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 601–700 of 1,007
Heat event detection in dairy cows with collar sensors: An unsupervised machine learning approach
Shahriar, M. S., Smith, D., Rahman, A., Henry, D. A., Bishop-Hurley, G. J., Rawnsley, R., Freeman, M., & Hills, J. L. (2015) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/icsens.2015.7370528 · Cited by 23
“For each segment of the time series (variables), we consider maximum(max), minimum(min), standard deviation(sd), amplitude (amp), energy (en), top 5 magnitudes (mag fft) of fast Fourier transform (FFT) [18], [19].”
MethodPreuveneers, D., Berbers, Y., & Joosen, W. (2016) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-150357 · Cited by 23
“We refer interested readers to recent surveys [1,7] for a more elaborate and in-depth overview of human activity recognition research.”
Fallmann, S., & Kropf, J. (2016) · IEEE Smart World Congress and International Conferences on Ubiquitous Intelligence & Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People (SmartWorld/UIC/ATC/ScalCom/CBDCom/IoP) · doi:10.1109/uic-atc-scalcom-cbdcom-iop-smartworld.2016.0039 · Cited by 23
“Features are calculated for each annotated activity with a shifted window sized 50, containing 50 data vectors, and an overlap of 50%, which is the most significant value for overlap in previous works.”
MethodResultInfluentialA dual model approach to EOG-based human activity recognition
Lu, Y., Zhang, C., Zhou, B., Gao, X., & Lv, Z. (2018) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2018.05.011 · Cited by 23
Mangiarotti, M., Ferrise, F., Graziosi, S., Tamburrino, F., & Bordegoni, M. (2018) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4041704 · Cited by 23
On-Device Deep Learning Inference for Efficient Activity Data Collection
Mairittha, N., Mairittha, T., & Inoue, S. (2019) · Sensors · doi:10.3390/s19153434 · Cited by 23
“In the field of ubiquitous computing, researches on human activity recognition technology using mobile sensors such as smartphones have been conducted [1].”
BackgroundA Comparative Research on Human Activity Recognition Using Deep Learning
Tüfek, N., & Özkaya, Ö. (2019) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2019.8806395 · Cited by 23
“Bu bağlamda jiroskop, ivmeölçer ve manyetik alan algılayıcısı gibi algılayıcılardan gelen verilerden yararlanılmaktadır [7].”
Hardiyanti, N. R., Lawi, A., Diaraya, & Aziz, F. (2018) · East Indonesia Conference on Computer and Information Technology (EIConCIT) · doi:10.1109/eiconcit.2018.8878627 · Cited by 23
“Research [5], similar research is also directed specifically in the field of activity recognition that uses inertial sensors in the body.”
BackgroundAutomatic detection algorithm for establishing standard to identify “surge blood pressure”
Kokubo, A., Kuwabara, M., Nakajima, H., Tomitani, N., Yamashita, S., Shiga, T., & Kario, K. (2020) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-020-02162-4 · Cited by 23
Drinking Event Detection and Episode Identification Using 3D-Printed Smart Cup
Liu, K.-C., Hsieh, C.-Y., Huang, H.-Y., Chiu, L.-T., Hsu, S. J.-P., & Chan, C.-T. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3004051 · Cited by 23
“Previous works based on these models have achieved the reliable system performance [24], [25].”
BackgroundRoth, E., Moencks, M., Bohné, T., & Pumplun, L. (2020) · IEEE International Conference on Human-Machine Systems (ICHMS) · doi:10.1109/ichms49158.2020.9209488 · Cited by 24
“%) can be partly explained by the sensor specific limitations of vision-based devices, e.g. occlusion [9].”
BackgroundMethodInfluentialContext-aware incremental learning-based method for personalized human activity recognition
Siirtola, P., & Röning, J. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02808-z · Cited by 23
Detecting Verbal and Non-Verbal Gestures Using Earables
Laporte, M., Baglat, P., Gashi, S., Gjoreski, M., Santini, S., & Langheinrich, M. (2021) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3460418.3479322 · Cited by 23
“used in the literature for human activity recognition from inertial signals [5].”
BackgroundInfluentialDiSalvo, B. J., Bandaru, D., Wang, Q., Li, H., & Plötz, T. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3550328 · Cited by 23
“Feature vectors are then extracted for individual frames and forwarded to a subsequent classification backend [11].”
Fully Connected Generative Adversarial Network for Human Activity Recognition
Jimale, A. O., & Noor, M. H. M. (2022) · IEEE Access · doi:10.1109/access.2022.3206952 · Cited by 23
“Many researchers investigated human activity recogni174 tion from images and videos [29].”
BackgroundCycleSense: Detecting near miss incidents in bicycle traffic from mobile motion sensors
Karakaya, A.-S., Ritter, T., Bießmann, F., & Bermbach, D. (2023) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2023.101779 · Cited by 23
“While various feature extraction and pattern recognition methods have been successfully applied in the past in this context [41], those approaches have constraints such as hand-crafted feature extraction, being able to only learn shallow features [42], or the requirement for large amounts of well-labeled data for mode…”
A framework of mining semantic-based probabilistic event relations for complex activity recognition
Liu, L., Wang, S., Su, G., Hu, B., Peng, Y., Xiong, Q., & Wen, J. (2017) · Information Sciences · doi:10.1016/j.ins.2017.07.022 · Cited by 23
Learning to judge like a human: convolutional networks for classification of ski jumping errors
Brock, H., Ohgi, Y., & Lee, J. (2017) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3123021.3123038 · Cited by 23
“Therefore, common wearable sensor-based HAR systems usually follow a fixed pipeline of work steps that aim to control and restrict the multi-dimensional output [7].”
BackgroundMalmi, L., Utting, I., & Ko, A. J. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.022 · Cited by 23
Deep learning for human motion analysis
Neverova, N. (2016) · theses.fr (ABES) · doi:10.70675/a8cda552zdc96z48c1z979bzac140403e58f · Cited by 23
Jamil, H., Qayyum, F., Iqbal, N., Jamil, F., & Kim, D. H. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3228120 · Cited by 22
“Bulling et al. [44] presented the activity recognition chain (ARC) in 2014 and investigated this issue.”
BackgroundConformer-Based Human Activity Recognition Using Inertial Measurement Units
Seenath, S., & Dharmaraj, M. (2023) · Sensors · doi:10.3390/s23177357 · Cited by 22
“…data from various sensor readings, utilizing the multi-head attention mechanism inherent in transformers; The model employs a sensor a tt ention unit that is designed for time-series data from various sensor readings, utilizing the multi-head a tt ention mechanism inherent in transformers;”
MethodLi, T., Wang, Q., An, Y., Guo, L. J., Ren, L., Lei, L., & Chen, X. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107750 · Cited by 22
Short-time activity recognition with wearable sensors using convolutional neural network
Sheng, M., Jiang, J., Su, B., Tang, Q., Yahya, A. A., & Wang, G. (2016) · ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry (VRCAI) · doi:10.1145/3013971.3014016 · Cited by 22
Multi-modal egocentric activity recognition using multi-kernel learning
Arabacı, M. A., Özkan, F., Sürer, E., Jančovič, P., & Temizel, A. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08789-7 · Cited by 22
“On the other hand, there are increasing number of studies in the literature proposing end-to-end solutions with deep learning techniques using visual [31, 41, 42] and wearable sensor [70, 71] information.”
BackgroundSensorSnaps: Integrating Wireless Sensor Nodes into Fabric Snap Fasteners for Textile Interfaces
Dementyev, A., Gálvez, T. A. V., & Olwal, A. (2019) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3332165.3347913 · Cited by 22
“The use of IMUs for gesture sensing on mobile phones [19], tablets [40] and watches [25] is indeed well studied in the research community, especially in the Human Activity Recognition field [6, 24].”
Development of a Wearable IMU System for Automatically Assessing Lifting Risk Factors
Lu, M., Barim, M. S., Feng, S., Hughes, G., Hayden, M. A., & Werren, D. M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-49904-4_15 · Cited by 22
Titchy: Online Time-Series Compression With Random Access for the Internet of Things
Vestergaard, R., Zhang, Q., Sipos, M., & Lucani, D. E. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3081868 · Cited by 22
Identification of reindeer fine-scale foraging behaviour using tri-axial accelerometer data
Rautiainen, H., Alam, M., Blackwell, P. G., & Skarin, A. (2022) · Movement Ecology · doi:10.1186/s40462-022-00339-0 · Cited by 22
“The features and their corresponding classified behaviours are used to train the models, which learn to distinguish between the classified behaviours given the differences in the acceleration data [41].”
MethodSiamese Networks for Weakly Supervised Human Activity Recognition
Sheng, T., & Huber, M. (2019) · 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC) · doi:10.1109/smc.2019.8914045 · Cited by 21
“The typical process [5] of human activity recognition includes signal preprocessing, data segmentation, feature extraction, and applying machine learning to recognize each”
MethodScheurer, S., Tedesco, S. A., O’Flynn, B., & Brown, K. N. (2020) · Sensors · doi:10.3390/s20133647 · Cited by 21
Gong, N. J., Clifford, G. D., Esper, C. D., Factor, S. A., McKay, J. L., & Kwon, H. (2023) · Sensors · doi:10.3390/s23198330 · Cited by 21
“Then, for the experiment, we applied a standard human activity recognition pipeline using a sliding window approach [39].”
MethodAutomatic Annotation of Unlabeled Data from Smartphone-Based Motion and Location Sensors
Owoh, N. P., Singh, M. M., & Zaaba, Z. F. (2018) · Sensors · doi:10.3390/s18072134 · Cited by 21
“Presently, a number of activity recognition systems depend on the application of supervised learning on sensor data for accurate prediction of user activity [20].”
BackgroundGestureKeeper: Gesture Recognition for Controlling Devices in IoT Environments
Sideridis, V., Zacharakis, A., Tzagkarakis, G., & Papadopouli, M. (2019) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2019.8903044 · Cited by 21
Efficient Smartphone-Based Human Activity Recognition Using Convolutional Neural Network
Dhanraj, S., De, S., & Dash, D. (2019) · doi:10.1109/icit48102.2019.00061 · Cited by 21
“Such networks are not only used for human activity recognition [46], but also in many other application domains (like, health-care, fitness, smart cities, Internet of Things etc.).”
BackgroundAblation Analysis to Select Wearable Sensors for Classifying Standing, Walking, and Running
Gonzalez, S., Stegall, P., Edwards, H., Stirling, L., & Siu, H. C. (2020) · Sensors · doi:10.3390/s21010194 · Cited by 21
“Every sensor has its benefits and drawbacks, but it has been shown that sensors can be used in tandem with HAR, and this fusion leads to increased accuracies in recognition of defined activities [9].”
BackgroundInfluentialBlock-Wise Training Residual Networks on Multi-Channel Time Series for Human Activity Recognition
Teng, Q., Zhang, L., Tang, Y., Song, S., Wang, X., & He, J. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3085360 · Cited by 21
“SEnsor based human activity recognition (HAR) [1] [2] is a hotspot where various human activities are analyzed via embedded inertial sensors such as accelerometer and gyroscope.”
BackgroundHAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data
Mohamed, A., Lejarza, F., Cahail, S., Claudel, C., & Thomaz, E. (2022) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops53856.2022.9767342 · Cited by 21
“Despite these recent advances, “ground truth annotation”, which involves labeling sensor readings, remains a critical challenge [3].”
BackgroundMonitoring Arm Movements Post-Stroke for Applications in Rehabilitation and Home Settings
Arrunátegui, G., Eng, J. J., & Hodgson, A. J. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3197993 · Cited by 21
“and movements, which can substantially increase the detection accuracy relative to using single sensors, though the increased complexity of multiple-sensor setups can compromise user comfort and present barriers to use in the home setting [8], [9].”
BackgroundMethodInfluentialContext-Aware Complex Human Activity Recognition Using Hybrid Deep Learning Models
Omolaja, A., Otebolaku, A., & Alfoudi, A. S. D. (2022) · Applied Sciences · doi:10.3390/app12189305 · Cited by 21
“This environment also provides leverage on the open-source interfaces, such as the TensorFlow machine learning framework, which comes bundled with Keras high-level API [74].”
BackgroundMethodResultInfluentialRecognition of reading activity from the saccadic samples of electrooculography data
Huda, K., Hossain, M. S., & Ahmad, M. (2015) · International Conference on Electrical & Electronic Engineering (ICEEE) · doi:10.1109/ceee.2015.7428296 · Cited by 21
“On the other hand wearable sensing system is preferred especially in pervasive healthcare as it provides long term continuous information about people’s activity [6]-[7].”
BackgroundAutonomous Human Activity Classification From Wearable Multi-Modal Sensors
Lu, Y., & Velipasalar, S. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2934678 · Cited by 21
Recognition of Aggressive Interactions of Children Toward Robotic Toys
Alhaddad, A. Y., Cabibihan, J., & Bonarini, A. (2019) · IEEE RO-MAN · doi:10.1109/ro-man46459.2019.8956375 · Cited by 21
“In human recognition applications, there is a trade off between recognition performance, recognition speed, and computational complexity [40].”
BackgroundDatta, S., Karmakar, C. K., Rao, A. S., Yan, B., & Palaniswami, M. S. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.2972285 · Cited by 21
“Shannon Entropy [25] and Zero Crossing Rate (ZCR) [26].”
BackgroundInfluentialTemporal Approaches for Human Activity Recognition Using Inertial Sensors
Garcia, F. A., Ranieri, C. M., & Romero, R. A. F. (2019) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars-sbr-wre48964.2019.00029 · Cited by 21
“To test the architectures, they used OPPORTUNITY and Hand Gesture [13], achieving state-of-art results.”
MethodActivity Recognition using Head Worn Inertial Sensors
Wolff, J.-P., Grützmacher, F., Wellnitz, A., & Haubelt, C. D. (2018) · International Workshop on Sensor-based Activity Recognition and Interaction (iWOAR) · doi:10.1145/3266157.3266218 · Cited by 20
“The applied steps or milestones for developing a human activity recognition system, sometimes called the ’activity recognition chain’ [7][10], are listed below: • Raw data acquisition and preprocessing”
BackgroundAnticipatory Detection of Compulsive Body-focused Repetitive Behaviors with Wearables
Searle, B. L., Spathis, D., Constantinides, M., Quercia, D., & Mascolo, C. (2021) · International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) · doi:10.1145/3447526.3472061 · Cited by 21
HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data
Mohamed, A., Lejarza, F., Cahail, S., Claudel, C., & Thomaz, E. (2022) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops53856.2022.9767259 · Cited by 20
“Technological advances regarding inertial sensors with longer battery life spans and improved computing capabilities have enabled gathering larger volumes of continuous data to be used for activity prediction [3].”
BackgroundCalico: Relocatable On-cloth Wearables with Fast, Reliable, and Precise Locomotion
Sathya, A., Li, J., Rahman, T., Gao, G., & Peng, H. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3550323 · Cited by 20
“Considerable efforts have also been made towards recognizing human activities at different locations of the body [4] — daily activities such as sitting, standing, walking, ascending & descending stairs (shirt pocket, belt) [34], eating & drinking (neck, wrist and upper arm) [1, 2, 40, 49]; sports like basketball (wris…”
BackgroundOnline Change Point Detection in Application With Transition-Aware Activity Recognition
Thakur, D., & Biswas, S. (2022) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2022.3185533 · Cited by 20
“[23] suggested a dynamic sliding window approach to segment data collected by a single accelerometer.”
BackgroundGEAR: Gaze-enabled augmented reality for human activity recognition
Bektaş, K., Strecker, J., Mayer, S., García, K., Hermann, J., Jenß, K. E., Antille, Y. S., & Solèr, M. E. (2023) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3588015.3588402 · Cited by 20
“Research on HAR is relevant for many applications in human-computer interaction and ubiquitous computing [Bulling et al. 2014] that focus on a seamless interaction between human users and interconnected systems.”
BackgroundA Study on Diffusion Modelling For Sensor-based Human Activity Recognition
Shao, S., & Sánchez, V. (2023) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf57495.2023.10157482 · Cited by 20
“We applied the sliding window technique [21] to segment sensor signals into frames to capture proper activity information.”
MethodDeepa, K., Bačanin, N., Askar, S., & Abouhawwash, M. (2023) · Scientific Reports · doi:10.1038/s41598-023-48860-5 · Cited by 20
Oh, Y., Choi, S.-A., Shin, Y., Jeong, Y., Lim, J., & Kim, S. (2023) · Sensors · doi:10.3390/s24010210 · Cited by 20
“Traditionally, time series data from wearable sensors are preprocessed and feature-engineered to be fed into machine learning algorithms for activity classification [15].”
BackgroundLearning Outside the Classroom
Begel, A., & Ko, A. J. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.027 · Cited by 20
Leveraging the Integrated Development Environment for Learning Analytics
Carter, A., Hundhausen, C. D., & Olivares, D. M. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.024 · Cited by 20
Truong, P. H., You, S., Ji, S.-H., & Jeong, G. (2020) · International Journal of Computers Communications & Control · doi:10.15837/ijccc.2019.6.3618 · Cited by 20
“Human Activity Recognition (HAR) is an emerging research area in human-machine interaction [5, 16, 19].”
BackgroundA Review of Physical Human Activity Recognition Chain Using Sensors
AlShorman, O., Alshorman, B., & Masadeh, M. (2020) · Indonesian Journal of Electrical Engineering and Informatics (IJEEI) · doi:10.11591/ijeei.v8i3.2312 · Cited by 20
Feature extraction and feature selection in smartphone-based activity recognition
Dehkordi, M. B., Zaraki, A., & Setchi, R. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.09.301 · Cited by 20
“Bulling et al. in [11] focused on AR using on-body inertial sensors, discussed the challenges and provided an overview of AR methods.”
MethodEbner, M., Fetzer, T., Bullmann, M., Deinzer, F., & Grzegorzek, M. (2020) · Sensors · doi:10.3390/s20226559 · Cited by 20
“This classification accuracy is composed of the class accuracies 95.8% for the positive, and 89.1% for the outlier class.”
BackgroundInfluentialCrowdAct: Achieving High-Quality Crowdsourced Datasets in Mobile Activity Recognition
Mairittha, N., Mairittha, T., Lago, P., & Inoue, S. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3432222 · Cited by 20
“1145/3432222 1 INTRODUCTION In the field of ubiquitous computing, research on human activity recognition technology has continued to grow over the last decade [12], with applications in numerous areas, such as daily routine monitoring, health monitoring, and nursing care activities.”
BackgroundHaden, P. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.007 · Cited by 20
MyoSpring: 3D Printing Mechanomyographic Sensors for Subtle Finger Gesture Recognition
Lin, S. S.-R., Gamage, N. M., Herath, K., & Withana, A. I. (2022) · International Conference on Tangible, Embedded, and Embodied Interaction (TEI) · doi:10.1145/3490149.3501321 · Cited by 20
“Due to these variations, software customisation such as personalised machine learning models perform better in human gesture recognition [6] than generalised machine learning models.”
MethodMoccia, S., Solbiati, S., Khornegah, M., Bossi, F., & Caiani, E. G. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.106753 · Cited by 20
Sensor-Based Activity Recognition via Learning From Distributions
Qian, H., Pan, S. J., & Miao, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12078 · Cited by 21
Dancing with horses: automated quality feedback for dressage riders
Thompson, R. J., Kyriazakis, I., Holden, A., Olivier, P. L., & Plötz, T. (2015) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2750858.2807536 · Cited by 20
“The overall field has matured and standard approaches are now available to researchers and practitioners in the field [8].”
BackgroundChronic Pain Protective Behavior Detection with Deep Learning
Wang, C., Olugbade, T., Mathur, A., Williams, A. C. D. C., Lane, N. D., & Bianchi‐Berthouze, N. (2021) · ACM Transactions on Computing for Healthcare · doi:10.1145/3449068 · Cited by 20
“Both for the training and testing set, a sliding-window segmentation method [2] is applied to generate consecutive frames from each activity instance.”
MethodA Neuro-Symbolic Approach to Structured Event Recognition
Apriceno, G., Passerini, A., & Serafini, L. (2021) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.time.2021.11 · Cited by 22
On specialized window lengths and detector based human activity recognition
Li, H., Abowd, G. D., & Plötz, T. (2018) · Proceedings of the 2018 ACM International Symposium on Wearable Computers · doi:10.1145/3267242.3267246 · Cited by 19
“Main stream HAR systems employ an activity recognition chain (ARC), which consists of data preprocessing, segmentation, feature extraction, and classification [2].”
BackgroundMethodA human activity recognition model based on deep neural network integrating attention mechanism
Xu, F., Gao, X., & Wang, W. (2025) · Scientific Reports · doi:10.1038/s41598-025-98763-w · Cited by 19
Comparison of two techniques for monitoring of human movements
Wagner, J., Mazurek, P., Miękina, A., Morawski, R. Z., Jacobsen, F. F., Sudmann, T. T., Børsheim, I. T., Øvsthus, K., & Ciamulski, T. (2017) · Measurement · doi:10.1016/j.measurement.2017.04.024 · Cited by 19
Convolutional neural networks (CNN) for indoor human activity recognition using Ubisense system
Li, J., Wu, R., Zhao, J., & Ma, Y. (2017) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2017.7978857 · Cited by 19
“For the sensorbased method[6, 7, 8, 10], experimenter is required to wear the wearable sensor nodes on the different positions of his or her body to receive the signals produced by his or her actions.”
MethodThyme: Improving Smartphone Prompt Timing Through Activity Awareness
Aminikhanghahi, S., Fallahzadeh, R., Sawyer, M., Cook, D. J., & Holder, L. B. (2017) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2017.0-141 · Cited by 19
“Researchers have utilized and enhanced many diverse learning approaches including support vector machines, Gaussian mixture models, decision trees, and probabilistic graphs [29], [36], [37], [41]–[46].”
BackgroundContext Impacts in Accelerometer-Based Walk Detection and Step Counting
Ao, B., Wang, Y., Liu, H., Li, D., Song, L., & Li, J. (2018) · Sensors · doi:10.3390/s18113604 · Cited by 19
Attention-based LSTM Network for Wearable Human Activity Recognition
Sun, B., Liu, M., Zheng, R., & Zhang, S. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8865360 · Cited by 20
“However, it is not reasonable to assume that an event in the distant past would actually influence current events as there is typically only little relation between current and distant past activities [9].”
BackgroundHaladjian, J. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3369813 · Cited by 19
“While the WDK enables the reuse of high-level components without having to understand their implementation details, developers still need to 1) be familiar with the Activity Recognition Chain and 2) understand the function, inputs and output produced by the components in the WDK.”
BackgroundMethodInfluentialJointly optimization for activity recognition in secure IoT-enabled elderly care applications
Tao, M., Li, X., Wei, W., & Yuan, H. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106788 · Cited by 19
Cust, E. E., Sweeting, A. J., Ball, K. A., & Robertson, S. J. (2020) · Journal of Sports Sciences · doi:10.1080/02640414.2020.1868678 · Cited by 19
“Specifically, when using IMUs for sport-specific action recognition the overall performance can be greatly influenced by the data capture methods, data processing, model development, and sensor hardware (Bulling et al., 2014; Cust, Sweeting, Ball, Robertson et al., 2019).”
MethodUnderstanding practices and needs of researchers in human state modeling by passive mobile sensing
Xu, X., Mankoff, J. C., & Dey, A. K. (2021) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-021-00072-4 · Cited by 19
“” (P7) This makes mobile sensing data different from other time-series data such as inertial measurement unit (IMU) signals (Bulling et al. 2014) and electromyography (EMG) (Fan et al. 2018) which usually contain simple information of a single dimension.”
BackgroundMeyer, J., Frank, A., Schlebusch, T., & Kasneci, E. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3530884 · Cited by 19
“As HAR refers to the concept of inferring activities based on a time series of observations [3], which is similar to the applications of Perslev et.”
BackgroundMethodInfluentialInertial Data-Based AI Approaches for ADL and Fall Recognition
Martins, L. M., Ribeiro, N. F., Soares, F., & Santos, C. P. (2022) · Sensors · doi:10.3390/s22114028 · Cited by 19
“Furthermore, intraclass variability (the same activity may differ from one subject to the other) and interclass similarity (various activities may exhibit similar forms) make recognizing human activities even more challenging [12].”
BackgroundFeature Set Optimization for Physical Activity Recognition Using Genetic Algorithms
Baldominos, A., Sáez, Y., & Isasi, P. (2015) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/2739482.2768506 · Cited by 19
“Recently, Bulling et al. [10] have examined the differ-ent characteristics of human activity recognition systems (which is a more general concept than that of physical activity recognition systems) according to different criteria: • According to its execution mode, the system can work either in an…”
BackgroundA Survey on Mobile Social Signal Processing
Palaghias, N., Hoseinitabatabaei, S. A., Nati, M., Gluhak, A., & Moessner, K. (2016) · ACM Computing Surveys · doi:10.1145/2893487 · Cited by 19
Mining Productive-Associated Periodic-Frequent Patterns in Body Sensor Data for Smart Home Care
Ismail, W. N., & Hassan, M. M. (2017) · Sensors · doi:10.3390/s17050952 · Cited by 19
“BSNs can be used to extract knowledge about the health condition of the patient and these have enabled the development of many real-time activity recognition approaches [11, 12, 13, 14].”
BackgroundOn-Line Detection and Segmentation of Sports Motions Using a Wearable Sensor
Kim, W., & Kim, M.-G. (2018) · Sensors · doi:10.3390/s18030913 · Cited by 19
“To estimate states, a sequence classifier N is defined as: from the sequence of the estimated states. x = ((cid:2206) (cid:2869) , (cid:2206) (cid:2870) , … , (cid:2206) (cid:3013) ) , where x is a sequence of feature vectors and y is a sequence of state probabilities. where x is a sequence of…”
BackgroundHänsel, K., Wilde, N., Haddadi, H., & Alomainy, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.05238 · Cited by 19
“Utilising Accelerometer data can identify activities such as walking, running, eating and drinking movements [Amft et al. 2005; Bulling et al. 2014].”
MethodSensor-based Detection and Classification of Soccer Goalkeeper Training Exercises
Haladjian, J., Schlabbers, D., Taheri, S., Tharr, M., & Bruegge, B. (2020) · ACM Transactions on Internet of Things · doi:10.1145/3372342 · Cited by 18
“The statistical features we chose have been previously used in similar wearable activity recognition applications [Blank et al. 2015; Bulling et al. 2014; Haladjian et al. 2017].”
BackgroundMethodInfluentialHong, S., Ham, Y., Chun, J., & Kim, H. (2023) · Sensors · doi:10.3390/s23177635 · Cited by 18
“The results of these studies can be further improved through the use of multiple sensors that can provide complementary information for improving accuracy [43,73].”
BackgroundMAG-Res2Net: a novel deep learning network for human activity recognition
Liu, H., Zhao, B., Dai, C., Sun, B., Li, A., & Wang, Z. (2023) · Physiological Measurement · doi:10.1088/1361-6579/ad0ab8 · Cited by 18
Oubre, B., & Lee, S. I. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3337156 · Cited by 18
Untapped Potential of Unobtrusive Observation for Studying Health Behaviors
Benton, J. S., & French, D. (2023) · JMIR Public Health and Surveillance · doi:10.2196/46638 · Cited by 18
Zhang, J., Feng, L., Liu, Z., Wu, Y., He, Y., Dong, Y., & Xu, D. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671828 · Cited by 18
Mao, W., Wang, C., Chou, P.-H., Liu, K.-C., & Tsao, Y. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3456577 · Cited by 18
“These nine features are widely used in FD [6] and HAR [52].”
A parallel CNN architecture for sport activity recognition based on minimal movement data
Zhao, H. V. (2024) · Scientific Reports · doi:10.1038/s41598-024-81733-z · Cited by 18
Accelerometer vs. Electromyogram in Activity Recognition
Koskimäki, H., & Siirtola, P. (2016) · ADCAIJ ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL · doi:10.14201/adcaij2016533142 · Cited by 18
Personalized weight loss strategies by mining activity tracker data
Gasparetti, F., Aiello, L. M., & Quercia, D. (2019) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-019-09242-7 · Cited by 18
A Localized Learning Approach Applied to Human Activity Recognition
Amer, A. Y. A., Aerts, J., Vanrumste, B., & Luca, S. (2020) · IEEE Intelligent Systems · doi:10.1109/mis.2020.2964738 · Cited by 19
“Human physical activities can be recognised by using computer vision techniques through the analysis of images and videos or by exploring sensory data that are obtained by wearable or portable sensors [1].”
BackgroundScoring Performance on the Y-Balance Test Using a Deep Learning Approach
Gil-Martín, M., Johnston, W., San-Segundo, R., & Caulfield, B. M. (2021) · Sensors · doi:10.3390/s21217110 · Cited by 18
“HAR systems typically use a general-purpose framework [17] with several modules for activity recognition tasks, which could be extended for regression tasks.”
BackgroundMethodKumar, P., & Suresh, S. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100681 · Cited by 18
Time Series Data Mining for Sport Data: a Review
Komitova, R., Raabe, D., Rein, R., & Memmert, D. (2022) · Int. J. Comput. Sci. Sport · doi:10.2478/ijcss-2022-0008 · Cited by 18
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.