{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T15:14:20Z","timestamp":1761664460570,"version":"build-2065373602"},"reference-count":41,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T00:00:00Z","timestamp":1663113600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Faculty of Electrical Engineering, Mechanical Engineering, and Naval Architecture, University of Split, Croatia"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computation"],"abstract":"<jats:p>Gesture recognition is a topic in computer science and language technology that aims to interpret human gestures with computer programs and many different algorithms. It can be seen as the way computers can understand human body language. Today, the main interaction tools between computers and humans are still the keyboard and mouse. Gesture recognition can be used as a tool for communication with the machine and interaction without any mechanical device such as a keyboard or mouse. In this paper, we present the results of a comparison of eight different machine learning (ML) classifiers in the task of human hand gesture recognition and classification to explore how to efficiently implement one or more tested ML algorithms on an 8-bit AVR microcontroller for on-line human gesture recognition with the intention to gesturally control the mobile robot. The 8-bit AVR microcontrollers are still widely used in the industry, but due to their lack of computational power and limited memory, it is a challenging task to efficiently implement ML algorithms on them for on-line classification. Gestures were recorded by using inertial sensors, gyroscopes, and accelerometers placed at the wrist and index finger. One thousand and eight hundred (1800) hand gestures were recorded and labelled. Six important features were defined for the identification of nine different hand gestures using eight different machine learning classifiers: Decision Tree (DT), Random Forests (RF), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM) with linear kernel, Na\u00efve Bayes classifier (NB), K-Nearest Neighbours (KNN), and Stochastic Gradient Descent (SGD). All tested algorithms were ranged according to Precision, Recall, and F1-score (abb.: P-R-F1). The best algorithms were SVM (P-R-F1: 0.9865, 0.9861, and 0.0863), and RF (P-R-F1: 0.9863, 0.9861, and 0.0862), but their main disadvantage is their unusability for on-line implementations in 8-bit AVR microcontrollers, as proven in the paper. The next best algorithms have had only slightly poorer performance than SVM and RF: KNN (P-R-F1: 0.9835, 0.9833, and 0.9834) and LR (P-R-F1: 0.9810, 0.9810, and 0.9810). Regarding the implementation on 8-bit microcontrollers, KNN has proven to be inadequate, like SVM and RF. However, the analysis for LR has proved that this classifier could be efficiently implemented on targeted microcontrollers. Having in mind its high F1-score (comparable to SVM, RF, and KNN), this leads to the conclusion that the LR is the most suitable classifier among tested for on-line applications in resource-constrained environments, such as embedded devices based on 8-bit AVR microcontrollers, due to its lower computational complexity in comparison with other tested algorithms.<\/jats:p>","DOI":"10.3390\/computation10090159","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T20:50:45Z","timestamp":1663188645000},"page":"159","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Comparison and Evaluation of Machine Learning-Based Classification of Hand Gestures Captured by Inertial Sensors"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9607-1791","authenticated-orcid":false,"given":"Ivo","family":"Stan\u010di\u0107","sequence":"first","affiliation":[{"name":"Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture\u2014FESB, University of Split, 21000 Split, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josip","family":"Musi\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture\u2014FESB, University of Split, 21000 Split, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tamara","family":"Gruji\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture\u2014FESB, University of Split, 21000 Split, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8441-0693","authenticated-orcid":false,"given":"Mirela Kundid","family":"Vasi\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, Computing and Electrical Engineering, University of Mostar, 88000 Mostar, Bosnia and Herzegovina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mirjana","family":"Bonkovi\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture\u2014FESB, University of Split, 21000 Split, Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1504\/IJCVR.2017.084991","article-title":"An efficient interpretation of hand gestures to control smart interactive television","volume":"7","author":"Vishwakarma","year":"2017","journal-title":"Int. J. Comput. Vis. Robot."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.engappai.2017.08.013","article-title":"Gesture recognition system for real-time mobile robot control based on inertial sensors and motion strings","volume":"66","year":"2017","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Oudah, M., Al-Naji, A., and Chahl, J. (2020). Hand gesture recognition based on computer vision: A review of techniques. J. Imaging, 6.","DOI":"10.3390\/jimaging6080073"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s11265-015-1090-5","article-title":"Real-time motion-based hand gestures recognition from time-of-flight video","volume":"86","author":"Molina","year":"2017","journal-title":"J. Signal Process. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chen, Y.-L., Hwang, W.-J., Tai, T.-M., and Cheng, P.-S. (2022). Sensor-based hand gesture detection and recognition by key intervals. Appl. Sci., 12.","DOI":"10.3390\/app12157410"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chu, Y.C., Jhang, Y.J., Tai, T.M., and Hwang, W.J. (2020). Recognition of hand gesture sequences by accelerometers and gyroscopes. Appl. Sci., 10.","DOI":"10.3390\/app10186507"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"6000704","DOI":"10.1109\/LSENS.2018.2864963","article-title":"Sensor-based continuous hand gesture recognition by long short-term memory","volume":"2","author":"Tai","year":"2018","journal-title":"IEEE Sens. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"6425","DOI":"10.1109\/JSEN.2016.2581023","article-title":"Continuous hand gestures recognition technique for human\u2013machine interaction using accelerometer and gyroscope sensors","volume":"16","author":"Gupta","year":"2016","journal-title":"IEEE Sens. J."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1007\/978-3-319-09903-3_19","article-title":"Inertial gesture recognition with BLSTM-RNN","volume":"Volume 4","author":"Lefebvre","year":"2015","journal-title":"Artificial Neural Networks"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Jaramillo-Y\u00e1nez, A., Benalc\u00e1zar, M.E., and Mena-Maldonado, E. (2020). Real-time hand gesture recognition using surface electromyography and machine learning: A systematic literature review. Sensors, 20.","DOI":"10.3390\/s20092467"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kundid Vasi\u0107, M., Gali\u0107, I., and Vasi\u0107, D. (2015, January 28\u201330). Human action identification and search in video files. Proceedings of the 57th International Symposium on Electronics in Marine\u2014ELMAR, Zadar, Croatia.","DOI":"10.1109\/ELMAR.2015.7334534"},{"key":"ref_12","first-page":"249","article-title":"Design and implementation of a natural user interface using hand gesture recognition method","volume":"10","author":"Choondal","year":"2013","journal-title":"Int. J. Innov. Technol. Explor. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1109\/JSEN.2011.2166953","article-title":"MEMS Accelerometer based nonspecific-user hand gesture recognition","volume":"12","author":"Xu","year":"2012","journal-title":"IEEE Sens. J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5809769","DOI":"10.1155\/2018\/5809769","article-title":"Kinect sensor-based long-distance hand gesture recognition and fingertip detection with depth information","volume":"2018","author":"Ma","year":"2018","journal-title":"J. Sens."},{"key":"ref_15","first-page":"407","article-title":"Hand gesture recognition for Kinect v2 sensor in the near distance where depth data are not provided","volume":"10","author":"Kim","year":"2016","journal-title":"Int. J. Softw. Eng. Its Appl."},{"key":"ref_16","first-page":"1","article-title":"Real-time hands detection in depth image by using distance with Kinect camera","volume":"4","author":"Karbasi","year":"2015","journal-title":"Int. J. Internet Things"},{"key":"ref_17","unstructured":"Li, Y. (2012, January 22\u201324). Hand gesture recognition using Kinect. Proceedings of the 2012 IEEE International Conference on Computer Science and Automation Engineering, Beijing, China."},{"key":"ref_18","unstructured":"Filaretov, V., Yukhimetsa, D., and Mursalimov, E. (2014, January 26\u201329). The universal onboard information-control system for mobile robots. Proceedings of the 25th DAAAM International Symposium on Intelligent Manufacturing and Automation, Vienna, Austria."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Riek, L., Rabinowitch, T., Bremner, P., Pipe, A., and Fraser, M. (2010, January 2\u20135). Cooperative Gestures: Effective signaling for humanoid robots. Proceedings of the 5th ACM\/IEEE International Conference on Human-Robot Interaction, Osaka, Japan.","DOI":"10.1109\/HRI.2010.5453266"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ajani, T.S., Imoize, A.L., and Atayero, A.A. (2021). An Overview of Machine Learning within Embedded and Mobile Devices\u2013Optimizations and Applications. Sensors, 21.","DOI":"10.3390\/s21134412"},{"key":"ref_21","first-page":"8083","article-title":"A smart building energy management using internet of things (IoT) and machine learning","volume":"83","author":"Mazlan","year":"2020","journal-title":"Test. Eng. Manag."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Cornetta, G., and Touhafi, A. (2021). Design and evaluation of a new machine learning framework for IoT and embedded devices. Electronics, 10.","DOI":"10.3390\/electronics10050600"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"106457","DOI":"10.1016\/j.compeleceng.2019.106457","article-title":"Toward energy efficient microcontrollers and Internet-of-Things systems","volume":"79","year":"2019","journal-title":"Comput. Electr. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Dudak, J., Kebisek, M., Gaspar, G., and Fabo, P. (2020, January 2\u20134). Implementation of machine learning algorithm in embedded devices. Proceedings of the 19th International Conference on Mechatronics\u2014Mechatronika (ME), Prague, Czech Republic.","DOI":"10.1109\/ME49197.2020.9286705"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Sakr, F., Bellotti, F., Berta, R., and De Gloria, A. (2020). Machine learning on mainstream microcontrollers. Sensors, 20.","DOI":"10.3390\/s20092638"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Saha, S.S., Sandha, S.S., and Srivastava, M. (IEEE Sens. J., 2022). Machine Learning for Microcontroller-Class Hardware\u2014A Review, IEEE Sens. J., accepted.","DOI":"10.1109\/JSEN.2022.3210773"},{"key":"ref_27","unstructured":"(2022, August 30). Application Ideas for 8-Bit Low-Pin-Count Microcontrollers. Available online: https:\/\/www.digikey.com\/en\/articles\/application-ideas-for-8-bit-low-pin-count-microcontrollers."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.3390\/s100201154","article-title":"Machine learning methods for classifying human physical activity from on-body accelerometers","volume":"10","author":"Mannini","year":"2010","journal-title":"Sensors"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Sousa Lima, W., Souto, E., El-Khatib, K., Jalali, R., and Gama, J. (2019). Human Activity Recognition Using Inertial Sensors in a Smartphone: An Overview. Sensors, 19.","DOI":"10.3390\/s19143213"},{"key":"ref_30","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J. (2008). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer. [2nd ed.]."},{"key":"ref_31","unstructured":"Wai, M.M.N. (2011, January 24\u201326). Classification based automatic information extraction. Proceedings of the 10th WSEAS International Conference on Communications, Canary Islands, Spain."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"McCullagh, P., and Nelder, J. (1989). Generalized Linear Models, CRC Press.","DOI":"10.1007\/978-1-4899-3242-6"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Izenman, A.J. (2013). Linear discriminant analysis. Modern Multivariate Statistical Techniques, Springer. Springer Texts in Statistics.","DOI":"10.1007\/978-0-387-78189-1_8"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"3","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Pardos, Z., and Heffernan, N. (2010, January 20\u201324). Modeling individualization in a Bayesian networks implementation of knowledge tracing. Proceedings of the International Conference UMAP, Big Island, HI, USA.","DOI":"10.1007\/978-3-642-13470-8_24"},{"key":"ref_36","unstructured":"Burkov, A. (2019). The Hundred-Page Machine Learning Book, Andriy Burkov."},{"key":"ref_37","unstructured":"Chen, J., and Melo, G.D. (June, January 31). Semantic information extraction for improved word embeddings. Proceedings of the NAACL-HLT, Denver, CO, USA."},{"key":"ref_38","unstructured":"(2022, July 01). Scikit-Learn: Machine Learning in Python. Available online: https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.linear_model.LogisticRegression.html#sklearn.linear_model.LogisticRegression."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_40","unstructured":"(2022, July 20). AIfES for Arduino. Available online: https:\/\/github.com\/Fraunhofer-IMS\/AIfES_for_Arduino."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1038\/s42256-021-00356-5","article-title":"Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors","volume":"3","author":"Coelho","year":"2021","journal-title":"Nat. Mach. Intell."}],"container-title":["Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-3197\/10\/9\/159\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:31:34Z","timestamp":1760142694000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-3197\/10\/9\/159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,14]]},"references-count":41,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["computation10090159"],"URL":"https:\/\/doi.org\/10.3390\/computation10090159","relation":{},"ISSN":["2079-3197"],"issn-type":[{"type":"electronic","value":"2079-3197"}],"subject":[],"published":{"date-parts":[[2022,9,14]]}}}