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 201–300 of 1,007
Wearable sensors for the monitoring of movement disorders
Jalloul, N. (2018) · Biomedical Journal · doi:10.1016/j.bj.2018.06.003 · Cited by 80
Cross-Modal Federated Human Activity Recognition
Yang, X., Xiong, B., Huang, Y., & Xu, C. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3367412 · Cited by 78
Activity Recognition Invariant to Sensor Orientation with Wearable Motion Sensors
Yurtman, A., & Barshan, B. (2017) · Sensors · doi:10.3390/s17081838 · Cited by 77
Wang, H., Gong, J., Zhuang, Y., Shen, H., & Lach, J. (2017) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2017.8258047 · Cited by 77
“Researchers have developed supervised and unsupervised machine learning techniques [44, 45, 11] to extract information from sensed data for human behavior inference[46, 11, 47, 48, 33, 34].”
BackgroundReplacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis
Malekzadeh, M., Clegg, R. G., & Haddadi, H. (2018) · 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi.2018.00025 · Cited by 76
“For Skoda and Hand-Gesture datasets, we randomly select 80% of time-windows for training phase and the remaining 20% is used for the tests.”
MethodInfluentialO'Brien, J. T., Gallagher, P., Stow, D., Hammerla, N., Ploetz, T., Firbank, M., Ladha, C., Ladha, K., Jackson, D., McNaney, R., et al. (2017) · Psychological Medicine · doi:10.1017/s0033291716002166 · Cited by 76
“…an understanding of disease-speci fi c idiosyncrasies in physical behaviour, for example: gait analysis (Lemke et al. 2000), activity recognition (Bulling et al. 2014), automated symptom assessment (Hammerla et al. 2015), analysis of aggressive behaviour (Plötz et al. 2012), or skill…”
A Comparison Study of Classifier Algorithms for Cross-Person Physical Activity Recognition
Sáez, Y., Baldominos, A., & Isasi, P. (2016) · Sensors · doi:10.3390/s17010066 · Cited by 77
“This sequence of steps was extensively described by [38] as a general-purpose framework for acquiring data samples and building and evaluating activity recognition systems.”
BackgroundUnobtrusive and Wearable Systems for Automatic Dietary Monitoring
Prioleau, T., Moore, E., & Ghovanloo, M. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2016.2631246 · Cited by 70
Outlier Detection in Wearable Sensor Data for Human Activity Recognition (HAR) Based on DRNNs
Munoz-Organero, M. (2019) · IEEE Access · doi:10.1109/access.2019.2921096 · Cited by 69
“Hand-made features were formerly usedwith shallow learning algorithms for classification of activities [1], [2].”
BackgroundMethodMulti-sensor fusion based on multiple classifier systems for human activity identification
Nweke, H. F., Wah, T. Y., Mujtaba, G., Alo, U. R., & Al-Garadi, M. A. (2019) · Human-centric Computing and Information Sciences · doi:10.1186/s13673-019-0194-5 · Cited by 76
“The sliding window approach is considered in this study for its effectiveness in human activity detection [61].”
MethodAutomatic recognition of ingestive-related behaviors of dairy cows based on triaxial acceleration
Shen, W., Cheng, F., Zhang, Y., Wei, X., Fu, Q., & Zhang, Y. (2019) · Information Processing in Agriculture · doi:10.1016/j.inpa.2019.10.004 · Cited by 75
Development of a Human Activity Recognition System for Ballet Tasks
Hendry, D., Chai, K. E. K., Campbell, A., Hopper, L., O’Sullivan, P., & Straker, L. M. (2020) · Sports Medicine - Open · doi:10.1186/s40798-020-0237-5 · Cited by 75
Improving Deep Learning for HAR with Shallow LSTMs
Bock, M., Hölzemann, A., Moeller, M., & Van Laerhoven, K. (2021) · 2021 International Symposium on Wearable Computers · doi:10.1145/3460421.3480419 · Cited by 74
“Which activity, and how it is performed, can reveal a person’s intention, habit, fitness, and state of mind; it is therefore not surprising that a range of research fields, from cognitive science to healthcare, display a growing interest in the machine recognition of human activities, also known as Human Activity Reco…”
BackgroundAiello, G., Catania, P., Vallone, M., & Venticinque, M. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106637 · Cited by 74
Challenges and advances in the use of wearable sensors for lower extremity biomechanics
Hafer, J. F., Vitali, R. V., Gurchiek, R. D., Curtze, C., Shull, P. B., & Cain, S. M. (2023) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2023.111714 · Cited by 74
ImgFi: A High Accuracy and Lightweight Human Activity Recognition Framework Using CSI Image
Zhang, C., & Jiao, W. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3296445 · Cited by 74
“For the HAR based on sensors, the sensor must be mounted or worn on various parts of the body [4], which is less convenient than other categories.”
A Novel Distribution-Embedded Neural Network for Sensor-Based Activity Recognition
Qian, H., Pan, S. J., Da, B., & Miao, C. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/779 · Cited by 56
“Human activity recognition is an important technique with a wide range of real-world applications, e.g., assisted living, personalized health monitoring, security and smart homes [Janidarmian et al. , 2017; Bulling et al. , 2014; Lara and Labrador, 2013].”
BackgroundHuman activity recognition from wearable sensors using extremely randomized trees
Uddin, M. T., & Uddiny, M. A. (2015) · International Conference on Electrical Engineering and Information Communication Technology · doi:10.1109/iceeict.2015.7307384 · Cited by 73
“collecting and filtering data, extracting and selecting features from filtered data, and building classification model using these features to classify different activities [2].”
BackgroundMethodUsing Smart Homes to Detect and Analyze Health Events
Sprint, G., Cook, D. J., Fritz, R., & Schmitter-Edgecombe, M. (2016) · Computer · doi:10.1109/mc.2016.338 · Cited by 66
“Activity recognition algorithms have been designed for wearable, phone, home, video, and other sensors using machine learning techniques that range from naïve Bayes classifiers and decision trees to more complex models including Gaussian mixture models and conditional random fields [8], [9].”
MethodProgramming Paradigms and Beyond
Krishnamurthi, S., & Fisler, K. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.014 · Cited by 75
Deep Fisher discriminant learning for mobile hand gesture recognition
Li, C., Xie, C., Zhang, B., Chen, C., & Han, J. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.12.023 · Cited by 72
“problem on mobile devices using inertial sensors [37, 38, 39, 40, 6, 5].”
BackgroundDeep learning based multimodal complex human activity recognition using wearable devices
Chen, L., Liu, X., Peng, L., & Wu, M. (2020) · Applied Intelligence · doi:10.1007/s10489-020-02005-7 · Cited by 72
“Yang et al. [30] used a CNN instead of traditional methods (e.g., basis transform coding [31], the statistics of raw signals [32], and symbolic representation [33]) to extract features from row inputs automatically.”
MethodHorn, M., & Bers, M. U. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.023 · Cited by 72
Beyond activity recognition: skill assessment from accelerometer data
Khan, A., Mellor, S., Berlin, E., Thompson, R., McNaney, R., Olivier, P., & Plötz, T. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2807534 · Cited by 67
“For traditional activity recognition tasks, the first step of processing typically corresponds to feature extraction, often based on a sliding window procedure that processes analysis frames of consecutive sensor readings [12].”
MethodA Platform for Free-Weight Exercise Monitoring with Passive Tags
Ding, H., Han, J., Shangguan, L., Xi, W., Jiang, Z., Yang, Z., Zhou, Z., Yang, P., & Zhao, J. (2017) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2017.2691705 · Cited by 72
“We evaluate the activity segmentation scheme based on six metrics [10]: insertion rate, deletion rate, fragmentation rate, merge rate, underfill rate and accuracy.”
BackgroundMethodDeActive: Scaling Activity Recognition with Active Deep Learning
Hossain, H. M. S., Al Haiz Khan, M. A., & Roy, N. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3214269 · Cited by 56
“The widely used features in activity recognition domain include basis transform coding (e.g.signals with wavelet transform and Fourier transform) [39], statistical parameters extracted from raw sensor signals [19] and symbolic representation [31].”
BackgroundMethodWITS: an IoT-endowed computational framework for activity recognition in personalized smart homes
Yao, L., Sheng, Q. Z., Benatallah, B., Dustdar, S., Wang, X., Shemshadi, A., & Kanhere, S. S. (2018) · Computing · doi:10.1007/s00607-018-0603-z · Cited by 71
“However, it has not been fully investigated how to interpret human behaviors from the massive, user-generated, heterogeneous, multi-modal, and context-relevant sensory data [3,5,17,29,30], as a result of several challenging issues.”
BackgroundAutomatic Annotation for Human Activity Recognition in Free Living Using a Smartphone
Cruciani, F., Cleland, I., Nugent, C., McCullagh, P., Synnes, K., & Hallberg, J. (2018) · Sensors · doi:10.3390/s18072203 · Cited by 60
“Another major issue to be faced is class imbalance [6], particularly when collecting data in free-living situations where samples corresponding to some of the activities may be less likely to occur.”
BackgroundResultInfluentialMazilu, S., Blanke, U., Dorfman, M., Gazit, E., Mirelman, A., Hausdorff, J. M., & Tröster, G. (2015) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/2701431 · Cited by 70
“Machine learning models have been proven to be useful in accurately detecting human activities such as walking, sitting, standing, and falling [Bulling et al. 2014; Choi et al. 2011].”
BackgroundSelf-citationWearables, smartphones, and artificial intelligence for digital phenotyping and health
Perez-Pozuelo, I., Spathis, D., Clifton, E. A. D., & Mascolo, C. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-820077-3.00003-1 · Cited by 69
A Survey of Deep Learning Based Models for Human Activity Recognition
Khan, N. S., & Ghani, M. S. (2021) · Wireless Personal Communications · doi:10.1007/s11277-021-08525-w · Cited by 69
“Another widely studied domain is related with the fitness (gym) [52, 53] and sports activities (SA) [38, 39, 51] such as tennis (T) [33] etc.”
BackgroundMethodInfluentialA perspective on human activity recognition from inertial motion data
Gomaa, W., & Khamis, M. A. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08863-9 · Cited by 54
Data-Driven Design of Intelligent Wireless Networks: An Overview and Tutorial
Kulin, M., Fortuna, C., Poorter, E. D., Deschrijver, D., & Moerman, I. (2016) · Sensors · doi:10.3390/s16060790 · Cited by 69
“[21] present a comprehensive tutorial on human activity recognition (HAR) using on-body inertial sensors.”
BackgroundDahmen, J., Cook, D. J., Wang, X., & Honglei, W. (2017) · Journal of Reliable Intelligent Environments · doi:10.1007/s40860-017-0035-0 · Cited by 69
Quantifying Sources and Types of Smartwatch Usage Sessions
Visuri, A., Sarsenbayeva, Z., van Berkel, N., Goncalves, J., Rawassizadeh, R., Kostakos, V., & Ferreira, D. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025817 · Cited by 60
Cantin-Garside, K. D., Kong, Z., White, S. W., Antezana, L., Kim, S., & Nussbaum, M. A. (2020) · Journal of Autism and Developmental Disorders · doi:10.1007/s10803-020-04463-x · Cited by 71
Gil-Martín, M., San-Segundo, R., Fernández-Martínez, F., & Ferreiros, J. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.103679 · Cited by 69
Ye, X., Sakurai, K., Nair, N. C., & Wang, K. I. (2024) · Sensors · doi:10.3390/s24247975 · Cited by 68
“We follow the definition of sensor-based HAR as previous work [9][2][84].”
MethodActivity Learning as a Foundation for Security Monitoring in Smart Homes
Dahmen, J., Thomas, B., Cook, D. J., & Wang, X. (2017) · Sensors · doi:10.3390/s17040737 · Cited by 68
A scoping review of neurodegenerative manifestations in explainable digital phenotyping
Alfalahi, H., Dias, S. B., Khandoker, A. H., Chaudhuri, К. R., & Hadjileontiadis, L. J. (2023) · npj Parkinson s Disease · doi:10.1038/s41531-023-00494-0 · Cited by 67
“Furthermore, among the most reliable models of sequential data are Hidden Markov Models that have been utilized for Daily Activity Recognition 185 .”
MethodA Review of AIoT-Based Human Activity Recognition: From Application to Technique
Qi, W., Xu, X., Qian, K., Schuller, B. W., Fortino, G., & Aliverti, A. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3406737 · Cited by 68
“It needed to be carried on specific body positions, while a more than single physical inertial sensor was required to identify more complex motions, such as drinking coffee and cooking [10].”
TagFree Activity Identification with RFIDs
Fan, X., Gong, W., & Liu, J. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3191739 · Cited by 62
“It has received significant 7:2 • X. Fan et al. attention from both academia and industry, with diverse solutions based on radars [30], cameras [4], inertial sensors [3], etc.”
BackgroundBARNET: Towards Activity Recognition Using Passive Backscattering Tag-to-Tag Network
Ryoo, J., Karimi, Y., Athalye, A., Stanaćević, M., Das, S. R., & Djurić, P. M. (2018) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3210240.3210336 · Cited by 67
“We adopt the commonly used architecture of the CNN used for hand gesture recognition [14].”
MethodMulti-target affect detection in the wild: an exploratory study
Schmidt, P., Dürichen, R., Reiss, A., Laerhoven, K. V., & Plötz, T. (2019) · International Symposium on Wearable Computers · doi:10.1145/3341163.3347741 · Cited by 67
“For the classical experiments we followed the HAR pipeline [4] and extracted features from windowed data (size 60 sec, shift 5 sec).”
MethodInoue, S., Lago, P., Hossain, T., Mairittha, T., & Mairittha, N. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3351244 · Cited by 67
“2 Label Collection for Activity Recognition Activity recognition, the automatic identication of what a user is doing based on sensor data, is an active eld of research in the ubiquitous computing community [3, 15, 16, 26, 27], but there are few examples of real world activity recognition.”
BackgroundPhysical Workload Tracking Using Human Activity Recognition with Wearable Devices
Manjarrés, J., Narváez, P., Gasser, K., Percybrooks, W., & Pardo, M. (2019) · Sensors · doi:10.3390/s20010039 · Cited by 68
Data-Driven Activity Prediction: Algorithms, Evaluation Methodology, and Applications
Minor, B., Doppa, J. R., & Cook, D. J. (2015) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2783258.2783408 · Cited by 66
“Activity recognition algorithms have been investigated over the last decade for a plethora of sensor platforms, including ambient sensors, wearable sensors, phone sensors, and audio/video data [2, 3, 14, 20, 25].”
BackgroundA sliding window approach to natural hand gesture recognition using a custom data glove
Luzhnica, G., Simon, J., Lex, E., & Pammer‐Schindler, V. (2016) · IEEE Symposium on 3D User Interfaces (3DUI) · doi:10.1109/3dui.2016.7460035 · Cited by 66
“According to the survey presented in [3], discriminative classification algorithms are very effective in identifying features that mostly contribute to discriminations between activities using wearable sensors.”
BackgroundGong, J., Huang, Y., Chow, P. I., Fua, K., Gerber, M. S., Teachman, B. A., & Barnes, L. E. (2018) · Information Fusion · doi:10.1016/j.inffus.2018.09.002 · Cited by 68
Deep Dilated Convolution on Multimodality Time Series for Human Activity Recognition
Xi, R., Hou, M., Fu, M., Qu, H., & Liu, D. (2018) · 2018 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489540 · Cited by 51
“Besides, they ignore the characteristics of HAR task: intra-class variability and similarity, and complexness of physical activities [9].”
BackgroundDetection of Artifacts in Ambulatory Electrodermal Activity Data
Gashi, S., Lascio, E. D., Stancu, B., Swain, V. D., Mishra, V., Gjoreski, M., & Silvia Santini, B. (2020) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3397316 · Cited by 65
“As a first processing step we convert the unit to g by dividing with 64, as suggested in [6, 64].”
BackgroundMethodInfluentialA guided random forest based feature selection approach for activity recognition
Uddin, M. T., & Uddiny, M. A. (2015) · International Conference on Electrical Engineering and Information Communication Technology · doi:10.1109/iceeict.2015.7307376 · Cited by 65
Learning from less for better: semi-supervised activity recognition via shared structure discovery
Yao, L., Nie, F., Sheng, Q. Z., Gu, T., Li, X., & Wang, S. (2016) · Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2971648.2971701 · Cited by 58
“One challenge is how to effectively deal with intra-class variability [10].”
BackgroundLearning Activity Predictors from Sensor Data: Algorithms, Evaluation, and Applications
Minor, B., Doppa, J. R., & Cook, D. J. (2017) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2017.2750669 · Cited by 65
“Activity learning has been investigated over the last decade for a plethora of sensor platforms, including ambient sensors, wearable sensors, phone sensors, and audio/video data [13], [16].”
How Validation Methodology Influences Human Activity Recognition Mobile Systems
Bragança, H. L. D. S., Colonna, J. G., Oliveira, H. A. B. F., & Souto, E. (2022) · Sensors · doi:10.3390/s22062360 · Cited by 65
“F Measure 2 × Precision×RecallPrecision+Recall The F-measure is the harmonic mean of Precision and Recall.”
BackgroundMethodInfluentialApplication of human activity/action recognition: a review
sedaghati, N., Ardebili, S., & Ghaffari, A. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20576-2 · Cited by 65
Bootstrapping Personalised Human Activity Recognition Models Using Online Active Learning
Miu, T., Missier, P., & Plotz, T. (2015) · 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing · doi:10.1109/cit/iucc/dasc/picom.2015.170 · Cited by 54
“[38] review numerous machine learning procedures and algorithms (such as data preprocessing, feature extraction, model building) that have been used in HAR.”
MethodA Low Power Fall Sensing Technology Based on FD-CNN
He, J., Zhang, Z., Wang, X., & Yang, S. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2903482 · Cited by 66
“With the development of microelectromechanical systems (MEMS), researchers have integrated inertial sensors into small wearable devices to achieve fall detection [10], [11].”
BackgroundCAVIAR: Context-driven Active and Incremental Activity Recognition
Bettini, C., Civitarese, G., & Presotto, R. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.105816 · Cited by 64
Machine Learning-Based Algorithms to Knowledge Extraction from Time Series Data: A Review
Ciaburro, G., & Iannace, G. (2021) · Data · doi:10.3390/data6060055 · Cited by 63
A Tutorial on Internet of Behaviors: Concept, Architecture, Technology, Applications, and Challenges
Zhao, Q., Li, G., Cai, J., Zhou, M., & Feng, L. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3246993 · Cited by 63
Human Activity Recognition from Multiple Sensors Data Using Multi-fusion Representations and CNNs
Noori, F. M., Riegler, M. A., Uddin, M. Z., & Tørresen, J. (2020) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3377882 · Cited by 63
“Furthermore, a multi-source fusion framework driven by user-defined knowledge for egocentric activity recognition was proposed in Reference [60].”
MethodInfluentialPonce-Espinosa, H., Martínez-Villaseñor, L., & Miralles‐Pechuán, L. (2016) · Sensors · doi:10.3390/s16071033 · Cited by 62
“Therefore, some authors choose to experiment with raw data for comparison and evaluation of the recognition performance of supervised and/or unsupervised machine learning techniques [32,33].”
BackgroundMethodInfluentialClustering Big Spatiotemporal-Interval Data
Shao, W., Salim, F. D., Song, A., & Bouguettaya, A. (2016) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2016.2599923 · Cited by 62
“For example, the tri-axial accelerometer, the most popular sensor in human activity recognition is a typical time-series data [9], [10], [11].”
BackgroundTechnology-Enabled Assessment of Functional Health
Cook, D. J., Schmitter-Edgecombe, M., Jonsson, L., & Morant, A. V. (2019) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2018.2851500 · Cited by 54
“algorithms such as support vector machines, Gaussian mixture models, decision trees, and probabilistic graphs [103], [104].”
MethodChan, S., Hang, Y., Tong, C., Acquah, A., Schonfeldt, A., Gershuny, J., & Doherty, A. (2024) · Scientific Data · doi:10.1038/s41597-024-03960-3 · Cited by 61
“We followed the common practice of sliding-window segmentation 22 to extract fixed-size, non-overlapping windows of ten seconds.”
IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition
Leng, Z., Bhattacharjee, A., Rajasekhar, H., Zhang, L., Bruda, E., Kwon, H., & Plötz, T. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3678545 · Cited by 61
“Conventional HAR applications are typically based on (some variant of) the "Activity Recognition Chain (ARC)" (e.g., [14]), which divides the analysis problem into five general processing blocks: recording, preprocessing, (sliding-window) segmentation, feature extraction, and classification.”
Hoelzemann, A., Romero, J., Bock, M., Laerhoven, K. V., & Lv, Q. (2023) · Sensors · doi:10.3390/s23135879 · Cited by 61
“The two levels of skills, novice and expert, inherit a strong intraclass and intersubject signal-variability which has already been mentioned by Bulling et al. [12] in 2014 and is still an ongoing research challenge in real-world scenarios.”
BackgroundMethodInfluentialPhysical Behavior in Older Persons during Daily Life: Insights from Instrumented Shoes
el Achkar, C. M., Lenoble-Hoskovec, C., Paraschiv-Ionescu, A., Major, K., Büla, C., & Aminian, K. (2016) · Sensors · doi:10.3390/s16081225 · Cited by 61
“This task is highly time-, effort-, and resource-consuming [19].”
BackgroundRobust Human Interaction Recognition Using Extended Kalman Filter
Bukht, T. F. N., Alazeb, A., Mudawi, N. A., Alabdullah, B. I., Alnowaiser, K., Jalal, A., & Liu, H. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.053547 · Cited by 60
Multi-resident activity tracking and recognition in smart environments
Alemdar, H. O., & Ersoy, C. (2017) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-016-0440-x · Cited by 60
“More recently, the unprecedented growth of the wearable devices gave rise to a whole new track of well-being applications that require automatic recognition of activities (Bulling et al. 2014; Lara and Labrador 2013).”
BackgroundAudio content analysis for unobtrusive event detection in smart homes
Vafeiadis, A., Votis, K., Giakoumis, D., Tzovaras, D. K., Chen, L., & Hamzaoui, R. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2019.08.020 · Cited by 60
“One common approach to automated HAR uses portable sensors such as accelerometers and gyroscopes [7, 8].”
MethodGuerra, B. M. V., Torti, E., Marenzi, E., Schmid, M., Ramat, S., Leporati, F., & Danese, G. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1256682 · Cited by 61
“Concerning EDSW, it differs from the others since the number of samples included in the time window is not fixed (i.e., it features a variable window size) (Devanne et al., 2019).”
Ni, Q., Patterson, T. J., Cleland, I., & Nugent, C. (2016) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2016.07.005 · Cited by 59
Adaimi, R., & Thomaz, E. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3351228 · Cited by 59
“In HAR research focused on naturalistic settings, data annotation is often a time-consuming and burdensome process, and considered a key challenge [9].”
New Sensor Data Structuring for Deeper Feature Extraction in Human Activity Recognition
Alemayoh, T. T., Lee, J. H., & Okamoto, S. (2021) · Sensors · doi:10.3390/s21082814 · Cited by 59
“HAR methods intend to understand a person’s activity behaviors to enable computing systems to proactively assist users in various fields [7].”
MethodHuman Activity Recognition by Combining a Small Number of Classifiers
Nazabal, A., Garcia-Moreno, P., Artes-Rodriguez, A., & Ghahramani, Z. (2016) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2015.2458274 · Cited by 49
“Wearable sensors [4], [6], [7] become an attractive alternative for such HAR systems (see [3] and [8] for recents reviews), specially when traditional wired sensors become wireless [9] making use of new wireless protocols like Bluetooth Smart (also known as Bluetooth Low Energy) [10], [11].”
BackgroundCognitive Sciences for Computing Education
Robins, A. V., Margulieux, L. E., & Morrison, B. B. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108654555.010 · Cited by 59
Jung, I. D., Shin, D. S., Kim, D., Lee, J., Lee, M. S., Son, H. J., Reddy, N. S., Kim, M., Moon, S. K., Kim, K. T., et al. (2020) · Materialia · doi:10.1016/j.mtla.2020.100699 · Cited by 58
Enhanced Human Activity Recognition Using Wearable Sensors via a Hybrid Feature Selection Method
Fan, C., & Gao, F. (2021) · Sensors · doi:10.3390/s21196434 · Cited by 58
“Table 1 shows some popular features extracted from three axial data from both an accelerometer and gyroscope for HAR tasks, many of which are commonly used across existing studies of activity recognition [36].”
BackgroundAssessing Human Motion During Exercise Using Machine Learning: A Literature Review
Frangoudes, F., Matsangidou, M., Schiza, E. C., Neokleous, K., & Pattichis, C. S. (2022) · IEEE Access · doi:10.1109/access.2022.3198935 · Cited by 57
“In addition, data from exercises may also display inter-class similarities [161].”
BackgroundLiang, W., Wang, F., Fan, A., Zhao, W., Yao, W., & Yang, P. (2023) · Sensors · doi:10.3390/s23094229 · Cited by 59
Distributionally Robust Semi-Supervised Learning for People-Centric Sensing
Chen, K., Yao, L., Zhang, D., Chang, X., Long, G., & Wang, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013321 · Cited by 49
Dezert-Smarandache Theory-Based Fusion for Human Activity Recognition in Body Sensor Networks
Dong, Y., Li, X., Dezert, J., Khyam, M. O., Noor‐A‐Rahim, M., & Ge, S. S. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2976812 · Cited by 57
“Generally speaking, multi-sensor fusion strategies can be mainly categorized into three level categories depending on the abstraction level used for data processing: data-fusion level [8], feature-fusion level [9] and decision-level fusion [10].”
BackgroundWang, K., He, J., & Zhang, L. (2021) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2021.3086008 · Cited by 49
“H UMAN activity is unique, as the information inferred from raw activity data has been proved to be very critical in human activity recognition (HAR) [1], health support [2], and smart homes [3] to name a few.”
BackgroundAutomated Class Discovery and One-Shot Interactions for Acoustic Activity Recognition
Wu, J., Harrison, C., Bigham, J. P., & Laput, G. (2020) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376875 · Cited by 57
“Optical sensors, such as RGB cameras [23][32][35][36] or depth sensors [38][82] are popular approaches for human activity recognition [14], but these systems are susceptible to occlusion.”
BackgroundMethodHuang, W., Zhang, L., Teng, Q., Song, C., & He, J. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3092396 · Cited by 56
“Wearable sensor based human activity recognition (HAR)[1][2] has turned into a new research hotspot with various real-world applications like health monitoring[3][4][5][6], sports tracking[7][8], smart homes[9], and game console designing[10] etc .”
BackgroundCheng, D., Zhang, L., Bu, C., Wu, H., & Song, A. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110789 · Cited by 55
Random forests based recognition of human activities and postural transitions on smartphone
Uddin, M. T., Billah, M. M., & Hossain, M. F. (2016) · International Conference on Informatics, Electronics & Vision (ICIEV) · doi:10.1109/iciev.2016.7760005 · Cited by 55
“ARC comprises of numerous techniques from multiple domains including signal processing and machine learning for data acquisition and preprocessing, data segmentation, feature extraction and selection, training and classification, decision fusion, and performance evaluation.”
BackgroundInfluentialJuutinen, M., Wang, C., Zhu, J. X., Haladjian, J., Ruokolainen, J., Puustinen, J., & Vehkaoja, A. T. (2020) · PLoS ONE · doi:10.1371/journal.pone.0236258 · Cited by 55
Recent Advances in Pedestrian Inertial Navigation Based on Smartphone: A Review
Wang, Q., Fu, M., Wang, Q., Luo, H., Sun, L., Ma, Z., Li, W., Zhang, C., Huang, R. Y., Li, X., et al. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3213836 · Cited by 55
“For sensor-based PNAR, interactivity similarity makes feature extraction more difficult [281].”
Multi-STMT: Multi-Level Network for Human Activity Recognition Based on Wearable Sensors
Zhang, H., & Xu, L. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3365155 · Cited by 57
“Traditional machine learning (ML), such as Naive Bayes (NB) [5], random forest (RF) [6], K -nearest neighbors (KNNs) [7], the decision tree (DT) [8], and support vector machines (SVMs) [9], are widely used in HAR tasks.”
MethodLiu, L., Wang, S., Su, G., Huang, Z., & Liu, M. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.02.028 · Cited by 54
“Current techniques are becoming mature to recognize basic actions and movements from cameras or other sensors [8, 9, 17, 6, 44, 21].”
BackgroundPrivacy and utility preserving sensor-data transformations
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2020) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2020.101132 · Cited by 54
Unsupervised Domain Adaptation for RF-Based Gesture Recognition
Zhang, B., Zhang, D., Li, Y., Hu, Y., & Chen, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3284496 · Cited by 53
“etc. Traditional approaches adopt cameras [1], [2], wearable devices, and phones [3], [4] as the sensing front-end, which however suffer from inherent drawbacks, including privacy leakage, inconvenience, and limited sensing range.”
Mario, M.-O. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2882943 · Cited by 50
“THE information provided by user-worn sensors such as accelerometers and gyroscopes has proven to be a valid candidate in order to estimate the activity that the user is performing [1]–[3].”
BackgroundRemote Health Monitoring Systems for Elderly People: A Survey
Ahmed, S., Irfan, S., Kiran, N., Masood, N., Anjum, N., & Ramzan, N. (2023) · Sensors · doi:10.3390/s23167095 · Cited by 52
“With the rapid development of new and improved sensors, the data collected from them is becoming more and more accurate [25,80,81].”
BackgroundHandling annotation uncertainty in human activity recognition
Kwon, H., Abowd, G. D., & Plötz, T. (2019) · Proceedings of the 23rd International Symposium on Wearable Computers · doi:10.1145/3341163.3347744 · Cited by 52
“When training, the model predicted the target label probability at the last timestep in the window [5, 24].”
MethodYang, X., Xiong, B., Huang, Y., & Xu, C. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20213 · Cited by 52
“…video and sensor data, which has significantly inspired the research on vision-based (Simonyan and Zisserman 2014; Song et al. 2016a), sensor-based (Bulling, Blanke, and Schiele 2014) and multimodal (Nakamura et al. 2017; Possas, Pinto-Caceres, and Ramos 2018) activity recognition approaches.”
MethodWang, F., Zhang, T., Xi, W., Ding, H., Wang, G., Zhang, D., Cui, Y., Liu, F., Han, J., Xu, J., et al. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3670854 · Cited by 53
“For instance, SFTSeg [171] trains a model on the IMU-based HandGesture dataset [259] and transfers it to the Wi-Fi-based WiFiAction dataset [260], achieving few-shot recognition across sensing modalities. b) Learning with Contrastive Learning: Contrastive learning also relies on constructing…”
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.