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
Items 101–200 of 509
Conformance Constraint Discovery: Measuring Trust in Data-Driven Systems
Fariha, A., Tiwari, A., Radhakrishna, A., Gulwani, S., & Meliou, A. (2021) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3448016.3452795 · Cited by 29
Chan, H., Ouyang, Y., Chen, R., Lai, Y., Kuo, C.-C., Liao, G.-S., Hsu, W.-Y., & Chang, Y. (2023) · Sensors · doi:10.3390/s23010495 · Cited by 28
“[49] Realworld HAR/15 [27] A chest, head, waist, arm, thigh, shin signals CNN jump, jog, lay, stand, sit, walk, stairs F1 = 0.”
A novel orientation- and location-independent activity recognition method
Shi, D., Wang, R., Wu, Y. X., Mo, X., & Wei, J. (2017) · Personal and Ubiquitous Computing · doi:10.1007/s00779-017-1007-3 · Cited by 28
“[32] focused on the location recognition problem and proposed a method of positioning the mobile device using the random forest classifier.”
MethodResultGOAT: A Generalized Cross-Dataset Activity Recognition Framework with Natural Language Supervision
Miao, S., & Chen, L. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3699736 · Cited by 27
“RealWorld dataset [64] was collected from 15 subjects.”
SCEI: A Smart-Contract Driven Edge Intelligence Framework for IoT Systems
Xu, C., Ge, J., Li, Y., Deng, Y., Gao, L., Zhang, M., Xiang, Y., & Zheng, X. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3290925 · Cited by 27
“Six public datasets are used in the experiments, including MNIST, CIFAR-10, CIFAR-100, IMAGENET [40], UCI [41], and REALWORLD [42].”
MethodChai, Y., Liu, H., Zhu, H., Pan, Y., Zhou, A., Liu, H., Liu, J., & Qian, Y. (2024) · Information & Management · doi:10.1016/j.im.2024.103922 · Cited by 26
Martindale, C. F., Šprager, S., & Eskofier, B. M. (2019) · Sensors · doi:10.3390/s19081820 · Cited by 26
“MAREA [9] 20 34 min per subject Heel strike, toe off (using FSR) Bradjic [29] 27 Unknown Step count (from video) CMU-MMAC [5] 43 5 recipes N/A MHAD [7] 12 82 min (total) N/A OU-ISIR2012 [10] 744 Under 20 steps per subject N/A ZJU-GaitAcc [30] 175 6 times 20 m Cycle borders (Signal analysis) Real World (HAR) [28] 15 70…”
BackgroundMethodInfluentialTowards Generalizable Human Activity Recognition: A SurveyPreprint
Cai, Y., Guo, B., Salim, F., & Hong, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.12213 · Cited by 26
“• RealWorld HAR [175]: The RealWorld HAR dataset provides comprehensive multimodal sensor data collected from 15 participants performing a variety of common daily activities.”
AutoAugHAR: Automated Data Augmentation for Sensor-based Human Activity Recognition
Zhou, Y., Zhao, H., Huang, Y., Röddiger, T., Kurnaz, M., Riedel, T., & Beigl, M. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3659589 · Cited by 25
“Baseline SFN SF-DM AutoAugHar AutoAugHAR(N) FTS Reverse STM ChannelDropout Drawing on an extensive review of the prevalent DA operators for EEG classification [57], we have selected four types of DA operators considered to be the most effective.”
BackgroundHuman Activity Recognition Based on Acceleration Data From Smartphones Using HMMs
Iloga, S., Bordat, A., Kernec, J. L., & Romain, O. (2021) · IEEE Access · doi:10.1109/access.2021.3117336 · Cited by 26
“• Decision trees (DT) [13], [17], [19]–[22], [25], [29]–[34].”
InfluentialA smart data annotation tool for multi-sensor activity recognition
Diete, A., Sztyler, T., & Stuckenschmidt, H. (2017) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2017.7917542 · Cited by 25
“Thus, we enhanced an Android application of a previous work [8] where especially the support of smart-glasses was added.”
MethodSelf-citationNakamura, Y., Matsuda, Y., Arakawa, Y., & Yasumoto, K. (2019) · Sensors · doi:10.3390/s19204600 · Cited by 24
Kumar, P., & Suresh, S. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.10.208 · Cited by 24
The use of deep learning for smartphone-based human activity recognition
Stampfler, T., Elgendi, M., Fletcher, R., & Menon, C. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1086671 · Cited by 24
Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity
Presotto, R., Ek, S., Civitarese, G., Portet, F., Lalanda, P., & Bettini, C. (2023) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp58114.2023.00022 · Cited by 24
“This show that it is important to evaluate pre-training on different datasets TABLE VII: DeepConvLSTM evaluated using LODO ft ratio 0% 1% 5% 10% All Train Target dataset PU Rd PF PU Rd PF PU Rd PF PU Rd PF PU HHAR 05.58 80.37 60.00 66.26 83.28 79.03 82.12 86.15 87.71 89.42 88.48 94.04 94.87 MobiAct 06.55 51.94 28.21 4…”
MethodInfluentialPham, C.-H., Huynh‐The, T., Gooya, E. S., Elbouz, M., & Alfalou, A. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107854 · Cited by 24
Beyond position-awareness—Extending a self-adaptive fall detection system
Krupitzer, C., Sztyler, T., Edinger, J., Breitbach, M., Stuckenschmidt, H., & Becker, C. (2019) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2019.05.007 · Cited by 24
Self-citationSpatial-Temporal Masked Autoencoder for Multi-Device Wearable Human Activity Recognition
Miao, S., Chen, L., & Hu, R. (2023) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3631415 · Cited by 23
“The performance of supervised learning methods is particularly dependent on large-scale labeled datasets, which require significant human efforts and financial costs [62].”
BackgroundMethodInfluentialLearning Disentangled Representation for Multi-Modal Time-Series Sensing Signals
Cai, R., Jiang, Z., Zheng, K., Li, Z., Chen, W., XueXin, C., Shen, Y., Chen, G., Hao, Z., & Zhang, K. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714931 · Cited by 23
Context-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
“1 3 There are a lot of studies where context-aware models that can recognize the body position of the sensor are studied (for instance Fujinami et al. 2012; Sztyler and Stuckenschmidt 2016).”
BackgroundWearable Accelerometer and Gyroscope Sensors for Estimating the Severity of Essential Tremor
Ali, S. M., Arjunan, S. P., Peter, J., Perju-Dumbrava, L., Ding, C., Eller, M., Raghav, S., Kempster, P., Motin, M. A., Radcliffe, P. J., et al. (2024) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2023.3329344 · Cited by 22
“Wearable accelerometers have been used to study activities of daily living [13], [14], [15], [16], inferring metabolic energy expenditure [17], [18], [19], measuring gait parameters [20] and predicting falls [21].”
MethodSmartphone-Based Environmental Sensing Using Device Location as Metadata
Fujinami, K. (2016) · International Journal on Smart Sensing and Intelligent Systems · doi:10.21307/ijssis-2017-963 · Cited by 22
“Intended applications include activity recognition and measurement [11][15] [20][32], notification modality control [11][8], and reliable environmental sensing [11][22][38].”
BackgroundGait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns
Peinado-Contreras, A., & Muñoz-Organero, M. (2020) · Sensors · doi:10.3390/s20236900 · Cited by 22
“For this experi ent e ill also try to recreate as reliably as possible the activities perfor ed in the original database [3].”
BackgroundMethodInfluentialKeusch, F., Wenz, A., & Conrad, F. G. (2021) · Computers in Human Behavior · doi:10.1016/j.chb.2021.107054 · Cited by 22
Wei, Q., Huang, J., Gao, Y. C., & Dong, W. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3749509 · Cited by 21
“Specifically, the resulting test sets contain 5773 samples for HHAR [51], 1542 for Pamap2 [44], 7098 for Realworld [54], 2443 for UCI-HAR [45], and 2178 for USC-HAD [70].”
InfluentialBursa, S. Ö., İncel, Ö. D., & Alptekin, G. I. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108777 · Cited by 21
Wearable Smart Rings for Multifinger Gesture Recognition Using Supervised Learning
Mousavi, S. A., & Šelmić, R. R. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3304703 · Cited by 21
“The time frame is considered sufficient, as most recent studies use sample sizes ranging between one and three seconds [78].”
BackgroundDeep Learning in the Recognition of Activities of Daily Living Using Smartwatch Data
Cavalcante, A. F., Kunst, V. H. D. L., Chaves, T., de Souza, J. D. T., Ribeiro, I. M., Quintino, J. P., da Silva, F. Q. B., Santos, A. L. M., Teichrieb, V., & Gama, A. E. F. D. (2023) · Sensors · doi:10.3390/s23177493 · Cited by 21
“Bock et al. [25] conducted their experiments using datasets such as Opportunity [44], Wetlab [45], SBHAR [46], RealWorld-HAR [49], and HHAR [42], reporting maximum precision of 77.6%, recall of 76.3%, and F1-score of 74.4% using the RealWorld-HAR dataset.”
MethodInfluentialBui, D. T., Nguyen, N. D., & Jeong, G. (2018) · Sensors · doi:10.3390/s18072034 · Cited by 21
“However, this is inconvenient for users if they simultaneously use many devices and perform various daily activities [11].”
BackgroundHandling Missing Sensors in Topology-Aware IoT Applications with Gated Graph Neural Network
Liu, S., Yao, S., Huang, Y., Liu, D., Shao, H., Zhao, Y., Li, J., Wang, T., Wang, R., Yang, C., et al. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3411818 · Cited by 20
“They are human activity recognition (HAR) trained with DeepSense [59] on two public datasets (REALDISP [8], RealWorld-HAR [50]), and EEG-based motor-imagery recognition trained with CNN [43] on the EEG-MMID [48] dataset.”
BackgroundMethodScheurer, S., Tedesco, S. A., O’Flynn, B., & Brown, K. N. (2020) · Sensors · doi:10.3390/s20133647 · Cited by 21
“[8] FUSION 7 10 90 ± 0 50 [11] MHEALTH 11 10 38 ± 0 50 [3] OPPORT 4 4 590 ± 258 30 [9] PAMAP2 12 9 81 ± 8 100 [16] REALWORLD 8 15 318 ± 42 50 [24] SAFESENS 17 11 91 ± 13 33 [18] SIMFALL 16 17 128 ± 8 25 [20] UTSMOKE 7 11 859 ± 7 50”
BackgroundMethodHuang, Y., Zhou, Y., Zhao, H., Riedel, T., & Beigl, M. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650060 · Cited by 20
“This variability is influenced by numerous factors, including, but not limited to, differences in the exercise habits [64], how the device is worn [80], variations in health conditions [81], age [82], and the specific environment where the activity occurs [79].”
BackgroundPhyMask: An Adaptive Masking Paradigm for Efficient Self-Supervised Learning in IoT
Kara, D., Kimura, T., Chen, Y., Li, J., Wang, R., Chen, Y., Wang, T., Liu, S., & Abdelzaher, T. (2024) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3666025.3699325 · Cited by 20
A CNN Based Transfer Learning Model for Automatic Activity Recognition from Accelerometer Sensors
Chikhaoui, B., Gouineau, F., & Sotir, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-96133-0_23 · Cited by 20
“Characteristics Heterogeneity HAR [27] RealWorld (HAR) [28] MobiAct [29]”
BackgroundKhowaja, S. A., Khuwaja, P., Dharejo, F. A., Raza, S., Lee, I. H., Naqvi, R. A., & Dev, K. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102044 · Cited by 19
Yang, Z., Li, K., & Huang, Z. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108110 · Cited by 19
PRimuS: Pretraining IMU Encoders with Multimodal Self-Supervision
Das, A. M., Tang, C. I., Kawsar, F., & Malekzadeh, M. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888874 · Cited by 19
“REALWORLD [29].”
Leotta, M., Fasciglione, A., & Verri, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68790-8_15 · Cited by 19
“Regarding the second criterion, a large number of the datasets that we have analysed used data recorded with an Android smartphone, with a requested sampling frequency of 50 Hz (e.g. [16, 1, 13]).”
BackgroundMethodUnstructured Handwashing Recognition Using Smartwatch to Reduce Contact Transmission of Pathogens
Lattanzi, E., Calisti, L., & Freschi, V. (2022) · IEEE Access · doi:10.1109/access.2022.3197279 · Cited by 19
ARC-Net: Activity Recognition Through Capsules
Damirchi, H., Khorrambakht, R., & Taghirad, H. D. (2020) · International Conference on Machine Learning and Applications · doi:10.1109/icmla51294.2020.00215 · Cited by 19
“The proposed method was tested on the PAMAP2 [19] and RealWorld [20] HAR datasets.”
BackgroundMethodInfluentialSelf-Supervised Gait Event Detection from Smartphone IMUs for Human Performance and Sports Medicine
TUDOR, A. C., Mănescu, D. C., & Mănescu, D. C. (2025) · Applied Sciences · doi:10.3390/app152211974 · Cited by 18
Towards LLMs for Sensor Data: Multi-Task Self-Supervised Learning
Okita, T., Ukita, K., Matsuishi, K., Kagiyama, M., Hirata, K., & Miyazaki, A. (2023) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3594739.3610745 · Cited by 18
“For downstream tasks, we used the 5 kinds of dataset including ADL [3], Opportunity dataset [22] PAMAP2 [21], RealWorld [24], and WISDM [28].”
MethodAccelerometer-Based Activity Recognition of Workers at Construction Sites
Gondo, T., & Miura, R. (2020) · Frontiers in Built Environment · doi:10.3389/fbuil.2020.563353 · Cited by 18
Strączkiewicz, M., Keating, N. L., Thompson, E., Matulonis, U. A., Campos, S. M., Wright, A. A., & Onnela, J.-P. “. (2023) · JMIR Cancer · doi:10.2196/47646 · Cited by 18
“…validation, we identified 5 publicly available data sets, including Daily Life Activities (DaLiAc) [33], Physical Activity Recognition Using Smartphone Sensors (PARUSS) [34], RealWorld [35], Simulated Falls and Daily Living Activities (SFDLA) [36], and Human Physical Activity (SPADES) [37].”
BackgroundA Signal-Level Transfer Learning Framework for Autonomous Reconfiguration of Wearable Systems
Saeedi, R., & Gebremedhin, A. H. (2018) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2018.2878673 · Cited by 18
“Another locationaware approach is presented in [36].”
MethodEnokibori, Y. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3699733 · Cited by 17
“MobileHART is evaluated using the following five datasets: UCI HAR, MotionSense [24], HHAR [36], Real-World [39], and OPPORTUNITY.”
ZeroHAR: Sensor Context Augments Zero-Shot Wearable Action Recognition
Chowdhury, R. R., Kapila, R., Panse, A., Zhang, X., Teng, D., Kulkarni, R., Hong, D., Gupta, R. K., & Shang, J. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i15.33762 · Cited by 17
Abdel‐Basset, M., Chang, V. I. C., Hawash, H., Chakrabortty, R. K., & Ryan, M. J. (2021) · Annals of Operations Research · doi:10.1007/s10479-021-04164-3 · Cited by 18
“SA5 Real world [69] Single 15 8 7 NA Sp & Sw A 50 Hz SA6 HAR [64] Single 30 6 561 10,299 Sp A, G 50 Hz SA7 M-HEALTH [65] Single 10 12 23 120 WS A, G, M 50 HZ SA8 HHAR [70] Single 9 5 16 43,930,257 Sp & Sw A, G 100–200 Hz SA9 HASC [71] Single 5 10 4 2,779 Sp A, G, M, 10–100 Hz SA10 DaSA [72] Single 8 19 45 9120 IMU A,…”
Human Activity Recognition: A Dynamic Inductive Bias Selection Perspective
Hamidi, M., & Osmani, A. (2021) · Sensors · doi:10.3390/s21217278 · Cited by 17
“Additionally, acceleration data generated by this particular position are identified to be invariant across positions [63].”
BackgroundSyed, A. S., Syed, Z. S., Shehram, M., & Saddar, S. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0110976 · Cited by 17
“Another approach which employs deep learning for human activity recognition in an industrial context is proposed in [4] who use CNNs with accelerometer data to differentiate between different activities from the dataset provided in [13].”
BackgroundFederated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR
Ek, S., Rombourg, R., Portet, F., & Lalanda, P. (2022) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops53856.2022.9767369 · Cited by 16
Hoelzemann, A., & Laerhoven, K. V. (2024) · Frontiers in Computer Science · doi:10.3389/fcomp.2024.1379788 · Cited by 16
“According to [10], this modification decreases the runtime up to 48 % compared to a two-layered DeepConvLSTM while significantly increasing the overall classification performance on 4/5 publicly available datasets: [17], [18], [1], [19], [20].”
MethodUhlenberg, L., Haeusler, L. O., & Amft, O. (2024) · IEEE Access · doi:10.1109/access.2024.3513477 · Cited by 16
“The dataset has been widely used in the literatures [13], [14], [29], and [58] and includes recordings outside the laboratory.”
InfluentialOuyang, X., Wu, J., Kimura, T., Lin, Y., Verma, G., Abdelzaher, T., & Srivastava, M. B. (2025) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3715014.3722053 · Cited by 16
Farid, F. A., Bari, A., Miah, A. S. M., Mansor, S. B., Uddin, J., & Kumaresan, S. P. (2025) · Journal of Imaging · doi:10.3390/jimaging11060182 · Cited by 16
Activity-Aware Vital Sign Monitoring Based on a Multi-Agent Architecture
Ivaşcu, T., & Negru, V. (2021) · Sensors · doi:10.3390/s21124181 · Cited by 16
Kostikis, N., Rigas, G., Konitsiotis, S., & Fotiadis, D. I. (2021) · Sensors · doi:10.3390/s21237801 · Cited by 16
“In [25], the authors present a method based on random forest classifiers to predict a mobile device’s position on the body, by analyzing acceleration data.”
MethodMagnetic Backscatter for In-body Communication and Localization
Tao, Y., Sie, E., Shenoy, J., & Vasisht, D. (2023) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3570361.3613301 · Cited by 16
“RF-Based In-Body Systems: There has been a large body of work that has used wireless technology to communicate and localize in-body implantable devices [3, 8, 28, 38, 40, 49].”
BackgroundJeon, H., Kim, S. L., Kim, S., & Lee, D. (2020) · Sensors · doi:10.3390/s20174996 · Cited by 16
“Using RealWorld Human Activity Recognition (HAR) public data [28], a hyper-parameter tuning was performed for optimal learning on CNN and eight dynamic activities were classified with 84–88% accuracy.”
MethodIoT System Based on parameter optimization of Deep Learning using Genetic Algorithm
Slim, S. O., Elfattah, M. M. A., Atia, A., & Mostafa, M.-S. (2021) · International journal of intelligent engineering and systems · doi:10.22266/ijies2021.0430.20 · Cited by 16
“[15] CNN 85% RealWorldHAR(L1O)[58] Independent”
Gao, X., Ruan, J., Gao, J., Xie, M., Zhang, Z., Liu, T., & Fu, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.06525 · Cited by 16
“The pre-training dataset for the activity recognition model was collected from publicly available datasets, including KU-HAR [ Sikder and Nahid, 2021 ] , RealWorld2016 [ Sztyler and Stuckenschmidt, 2016 ] , and MotionSense [ Malekzadeh et al. , 2018; Malekzadeh et al. , 2019 ] .”
Comparing self-supervised learning techniques for wearable human activity recognition
Ek, S., Presotto, R., Civitarese, G., Portet, F., Lalanda, P., & Bettini, C. (2025) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-024-00182-9 · Cited by 15
“This section provides an overview of the datasets used and the evaluation strategies employed to assess the performance of the pre-trained models obtained through various SSL techniques and architectures.”
HardenVR: Harassment Detection in Social Virtual Reality
Wang, N., Zhou, J., Li, J., Han, B., Li, F., & Chen, S. (2024) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr58804.2024.00033 · Cited by 15
“Three HAR datasets originally used include Skoda [56] for LSTM Ensemble, UCI [4] for deep Deep-Res-Bidir-LSTM, and RWHAR [57] for the shallow version of DeepConvLSTM, respectively.”
MethodAre Transformers a Useful Tool for Tiny devices in Human Activity Recognition?
Lattanzi, E., Calisti, L., & Contoli, C. (2024) · International Conference on Advances in Artificial Intelligence (ICAAI) · doi:10.1145/3704137.3704171 · Cited by 15
“The subjects had an average age of 32 years, weight of 74 kg, and height of 171 cm, and they participated in each activity for an average duration of approximately 10 minutes [33].”
Domain Adaptation with Representation Learning and Nonlinear Relation for Time Series
Hussein, A., & Hajj, H. M. (2022) · ACM Transactions on Internet of Things · doi:10.1145/3502905 · Cited by 15
“We picked a group of users as source domain {5, 10, 3, 12, 13, 14, 15} from PAR dataset and {a, g, c, b, h} from HAR dataset.”
MethodInfluentialFeature Fusion-Based Deep Learning Network to Recognize Table Tennis Actions
Yen, C.-T., Chen, T.-Y., Chen, U.-H., Wang, G., & Chen, Z.-X. (2022) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.032739 · Cited by 15
“Placing sensors in optimal positions is key for action recognition [13,14].”
A Lightweight Deep Human Activity Recognition Algorithm Using Multiknowledge Distillation
Chen, R., Luo, H., Zhao, F., Meng, X., Xie, Z., & Zhu, Y. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3443308 · Cited by 15
“HAR involves collecting data from external [23] and wearable devices [24] to analyze and identify the user’s current activity state, such as daily movement [25], transportation modes [26], [27], and work status [28], [29].”
BackgroundMethodRecognizing Grabbing Actions from Inertial and Video Sensor Data in a Warehouse Scenario
Diete, A., Sztyler, T., Weiland, L. R., & Stuckenschmidt, H. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.06.071 · Cited by 15
Self-citationSensor-based human activity recognition: Overcoming issues in a real world setting
Sztyler, T. (2019) · MADOC (University of Mannheim) · Cited by 15
Self-citationKwon, H., Tong, C., Haresamudram, H., Gao, Y., Abowd, G. D., Lane, N. D., & Ploetz, T. (2020) · arXiv · doi:10.48550/arxiv.2006.05675 · Cited by 14
“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…”
BackgroundMethodEnhancing Sensor-Based Human Activity Recognition With Multiresolution Wavelet-Attention
Wieland, C., & Pankratius, V. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3571572 · Cited by 14
“However, pretraining SHAR models with sensor signals from multiple SHAR datasets is challenging due to the inherent variations in human activities, sensing scenarios, sensor types, and sensor placements on the human body (see [2], [10], [11], [12], [13], [14], [15], [16], [17]).”
Adversarial domain adaptation for cross-user activity recognition via noise diffusion model
Ye, X., & Wang, K. I. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113952 · Cited by 14
Rey, V. F., Rezende, P. M. B., Zhou, B., Suh, S., & Lukowicz, P. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129288 · Cited by 14
IMUCoCo: Enabling Flexible On-Body IMU Placement for Human Pose Estimation and Activity Recognition
Zhou, H., Arakawa, R., Agarwal, Y., & Goel, M. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747695 · Cited by 14
“For instance, Sztyler and Stucken-schmidt [39] have proposed a method to recognize the on-body location of each device from IMU signals.”
CROMOSim: A Deep Learning-Based Cross-Modality Inertial Measurement Simulator
Hao, Y., Lou, X., Wang, B., & Zheng, R. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3230370 · Cited by 14
“For HAR evaluation, Realworld [39], the Physical Activity Monitoring version 2 (PAMAP2) [5] and Opportu-nity [40] datasets are used in task model training and testing.”
MethodAl-Saedi, A. A., & Boeva, V. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-34204-2_41 · Cited by 14
Ensemble of deep learning techniques to human activity recognition using smart phone signals
Imanzadeh, S., Tanha, J., & Jalili, M. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18935-0 · Cited by 14
“The pockets [33, 35, 37, 39, 40], the belt [28, 34, 36, 38], the arm [34, 38], the waist [34, 37, 38, 41], and the head [41] are a few examples where sensors are placed.”
OpenHAR: A Matlab Toolbox for Easy Access to Publicly Open Human Activity Data Sets
Siirtola, P., Koskimäki, H., & Röning, J. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3267503 · Cited by 14
“txt 60Hz numeral ±32767 9 RealworldHAR [21] .”
BackgroundMultilabel Classification Methods for Human Activity Recognition: A Comparison of Algorithms
Lentzas, A., Dalagdi, E., & Vrakas, D. (2022) · Sensors · doi:10.3390/s22062353 · Cited by 14
“Random forests have been proven an effective solution [10,11]; they provide robust and explainable results and are easy to implement and train.”
BackgroundWashSpot: Real-Time Spotting and Detection of Enacted Compulsive Hand Washing with Wearable Devices
Burchard, R., Scholl, P., Lieb, R., Laerhoven, K. V., & Wahl, K. (2022) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3544793.3563428 · Cited by 13
Xu, C., Ge, J., Deng, Y., Gao, L., Zhang, M., Li, Y., Zhou, W., & Zheng, X. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3374809 · Cited by 13
“In the experiments, a comprehensive evaluation of the proposed schemes is conducted using five diverse datasets: CIFAR-10 [11], FMNIST [49], UCI [50], REALWORLD [51], and IM-AGENET [52].”
MethodInternet of Things Ontologies for Well-Being, Aging and Health: A Scoping Literature Review
Belani, H., Šolić, P., Zdravevski, E., & Trajkovik, V. (2025) · Electronics · doi:10.3390/electronics14020394 · Cited by 13
Abdu-Aguye, M. G., & Gomaa, W. E. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852299 · Cited by 13
“Name Samples Activities Subjects Sample Rate MobiAct v2 [30] 1449 9 19+ 200Hz RealWorld [31] 824 8 15 50Hz IJCNN 2019.”
BackgroundOn the Utility of Virtual On-body Acceleration Data for Fine-grained Human Activity Recognition
Leng, Z., Jain, Y., Kwon, H., & Plötz, T. (2023) · International Symposium on Wearable Computers · doi:10.1145/3594738.3611364 · Cited by 13
Wang, T., Li, J., Wang, R., Kara, D., Liu, S., Wertheimer, D., Martin, A. V., Ganti, R., Srivatsa, M., & Abdelzaher, T. (2023) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3625687.3625785 · Cited by 13
“Below, we describe the data sets in more detail.”
MethodChen, Z., Zhang, X., & Cheng, X. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i6.20584 · Cited by 13
Electronic Productivity Performance Monitoring of Construction Workers
Ney, D. C. (2021) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · doi:10.34626/f1p8-e270 · Cited by 13
InfoMAE: Pair-Efficient Cross-Modal Alignment for Multimodal Time-Series Sensing Signals
Kimura, T., Li, X., Hanna, O. A., Chen, Y., Chen, Y., Kara, D., Wang, T., Li, J., Ouyang, X., Liu, S., et al. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714853 · Cited by 12
MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition
Zhang, H., Zhuang, Z., Wang, X., Yang, X., & Zhang, L. Y. (2025) · neural information processing systems · doi:10.52202/085713-1313 · Cited by 12
Zhang, Y., Wang, X., Han, P., Verschueren, S., Chen, W., & Vanrumste, B. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3186616 · Cited by 12
“The sensor on the ankle is more sensitive Walkingwas misclassified asstandingbalanceandwavinghands, within the range of the red dotted lines. to the movement of the lower extremity, such as walking, as proposed in study [37].”
BackgroundZhu, Y., Luo, H., Guo, S., & Zhao, F. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3204542 · Cited by 12
“As a result of various personal wearing preferences of mobile and wearable devices, the cross-domain HAR data demonstrate domain divergence [31].”
BackgroundAn Efficient CNN-LSTM Approach for Smartphone Sensor-Based Human Activity Recognition System
Choudhury, N. A., & Soni, B. (2022) · International Conference on Computational Intelligence and Networks (CINE) · doi:10.1109/cine56307.2022.10037495 · Cited by 12
Bento, N., Rebelo, J., Carreiro, A. V., Ravache, F., & Barandas, M. (2023) · Sensors · doi:10.3390/s23146511 · Cited by 12
Vision and Acceleration Modalities: Partners for Recognizing Complex Activities
Diete, A., Sztyler, T., & Stuckenschmidt, H. (2019) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2019.8730690 · Cited by 12
“it low-level [2], [7] or high-level activities [3], [8].”
BackgroundMethodResultInfluentialSelf-citationFusing Object Information and Inertial Data for Activity Recognition
Diete, A., & Stuckenschmidt, H. (2019) · Sensors · doi:10.3390/s19194119 · Cited by 12
“Features that are calculated from these windows are often from the time and frequency domain and may consist of measures, such as mean and variance, but also more computationally expensive and complicated features like energy [2].”
BackgroundMethodResultInfluentialSelf-citationOn the Benefit of Generative Foundation Models for Human Activity RecognitionPreprint
Leng, Z., Kwon, H., & Plötz, T. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.12085 · Cited by 12
“The effectiveness of this approach has been verified on three widely recognized HAR datasets - RealWorld [30], Pamap2 [25], and USC-HAD [33] - showing significant improvement in the performance of the downstream classifier.”
MethodAccurate human activity recognition with multi-task learning
Li, Y., Zhang, S., Zhu, B., & Wang, W. (2020) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-020-00042-2 · Cited by 11
“We compared the accuracy of our model and OLWD (Sztyler and Stuckenschmidt 2016) in the classification of body positions.”
BackgroundMethodResultInfluentialSuspicious Activity Detection using LRCN
Vinusha., B., V, Indhuja., V., Reddy, M. V., Nikhitha, N., & Pramila, R. P. (2023) · International Conference on Smart Systems and Inventive Technology (ICSSIT) · doi:10.1109/icssit55814.2023.10061045 · Cited by 11
Caramaschi, S., Papini, G. B., & Caiani, E. G. (2023) · Applied Sciences · doi:10.3390/app13074175 · Cited by 11
DOMINO: A Dataset for Context-Aware Human Activity Recognition using Mobile Devices
Arrotta, L., Civitarese, G., Presotto, R., & Bettini, C. (2023) · IEEE International Conference on Mobile Data Management (MDM) · doi:10.1109/mdm58254.2023.00063 · Cited by 11
“Finally, datasets like RealWorld [23] (scripted, involving 15 subjects) and Daily Log [24] (in-the-wild, involving 7 subjects) collected measurements from inertial sensors (i.e., accelerometer, gyroscope, magnetometer) and context data (e.g., GPS, microphone, and luminosity sensors) considering smartphones and smartwa…”
Background
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.