Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble
The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Abstract
Effectively utilizing multimodal information (e.g., heart rate and acceleration) is a promising way to achieve wearable sensor based human activity recognition (HAR). In this paper, an activity recognition approach MARCEL (Multimodal Activity Recognition with Classifier Ensemble) is proposed, which exploits the diversity of base classifiers to construct a good ensemble for multimodal HAR, and the diversity measure is obtained from both labeled and unlabeled data. MARCEL uses neural network (NN) as base classifiers to construct the HAR model, and the diversity of classifier ensemble is embedded in the error function of the model. In each iteration, the error of the model is decomposed and back-propagated to base classifiers. To ensure the overall accuracy of the model, the weights of base classifiers are learnt in the classifier fusion process with sparse group lasso. Extensive experiments show that MARCEL is able to yield a competitive HAR performance, and has its superiority on exploiting multimodal signals.
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
“Using a single feature vector for the training model is straightforward, but feature compatibility issues regarding heterogeneous sampling frequencies and configuration parameters can deteriorate the classifier performance [35].”
From Sensor Data Acquisition and Multimodal Sensor Fusion for Human Activity Recognition Using Deep Learning (2019) · cites this paper as [35]
In the citing paper
“Previous work in the HAR literature empirically adopted 5.12 s-long window size [35,39].”
From Sensor Data Acquisition and Multimodal Sensor Fusion for Human Activity Recognition Using Deep Learning (2019) · cites this paper as [35]
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 2×
“Sequential floating forward selection algorithm [45] is chosen to select out features for each modality.”
MethodRegression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 1×
“The popular lasso algorithm [33] aimed at encouraging the sparsity of feature coefficients by adding an additional L1-norm penalty on the widely used least squares loss.”
MethodModel Selection and Estimation in Regression with Grouped Variables
Yuan, M., & Lin, Y. (2006) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00532.x · Cited by 7,261 · cited 1×
“The group structure of the entire feature vector is considered in group lasso [35].”
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 3×
“Traditionally, researchers attempt to recognize human activity only from accelerometer data [1, 2, 3] or other data (e.g., electrocardiogram [4]).”
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 3×
“Traditionally, researchers attempt to recognize human activity only from accelerometer data [1, 2, 3] or other data (e.g., electrocardiogram [4]).”
BackgroundProceedings of the International Joint Conference on Artificial Intelligence 2007
Bundy, A. (2007) · International Joint Conference on Artificial Intelligence · Cited by 2,761
Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy
Kuncheva, L. I., & Whitaker, C. J. (2003) · Machine Learning · doi:10.1023/a:1022859003006 · Cited by 2,335
Activity recognition from accelerometer data
Ravi, N., Dandekar, N., Mysore, P., & Littman, M. L. (2005) · Innovative Applications of Artificial Intelligence · Cited by 1,775
Self-taught learning: transfer learning from unlabeled data
Raina, R., Battle, A., Lee, H., Packer, B., & Ng, A. Y. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273592 · Cited by 1,510 · cited 1×
“Sparse representation based feature selection can efficiently obtain a small subset from a large real world dataset, and meanwhile presents the importance of each type of features as sparsity coefficients [31, 32].”
BackgroundIntroducing a New Benchmarked Dataset for Activity Monitoring
Reiss, A., & Stricker, D. (2012) · 2012 16th International Symposium on Wearable Computers · doi:10.1109/iswc.2012.13 · Cited by 1,456 · cited 3×
“More importantly, the complexity of the classification problem would significantly increase in this way [48].”
BackgroundMethod
Research works printed but not linked: 10
- Subramanya A., 2006, Proceedings of the 22nd Conference on Uncertainty in Artificial Intelligence
- Yang J. B., 2015, Proceedings of International Joint Conference on Artificial Intelligence
- Krishnan N., 2008, Proceedings of Sensors, Signals and Information Processing Workshop
- Chen H., 2008, Diversity and regularization in neural network ensembles
- Yu Y., 2011, Proceedings of International Joint Conference on Artificial Intelligence
- 10.5555/1795114.1795154 · doi:10.5555/1795114.1795154
- Romaszko L., 2013, Workshop on Challenges in Representation Learning, ICML
- Skalak D.B., 1996, Proceedings of AAAI, Integrating Multiple Learned Models Workshop
- LeCun Y., 2012, Efficient backprop. Neural networks: Tricks of the Trade
- Liu J., 2009, Ye
Cited by
Deep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690
“y blending the recognition results from each modality as well. A range of ensemble approaches have been developed for fusing recognition results to yield an overall inference. For example, Guo et al. [52] proposed to use MLPs to create a base classifier for each sensing modality and incorporate all classifiers by assi…”
BackgroundMethodA Semisupervised Recurrent Convolutional Attention Model for Human Activity Recognition
Chen, K., Yao, L., Zhang, D., Wang, X., Chang, X., & Nie, F. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2927224 · Cited by 368
“Most existing works follow a supervised learning approach [3], [4], thus requiring a significant amount of training data to recognize meaningful activities.”
BackgroundResultDeep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314
“y blending the recognition results from each modality as well. A range of ensemble approaches have been developed for fusing recognition results to yield an overall inference. For example, Guo et al. [52] proposed to use MLPs to create a base classifier for each sensing modality and incorporate all classifiers by assi…”
BackgroundMethodImaging and fusing time series for wearable sensor-based human activity recognition
Qin, Z., Zhang, Y., Meng, S., Qin, Z., & Choo, K.-K. R. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.06.014 · Cited by 309
“Acc + Gyro Acc + Magn Acc + Gyro+Magn FEM + SVM [35] 0.671 0.708 0.708 AStack(CEM) [36] 0.700 0.732 0.712 FEM + MKL [37] 0.878 0.876 0.896 MARCEL [34] 0.900 0.917 0.919 FCN [38] 0.912 0.949 0.963 LSTM [39] 0.927 0.920 0.927 Our Method (GASF) 0.985 0.985 0.992 Our Method (GADF) 0.985 0.985 0.992 the…”
BackgroundInfluentialMultimodal Deep Learning for Activity and Context Recognition
Radu, V., Tong, C., Bhattacharya, S., Lane, N. D., Mascolo, C., Marina, M. K., & Kawsar, F. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3161174 · Cited by 281
“These features are used to perform sensor fusion following two strategies: Feature Concatenation (such as in [9, 28]) that treat features uniformly irrespective of their sensing modality to produce a single feature vector for classification; and Ensemble Classifiers (applied in [22, 72]) in which outputs of classifier…”
MethodInfluential
Metadata
- Authors
- Guo, H., Chen, L., Peng, L., & Chen, G.
- Affiliations
- Zhejiang University (CN)
- Venue
- Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
- Publisher
- ACM
- Published
- 2016-09-12
- Pages
- 1112-1123
- OpenAlex
- W2512840713
- Cited by
- 83
- References
- 48
- Citations by year
- 2026: 3 · 2025: 6 · 2024: 11 · 2023: 4 · 2022: 12 · 2021: 12 · 2020: 15 · 2019: 9 · 2018: 9 · 2017: 2
- FWCI
- 2.31
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Keywords
- human activity recognition, wearable sensors, multimodal fusion, ensemble classifiers, classifier diversity, unlabeled data, sparse group lasso, classifier weighting, heart rate, accelerometer
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble. https://app.cochat.ai/papers/10.1145/2971648.2971708
- The paper
- Guo, H., Chen, L., Peng, L., & Chen, G. (2016). Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble. Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. https://doi.org/10.1145/2971648.2971708
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.