Machine learning for grasping recognition using wearable sensors

Graciela Rodriguez Vega; Dora Aydee Rodríguez Vega

doi:10.31637/epsir-2025-1205

Autores/as

Graciela Rodriguez Vega Universidad de Sonora https://orcid.org/0000-0001-7366-1107
Dora Aydee Rodríguez Vega Universidad Politécnica de Sinaloa https://orcid.org/0000-0002-6521-7978

DOI:

https://doi.org/10.31637/epsir-2025-1205

Palabras clave:

Grasp recognition, Hand motion analysis, Wearable sensors, Windowing, Human behavior inference, Segmentation, Traditional classifiers, F-Score

Resumen

Introduction: The objective is to evaluate the traditional classifiers for the identification of the grasp while doing different jobs, in order to obtain information that can be used in the diagnostic of the physical work requirements and job design. Methodology: The analysis considered different combinations of the data acquired from inertial and force resistive sensors: a) acceleration and resistive force sensors, b) acceleration, angular velocity and resistive force sensors c) acceleration, angular velocity, magnetic fields, and resistive force sensors. Different combinations of window and step sizes were selected with two overlap options: 50% and greater than 50%. Traditional classification models were trained: support vector machines, ensembles, Naive-Bayes algorithm. Results: Results demonstrate that the window size that presented optimal performance in the present study was 3 seconds with an overlap greater than 50%, the window size is greater than that suggested in the literature, which ranges from 0.75 to 2.25 seconds. Conclusions: The accuracy and F-score metrics for the different window-step combinations are presented, both metrics indicate that the models trained through Support Vector Machine have the best performance (90 %) with the combination of acceleration, angular velocity, and resistive force sensor.

Descargas

Los datos de descargas todavía no están disponibles.

Biografía del autor/a

Graciela Rodriguez Vega, Universidad de Sonora

Industrial Engineer by the TecNM/Instituto Tecnológico de Los Mochis. Master of Science in Industrial Engineering from the TecNM/Instituto Tecnológico de Hermosillo. PhD in Information Sciences from the Universidad Autónoma de Sinaloa. She is a Full-Time Research Professor at the University of Sonora and a member of the National System of Researchers in the candidate category. She has worked in the area of Occupational Health, mainly in Ergonomics and Anthropometry, as well as in Machine Learning and Ergonomic Risk Level Prediction.

Dora Aydee Rodríguez Vega, Universidad Politécnica de Sinaloa

Dora Aydee Rodríguez Vega has a degree in Engineering, a Master of Science in Electronic Engineering with a specialisation in Image Processing and a PhD in Information Sciences. She has worked as a Full-Time Professor in the Mechatronics Engineering programme at the Polytechnic University of Sinaloa since 2005. She has a desirable PRODEP profile since 2007, is a member of the Sinaloan System of Researchers and Technologists in the Researcher category and a member of the National System of Researchers in the candidate category. Her line of research is the imitation of movements in humanoid robots, which includes the capture and interpretation of movements and their reproduction in humanoid robots.

Citas

Achumba, I. E., Bersch, S., Khusainov, R., Azzi, D., & Kamalu, U. (2012). Activity Classification, 427-430. DOI: https://doi.org/10.1109/HealthCom.2012.6379453

Anthony, G., Gregg, H., & Tshilidzi, M. (2007). Image classification using SVMs: One-Against-One Vs One-against-All. 28th Asian Conference on Remote Sensing 2007, ACRS 2007, 2, 801-806.

Armstrong, T. J., Foulke, J. A., Joseph, B. S., & Goldstein, S. A. (1982). Investigation of cumulative trauma disorders in a poultry processing plant. American Industrial Hygiene Association Journal, 43(2), 103-116. https://doi.org/10.1080/15298668291409433 DOI: https://doi.org/10.1080/15298668291409433

Baldominos, A., Cervantes, A., Saez, Y., & Isasi, P. (2019). A comparison of machine learning and deep learning techniques for activity recognition using mobile devices. Sensors (Switzerland), 19(3). https://doi.org/10.3390/s19030521 DOI: https://doi.org/10.3390/s19030521

Banos, O., Galvez, J. M., Damas, M., Pomares, H., & Rojas, I. (2014). Window size impact in human activity recognition. Sensors (Switzerland), 14(4), 6474-6499. https://doi.org/10.3390/s140406474 DOI: https://doi.org/10.3390/s140406474

Barr, A. E., Barbe, M. F., & Clark, B. D. (2004). Work-Related Musculoskeletal Disorders of the Hand and Wrist: Epidemiology, Pathophysiology, and Sensorimotor Changes. Journal of Orthopaedie & Sports Physical Therapy, 34(10), 610-627. DOI: https://doi.org/10.2519/jospt.2004.34.10.610

Bevan, S. (2015). Economic impact of musculoskeletal disorders (MSDs) on work in Europe. Best Practice and Research: Clinical Rheumatology, 29(3), 356-373. https://doi.org/10.1016/j.berh.2015.08.002 DOI: https://doi.org/10.1016/j.berh.2015.08.002

Bulling, A., Blanke, U. L. F., & Schiele, B. (2014). A Tutorial on Human Activity Recognition Using Body-Worn, 46(3), 1-33. DOI: https://doi.org/10.1145/2499621

Chandra Sen, P., Hajra, M., & Ghosh, M. (2020). Supervised Classification Algorithms in Machine Learning: A Survey and Review. In J. Mandal, and D. Bhattacharya (Eds.). Emerging Technology in Modelling and Graphics. Advances in Intelligent Systems and Computing (pp. 99-111). Springer Singapore. DOI: https://doi.org/10.1007/978-981-13-7403-6_11

https://doi.org/10.1007/978-981-13-7403-6 DOI: https://doi.org/10.1007/978-981-13-7403-6

Chen, Y., & Shen, C. (2017). Performance Analysis of Smartphone-Sensor Behavior for Human Activity Recognition. IEEE Access, 5(c), 3095-3110. https://doi.org/10.1109/ACCESS.2017.2676168 DOI: https://doi.org/10.1109/ACCESS.2017.2676168

Feix, T., Bullock, I. M., & Dollar, A. M. (2014). Analysis of human grasping behavior: Object characteristics and grasp type. IEEE Transactions on Haptics, 7(3), 311-323. https://doi.org/10.1109/TOH.2014.2326871 DOI: https://doi.org/10.1109/TOH.2014.2326871

Feix, T., Romero, J., Schmiedmayer, H. B., Dollar, A. M., & Kragic, D. (2016). The GRASP Taxonomy of Human Grasp Types. IEEE Transactions on Human-Machine Systems, 46(1), 66-77. https://doi.org/10.1109/THMS.2015.2470657 DOI: https://doi.org/10.1109/THMS.2015.2470657

Figo, D., Diniz, P. C., Ferreira, D. R., & Cardoso, M. P. (2010). Preprocessing techniques for context recognition from accelerometer data. Pers Ubiquit Comput, 14, 645-662. https://doi.org/10.1007/s00779-010-0293-9 DOI: https://doi.org/10.1007/s00779-010-0293-9

Govaerts, R., Tassignon, B., Ghillebert, J., Serrien, B., De Bock, S., Ampe, T., El Makrini, I., Vanderborght, B., Meeusen, R., & De Pauw, K. (2021). Prevalence and incidence of work-related musculoskeletal disorders in secondary industries of 21st century Europe: a systematic review and meta-analysis. BMC Musculoskeletal Disorders, 22(1), 1-30. https://doi.org/10.1186/s12891-021-04615-9 DOI: https://doi.org/10.1186/s12891-021-04615-9

Jianwei, N., Yiling, H., Muyuan, L., Xin, Z., Linghua, R., Chuzhi, Ch., & Baoqin, Z. (2010). A comparative study on application of data mining technique in human shape clustering: Principal component analysis vs. Factor analysis. 2010 5th IEEE Conference on Industrial Electronics and Applications, 2014-2018. https://doi.org/10.1109/ICIEA.2010.5515577 DOI: https://doi.org/10.1109/ICIEA.2010.5515577

Kubota, A., Iqbal, T., Shah, J. A., & Riek, L. D. (2019). Activity recognition in manufacturing: The roles of motion capture and sEMG+inertial wearables in detecting fine vs gross motion. Proceedings - IEEE International Conference on Robotics and Automation, 6533-6539. https://doi.org/10.1109/ICRA.2019.8793954 DOI: https://doi.org/10.1109/ICRA.2019.8793954

Lapucci, T., Troiano, L., Carobbi, C., & Capineri, L. (2021). Soft and hard iron compensation for the compasses of an operational towed hydrophone array without sensor motion by a helmholtz coil. Sensors, 21(23), 8104. https://doi.org/10.3390/s21238104 DOI: https://doi.org/10.3390/s21238104

Lara, D., & Labrador, M. A. (2013). A Survey on Human Activity Recognition using. IEEE Communications Surveys & Tutorials, 15(3), 1192-1209. https://doi.org/10.1109/SURV.2012.110112.00192 DOI: https://doi.org/10.1109/SURV.2012.110112.00192

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539 DOI: https://doi.org/10.1038/nature14539

Lima, W. S., Souto, E., El-khatib, K., Jalali, R., & Gama, J. (2019). Human Activity Recognition Using Inertial Sensors in a Smartphone : An Overview. Sensors, 19(14), 3213; https://doi.org/10.3390/s19143213 DOI: https://doi.org/10.3390/s19143213

Moschetti, A., Fiorini, L., Esposito, D., Dario, P., & Cavallo, F. (2016). Recognition of daily gestures with wearable inertial rings and bracelets. Sensors, 16(8), 1341. https://doi.org/10.3390/s16081341 DOI: https://doi.org/10.3390/s16081341

Ni, Q., Patterson, T., Cleland, I., & Nugent, C. (2016). Dynamic detection of window starting positions and its implementation within an activity recognition framework. Journal of Biomedical Informatics, 62, 171-180. https://doi.org/10.1016/j.jbi.2016.07.005 DOI: https://doi.org/10.1016/j.jbi.2016.07.005

Nur, N. M., Dawal, S. Z., & Dahari, M. (2014). The Prevalence of Work Related Musculoskeletal Disorders Among Workers Performing Industrial Repetitive Tasks in the Automotive Manufacturing Companies. In Proceedings of the 2014 International Conference on Industrial Engineering and Operations Management Bali, 1-8. http://ieomsociety.org/ieom2014/pdfs/303.pdf

Nweke, H. F., Teh, Y. W., Al-garadi, M. A., & Alo, U. R. (2018). Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: State of the art and research challenges. Expert Systems with Applications, 105, 233-261. https://doi.org/10.1016/j.eswa.2018.03.056 DOI: https://doi.org/10.1016/j.eswa.2018.03.056

Saez, Y., Baldominos, A., & Isasi, P. (2016). A Comparison Study of Classifier Algorithms for Cross-Person Physical Activity Recognition. Sensors (Basel, Switzerland), 17(1), 66. https://doi.org/10.3390/s17010066 DOI: https://doi.org/10.3390/s17010066

Shoaib, M., Bosch, S., Durmaz Incel, O., Scholten, H., & Havinga, P. J. M. (2014). Fusion of smartphone motion sensors for physical activity recognition. Sensors, 14(6). https://doi.org/10.3390/s140610146 DOI: https://doi.org/10.3390/s140610146

Xue, Y., Ju, Z., Xiang, K., Chen, J., & Liu, H. (2019). Multimodal Human Hand Motion Sensing and Analysis-A Review. IEEE Transactions on Cognitive and Developmental Systems, 11(2), 162-175. https://doi.org/10.1109/TCDS.2018.2800167 DOI: https://doi.org/10.1109/TCDS.2018.2800167

Zou, Y, Liu, H. & Zhang, J. (2019). Real-Time Grasp Type Recognition Using Leap Motion Controller. In: Yu, H., Liu, J., Liu, L., Ju, Z., Liu, Y., Zhou, D. (Eds.). Intelligent Robotics and Applications. ICIRA 2019. Lecture Notes in Computer Science (pp.472-480). https://doi.org/10.1007/978-3-030-27535-8_42 DOI: https://doi.org/10.1007/978-3-030-27535-8_42