On-body localization of wearable devices: An investigation of position-aware activity recognition
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Human activity recognition using mobile device sensors is an active area of research in pervasive computing. In our work, we aim at implementing activity recognition approaches that are suitable for real life situations. This paper focuses on the problem of recognizing the on-body position of the mobile device which in a real world setting is not known a priori. We present a new real world data set that has been collected from 15 participants for 8 common activities were they carried 7 wearable devices in different positions. Further, we introduce a device localization method that uses random forest classifiers to predict the device position based on acceleration data. We perform the most complete experiment in on-body device location that includes all relevant device positions for the recognition of a variety of different activities. We show that the method outperforms other approaches achieving an F-Measure of 89% across different positions. We also show that the detection of the device position consistently improves the result of activity recognition for common activities.
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 performance of supervised learning methods is particularly dependent on large-scale labeled datasets, which require significant human efforts and financial costs [62].”
From Spatial-Temporal Masked Autoencoder for Multi-Device Wearable Human Activity Recognition (2023) · cites this paper as [62]
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“Random forest classifiers are one of these ensemble methods that have been proposed by Breimann [17].”
MethodThe random subspace method for constructing decision forests
Ho, T. K. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.709601 · Cited by 6,842 · cited 1×
“This is necessary to ensure that the different generated decision trees are uncorrelated [18].”
BackgroundActivity Recognition from User-Annotated Acceleration Data
Bao, L., & Intille, S. S. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24646-6_1 · Cited by 3,147 · cited 2×
“The development of wearable devices such as smart-phones, smart-watches and fitness wristbands feature a variety of sensors that are carried all day long by many people (compare [3]) provide new opportunities for continuous monitoring of human activities such as running, sitting, standing, or walking [5].”
BackgroundActivity recognition using cell phone accelerometers
Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1964897.1964918 · Cited by 2,912 · cited 2×
“The sampling rate was chosen with consideration of battery life as well as with reference to previous studies [7], [14].”
BackgroundMethodA Survey on Human Activity Recognition using Wearable Sensors
Lara, O. D., & Labrador, M. A. (2013) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2012.110112.00192 · Cited by 2,662 · cited 1×
“Preceding studies in the context of activity recognition already examined different settings regarding the window size and meaningful features [15].”
BackgroundActivity recognition from accelerometer data
Ravi, N., Dandekar, N., Mysore, P., & Littman, M. L. (2005) · Innovative Applications of Artificial Intelligence · Cited by 1,775
Preece, S. J., Goulermas, J. Y., Kenney, L. P. J., & Howard, D. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2008.2006190 · Cited by 551 · cited 2×
“Nevertheless, some researchers have compared different groups of features and also stated that frequency-based features improve the accuracy of the recognition [16].”
BackgroundSensor Positioning for Activity Recognition Using Wearable Accelerometers
Atallah, L., Lo, B., King, R., & Yang, G.-Z. (2011) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2011.2160540 · Cited by 346 · cited 5×
“Further studies have shown that the optimal sensor placement depends on the activity to be recognized [6].”
BackgroundResultInfluentialYang, J.-Y., Wang, J.-S., & Chen, Y.-P. (2008) · Pattern Recognition Letters · doi:10.1016/j.patrec.2008.08.002 · Cited by 335 · cited 1×
“A similar distinction has been made in [19] to improve the accuracy of activity recognition.”
BackgroundSun, L., Zhang, D., Li, B., Guo, B., & Li, S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-16355-5_42 · Cited by 251 · cited 2×
“Activity Recognition is an active field of research in pervasive computing [1]–[4].”
Background
Cited by
Sensor-based and vision-based human activity recognition: A comprehensive survey
Minh Dang, L., Min, K., Wang, H., Jalil Piran, M., Hee Lee, C., & Moon, H. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107561 · Cited by 730
“On the other hand, benchmark datasets are often used by the researchers to verify the proposed frameworks [98,99] .”
BackgroundFlower: A Friendly Federated Learning Research Framework
Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Fernandez-Marques, J., Gao, Y., Sani, L., Li, K. H., Parcollet, T., de Gusmão, P. P. B., et al. (2020) · arXiv · doi:10.48550/arxiv.2007.14390 · Cited by 622
“We used the RealWorld dataset (Sztyler & Stuckenschmidt, 2016) consisting of time-series data from accelerometer and gyroscope sensors on mobile devices, and partitioned it across 10 mobile clients.”
MethodUniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · Applied Sciences · doi:10.3390/app7101101 · Cited by 596
A systematic review of smartphone-based human activity recognition methods for health research
Straczkiewicz, M., James, P., & Onnela, J.-P. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00514-4 · Cited by 247
Islam, M. M., Nooruddin, S., Karray, F., & Muhammad, G. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106060 · Cited by 217
“[59] 2018 RealWorld HAR [113] 2-D CNN Precision = 89, Recall = 87, F1 Score = 88 No generality losses are happened.”
BackgroundScaling Human Activity Recognition via Deep Learning-based Domain Adaptation
Khan, M. A. A. H., Roy, N., & Misra, A. (2018) · 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom.2018.8444585 · Cited by 139
“We observe that HDCNN achieves ≈ 76% and ≈ 73 %classification accuracy, for HHAR and HAR respectively, when adapting across device-instances.”
MethodInfluentialFLOWER: A FRIENDLY FEDERATED LEARNING FRAMEWORKPreprint
Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Fernández-Marqués, J., Gao, Y., Sani, L., Li, K. H., Parcollet, T., de Gusmão, P. P. B., et al. (2022) · HAL · Cited by 183
Non-intrusive human activity recognition and abnormal behavior detection on elderly people: a review
Lentzas, A., & Vrakas, D. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-019-09724-5 · Cited by 176
“The RealWorld HAR dataset (Sztyler and Stuckenschmidt 2016), used such an approach.”
MethodZheng, X., Wang, M., & Ordieres-Meré, J. (2018) · Sensors · doi:10.3390/s18072146 · Cited by 146
“A segmentation operation is necessary before applying any cla sification method [8].”
BackgroundMethodResultInfluentialArikumar, K., Prathiba, S., Alazab, M., Gadekallu, T., Pandya, S., Khan, J., & Moorthy, R. (2022) · Sensors · doi:10.3390/s22041377 · Cited by 168
“To effectively predict the PMI, we considered eight regular activities of a human, such as standing, sitting, lying, climbing up and down, walking, and jogging, which are the parts of the initial datasets taken from [6,18].”
BackgroundMethodInfluentialRetractedA Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison
EK, S., PORTET, F., LALANDA, P., & VEGA, G. (2021) · 2021 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom50583.2021.9439129 · Cited by 116
“The client model obtained a mean F-Score of 95.82% on the local-test set and 72.99% on the global test set.”
BackgroundMethodInfluentialSelf-supervised learning for human activity recognition using 700,000 person-days of wearable data
Yuan, H., Chan, S., Creagh, A. P., Tong, C., Acquah, A., Clifton, D. A., & Doherty, A. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01062-3 · Cited by 166
Kwon, H., Tong, C., Haresamudram, H., Gao, Y., Abowd, G. D., Lane, N. D., & Plötz, T. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3411841 · Cited by 152
“the overall approach and relevant technical details and explore the potential of the approach on practical recognition scenarios. Through a series of experiments on three benchmark datasets—RealWorld [86], PAMAP2 [72], and Opportunity [14]—we demonstrate the effectiveness of our approach. We discuss the overall potent…”
BackgroundMethodSensing with Earables: A Systematic Literature Review and Taxonomy of Phenomena
Röddiger, T., Clarke, C., Breitling, P., Schneegans, T., Zhao, H., Gellersen, H. W., & Beigl, M. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3550314 · Cited by 149
“More recent work has also shown similar results with only the knee and shin outperforming the head for activity classication for activities including climbing stairs, jumping, lying, standing, sitting, running/ jogging, and walking [324].”
Position-aware activity recognition with wearable devices
Sztyler, T., Stuckenschmidt, H., & Petrich, W. H. (2017) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2017.01.008 · Cited by 148
“Further, we also removed some tables which belong to the original publication [11].”
BackgroundResultSelf-citationA Comprehensive Study of Activity Recognition Using Accelerometers
Twomey, N., Diethe, T., Fafoutis, X., Elsts, A., McConville, R., Flach, P., & Craddock, I. (2018) · doi:10.20944/preprints201803.0147.v1 · Cited by 143
A Comprehensive Study of Activity Recognition Using Accelerometers
Twomey, N., Diethe, T., Fafoutis, X., Elsts, A., McConville, R., Flach, P., & Craddock, I. (2018) · Informatics · doi:10.3390/informatics5020027 · Cited by 143
“As there are numerous placement locations on the body another questions arises: will activity recognition benefit from taking into account data from different on-body locations? In [43] a study was performed to determine if a model trained on the combined on-body locations performed better than a model that is aware o…”
BackgroundUbiquitous Localization (UbiLoc): A Survey and Taxonomy on Device Free Localization for Smart World
Shit, R. C., Sharma, S. K., Puthal, D., James, P., Pradhan, B., van Moorsel, A., Zomaya, A. Y., & Ranjan, R. K. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2915923 · Cited by 143
“Social IoT [37] Social Computing [38] Wearable Applications [39] Affective Computing [40]”
BackgroundSuspicious activity detection using deep learning in secure assisted living IoT environments
Vallathan, G., John, A., Thirumalai, C., Mohan, S., Srivastava, G., & Lin, J. C. (2020) · The Journal of Supercomputing · doi:10.1007/s11227-020-03387-8 · Cited by 146
“The final implementation and results are based on HAR [39], AAR [40], and data care data sets.”
MethodLARa: Creating a Dataset for Human Activity Recognition in Logistics Using Semantic Attributes
Niemann, F., Reining, C., Rueda, F. M., Nair, N. R., Steffens, J. A., Fink, G. A., & ten Hompel, M. (2020) · Sensors · doi:10.3390/s20154083 · Cited by 120
Worker 4.0: The Future of Sensored Construction Sites
Calvetti, D., Mêda, P., Gonçalves, M. C., & Sousa, H. J. C. D. (2020) · Buildings · doi:10.3390/buildings10100169 · Cited by 115
“Smartphones [18,19,23,24,91], wearables devices (e.”
BackgroundFedHAR: Semi-Supervised Online Learning for Personalized Federated Human Activity Recognition
Yu, H., Chen, Z., Zhang, X., Chen, X., Zhuang, F., Xiong, H., & Cheng, X. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3136853 · Cited by 113
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition
Jain, Y., Tang, C. I., Min, C., Kawsar, F., & Mathur, A. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3517246 · Cited by 113
“In the remaining three cases, ColloSSL shows comparable 𝐹1 score with 25% of labeled data when evaluated at the thigh-worn device in RealWorld (ColloSSL: 0.690, Supervised-single: 0.701), a higher 𝐹1 score with 100% of labeled data when evaluated at the ankle-worn device in PAMAP2 (ColloSSL: 0.784, Supervised-single:…”
MethodInfluentialTrends in human activity recognition using smartphones
Ferrari, A., Micucci, D., Mobilio, M., & Napoletano, P. (2021) · Journal of Reliable Intelligent Environments · doi:10.1007/s40860-021-00147-0 · Cited by 110
“Furthermore, as afore mentioned, gyroscope data permit to infer device position that drastically impacts recognition performances [37,38].”
BackgroundRiboni, D., Sztyler, T., Civitarese, G., & Stuckenschmidt, H. (2016) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2971648.2971691 · Cited by 108
“Physical activity recognition systems are mainly based on data acquired from body-worn accelerometers [2, 3, 32].”
BackgroundSelf-citationSanhudo, L., Calvetti, D., Martins, J. P., Ramos, N., Mêda, P., Gonçalves, M. C., & Sousa, H. J. C. D. (2020) · Journal of Building Engineering · doi:10.1016/j.jobe.2020.102001 · Cited by 109
Yin, Y., Xie, L., Jiang, Z., Xiao, F., Cao, J., & Lu, S. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3357591 · Cited by 108
“…activity instances belonging to class i are correctly classified into class i , while using TN i = (cid:13) k = n k =1 (cid:13) j = n j =1 C kj , k (cid:8) = i , j (cid:8) = i to represent the true negatives , i.e., the activity instances not belonging to class i are classified into other classes.”
Deep Unsupervised Domain Adaptation with Time Series Sensor Data: A Survey
Shi, Y., Ying, X., & Yang, J. (2022) · Sensors · doi:10.3390/s22155507 · Cited by 103
UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · doi:10.20944/preprints201706.0033.v2 · Cited by 596
Transformer-based models to deal with heterogeneous environments in Human Activity Recognition
Ek, S., Portet, F., & Lalanda, P. (2023) · Personal and Ubiquitous Computing · doi:10.1007/s00779-023-01776-3 · Cited by 101
“The RealWorld (RW) dataset [43] is based on 15 subjects using 7 different devices with a sampling rate of 50 Hz.”
Activity recognition using accelerometer sensor and machine learning classifiers
Sukor, A. S. A., Zakaria, A., & Rahim, N. A. (2018) · IEEE International Colloquium on Signal Processing & Its Applications (CSPA) · doi:10.1109/cspa.2018.8368718 · Cited by 98
“This duration is considered sufficient, as most existing studies use different size duration between one and three seconds [11].”
BackgroundInfluentialFederated Learning on Multimodal Data: A Comprehensive Survey
Lin, Y., Gao, Y., Gong, M., Zhang, S., Zhang, Y., & Li, Z. (2023) · Machine Intelligence Research · doi:10.1007/s11633-022-1398-0 · Cited by 96
Positioning Methods and the Use of Location and Activity Data in Forests
Keefe, R. F., Wempe, A. M., Becker, R. M., Zimbelman, E. G., Nagler, E. S., Gilbert, S. L., & Caudill, C. C. (2019) · Forests · doi:10.3390/f10050458 · Cited by 93
A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM
Gao, X., Luo, H., Wang, Q., Zhao, F., Ye, L., & Zhang, Y. (2019) · Sensors · doi:10.3390/s19040947 · Cited by 92
“Besides, there are various publicly available datasets that provide strong support for human activities recognition such as UCI [16], WISDM [21], HASC [22], and RealWorld HAR [23].”
BackgroundLiu, S., Kimura, T., Liu, D., Wang, R., Li, J., Diggavi, S. N., Srivastava, M. B., & Abdelzaher, T. F. (2023) · neural information processing systems · doi:10.52202/075280-2049 · Cited by 82
FLAME: Federated Learning across Multi-device Environments
Cho, H., Mathur, A., & Kawsar, F. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3550289 · Cited by 79
“RealWorld [68] 7 15 1481 149 130 50Hz Opportunity [60] 5 4 3847 28 356 30Hz PAMAP2 [59] 3 8 1057 78 87 100Hz”
MethodInfluentialA Robust Deep Learning Approach for Position-Independent Smartphone-Based Human Activity Recognition
Almaslukh, B., Artoli, A. M., & Al-Muhtadi, J. (2018) · Sensors · doi:10.3390/s18113726 · Cited by 71
“In this study, we used a publicity available dataset (RealWorld HAR) [25] to build and evaluate the proposed method.”
MethodOutlier 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
“In the particular case of the dataset in [5], the number of outliers is relatively small and the results in Table 1 show that many of the outliers detected after a 2 iteration process are also detected if no outlier pre-detection and removing is performed (for both similarity thresholds).”
BackgroundMethodInfluentialImproving 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
“For the same reason as mentioned with the RWHAR dataset, we only used the raw 3D acceleration sensor data, which was sampled at 50𝐻𝑧.”
BackgroundMethodInfluentialA study of deep neural networks for human activity recognition
Sansano, E., Montoliu, R., & Belmonte Fernández, Ó. (2020) · Computational Intelligence · doi:10.1111/coin.12318 · Cited by 73
Huynh-The, T., Hua, C.-H., Tu, N. A., & Kim, D.-S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3013272 · Cited by 72
“For the performance evaluation, the data set is partitioned into 3-s samples and subsequently validated following the 10-fold cross-validation [17].”
BackgroundMethodInfluentialOnline personalization of cross-subjects based activity recognition models on wearable devices
Sztyler, T., & Stuckenschmidt, H. (2017) · 2017 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom.2017.7917864 · Cited by 57
Self-citationA 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
“Various existing research work has used smartwatches for this purpose [30, 41–44].”
BackgroundMethodCross-Domain HAR: Few-Shot Transfer Learning for Human Activity Recognition
Thukral, M., Haresamudram, H., & Plötz, T. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3704921 · Cited by 70
“The phone was placed freely in the pocket of the participant’s choice and in random orientation, in order to simulate everyday use.”
Ye, X., Sakurai, K., Nair, N. C., & Wang, K. I. (2024) · Sensors · doi:10.3390/s24247975 · Cited by 68
“Sztyler et al. [77] considered the influence of the different on-body positions of the mobile device and predicted the sensor position based on acceleration data via a random forest classifier.”
MethodA Wearable Inertial Sensor Approach for Locomotion and Localization Recognition on Physical Activity
Khan, D., Mudawi, N. A., Abdelhaq, M., Alazeb, A., Alotaibi, S. S., Algarni, A. M., & Jalal, A. (2024) · Sensors · doi:10.3390/s24030735 · Cited by 68
Strączkiewicz, M., Huang, E. J., & Onnela, J.-P. “. (2023) · npj Digital Medicine · doi:10.1038/s41746-022-00745-z · Cited by 67
CAVIAR: 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
On the Challenges and Potential of Using Barometric Sensors to Track Human Activity
Manivannan, A., Chin, W. C. B., Barrat, A., & Bouffanais, R. (2020) · Sensors · doi:10.3390/s20236786 · Cited by 63
“Video capturing [34,47,55,62], audio recording [63], and GPS localization have been highlighted as methods of direct observation without requiring one to monitor the subjects under constrained and controlled conditions.”
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
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
“VisualAcc [83] uses photometric effect-based interrogation and an optic-to-inertia transformer that senses human motion passively and reconstructs inertial data using the Optical Motion Field (OMF).”
Zero-Shot Learning for IMU-Based Activity Recognition Using Video Embeddings
Tong, C., Ge, J., & Lane, N. D. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3494995 · Cited by 40
“Where possible, we source annotated videos from public datasets, namely HMDB51 [30], UCF101 [50] Kinetics [12, 26] and RealWorld [52], by manually browsing videos annotated with semantically similar activities, e.g. we refer to videos annotated as “using computer” in Kinetics when sourcing videos for “computer work” .”
BackgroundMethodHoelzemann, A., Romero, J., Bock, M., Laerhoven, K. V., & Lv, Q. (2023) · Sensors · doi:10.3390/s23135879 · Cited by 61
“RWHAR [25] Smartphone, Wearable IMUs 15 8 Locomotion Controlled (Outside) Multimodal 2016”
MethodSelf-tracking Reloaded: Applying Process Mining to Personalized Health Care from Labeled Sensor Data
Sztyler, T., Carmona, J., Völker, J., & Stuckenschmidt, H. (2016) · Lecture notes in computer science · doi:10.1007/978-3-662-53401-4_8 · Cited by 58
Self-citationBANDANA — Body area network device-to-device authentication using natural gAit
Schürmann, D., Brüsch, A., Sigg, S., & Wolf, L. C. (2017) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2017.7917865 · Cited by 58
“[17] for position-aware activity recognition.”
(2020) · doi:10.1145/3380999 · Cited by 57
“However, due to the limitations of current publicly available sensing datasets, we demonstrate the effectiveness of GlobalFusion on four public human activity recognition (HAR) datasets: 1) PAMAP2 [27], 2) Realworld-HAR [31], 3) DSADS [4], and 4) DG [5].”
MethodA Comprehensive Methodological Survey of Human Activity Recognition Across Diverse Data Modalities
Shin, J., Hassan, N., Miah, A. S. M., & Nishimura, S. (2025) · Sensors · doi:10.3390/s25134028 · Cited by 58
Kraft, D., Srinivasan, K. K., & Bieber, G. (2020) · Technologies · doi:10.3390/technologies8040072 · Cited by 55
“To enrich the Notch, Smartwatch, and SmartFall datasets with additional activities of daily living, we added 500 random 10 s segments from the RealWorld Human Activity Recognition [47] dataset to the SmartFall, Smartwatch, and Notch datasets.”
Mario, M.-O. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2882943 · Cited by 50
“This section captures the main results of applying the proposed algorithm to detect walking, running, jumping, climbing up and climbing down activities from the dataset in [27].”
BackgroundMethodInfluentialA benchmark for domain adaptation and generalization in smartphone-based human activity recognition
Napoli, O. O., Duarte, D., Alves, P., Soto, D. H. P., de Oliveira, H. E., Rocha, A. D. R., Boccato, L., & Borin, E. (2024) · Scientific Data · doi:10.1038/s41597-024-03951-4 · Cited by 52
“In HAR literature, several datasets have been created to allow the evaluation of HAR models, typically used in isolation 3,18–20 .”
BackgroundMethodInfluentialBento, N., Rebelo, J., Barandas, M., Carreiro, A. V., Campagner, A., Cabitza, F., & Gamboa, H. F. S. (2022) · Sensors · doi:10.3390/s22197324 · Cited by 51
“The RealWorld dataset [46] generated considerably more windows than the other datasets, so one-third of these windows was randomly sampled and used in the experiments.”
MethodA Privacy and Energy-Aware Federated Framework for Human Activity Recognition
Khan, A. R., Manzoor, H. U., Ayaz, F., Imran, M. A., & Zoha, A. (2023) · Sensors · doi:10.3390/s23239339 · Cited by 51
“Hence, we chose a more realistic dataset collected by Sztyler and Stuckenschmidt [39].”
MethodLanger, P., Kaar, T., Rosenblattl, M., Xu, M. A., Chow, W., Maritsch, M., Jakob, R., Wang, N., Liu, J., Verma, A., et al. (2025) · arXiv (Cornell University) · doi:10.13140/rg.2.2.14827.60963 · Cited by 51
An Industrial IoT Solution for Evaluating Workers' Performance Via Activity Recognition
Forkan, A. R. M., Montori, F., Georgakopoulos, D., Jayaraman, P. P., Yavari, A., & Morshed, A. (2019) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2019.00139 · Cited by 50
“Activity recognition using wearable sensors [15], [16] is a popular research domain in areas such as healthcare [17], defence [18], smart home [19], and sports [20].”
BackgroundRecent Advances in Pedestrian Navigation Activity Recognition: A Review
Wang, Q., Luo, H., Wang, Q., Sun, L., Ma, Z., Zhang, C., Fu, M., & Zhao, F. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3153610 · Cited by 50
Xia, S., Chu, L., Pei, L., Zhang, Z., Yu, W., & Qiu, R. C. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3111996 · Cited by 40
Approaching the Real-World: Supporting Activity Recognition Training with Virtual IMU Data
Kwon, H., Wang, B., Abowd, G. D., & Plötz, T. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3478096 · Cited by 48
“It was demonstrated that virtual IMU data was useful for the analysis of both locomotion [9, 94] and more complex activities [82].”
BackgroundSecurity Properties of Gait for Mobile Device Pairing
Brusch, A., Nguyen, N., Schurmann, D., Sigg, S., & Wolf, L. (2019) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2019.2897933 · Cited by 48
“In particular, we investigated the variation in 4 bit chunks generated by the IPI protocol on the walking data from [65].”
BackgroundMethodInfluentialBarshan, B., & Yurtman, A. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2969840 · Cited by 48
“Sztyler and Stuckenschmidt [37] classify both the activity type and the sensor unit position following a three-stage approach which is more complicated.”
BackgroundnewNECTAR: Collaborative active learning for knowledge-based probabilistic activity recognition
Civitarese, G., Bettini, C., Sztyler, T., Riboni, D., & Stuckenschmidt, H. (2019) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2019.04.006 · Cited by 47
Self-citationCross-Domain HAR: Few Shot Transfer Learning for Human Activity Recognition
Thukral, M., Haresamudram, H., & Ploetz, T. (2023) · arXiv · doi:10.48550/arxiv.2310.14390 · Cited by 45
“The phone was placed freely in the pocket of the participant’s choice and in random orientation, in order to simulate everyday use.”
Activity-aware essential tremor evaluation using deep learning method based on acceleration data
Zheng, X., Vieira, A., Marcos, S. L., Aladro, Y., & Ordieres-Meré, J. B. (2018) · Parkinsonism & Related Disorders · doi:10.1016/j.parkreldis.2018.08.001 · Cited by 45
Hu, R., Chen, L., Miao, S., & Tang, X. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i5.25743 · Cited by 44
CSL-SHARE: A Multimodal Wearable Sensor-Based Human Activity Dataset
Liu, H., Hartmann, Y., & Schultz, T. (2021) · Frontiers in Computer Science · doi:10.3389/fcomp.2021.759136 · Cited by 44
A Novel Feature Incremental Learning Method for Sensor-Based Activity Recognition
Hu, C., Chen, Y., Peng, X., Yu, H., Gao, C., & Hu, L. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2855159 · Cited by 43
“They are DSADS [8], PAMAP2 [9] and RealWorld(HAR) [10].”
MethodMekruksavanich, S., & Jitpattanakul, A. (2024) · Applied Sciences · doi:10.3390/app14052107 · Cited by 42
“To implement this approach, the REALWORLD16 dataset [36] was chosen as the standardized public HAR dataset.”
MethodAuto-Key: Using Autoencoder to Speed Up Gait-based Key Generation in Body Area Networks
Wu, Y., Lin, Q., Jia, H., Hassan, M., & Hu, W. S. (2020) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3381004 · Cited by 42
“We use the public dataset in [30] for position-aware activity recognition to evaluate the impacts of key generation performance of proposed autoencoder in different body locations.”
MethodLeng, Z., Kwon, H., & Ploetz, T. (2023) · Proceedings of the 2023 International Symposium on Wearable Computers · doi:10.1145/3594738.3611361 · Cited by 39
Li, J., Li, X., Steinberg, J., Choube, A., Yao, B., Xu, X., Wang, D., Mynatt, E. D., & Mishra, V. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3749508 · Cited by 39
“In this section, we describe our initial interviews with experts about the challenges they face in deriving insights from personal tracking data, highlighting the needs and opportunities in assisting experts in their sensemaking process.”
Smartphone Location Recognition: A Deep Learning-Based Approach
Klein, I. (2019) · Sensors · doi:10.3390/s20010214 · Cited by 39
“Parameter/Dataset U1 HTA RIDI [32] OXF [33] MSR [34] WIS [35] WOB [36] PAR [37]”
BackgroundMethodInfluentialSmartphone Sensor-Based Human Locomotion Surveillance System Using Multilayer Perceptron
Azmat, U., Ghadi, Y. Y., Shloul, T. A., Alsuhibany, S. A., Jalal, A., & Park, J. (2022) · Applied Sciences · doi:10.3390/app12052550 · Cited by 39
“16%, while a previous implementation that include position-unaware and position-aware system modes with a random forest model [67] achieved 80.”
BackgroundMethodFreqMAE: Frequency-Aware Masked Autoencoder for Multi-Modal IoT Sensing
Kara, D., Kimura, T., Liu, S., Li, J., Liu, D., Wang, T., Wang, R., Chen, Y., Hu, Y., & Abdelzaher, T. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3645346 · Cited by 38
“For ACIDS, overly high 𝜆 values disproportionately prioritize energy in learned representations, detrimental compared to HAR tasks where IMU sensors, placed directly on the body, exhibit less activity-related energy variation [40].”
BackgroundA Public Domain Dataset for Human Activity Recognition in Free-Living Conditions
Cruciani, F., Sun, C., Zhang, S., Nugent, C., Li, C., Song, S., Cheng, C., Cleland, I., & McCullagh, P. J. (2019) · IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) · doi:10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00071 · Cited by 38
“Characteristics Dataset Set of Sensors Conditions∗ Subjects UCI-HAR Smartphone’s acceleroP 30 [6] meter, gyroscope (waist) PAMAP2 3 IMUs (wrist, chest, P 9 [8] ankle) + HR Monitor Opportunity 7 IMUs P 4 [9] 12 accelerometers (various locations) MHealth 3 IMUs P 5 [13] (wrist, chest, ankle) Real World 7 IMUs (various l…”
MethodCastro-García, J. A., Molina-Cantero, A. J., Gómez, I., Lafuente-Arroyo, S., & Merino-Monge, M. (2022) · Electronics · doi:10.3390/electronics11010155 · Cited by 38
“These have included kNN [14,30,33,35], random forest (RF), decision tree (DT) [20,38], gaussian mixture model (GMM) and hidden Markov models (HMM) [16,24] or even models based exclusively on thresholds [29] ], all of which requires domain-specific expert knowledge to process raw data.”
BackgroundSignificant Features for Human Activity Recognition Using Tri-Axial Accelerometers
Bennasar, M., Price, B. A., Gooch, D., Bandara, A. K., & Nuseibeh, B. (2022) · Sensors · doi:10.3390/s22197482 · Cited by 38
Miao, S., Chen, L., Hu, R., & Luo, Y. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550331 · Cited by 36
“Following the common data preprocessing method [28], we only use the data from the accelerometer, gyroscope, and magnetometer for Opportunity [38], RealWorld [45], and Realdisp [2].”
BackgroundMethodInfluentialPerformance of Machine Learning Classifiers for Indoor Person Localization With Capacitive Sensors
Bin Tariq, O., Lazarescu, M. T., Iqbal, J., & Lavagno, L. (2017) · IEEE Access · doi:10.1109/access.2017.2721538 · Cited by 36
“Its internal model is generated by training multiple trees separately with the same distribution and choosing randomly the data samples to ensure that the decision trees are not correlated [54].”
Hips Do Lie! A Position-Aware Mobile Fall Detection System
Krupitzer, C., Sztyler, T., Edinger, J., Breitbach, M., Stuckenschmidt, H., & Becker, C. (2018) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2018.8444583 · Cited by 36
“The implementation of the window manager and the feature extraction is based on [10].”
BackgroundMethodSelf-citationChen, L., Hu, R., Wu, M., & Zhou, X. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3610909 · Cited by 36
SelfPAB: large-scale pre-training on accelerometer data for human activity recognition
Logacjov, A., Herland, S., Ustad, A., & Bach, K. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05322-3 · Cited by 35
Accelerometer-Based Key Generation and Distribution Method for Wearable IoT Devices
Sun, F., Zang, W., Huang, H., Farkhatdinov, I., & Li, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3014646 · Cited by 35
“Furthermore, we used the real-world data set RealWorld (HAR) shared by [42], [43] to test the robustness of the proposed methods.”
MethodEk, S., Portet, F., Lalanda, P., & Vega, G. (2022) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2022.101714 · Cited by 35
“48% of F-Score, which is far above the current state-of-the-art on RealWorld dataset, which was previously 81% of F-Score [29].”
BackgroundMethodInfluentialWhat Lies Beneath One’s Feet? Terrain Classification Using Inertial Data of Human Walk
Hashmi, M. Z. U. H., Riaz, Q., Hussain, M., & Shahzad, M. (2019) · Applied Sciences · doi:10.3390/app9153099 · Cited by 34
Yu, T. C., Arakawa, R., McCann, J., & Goel, M. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580692 · Cited by 33
“Prior work on on-body localization used IMU sensors [33, 67] or vision sensors [5] to recognize the position passively.”
AlMuhaideb, S., AlAbdulkarim, L., AlShahrani, D. M., AlDhubaib, H., & AlSadoun, D. E. (2024) · Sensors · doi:10.3390/s24165436 · Cited by 32
“…91.61% KU-HAR [57] 1D CNN, ResBiLSTM, and attention [14] 97.89% Transformer [46] 99.2% UNIMIB-SHAR [66] CNN using conditionally parametrized convolution [28] 77.31% CNN using lego filters [26] 74.46% * RealWorld [67] Transformer [48] 95.81% SHL Preview [68,69] Transformer [48] 94.86% * F 1-Score.”
MethodInfluentialIn-depth analysis of design & development for sensor-based human activity recognition system
Choudhury, N. A., & Soni, B. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16423-5 · Cited by 30
Situation-Aware Emotion Regulation of Conversational Agents with Kinetic Earables
Katayama, S., Mathur, A., den Broeck, M. V., Okoshi, T., Nakazawa, J., & Kawsar, F. (2019) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii.2019.8925449 · Cited by 30
“The model is trained on two publicly available HAR datasets, namely the Opportunity dataset [24] and RealWorld HAR dataset [25].”
Contrastive Self-Supervised Learning for Sensor-Based Human Activity Recognition: A Review
Chen, H., Gouin-Vallerand, C., Bouchard, K., Gaboury, S., Couture, M., Bier, N., & Giroux, S. (2024) · IEEE Access · doi:10.1109/access.2024.3480814 · Cited by 29
Temporal Action Localization for Inertial-based Human Activity Recognition
Bock, M., Moeller, M., & Laerhoven, K. V. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3699770 · Cited by 29
“Unlike the other datasets featured in this benchmark analysis, the RWHAR dataset does not contain a NULL-class, as recordings were trimmed to only contain the activities of relevancy, cutting out the breaks in-between.”
InfluentialA closer look at quality-aware runtime assessment of sensing models in multi-device environments
Min, C., Montanari, A., Mathur, A., & Kawsar, F. (2019) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3356250.3360043 · Cited by 30
“Datasets: To evaluate the performance of our approach in the HAR task, we use two public datasets which contain IMU data from multiple wearable devices: the Opportunity activity recognition dataset [29] and the RealWorld (HAR) dataset [35].”
BackgroundMethod
Metadata
- Authors
- Sztyler, T., & Stuckenschmidt, H.
- Affiliations
- University of Mannheim (DE)
- Venue
- 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom)
- Publisher
- IEEE
- Published
- 2016-03
- Pages
- 1-9
- ISSN
- 2474-249X (ISSN-L)
- OpenAlex
- W2340025709
- Cited by
- 369
- References
- 19
- Citations by year
- 2026: 30 · 2025: 55 · 2024: 60 · 2023: 38 · 2022: 39 · 2021: 35 · 2020: 41 · 2019: 33 · 2018: 22 · 2017: 11 · 2016: 5
- FWCI
- 8.21
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Pervasive Computing and Communications (publishedVersion)
- MADOC (University of Mannheim) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Indoor and Outdoor Localization Technologies
- Social Sciences › Transportation › Human Mobility and Location-Based Analysis
- Keywords
- wearable devices, activity recognition, accelerometer data, random forest classification, mobile device sensors, real-world data, ubiquitous computing
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.