Toward Personalized Activity Recognition Systems With a Semipopulation Approach
The DOI matches its Crossref record; 46 of the 47 references it cites were found in a registry or an index.
Abstract
Activity recognition is a key component of context-aware computing to support people's physical activity, but conventional approaches often lack in their generalizability and scalability due to problems of diversity in how individuals perform activities, overfitting when building activity models, and collection of a large amount of labeled data from end users. To address these limitations, we propose a semipopulation-based approach that exploits activity models trained from other users; therefore, a new user does not need to provide a large volume of labeled activity data. Instead of relying on any additional information from users like their weight or height, our approach directly measures the fitness of others' models on a small amount of labeled data collected from the new user. With these shared activity models among users, we compose a hybrid model of Bayesian networks and support vector machines to accurately recognize the activity of the new user. On activity data collected from 28 people with a diversity in gender, age, weight, and height, our approach produced an average accuracy of 83.4% (kappa: 0.852), compared with individual and (standard) population models that had accuracies of 77.3% (kappa: 0.79) and 77.7% (kappa: 0.743), respectively. Through an analysis on the performance of our approach and users' demographic information, our approach outperforms others that rely on users' demographic information for recognizing their activities, which may contradict the commonly held belief that physically similar people would have similar activity patterns.
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
“In contrast, real-world HAR systems may fail to distinct to new members and/or situations, resulting in low computational efficiency in practical applications [13], [14].”
From Deep CNN-LSTM With Self-Attention Model for Human Activity Recognition Using Wearable Sensor (2022) · cites this paper as [13]
In the citing paper
“While extensive explore has been completed on the effects of human traits on recognition accuracy, few studies have looked into the effects of position and device features [13], [15]–[18].”
From Deep CNN-LSTM With Self-Attention Model for Human Activity Recognition Using Wearable Sensor (2022) · cites this paper as [13]
Citations
Cites
A robust layered control system for a mobile robot
Brooks, R. (1986) · IEEE Journal on Robotics and Automation · doi:10.1109/jra.1986.1087032 · Cited by 7,799
Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
Powers, D. M. W. (2020) · arXiv · doi:10.48550/arxiv.2010.16061 · Cited by 5,440
Neural Networks and the Bias/Variance Dilemma
Geman, S., Bienenstock, E., & Doursat, R. (1992) · Neural Computation · doi:10.1162/neco.1992.4.1.1 · Cited by 3,578 · cited 1×
“Both situations are to be avoided as they can contribute to poor performance [17].”
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 1×
“In this study, we do not directly deal with the issue of sensor placement, but instead adopted a sensor placement approach commonly used [2], [3], [19], [21], [22], [24], [32], [40].”
MethodA 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 6×
“In the activity recognition community, there is an on-going open debate about the relative merits of subject-dependent (or individual) models and subject-independent (or population) models [26].”
BackgroundInfluentialAssessing Agreement on Classification Tasks: The Kappa Statistic
Carletta, J. (1996) · arXiv · doi:10.48550/arxiv.cmp-lg/9602004 · Cited by 2,088
The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition
Chavarriaga, R., Sagha, H., Calatroni, A., Digumarti, S. T., Tröster, G., Millán, J. D. R., & Roggen, D. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.12.014 · Cited by 742
A Knowledge-Driven Approach to Activity Recognition in Smart Homes
Chen, L., Nugent, C. D., & Wang, H. (2012) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2011.51 · Cited by 589
USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors
Zhang, M., & Sawchuk, A. A. (2012) · Proceedings of the 2012 ACM Conference on Ubiquitous Computing · doi:10.1145/2370216.2370438 · Cited by 554 · cited 1×
“This is especially true for medical, military, and activities-of-daily-living-based applications [12], [15], [26], [27], [30], [43].”
BackgroundKhan, A. M., Lee, Y.-K., Lee, S. Y., & Kim, T.-S. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2010.2051955 · Cited by 518 · cited 2×
“Advances in mobile sensing technology have led to the development of a number of human-activity recognition methods and systems, mostly using accelerometers [4], [11], [18], [22], [23], [47].”
BackgroundMethod
Research works printed but not linked: 1
- cvetkovic, 0, Semi-supervised learning for adaptation of human activity recognition classifier to the user, Proc Workshop Space Time Ambient Intell, 24
Cited by
Deep CNN-LSTM With Self-Attention Model for Human Activity Recognition Using Wearable Sensor
Khatun, M. A., Yousuf, M. A., Ahmed, S., Uddin, M. Z., Alyami, S. A., Al-Ashhab, S., Akhdar, H. F., Khan, A., Azad, A., & Moni, M. A. (2022) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2022.3177710 · Cited by 288
“While extensive explore has been completed on the effects of human traits on recognition accuracy, few studies have looked into the effects of position and device features [13], [15]–[18].”
Robust Human Activity Recognition Using Smartphone Sensors via CT-PCA and Online SVM
Chen, Z., Zhu, Q., Soh, Y. C., & Zhang, L. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2712746 · Cited by 247
“Since smartphones are widely used in our daily life and nonintrusive for users, they can be a good candidate for human activity recognition [8].”
BackgroundLonini, L., Dai, A., Shawen, N., Simuni, T., Poon, C., Shimanovich, L., Daeschler, M., Ghaffari, R., Rogers, J. A., & Jayaraman, A. (2018) · npj Digital Medicine · doi:10.1038/s41746-018-0071-z · Cited by 209
Distilling the Knowledge From Handcrafted Features for Human Activity Recognition
Chen, Z., Zhang, L., Cao, Z., & Guo, J. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2789925 · Cited by 160
“Since they are widely available and nonintrusive for users, human activity recognition with smartphone sensors becomes more and more popular [10], [11].”
BackgroundOn the Personalization of Classification Models for Human Activity Recognition
Ferrari, A., Micucci, D., Mobilio, M., & Napoletano, P. (2020) · IEEE Access · doi:10.1109/access.2020.2973425 · Cited by 146
“However, real-world HAR systems may achieve non satisfying recognition accuracy in real world applications because HAR techniques may struggle to generalize to new users and/or new environments [14], [15].”
BackgroundMethodInfluential2D Federated Learning for Personalized Human Activity Recognition in Cyber-Physical-Social Systems
Zhou, X., Liang, W., Ma, J., Yan, Z., & Wang, K. I.-K. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3144699 · Cited by 114
“[13] focused on a semi-population based mechanism which only required a small number of labeled data from a new user to fit his/her features in a trained activity learning model.”
BackgroundSuh, S., Rey, V. F., & Lukowicz, P. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110143 · Cited by 107
Deep learning and model personalization in sensor-based human activity recognition
Ferrari, A., Micucci, D., Mobilio, M., & Napoletano, P. (2022) · Journal of Reliable Intelligent Environments · doi:10.1007/s40860-021-00167-w · Cited by 115
“[16] propose to combine models that have been trained relying on an a subject-dependent approach for dataset split.”
BackgroundMethodTrends 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
Recognition of human activity using GRU deep learning algorithm
Mohsen, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15571-y · Cited by 106
“However, the level of accuracy of these algorithms remains an issue [23, 27].”
BackgroundIndustry 4.0-Oriented Deep Learning Models for Human Activity Recognition
Mohsen, S., Elkaseer, A., & Scholz, S. G. (2021) · IEEE Access · doi:10.1109/access.2021.3125733 · Cited by 95
“Many traditional machine learning approaches have been proposed for accurately recognition of a human activity [15]–[18], but do not always achieve a satisfactory level of accuracy [19], [20].”
BackgroundHuman Activity Recognition Using K-Nearest Neighbor Machine Learning Algorithm
Mohsen, S., Elkaseer, A., & Scholz, S. G. (2021) · Smart innovation, systems and technologies · doi:10.1007/978-981-16-6128-0_29 · Cited by 99
Xu, X., Chikersal, P., Dutcher, J. M., Sefidgar, Y. S., Seo, W., Tumminia, M. J., Villalba, D. K., Cohen, S., Creswell, K. G., Creswell, J. D., et al. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3448107 · Cited by 65
“In some domains, such as activity recognition [26, 34], labels are easier to obtain, as opposed to domains like mental health monitoring.”
BackgroundSelf-citationLing, C. (2020) · doi:10.1145/3381012 · Cited by 72
“The second category built a personalized model for each user [14, 19, 21, 41].”
BackgroundEmpirical Study and Improvement on Deep Transfer Learning for Human Activity Recognition
Ding, R., Li, X., Nie, L., Li, J., Si, X., Chu, D., Liu, G., & Zhan, D. (2018) · Sensors · doi:10.3390/s19010057 · Cited by 63
“They [4] combined naive Bayes with Support Vector Machine (SVM) and the accuracy increased by 6% for new users.”
MethodAutomatic 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
“[36], an alternative approach has been proposed to reduce the required amount of labeled data, aiming to exploit activity models trained on other users.”
BackgroundYe, X., Sakurai, K., Nair, N. C., & Wang, K. I. (2024) · Sensors · doi:10.3390/s24247975 · Cited by 68
“Hong et al. [42] trained a Bayesian network, a naïve Bayes classifier and a SVM separately for each user’s activities to construct a pool of activity models.”
A WiFi-Based Method for Recognizing Fine-Grained Multiple-Subject Human Activities
Moghaddam, M. G., Shirehjini, A. A. N., & Shirmohammadi, S. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3289547 · Cited by 61
“Although using a one-fits-all model for recognizing human activities is more generalized and practical in the real environment, many researchers prefer to have a personalized model for each subject [62], or train and test the model for a small group of people [48].”
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
“Because of the insight that automated activity recognition sheds on human behavior and the valuable context activity labels bring to technology customization, activity recognition is a highly-investigated area of research [13], [14], [15], [16], [17].”
Generic online animal activity recognition on collar tags
Kamminga, J. W., Bisby, H. C., Le, D. V., Meratnia, N., & Havinga, P. (2017) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3123024.3124407 · Cited by 52
Energy-Efficient Real-Time Human Activity Recognition on Smart Mobile Devices
Lee, J., & Kim, J. (2016) · Mobile Information Systems · doi:10.1155/2016/2316757 · Cited by 53
“[21] presented a personalized HAR system using Bayesian network and support vector machine (SVM).”
MethodKhowaja, S. A., Yahya, B. N., & Lee, S. (2020) · Human-centric Computing and Information Sciences · doi:10.1186/s13673-020-00240-y · Cited by 54
Mazankiewicz, A., Böhm, K., & Berges, M. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3432230 · Cited by 35
“dels. Because collecting a sufficient amount of data for each target user is not practical, much research focused on methods to fine-tune general models given only a small amount of labeled target data [12, 13, 14, 15, 16, 17, 18, 19]. Acquiring even a small set of labeled data 2 Incremental Real-Time Personalization in…”
BackgroundHu, 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
A lightweight and aggregated system for indoor/outdoor detection using smart devices
Li, S., Qin, Z., Song, H., Si, C., Sun, B., Xiao, Y., & Zhang, R. (2017) · Future Generation Computer Systems · doi:10.1016/j.future.2017.05.028 · Cited by 44
Activity-Aware Energy-Efficient Automation of Smart Buildings
Thomas, B., & Cook, D. (2016) · Energies · doi:10.3390/en9080624 · Cited by 42
Transfer Learning in Sensor-Based Human Activity Recognition: A Survey
Dhekane, S. G., & Ploetz, T. (2025) · ACM Computing Surveys · doi:10.1145/3717608 · Cited by 42
Automatic modulation recognition using CNN deep learning models
Mohsen, S., Ali, A. M., & Emam, A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15814-y · Cited by 46
“Many conventional neural networks have been presented to recognize modulation techniques [13, 28, 30, 35], but do not always achieve a satisfactory level of accuracy [8, 9].”
Local Domain Adaptation for Cross-Domain Activity Recognition
Zhao, J., Deng, F., He, H., & Chen, J. (2021) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2020.3039196 · Cited by 36
“[9] presented a semipopulation approach for cross-person HAR.”
BackgroundMethodTransfer learning and its extensive appositeness in human activity recognition: A survey
Ray, A., & Kolekar, M. H. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122538 · Cited by 39
Personalized Activity Recognition with Deep Triplet Embeddings
Burns, D., Boyer, P., Arrowsmith, C., & Whyne, C. M. (2022) · Sensors · doi:10.3390/s22145222 · Cited by 42
“Both non-neural and neural network supervised learning models have been applied to personalized activity recognition [10–16].”
MethodMultisource Weighted Domain Adaptation With Evidential Reasoning for Activity Recognition
Dong, Y., Li, X., Dezert, J., Zhou, R., Zhu, C., Cao, L., Khyam, M. O., & Ge, S. S. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3182780 · Cited by 34
“[21] proposed a novel single-source DA method based on semipopulation strategy; Wang et al.”
MethodSocial recommendations for personalized fitness assistance
Dharia, S., Eirinaki, M., Jain, V., Patel, J., Varlamis, I., Vora, J., & Yamauchi, R. (2017) · Personal and Ubiquitous Computing · doi:10.1007/s00779-017-1039-8 · Cited by 37
“A lot of research work has been done in this area, by employing machine learning algorithms on past user activity data [20], heart rate data [6], and accelerometer data [4, 5] to identify the type of activity, and/or estimate caloric consumption.”
BackgroundFrom Multimedia Logs to Personal Chronicles
Oh, H., & Jain, R. (2017) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3123266.3123375 · Cited by 35
“Classification techniques have also contributed to the recognition of higher-level semantics, such as physical activity [3, 17, 24, 36], more so sensor measurements.”
BackgroundHierHAR: Sensor-Based Data-Driven Hierarchical Human Activity Recognition
Wang, A., Zhao, S., Zheng, C., Chen, H., Liu, L., & Chen, G. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3023860 · Cited by 29
“Typically, there exists inter-subject variation in the way of doing an activity, where an activity recognizer that works well on one user probably fails to generalize well to others [10].”
BackgroundTowards Human Motion Tracking: Multi-Sensory IMU/TOA Fusion Method and Fundamental Limits
Xu, C., He, J., Zhang, X., Zhou, X., & Duan, S. (2019) · Electronics · doi:10.3390/electronics8020142 · Cited by 31
“Thus, they are more suitable for large-scale and dynamic applications [14].”
BackgroundPalmius, N., Saunders, K., Carr, O., Geddes, J. R., Goodwin, G. M., & Vos, M. D. (2018) · Journal of Medical Internet Research · doi:10.2196/10194 · Cited by 32
“Hong et al have also previously demonstrated that demographic features poorly predict sensor data similarity [13].”
BackgroundLonini, L., Gupta, A. N., Kording, K. P., & Jayaraman, A. (2016) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2016.7591425 · Cited by 30
“In this scenario, generalization could be improved through featureselection methods for the patient population [8] as well as by using transfer learning methods [9,10].”
MethodAdversarial Deep Feature Extraction Network for User Independent Human Activity Recognition
Suh, S., Rey, V. F., & Lukowicz, P. (2022) · 2022 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom53586.2022.9762387 · Cited by 25
Fang, H., Tang, P. S., & Si, H. (2020) · Journal of Healthcare Engineering · doi:10.1155/2020/8876782 · Cited by 30
A Personalized Classifier for Human Motion Activities With Semi-Supervised Learning
Singh, G., Chowdhary, M., Kumar, A., & Bahl, R. (2020) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2020.3036277 · Cited by 25
“Hong et al. [29] echoed the same results that as the amount of data increases the isolated (i.e., personal) model outperforms single (i.e., impersonal) model.”
ResultA Novel Approach to Face Pattern Analysis
Bhushan, S., Alshehri, M., Agarwal, N., Keshta, I. M., Rajpurohit, J., & Abugabah, A. (2022) · Electronics · doi:10.3390/electronics11030444 · Cited by 28
“PCA [25] and LDA [26] are two commonly used algorithms that are used to fuse fea‐ tures, human activity recognition [27,28], and feature extraction [29].”
MethodToward Hand-Dominated Activity Recognition Systems With Wristband-Interaction Behavior Analysis
Shen, C. Q., Chen, Y., Yang, G., & Guan, X. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2819026 · Cited by 24
“The streaming data from wristband sensors can be segmented using a sliding-time window with fixed width and overlap (e.g., a 2s sliding window with 50% overlap in [37]).”
MethodMartindale, C. F., Šprager, S., & Eskofier, B. M. (2019) · Sensors · doi:10.3390/s19081820 · Cited by 26
“For example, [24] uses gender and physical characteristics to find a matching model, and in [25] a new user is matched to the most similar model from the existing trained models.”
MethodTowards an Automated Islamic Fatwa System: Survey, Dataset and Benchmarks
Munshi, A., Alsabban, W. H., Farag, A. T., Rakha, O. E., Sallab, A. A. A., & Alotaibi, M. (2021) · International Journal of Computer Science and Mobile Computing · doi:10.47760/ijcsmc.2021.v10i04.017 · Cited by 26
Moghaddam, G. K., & Lowe, C. R. (2018) · SpringerBriefs in applied sciences and technology · doi:10.1007/978-3-030-01557-2_2 · Cited by 22
A WiFi-based System for Recognizing Fine-grained Multiple-Subject Human Activities
Moghaddam, M. G., Shirehjini, A. A. N., & Shirmohammadi, S. (2022) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc48687.2022.9806622 · Cited by 21
“Although using a one-fits-all model for recognizing human activities is more generalized and practical in the real environment, many researchers prefer to have a personalized model for each subject [38].”
BackgroundPRO-Fit: A personalized fitness assistant framework
Dharia, S., Jain, V., Patel, J., Vora, J., Chawla, S., & Eirinaki, M. (2016) · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering · doi:10.18293/seke2016-174 · Cited by 20
“A lot of research work has been done in this area, by employing machine learning algorithms on past user activity data [2], heart rate data [3], and accelerometer data [4,5, 6] to identify the type of activity, or estimate caloric consumption.”
BackgroundAutomatic Annotation of Unlabeled Data from Smartphone-Based Motion and Location Sensors
Owoh, N. P., Singh, M. M., & Zaaba, Z. F. (2018) · Sensors · doi:10.3390/s18072134 · Cited by 21
“[15,30] performed semi-supervised learning by dividing data into identical groups (called ‘populations’) and then fully label only a portion of each population.”
BackgroundA systematic approach to multi-task learning from time-series data
Mahmoud, R. A., Hajj, H. M., & Karameh, F. N. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106586 · Cited by 23
Context Impacts in Accelerometer-Based Walk Detection and Step Counting
Ao, B., Wang, Y., Liu, H., Li, D., Song, L., & Li, J. (2018) · Sensors · doi:10.3390/s18113604 · Cited by 19
“By using active learning and semi-supervised learning algorithms, [23,24] in fact developed a personalized model based on a original classifier and showed the significant improvement over the original classifier, which was trained on the data from many users.”
MethodThyme: Improving Smartphone Prompt Timing Through Activity Awareness
Aminikhanghahi, S., Fallahzadeh, R., Sawyer, M., Cook, D. J., & Holder, L. B. (2017) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2017.0-141 · Cited by 19
“Because of the insights that automated activity recognition offers on human behavior and the enriched context description that activity labels bring to mobile systems, activity recognition is a highly-investigated area of research [36]–[40].”
BackgroundElshafei, M., Costa, D. E., & Shihab, E. (2022) · Sensors · doi:10.3390/s22041454 · Cited by 15
“Moreover, these models often suffer from dramatic performance drops in real-time applications if the subject’s data are unavailable or insufficient [37,38].”
BackgroundMethodKhatun, M. A., Yousuf, M., & Moni, M. A. (2023) · International Conference on Electrical, Computer and Communication Engineering · doi:10.1109/ecce57851.2023.10101550 · Cited by 19
“Numerous conventional machine-learning strategies have been put forth for the precise recognition of human activity, but they don’t permanently reach a level of precision that is satisfactory [6].”
BackgroundSmart Annotation of Cyclic Data Using Hierarchical Hidden Markov Models
Martindale, C. F., Hoenig, F., Strohrmann, C., & Eskofier, B. M. (2017) · Sensors · doi:10.3390/s17102328 · Cited by 15
Lonini, L., Gupta, A. N., Deems-Dluhy, S., Hoppe-Ludwig, S., Kording, K. P., & Jayaraman, A. (2017) · JMIR Rehabilitation and Assistive Technologies · doi:10.2196/rehab.7317 · Cited by 14
“For example, activity-specific personal models from other subjects can be combined to fit a small dataset of labeled data from the target subject (semipopulation models) [31].”
BackgroundIdentification of Walker Identity Using Smartphone Sensors: An Experiment Using Ensemble Learning
Angrisano, A., Bernardi, M. L., Cimitile, M., Gaglione, S., & Vultaggio, M. (2020) · IEEE Access · doi:10.1109/access.2020.2971693 · Cited by 13
“Other studies explore semi-unsupervised learning approaches allowing to minimize the number of fully-labeled needed data (Hong et al., 2016).”
BackgroundPersonalizing Activity Recognition With a Clustering Based Semi-Population Approach
Cruciani, F., Nugent, C., Medina-Quero, J., Cleland, I., McCullagh, P. J., Synnes, K., & Hallberg, J. (2020) · IEEE Access · doi:10.1109/access.2020.3038084 · Cited by 13
“pre-existing population, however, restricting it to users that present similar characteristics to the target users, as presented in [12].”
BackgroundMethodInfluentialData Processing of Physiological Sensor Data and Alarm Determination Utilising Activity Recognition
Kang, J. J., Luan, T. H., & Larkin, H. (2016) · International Journal of Information Communication Technology and Applications · doi:10.17972/ijicta20162132 · Cited by 13
Domain adaptation framework for personalized human activity recognition models
Mhalla, A., & Favreau, J.-M. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18267-z · Cited by 10
On the Homogenization of Heterogeneous Inertial-Based Databases for Human Activity Recognition
Ferrari, A., Mobilio, M., Micucci, D., & Napoletano, P. (2019) · IEEE World Congress on Services (SERVICES) · doi:10.1109/services.2019.00084 · Cited by 12
“walking physical activity [15], [16], [17] dynamic activity [18], [19] ADL [20], [18], [21] simple activity [22], [23] basic and common activities in people’s daily living [24] common activities in people’s daily living [25] daily living human activities [26] basic movement [27] daily activity [28], [29] body state [3…”
BackgroundSelf-Supervised Learning for Activity Recognition Based on Datasets With Imbalanced Classes
Hamad, R. A., Woo, W. L., Wei, B. W., & Yang, L. (2025) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2025.3526504 · Cited by 11
Convolutional neural network for human behavior recognition based on smart bracelet
Qu, J., Qiao, N., Shi, H., Su, C., & Razi, A. (2020) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-179651 · Cited by 12
“…of the fall detection bracelet and the hardware function requirements analysis, the smart bracelet can be divided into five modules: MPU6050 six-axis inertial measurement module, STM32 microprocessor module, SIM808 communication positioning module, micro SD card storage module and power module [10].”
Cascading Scene and Viewpoint Feature Learning for Pedestrian Gender Recognition
Cai, L., Zeng, H., Zhu, J., Cao, J., Wang, Y., & Ma, K. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3021763 · Cited by 10
“For example, the intelligent machines (e.g., robots) need the gender information for providing appropriate interaction and communication [15].”
BackgroundCompressed Deep Learning Model For Human Activity Recognition
k, A. A. O., Semwal, V. B., & Soni, V. (2024) · IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS) · doi:10.1109/sceecs61402.2024.10482048 · Cited by 11
“Prior research has shown that these sensors provide valuable insights into human movement [12].”
BackgroundBaseline Model Training in Sensor-Based Human Activity Recognition: An Incremental Learning Approach
Xiao, J., Chen, L., Chen, H., & Hong, X. (2021) · IEEE Access · doi:10.1109/access.2021.3077764 · Cited by 10
“Take Table 2 for example, the best performance is given by SVM, which costs 389 .”
MethodInfluentialEvaluation of Transfer Learning for Human Activity Recognition Among Different Datasets
Islam, M. S., Okita, T., & Inoue, S. (2019) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/cbdcom/cyberscitech.2019.00155 · Cited by 11
“Some use transfer learning models to transfer knowledge among body parts, some transfer among devices, locations etc. [1 – 3].”
BackgroundPRO-Fit: Exercise with friends
Dharia, S., Jain, V., Patel, J., Vora, J., Yamauchi, R., Eirinaki, M., & Varlamis, I. (2016) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2016.7752437 · Cited by 8
“Most of the research projects related to activity tracking focus on determining the type of activity and fitness level of an individual by applying machine learning algorithms [9-11] on past user activity data [3, 8], heart rate data [4], and accelerometer data [1, 5-7].”
Investigation of Heterogeneity Sources for Occupational Task Recognition via Transfer Learning
Hajifar, S., Lamooki, S. R., Cavuoto, L. A., Megahed, F. M., & Sun, H. (2021) · Sensors · doi:10.3390/s21196677 · Cited by 8
“[31], who showed that the accuracy of their ADL recognition for field (in-home) and lab studies were comparable.”
BackgroundTowards Personalized Learning in Mobile Sensing Systems
Jiang, W., Li, Q., Su, L., Miao, C., Gu, Q., & Xu, W. (2018) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2018.00040 · Cited by 9
Personalized travel mode detection with smartphone sensors
Su, X., Yao, Y., He, Q., Lu, J., & Tong, H. (2017) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2017.8258065 · Cited by 6
“[19] propose a method to measure the performance (or fitness) of activity models trained from other people in the pool, and aggregate the best performing activity recognition models on the target user’s labeled data to construct a personalized hybrid model.”
MethodAutoAct: An Auto Labeling Approach Based on Activities of Daily Living in the Wild Domain
Hassan, I., Mursalin, A., Salam, R. B., Sakib, N., & Haque, H. M. Z. (2021) · International Conference on Informatics, Electronics & Vision (ICIEV) · doi:10.1109/icievicivpr52578.2021.9564211 · Cited by 6
Sudershan, B. (2023) · doi:10.1145/3610896 · Cited by 5
“The vision of Human Activity Recognition (HAR) approaches is to enable a better understanding of human behavior for applications in healthcare and human-computer interaction [31].”
Background2D Convolutional LSTM-Based Approach for Human Action Recognition on Various Sensor Data
Pandey, A., Kumar, P., & Prasad, S. (2023) · Smart innovation, systems and technologies · doi:10.1007/978-981-19-7524-0_36 · Cited by 6
Personalized Weighted AdaBoost for Animal Behavior Recognition from Sensor Data
Dissanayake, O. I., Mcpherson, S. E., Allyndrée, J., Kennedy, E., Cunningham, P., & Riaboff, L. (2023) · Irish Conference on Artificial Intelligence and Cognitive Science (AICS) · doi:10.1109/aics60730.2023.10470889 · Cited by 7
“However, generalizing ML models to new subjects is a primary challenge highlighted both in Animal Behavior Recognition (ABR) and Human Behavior Recognition (HBR) due to the inter-individual diversity [6], [7].”
BackgroundToward Personalized Human Activity Recognition Model with Auto-Supervised Learning Framework
Mhalla, A., & Favreau, J.-M. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428296 · Cited by 4
“The third scheme involves using an ensemble of classifiers [10].”
BackgroundMethodEnhancement of Sensor-based User Identification using Data Augmentation Techniques
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2022) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon53731.2022.9720293 · Cited by 4
“Several other works [24] investigate semi-unsupervised learning algorithms that reduce the amount of fully-labeled data sets that must be collected.”
BackgroundPersonalization in Human Activity RecognitionPreprint
Ferrari, A., Micucci, D., Mobilio, M., & Napoletano, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.00268 · Cited by 5
“Regardless of the underlaying learning method (either classic machine learning or deep learning), real-world HAR systems achieve non satisfying recognition accuracy in real world applications mostly because HAR techniques struggle to generalize to new users and/or new environments [5], [6].”
Hiding in the deep : online animal activity recognition using motion sensors and machine learning
Kamminga, J. W. (2020) · doi:10.3990/1.9789036550550 · Cited by 5
Li, X., Wang, Y., Ma, J., & Jin, Q. (2021) · IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC) · doi:10.1109/euc53437.2021.00013 · Cited by 3
Plunk, A., Amat, A. Z., Wilkes, D. M., & Sarkar, N. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-37660-3_14 · Cited by 3
Stream Data Analysis and Processing Frameworks for Detecting Outliers in Human Activities: A Review
Sabha, M., & Tuğrul, B. (2025) · WSEAS Transactions on Information Science and Applications archive · doi:10.37394/23209.2025.22.11 · Cited by 4
CRoP: Context-wise Robust Static Human-Sensing Personalization
Kaur, S., Gump, A., Xiao, Y., Xin, J., Sharma, H., Benway, N. R., Preston, J. L., & Salekin, A. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3729483 · Cited by 2
“Table1acompares the performance of generic and conventionally-finetuned [25] personalized models on each user’s data belonging to context C1 and evaluated to the same user’s disjoint data in both C1 (available) and C2 (unseen) contexts.”
InfluentialKnowledge Mapping of Human Activity Recognition Techniques for Assistive Living
Agarwal, P., & Alam, M. (2023) · International Journal of Sensors Wireless Communications and Control · doi:10.2174/2210327913666230911113149 · Cited by 6
Activity Recognition for Stroke Patients
Vågeskar, E. (2017) · BIBSYS Brage (BIBSYS (Norway)) · Cited by 4
Adaptive coefficient-based kernelized network for personalized activity recognition
Hu, L., Hu, C., Jiang, X., & Huo, Z. (2021) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-021-01455-w · Cited by 1
“2) they firstly construct plenty of diverse models based on the non-target data, select a few of the models which have high recognition ability on the target data, and integrate the selected models into a batch mode model [38].”
BackgroundXiao, S., Cai, L., & Tang, C. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3651746 · Cited by 1
Bicer, M., Pope, J., Rochester, L., Din, S. D., & Alcock, L. (2026) · Sensors · doi:10.3390/s26041320 · Cited by 1
“The networks, serving as general or population-wide recognition models, can be personalised for each individual [43] through fine-tuning, which involves additional training using the individual’s data.”
A Personalized Deep Neural Network to Recognize Human Activities in Healthy Subjects
Fereidoonian, F., & Ahmadi‐Pajouh, M. A. (2022) · National and International Iranian Conference on Biomedical Engineering (ICBME) · doi:10.1109/icbme57741.2022.10052893 · Cited by 1
“This method needs a small amount of data from the end-user [27].”
MethodPersonalized and Weakly Supervised Learning for Parkinson's Disease Symptom Detection
Zhang, A. (2020) · Figshare · doi:10.1184/r1/11591562 · Cited by 3
PRO-fit: exercise with friends
Dharia, S., Jain, V., Patel, J., Vora, J., Yamauchi, R., Eirinaki, M., & Varlamis, I. (2016) · Advances in Social Networks Analysis and Mining · doi:10.5555/3192424.3192698
Li, J., Ding, R., Nie, L., Li, X., Si, X., Wang, L., Chu, D., & Zhan, D. (2018) · EAI International Conference on Mobile Multimedia Communications (MobiMedia) · doi:10.4108/eai.21-6-2018.2276633
“In [29], a combination of naive Bayesian and Support Vector Machine (SVM) was proposed, which had better prediction accuracy for new users in activity recognition test set.”
MethodFerrari, A., Micucci, D., Mobilio, M., & Napoletano, P. (2020)
Chen, S., Wu, S. K., Zhu, L., & Yang, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-95384-3_7
Human Activity Recognition Using Transformer Model
Ghafoor, H. Y., Izhar, M., Zubair, M., Abid, M. N., & Jahangir, R. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-77620-5_12
Τοπάλη, Κ. Ι., & Τοπάλη, Κ. Ι. (2023) · University of Thessaly Institutional Repository (University of Thessaly)
Trang, V. T. (2021) · Institutional Repositories DataBase (IRDB)
Conception d’environnement instrumenté pour la veille à la personne
Massein, A. (2018) · theses.fr (ABES) · doi:10.70675/b23ba272z0f28z47beza3fazee30285ac897
Metadata
- Authors
- Hong, J.-H., Ramos, J., & Dey, A. K.
- Affiliations
- Samsung Electronics (South Korea) (KR)
- Carnegie Mellon University (US)
- Venue
- IEEE Transactions on Human-Machine Systems
- Published
- 2016-02
- Volume
- 46
- Issue
- 1
- Pages
- 101-112
- ISSN
- 2168-2291 (ISSN-L)
- 2168-2305
- OpenAlex
- W2285292066
- Cited by
- 94
- References
- 47
- Citations by year
- 2025: 6 · 2024: 3 · 2023: 11 · 2022: 13 · 2021: 11 · 2020: 16 · 2019: 4 · 2018: 12 · 2017: 11 · 2016: 7
- FWCI
- 8.67
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Human-Machine Systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Social Sciences › Transportation › Human Mobility and Location-Based Analysis
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Physical Activity and Health
- Keywords
- activity recognition, context-aware computing, physical activity, Bayesian networks, support vector machine, hybrid model, demographic diversity, overfitting
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.