{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T21:31:57Z","timestamp":1779399117500,"version":"3.53.1"},"reference-count":48,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T00:00:00Z","timestamp":1620604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903180"],"award-info":[{"award-number":["61903180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Although commercial motion-capture systems have been widely used in various applications, the complex setup limits their application scenarios for ordinary consumers. To overcome the drawbacks of wearability, human posture reconstruction based on a few wearable sensors have been actively studied in recent years. In this paper, we propose a deep-learning-based sparse inertial sensor human posture reconstruction method. This method uses bidirectional recurrent neural network (Bi-RNN) to build an a priori model from a large motion dataset to build human motion, thereby the low-dimensional motion measurements are mapped to whole-body posture. To improve the motion reconstruction performance for specific application scenarios, two fundamental problems in the model construction are investigated: training data selection and sparse sensor placement. The problem of deep-learning training data selection is to select independent and identically distributed (IID) data for a certain scenario from the accumulated imbalanced motion dataset with sufficient information. We formulate the data selection into an optimization problem to obtain continuous and IID data segments, which comply with a small reference dataset collected from the target scenario. A two-step heuristic algorithm is proposed to solve the data selection problem. On the other hand, the optimal sensor placement problem is studied to exploit most information from partial observation of human movement. A method for evaluating the motion information amount of any group of wearable inertial sensors based on mutual information is proposed, and a greedy searching method is adopted to obtain the approximate optimal sensor placement of a given sensor number, so that the maximum motion information and minimum redundancy is achieved. Finally, the human posture reconstruction performance is evaluated with different training data and sensor placement selection methods, and experimental results show that the proposed method takes advantages in both posture reconstruction accuracy and model training time. In the 6 sensors configuration, the posture reconstruction errors of our model for walking, running, and playing basketball are 7.25\u00b0, 8.84\u00b0, and 14.13\u00b0, respectively.<\/jats:p>","DOI":"10.3390\/e23050588","type":"journal-article","created":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T10:49:51Z","timestamp":1620643791000},"page":"588","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Training Data Selection and Optimal Sensor Placement for Deep-Learning-Based Sparse Inertial Sensor Human Posture Reconstruction"],"prefix":"10.3390","volume":"23","author":[{"given":"Zhaolong","family":"Zheng","sequence":"first","affiliation":[{"name":"Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China"},{"name":"Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Ma","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China"},{"name":"Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weichao","family":"Yan","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China"},{"name":"Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Sports Engineering, Beijing Sport University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zaiyue","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China"},{"name":"Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Mu\u00f1oz, J.E., Chavarriaga, R., Villada, J.F., and SebastianLopez, D. (2014, January 10\u201313). BCI and motion capture technologies for rehabilitation based on videogames. Proceedings of the IEEE Global Humanitarian Technology Conference (GHTC 2014), San Jose, CA, USA.","DOI":"10.1109\/GHTC.2014.6970312"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Jie, G., Guiling, C., Lin, H., and Dong, Z. (2010, January 26\u201328). Application research on motion capture system data reuse in virtual reality environment. Proceedings of the 2010 Second International Conference on Intelligent Human-Machine Systems and Cybernetics, Nanjing, China.","DOI":"10.1109\/IHMSC.2010.36"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Noiumkar, S., and Tirakoat, S. (2013, January 4\u20136). Use of optical motion capture in sports science: A case study of golf swing. Proceedings of the 2013 International Conference on Informatics and Creative Multimedia, Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICICM.2013.58"},{"key":"ref_4","unstructured":"Roetenberg, D., Luinge, H., and Slycke, P. (2021, May 08). Xsens Mvn: Full 6 Dof Human Motion Tracking Using Miniature Inertial Sensors. Xsens Motion Technologies BV. Technical Report. Available online: http:\/\/human.kyst.com.tw\/upload\/pdfs120702543998066.pdf."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1167\/2.5.2","article-title":"Decomposing biological motion: A framework for analysis and synthesis of human gait patterns","volume":"2","author":"Troje","year":"2002","journal-title":"J. Vis."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1523\/JNEUROSCI.20-03-01066.2000","article-title":"Human arm movements described by a low-dimensional superposition of principal components","volume":"20","author":"Sanger","year":"2000","journal-title":"J. Neurosci. Off. J. Soc. Neurosci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1145\/1015706.1015754","article-title":"Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces","volume":"23","author":"Safonova","year":"2004","journal-title":"ACM Trans. Graph."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Marcard, T., Rosenhahn, B., Black, M., and Pons-Moll, G. (2017). Sparse inertial poser: Automatic 3D human pose estimation from sparse iMUs. Computer Graphics Forum, Wiley.","DOI":"10.1111\/cgf.13131"},{"key":"ref_9","first-page":"1","article-title":"Deep inertial poser: Learning to reconstruct human pose from sparse inertial measurements in real time","volume":"37","author":"Huang","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2138","DOI":"10.3390\/s16122138","article-title":"Estimation of full-bod poses using only five inertial sensors: An eager or lazy learning approach?","volume":"16","author":"Wouda","year":"2016","journal-title":"Sensors"},{"key":"ref_11","unstructured":"Bertsekas, D.P., and Tsitsiklis, J.N. (2008). Introduction to Probability, Athena Scientific. [2nd ed.]."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"18813","DOI":"10.3390\/s150818813","article-title":"Upper limb kinematics using inertial and magnetic Sensors: Comparison of Sensor-to-Segment calibrations","volume":"15","author":"Bouvier","year":"2015","journal-title":"Sensors"},{"key":"ref_13","unstructured":"Taetz, B., Bleser, G., and Miezal, M. (2016, January 5\u20138). Towards self-calibrating inertial body motion capture. Proceedings of the 2016 International Conference on Information Fusion (FUSION), Heidelberg, Germany."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1109\/JBHI.2016.2639537","article-title":"Alignment-free, self-calibrating elbow angles measurement using inertial sensors","volume":"21","author":"Schauer","year":"2017","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Miezal, M., Taetz, B., and Bleser, G. (June, January 29). Real-time inertial lower body kinematics and ground contact estimation at anatomical foot points for agile human locomotion. Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore.","DOI":"10.1109\/ICRA.2017.7989371"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"79","DOI":"10.3182\/20140824-6-ZA-1003.02252","article-title":"An optimization-based approach to human body motion capture using inertial sensors","volume":"47","author":"Kok","year":"2014","journal-title":"IFAC Proc. Vol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1145\/1276377.1276421","article-title":"Practical motion capture in everyday surroundings","volume":"26","author":"Vlasic","year":"2007","journal-title":"ACM Trans. Graph."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Trumble, M., Gilbert, A., Hilton, A., and Collomosse, J. (2018, January 8\u201314). Deep autoencoder for combined human pose estimation and body model upscaling. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01249-6_48"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Pons-Moll, G., Baak, A., Gall, J., Leal-Taixe, L., Muller, M., Seidel, H.P., and Rosenhahn, B. (2011, January 6\u201313). Outdoor human motion capture using inverse kinematics and von mises-fisher sampling. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126375"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TPAMI.2016.2522398","article-title":"Human pose estimation from video and IMUs","volume":"38","author":"Marcard","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Andrews, S., Huerta, I., Komura, T., Sigal, L., and Mitchell, K. (2016, January 12\u201313). Real-time physics-based motion capture with sparse sensors. Proceedings of the 13th European conference on visual media production (CVMP 2016), London, UK.","DOI":"10.1145\/2998559.2998564"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Liu, H., Wei, X., Chai, J., Ha, I., and Rhee, T. (2011, January 18\u201320). Realtime human motion control with a small number of inertial sensors. Proceedings of the Symposium on Interactive 3D Graphics and Games, San Francisco, CA, USA.","DOI":"10.1145\/1944745.1944768"},{"key":"ref_23","unstructured":"Yang, Y., Lu, Y., Yao, M., Xia, Y., and Hao, Y. (2011, January 6\u20137). Training data selection for short term load forecasting. Proceedings of the 2011 Third International Conference on Measuring Technology and Mechatronics Automation, Shanghai, China."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Abe, N., Khardon, R., and Zeugmann, T. (2001). A random sampling technique for training support vector machines. Algorithmic Learning Theory, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/3-540-45583-3"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ferragut, E.M., and Laska, J. (2012, January 12\u201315). Randomized sampling for large data application of SVM. Proceedings of the 2012 11th International Conference on Machine Learning and Applications, Boca Raton, FL, USA.","DOI":"10.1109\/ICMLA.2012.65"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Tsagalidis, E., and Evangelidis, G. (2010, January 10\u201312). The effect of training set selection in meteorological data mining. Proceedings of the 2010 14th Panhellenic Conference on Informatics, Tripoli, Greece.","DOI":"10.1109\/PCI.2010.37"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., and Mangasarian, O.L. (2001, January 5\u20137). RSVM: Reduced support vector machines. Proceedings of the 2001 SIAM International Conference on Data Mining, Chicago, IL, USA.","DOI":"10.1137\/1.9781611972719.13"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TNN.2006.883722","article-title":"Reduced support vector machines: A statistical theory","volume":"18","author":"Lee","year":"2007","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"897","DOI":"10.3233\/IDA-2012-00558","article-title":"Fast classification for large data sets via random selection clustering and support vector machines","volume":"16","author":"Li","year":"2012","journal-title":"Intell. Data Anal."},{"key":"ref_30","unstructured":"Zhai, J.H., Xui, H.Y., Zhang, S.F., Li, N., and Li, T. (2012, January 15\u201317). Instance selection based on supervised clustering. Proceedings of the 2012 International Conference on Machine Learning and Cybernetics, Xi\u2019an, China."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Koskim\u00e4ki, H., Juutilainen, I., Laurinen, P., and R\u00f6ning, J. (2008, January 1\u20138). Two-level clustering approach to training data instance selection: A case study for the steel industry. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks, Hong Kong, China.","DOI":"10.1109\/IJCNN.2008.4634228"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Kaneda, Y., Zhao, Q., and Liu, Y. (2016, January 6\u20139). On-line training with guide data: Shall we select the guide data randomly or based on cluster centers?. Proceedings of the 2016 IEEE Symposium Series on Computational Intelligence (SSCI), Athens, Greece.","DOI":"10.1109\/SSCI.2016.7850192"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zheng, J., Yang, W., and Li, X. (2017, January 5\u20139). Training data reduction in deep neural networks with partial mutual information based feature selection and correlation matching based active learning. Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA.","DOI":"10.1109\/ICASSP.2017.7952579"},{"key":"ref_34","unstructured":"Liu, S.H., Chu, F.H., Lin, S.H., Lee, H.S., and Chen, B. (2007, January 9\u201313). Training data selection for improving discriminative training of acoustic models. Proceedings of the 2007 IEEE Workshop on Automatic Speech Recognition Understanding (ASRU), Kyoto, Japan."},{"key":"ref_35","unstructured":"Moore, R., and Lewis, W. (2010, January 11\u201316). Intelligent selection of language model training data. Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Uppsala, Sweden."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Cole, C.A., Thrasher, J.F., Strayer, S.M., and Valafar, H. (2017, January 16\u201319). Resolving ambiguities in accelerometer data due to location of sensor on wrist in application to detection of smoking gesture. Proceedings of the 2017 IEEE EMBS International Conference on Biomedical Health Informatics (BHI), Orlando, FL, USA.","DOI":"10.1109\/BHI.2017.7897312"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Orha, I., and Oniga, S. (2014, January 23\u201326). Study regarding the optimal sensors placement on the body for human activity recognition. Proceedings of the 2014 IEEE 20th International Symposium for Design and Technology in Electronic Packaging (SIITME), Bucharest, Romania.","DOI":"10.1109\/SIITME.2014.6967028"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Dobrucal\u0131, O., and Barshan, B. (2013). Sensor-activity relevance in human activity recognition with wearable motion sensors and mutual information criterion. Information Sciences and Systems 2013, Springer.","DOI":"10.1007\/978-3-319-01604-7_28"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ching, Y.T., Cheng, C.C., He, G.W., and Yang, Y.J. (2017, January 11\u201315). Full model for sensors placement and activities recognition. Proceedings of the UbiComp \u201917 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers, Maui, HI, USA.","DOI":"10.1145\/3123024.3123096"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Murao, K., Mogari, H., Terada, T., and Tsukamoto, M. (2013, January 8\u201312). Evaluation function of sensor position for activity recognition considering wearability. Proceedings of the 2013 ACM Conference on Pervasive and Ubiquitous Computing Adjunct Publication, Zurich, Switzerland.","DOI":"10.1145\/2494091.2495983"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"9995","DOI":"10.3390\/s140609995","article-title":"Dealing with the effects of sensor displacement in wearable activity recognition","volume":"14","author":"Banos","year":"2014","journal-title":"Sensors"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MPRV.2014.73","article-title":"Sensor placement variations in wearable activity recognition","volume":"13","author":"Kunze","year":"2014","journal-title":"IEEE Pervasive Comput."},{"key":"ref_43","unstructured":"(2021, May 09). Perception Neuron Studio System Landing Page. Available online: https:\/\/neuronmocap.com\/perception-neuron-studio-system."},{"key":"ref_44","unstructured":"Bahdanau, D., Cho, K., and Bengio, Y. (2015, January 7\u20139). Neural machine translation by jointly learning to align and translate. Proceedings of the 2015 International Conference on Learning Representations (ICLR), San Diego, CA, USA."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1142\/S0219720005001004","article-title":"Minimum redundancy feature selection from microarray gene expression data","volume":"3","author":"Ding","year":"2005","journal-title":"J. Bioinform. Comput. Biol."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1518","DOI":"10.1126\/science.1205438","article-title":"Detecting novel associations in large data sets","volume":"334","author":"Reshef","year":"2011","journal-title":"Science"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.1109\/TIM.2004.834070","article-title":"PCA-based feature selection scheme for machine defect classification","volume":"53","author":"Malhi","year":"2004","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_48","unstructured":"Mixamo (2021, May 09). Available online: https:\/\/www.mixamo.com\/#\/?page=1&type=Character."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/5\/588\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:58:44Z","timestamp":1760162324000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/5\/588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,10]]},"references-count":48,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["e23050588"],"URL":"https:\/\/doi.org\/10.3390\/e23050588","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,10]]}}}