3390/s21010106 · Cited by 16
“This study utilizes a leave-one-subject-out cross-validation approach [32] to validate the system performance of the proposed shoulder task identification and sub-task segmentation.”
BackgroundMethodInfluentialDeep Learning for Detecting Human Activities From Piezoelectric-Based Kinetic Energy Signals
Manjarrés, J., Lan, G., Gorlatova, M. A., Hassan, M., & Pardo, M. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3093245 · Cited by 16
Avoiding Bias in Classification Accuracy - A Case Study for Activity Recognition
Koskimäki, H. (2015) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2015.52 · Cited by 16
“The overall activity recognition process includes a data set collected from the activities wanted to be recognized, preprocessing, segmentation, feature extraction and selection, and classification [1].”
MethodFitness activity classification by using multiclass support vector machines on head-worn sensors
Loh, D., Lee, T. J., Zihajehzadeh, S., Hoskinson, R., & Park, E. J. (2015) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7318409 · Cited by 16
A Role-Based Approach for Orchestrating Emergent Configurations in the Internet of ThingsPreprint
Mihailescu, R., Spalazzese, R., Heyer, C., & Davidsson, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.09870 · Cited by 16
“…an extensive body of work focusing on the area of activity recognition and context-awareness, as it pertains to the various sensing modalities (e.g. smartphones [20], vision [31], ambient sensors [25,23]) and the different application domains (e.g. health [7], smart living spaces [22], sports [5]).”
BackgroundWIMUSim: simulating realistic variabilities in wearable IMUs for human activity recognition
Oishi, N., Birch, P. M., Roggen, D., & Lago, P. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1514933 · Cited by 15
Vahrenhold, J., Cutts, Q. I., & Falkner, K. E. K. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.019 · Cited by 15
Sensors-based Human Activity Recognition with Convolutional Neural Network and Attention Mechanism
Zhang, W., Zhu, T., Yang, C., Xiao, J., & Ning, H. (2020) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess49938.2020.9237720 · Cited by 15
“In order to analyze and model the time series data, the time context of each sensor reading needs to be taken into account, which is usually implemented by sliding window method [4].”
MethodKhan, A., Mellor, S., King, R., Janko, B., Harwin, W., Sherratt, R. S., Craddock, I. J., & Plötz, T. (2020) · ACM Transactions on Computing for Healthcare · doi:10.1145/3422168 · Cited by 15
“(1) Segmenting the data into activity windows (sliding-window-based approach may also be used in this context) for further feature extraction and classification [8].”
BackgroundMethodChang, J., Kang, M., & Park, D. (2022) · Electronics · doi:10.3390/electronics11010139 · Cited by 15
“In HAR, traditional PR tactics have achieved remarkable progress [21].”
BackgroundAgenda- and Activity-Based Triggers for Microlearning
Draxler, F., Brenner, J. M., Eska, M., Schmidt, A., & Chuang, L. L. (2022) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3490099.3511133 · Cited by 15
“However, implicit on-device activity recognition and sensing of cognitive state are complex [5, 29, 34] and need to be well-adjusted for reliable results.”
BackgroundSelf-Supervised Few-Shot Time-series Segmentation for Activity Recognition
Xiao, C., Chen, S., Zhou, F., & Wu, J. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3199015 · Cited by 15
“HandGesture [35]: This dataset includes twelve hand movement activities performed by two subjects and captured by inertial measurement units.”
MethodMulti-agent Transformer Networks for Multimodal Human Activity Recognition
Li, J., Yao, L., Li, B., Wang, X., & Sammut, C. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557402 · Cited by 15
“The data collection step may focus on quite diverse requirements, such as high data quality, large numbers of modalities or sensors, long-term recordings, or large numbers of participants [7].”
BackgroundMethodImproving accuracy and explainability of online handwritten character recognition
Azimi, H., Chang, S., Gold, J., & Karabina, K. (2023) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-023-00456-5 · Cited by 16
A Lightweight Deep Human Activity Recognition Algorithm Using Multiknowledge Distillation
Chen, R., Luo, H., Zhao, F., Meng, X., Xie, Z., & Zhu, Y. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3443308 · Cited by 15
“Many traditional HAR algorithms primarily focus on extracting manually designed statistical features [5].”
BackgroundNewball, A. A. N., Sánchez, I. M., Prakash, E., Arya, A., Contreras, V. E., Quiceno, V. A., Lozano, S., Mejìa, J. D., & Loaiza, D. F. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2667-5 · Cited by 15
“Moreover, human motion plays an important role in technologies such as human activity recognition [1].”
BackgroundMethodIwasawa, Y., Yairi, I. E., & Matsuo, Y. (2016) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2015edp7278 · Cited by 15
“[31].”
BackgroundA benchmark study on feature selection for human activity recognition
Karagiannaki, K., Πανουσοπούλου, Α., & Tsakalides, P. (2016) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2968219.2971421 · Cited by 15
“The FORTH-TRACE library adopts a modular design on implementing the intermediate steps between the raw data collection and the classification of human actions, according to the Activity Recognition Chain (ARC) [2].”
MethodCodebook approach for sensor-based human activity recognition
Shirahama, K., Köping, L., & Grzegorzek, M. (2016) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2968219.2971416 · Cited by 15
“Sensor-based human activity recognition is the task of extracting high-level descriptions (i.e., activities) from low-level sensor data [2].”
BackgroundGymApp: A Real Time Physical Activity Trainner on Wearable Devices
Viana, P., Ferreira, T., Castro, L., Soares, M., Pinto, J., Andrade, M. T., & Carvalho, P. (2018) · Conference on Human System Interactions · doi:10.1109/hsi.2018.8431358 · Cited by 15
Reining, C., Rueda, F. M., ten Hompel, M., & Fink, G. A. (2018) · Annals of Computer Science and Information Systems · doi:10.15439/2018f188 · Cited by 15
“environment settings, number of participants and number of sensors [4].”
BackgroundFluid intake recognition using inertial sensors
Wellnitz, A., Wolff, J.-P., Haubelt, C. D., & Kirste, T. (2019) · International Workshop on Sensor-based Activity Recognition and Interaction (iWOAR) · doi:10.1145/3361684.3361688 · Cited by 15
“Activity recognition approaches rely on different types of electronic sensing equipment as well as a vast range of classification methods[3].”
BackgroundActivity and Safety Recognition using Smart Work Shoes for Construction Worksite
Wang, C., Kim, Y., Lee, S. H., Sung, N.-J., Min, S. D., & Choi, M. (2020) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2020.02.010 · Cited by 15
“Many studies have performed motion analysis on daily activities and gait of various patients and healthy individuals [24,25,27-31], but not much research has focused on the causes and preventions for falling accidents from stairway at construction work sites.”
BackgroundCausality Analysis of Inertial Body Sensors for Multiple Sclerosis Diagnostic Enhancement
Gong, J., Qi, Y., Goldman, M. D., & Lach, J. (2016) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2589902 · Cited by 15
“I. INTRODUCTION MOBILITY impairment is a common marker for diagnos-ing, tracking the severity of, and evaluating therapeutic efficacy against various diseases, disorders, and injuries.”
BackgroundA ROBUST AUTOMATIC GAIT MONITORING APPROACH USING A SINGLE IMU FOR HOME-BASED APPLICATIONS
Ghobadi, M., & Esfahani, E. T. (2017) · Journal of Mechanics in Medicine and Biology · doi:10.1142/s0219519417500774 · Cited by 15
“The performance of the activity analysis in this approach is highly dependent on the window size [15,16].”
BackgroundLancaster, T., Robins, A. V., & Fincher, S. A. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.015 · Cited by 15
Event-Centered Data Segmentation in Accelerometer-Based Fall Detection Algorithms
Šeketa, G., Pavlaković, L., Džaja, D., Lacković, I., & Magjarević, R. (2021) · Sensors · doi:10.3390/s21134335 · Cited by 15
“However, only a few research publications so far have focused on the data segmentation stage, although it significantly affects the systems performance in terms of power efficiency and detection accuracy [12,13].”
BackgroundSensor-based human activity recognition: Overcoming issues in a real world setting
Sztyler, T. (2019) · MADOC (University of Mannheim) · Cited by 15
Haresamudram, H., Essa, I., & Plötz, T. (2024) · Sensors · doi:10.3390/s24041238 · Cited by 14
“The de facto approach for obtaining features is to compute them via statistical metrics [6,7] and the empirical cumulative distribution function [8], or to learn them directly from the data itself (e.g., via end-to-end training [9–13] or unsupervised learning [14–16]).”
MethodWahl, K., Scholl, P., Miché, M., Wirth, S., Burchard, R., & Lieb, R. (2023) · Journal of Obsessive-Compulsive and Related Disorders · doi:10.1016/j.jocrd.2023.100845 · Cited by 14
Skeletal joint image-based multi-channel fusion network for human activity recognition
Sun, T., Lian, C., Dong, F., Shao, J., Zhang, X., Xiao, Q., Ju, Z., & Zhao, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113232 · Cited by 14
Ojelade, A., Rajabi, M. S., Kim, S., & Nussbaum, M. A. (2025) · International Journal of Industrial Ergonomics · doi:10.1016/j.ergon.2025.103755 · Cited by 14
Rey, V. F., Rezende, P. M. B., Zhou, B., Suh, S., & Lukowicz, P. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129288 · Cited by 14
IMUCoCo: Enabling Flexible On-Body IMU Placement for Human Pose Estimation and Activity Recognition
Zhou, H., Arakawa, R., Agarwal, Y., & Goel, M. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747695 · Cited by 15
“Using these datasets, numerous machine learning-based approaches have emerged [7, 34, 56].”
He, H. S., Tan, Y., & Huang, J. (2017) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee.2017.8015566 · Cited by 14
A Case Study of Qualitative Methods
Lewis, C. M. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.032 · Cited by 14
Unobtrusive Activity Recognition and Position Estimation for Work Surfaces Using RF-Radar Sensing
Avrahami, D., Patel, M., Yamaura, Y., Kratz, S., & Cooper, M. (2019) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3241383 · Cited by 14
“Several systems (cf. [4, 5, 8, 10, 13, 21, 31, 33]) recognize physical human activities (walking, running, cycling, etc.) using a worn IMU, now a common feature of smartphones and smartwatches (for a survey on activity recognition using acceleration sensors see [21]).”
BackgroundMani, N., Haridoss, P., & George, B. (2023) · IEEE Open Journal of Instrumentation and Measurement · doi:10.1109/ojim.2023.3301861 · Cited by 14
“Standard HAR measurements produce the vector of attributes from each window [16], [17], [18], using the time and frequency domain features as part of extracting the necessary features.”
MethodPhase Randomization: A data augmentation for domain adaptation in human action recognition
Mitsuzumi, Y., Irie, G., Kimura, A., & Nakazawa, A. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110051 · Cited by 14
Unsupervised Race Walking Recognition Using Smartphone Accelerometers
Wei, Y., Liu, L., Zhong, J., Lu, Y., & Sun, L. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-25159-2_63 · Cited by 14
A context-sensitive conceptual framework for activity modeling
Das, R. D., & Winter, S. (2016) · Journal of Spatial Information Science · doi:10.5311/josis.2016.12.260 · Cited by 14
“Bulling and colleagues pointed out taxonomic classification of activities based on different aspects, such as metabolic activities which are widely used in the medical sector [6], as well as time use pattern [67].”
BackgroundMethodFeature Engineering for Activity Recognition from Wrist-worn Motion Sensors
Konak, S., TURAN, F., Shoaib, M. A., & İncel, Ö. D. (2016) · International Conference on Pervasive and Embedded Computing and Communication Systems · doi:10.5220/0006007100760084 · Cited by 14
“Mobile phones’ ubiquity and the rich set of sensors available on these devices make them a suitable platform for human activity recognition (Incel et al., 2013; Bulling et al., 2014).”
BackgroundActivity Recognition in a Home Setting Using Off the Shelf Smart Watch Technology
Filippoupolitis, A., Takand, B., & Loukas, G. (2016) · International Conference on Ubiquitous Computing and Communications (IUCC) · doi:10.1109/iucc-css.2016.014 · Cited by 14
“At the same time, major advances have been achieved over the last few years in the area of activity recognition based on wearable technologies [5], [6], but these have not been evaluated in a home environment (see Table 1 for a summary of the literature, indicating the particular gap).”
BackgroundMethodLee, J. S., Choi, S., & Kwon, O. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.03.062 · Cited by 14
“, 2004), and sound data from a microphone (Cowling & Sitte, 2003; Bulling et al., 2014).”
BackgroundUsing Machine Learning to Identify Activities of a Flying Drone from Sensor Readings.
Barták, R., & Vomlelová, M. (2017) · The Florida AI Research Society · Cited by 14
Zhang, S., Ng, W. W. Y., Zhang, J., Nugent, C., Irvine, N., & Wang, T. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-019-01246-w · Cited by 14
“There has been extensive work in the literature on the activity recognition on the wearable sensors / devices (Hegde et al. 2017; Liu et al. 2017; Medina et al. 2017; Fullerton et al. 2017; Bulling et al. 2014), mostly focused on the physical activities such as running, sitting etc.”
BackgroundAllik, A., Pilt, K., Karai, D., Fridolin, I., Leier, M., & Jervan, G. (2019) · Applied Sciences · doi:10.3390/app9224833 · Cited by 14
“5 s [17] and 5 s [13]) affect physical activity classification performance [15,18], but the lack of gold standard in physical activity classification makes it difficult to compare these results [19].”
ResultLu, M., Feng, S., Hughes, G., Barim, M. S., Hayden, M. A., & Werren, D. M. (2019) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1071181319631252 · Cited by 14
“A typical sliding window approach (Spriggs et al., 2009; Bulling et al., 2014; MoncadaTorres a t al., 2014; Attal at al., 2015) with a window of 2.5 seconds and a 0.5 second overlap was employed.”
MethodInfluentialSensor-Based Transportation Mode Recognition Using Variational Autoencoder
Islam, Z., & Abdel-Aty, M. A. (2021) · Journal of Big Data Analytics in Transportation · doi:10.1007/s42421-021-00035-2 · Cited by 14
Comparative Analysis of LSTM-based Deep Learning Models for HAR using Smartphone Sensor
Rojanavasu, P., Jitpattanakul, A., & Mekruksavanich, S. (2021) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon51128.2021.9425733 · Cited by 14
“Human activity recognition (briefly called HAR) describes the process of determining a physical accomplished activity of human by an individual relying on an indication of human movement within a definite environment [1].”
BackgroundSimilarity Embedding Networks for Robust Human Activity Recognition
Li, C., Tong, C. L., Niu, D., Jiang, B., Zuo, X. M., Cheng, L., Xiong, J., & Yang, J. (2021) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3448021 · Cited by 14
“Traditional machine learning approaches such as decision trees, support vector machines [2], hidden Markov models [29], and random forest [26] models have been developed based on manually extracted features and achieved decent performance in some controlled environments [7].”
BackgroundA dynamic window-size based segmentation technique to detect driver entry and exit from a car
Hirawat, A., Taterh, S., & Sharma, T. K. (2021) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.08.028 · Cited by 14
Teacher Knowledge for Inclusive Computing Learning
Goode, J., & Ryoo, J. J. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.025 · Cited by 14
AtLAS: An Activity-Based Indoor Localization and Semantic Labeling Mechanism for Residences
Niu, X., Xie, L., Wang, J., Chen, H., Liu, D., & Chen, R. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3004496 · Cited by 14
“In addition, Inertial sensors in smartphones or wearable devices have been widely used for human activity recognition (HAR) [22].”
BackgroundKumar, P., & Chauhan, S. (2021) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-021-00063-5 · Cited by 13
Retracted
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.