{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T20:47:21Z","timestamp":1784753241946,"version":"3.55.0"},"reference-count":56,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2021,3,9]],"date-time":"2021-03-09T00:00:00Z","timestamp":1615248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Recurrent Neural Networks (RNNs) are known for their ability to learn relationships within temporal sequences. Gated Recurrent Unit (GRU) networks have found use in challenging time-dependent applications such as Natural Language Processing (NLP), financial analysis and sensor fusion due to their capability to cope with the vanishing gradient problem. GRUs are also known to be more computationally efficient than their variant, the Long Short-Term Memory neural network (LSTM), due to their less complex structure and as such, are more suitable for applications requiring more efficient management of computational resources. Many of such applications require a stronger mapping of their features to further enhance the prediction accuracy. A novel Quaternion Gated Recurrent Unit (QGRU) is proposed in this paper, which leverages the internal and external dependencies within the quaternion algebra to map correlations within and across multidimensional features. The QGRU can be used to efficiently capture the inter- and intra-dependencies within multidimensional features unlike the GRU, which only captures the dependencies within the sequence. Furthermore, the performance of the proposed method is evaluated on a sensor fusion problem involving navigation in Global Navigation Satellite System (GNSS) deprived environments as well as a human activity recognition problem. The results obtained show that the QGRU produces competitive results with almost 3.7 times fewer parameters compared to the GRU.<\/jats:p>","DOI":"10.3390\/info12030117","type":"journal-article","created":{"date-parts":[[2021,3,9]],"date-time":"2021-03-09T12:08:01Z","timestamp":1615291681000},"page":"117","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["A Quaternion Gated Recurrent Unit Neural Network for Sensor Fusion"],"prefix":"10.3390","volume":"12","author":[{"given":"Uche","family":"Onyekpe","sequence":"first","affiliation":[{"name":"Research Centre for Data Science, Coventry University, Coventry CV1 5FB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6768-8394","authenticated-orcid":false,"given":"Vasile","family":"Palade","sequence":"additional","affiliation":[{"name":"Research Centre for Data Science, Coventry University, Coventry CV1 5FB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stratis","family":"Kanarachos","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Computing, Coventry University, Coventry CV1 5FB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8468-2998","authenticated-orcid":false,"given":"Stavros-Richard","family":"Christopoulos","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Computing, Coventry University, Coventry CV1 5FB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,3,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Purohit, H., Tanabe, R., Ichige, K., Endo, T., Nikaido, Y., Suefusa, K., and Kawaguchi, Y. (2019). MIMII dataset: Sound dataset for malfunctioning industrial machine investigation and inspection. arXiv.","DOI":"10.33682\/m76f-d618"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Tsang, G., Deng, J., and Xie, X. (2018). Recurrent neural networks for financial time-series modelling. Proceedings of the International Conference on Pattern Recognition, Beijing, China, 20\u201324 August 2018, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/ICPR.2018.8545666"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"24013","DOI":"10.1007\/s11042-019-08293-7","article-title":"Text-independent speaker recognition using LSTM-RNN and speech enhancement","volume":"79","author":"Nassar","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_4","first-page":"1","article-title":"RNN-based room scale hand motion tracking","volume":"Volume 19","author":"Mao","year":"2019","journal-title":"Proceedings of the 25th Annual International Conference on Mobile Computing and Networking, Los Cabos, Mexico, 21\u201325 October 2019"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Senturk, U., Yucedag, I., and Polat, K. (2018). Repetitive neural network (RNN) based blood pressure estimation using PPG and ECG signals. Proceedings of the ISMSIT 2018\u20142nd International Symposium on Multidisciplinary Studies and Innovative Technologies, Ankara, Turkey, 19\u201321 October 2018, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/ISMSIT.2018.8567071"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","author":"Rajkomar","year":"2018","journal-title":"NPJ Digit. Med."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Nwe, T.L., Dat, T.H., and Ma, B. (2018). Convolutional neural network with multi-task learning scheme for acoustic scene classification. Proceedings of the 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, Kuala Lumpur, Malaysia, 12\u201315 December 2017, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/APSIPA.2017.8282241"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Susto, G.A., Cenedese, A., and Terzi, M. (2018). Time-series classification methods: Review and Applications to power systems data. Big Data Application in Power Systems, Elsevier.","DOI":"10.1016\/B978-0-12-811968-6.00009-7"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/j.eswa.2018.03.056","article-title":"Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: State of the art and research challenges","volume":"105","author":"Nweke","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","article-title":"Deep learning for sensor-based activity recognition: A survey","volume":"119","author":"Wang","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, C., Lu, X., Markham, A., and Trigoni, N. (2018). IONet: Learning to cure the curse of drift in inertial odometry. arXiv.","DOI":"10.1609\/aaai.v32i1.12102"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Dai, H.F., Bian, H.W., Wang, R.Y., and Ma, H. (2019). An INS\/GNSS integrated navigation in GNSS denied environment using recurrent neural network. Def. Technol.","DOI":"10.1016\/j.dt.2019.08.011"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Fang, W., Jiang, J., Lu, S., Gong, Y., Tao, Y., Tang, Y., Yan, P., Luo, H., and Liu, J. (2020). A LSTM algorithm estimating pseudo measurements for aiding INS during GNSS Signal outages. Remote Sens., 12.","DOI":"10.3390\/rs12020256"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Brossard, M., Barrau, A., and Bonnabel, S. (2020). AI-IMU dead-reckoning. IEEE Trans. Intell. Veh.","DOI":"10.1109\/TIV.2020.2980758"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Onyekpe, U., Palade, V., and Kanarachos, S. (2021). Learning to localise automated vehicles in challenging environments using Inertial Navigation Systems (INS). Appl. Sci., 11.","DOI":"10.3390\/app11031270"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2957","DOI":"10.1007\/s10462-019-09752-1","article-title":"A survey of quaternion neural networks","volume":"53","author":"Parcollet","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"ref_18","first-page":"149","article-title":"Quaternion neural network with geometrical operators","volume":"15","author":"Matsui","year":"2004","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_19","unstructured":"Kusamichi, H., Kusamichi, H., Isokawa, T., Isokawa, T., Matsui, N., Matsui, N., Ogawa, Y., Ogawa, Y., Maeda, K., and Maeda, K. (2004, January 13\u201315). A new scheme for color night vision by quaternion neural network. Proceedings of the 2nd International Conference on Autonomous Robots and Agents (ICARA2004), Palmerston North, New Zealand."},{"key":"ref_20","unstructured":"Parcollet, T., Ravanelli, M., Morchid, M., Linar\u00e8s, G., Trabelsi, C., De Mori, R., and Bengio, Y. (2020, June 16). Quaternion Recurrent Neural Networks. Available online: https:\/\/github.com\/Orkis-Research\/Pytorch-Quaternion-Neural-Networks."},{"key":"ref_21","unstructured":"Choi, J., Wang, Z., Venkataramani, S., Chuang, P.I.-J., Srinivasan, V., and Gopalakrishnan, K. (2018). PACT: Parameterized Clipping Activation for Quantized Neural Networks. arXiv."},{"key":"ref_22","first-page":"318","article-title":"Quaternion neural network and its application","volume":"Voluem 2774","author":"Isokawa","year":"2003","journal-title":"Proceedings of the Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Parcollet, T., Morchid, M., and Linares, G. (2019). Quaternion convolutional neural networks for heterogeneous image processing. Proceedings of the ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Brighton, UK, 12\u201317 May 2019, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/ICASSP.2019.8682495"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.patrec.2019.12.001","article-title":"A bio-inspired quaternion local phase CNN layer with contrast invariance and linear sensitivity to rotation angles","volume":"131","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100890","DOI":"10.1109\/ACCESS.2020.2997177","article-title":"A quaternion-embedded capsule network model for knowledge graph completion","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"ref_26","unstructured":"\u00d6zcan, B., K\u0131nl\u0131, F., and K\u0131ra\u00e7, F. (2020). Quaternion Capsule Networks. arXiv, Available online: https:\/\/github.com\/Boazrciasn\/Quaternion-Capsule-Networks.git."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Grassucci, E., Comminiello, D., and Uncini, A. (2020). QUATERNION-VALUED VARIATIONAL AUTOENCODER. arXiv.","DOI":"10.1109\/ICASSP39728.2021.9413859"},{"key":"ref_28","unstructured":"Nguyen, D.Q., Nguyen, T.D., and Phung, D. (2020). Quaternion graph neural networks. arXiv, Available online: https:\/\/github.com\/daiquocnguyen\/QGNN."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Parcollet, T., Morchid, M., Linares, G., and De Mori, R. (2019). Bidirectional quaternion long short-term memory recurrent neural networks for speech recognition. Proceedings of the ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Brighton, UK, 12\u201317 May 2019, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/ICASSP.2019.8683583"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Onyekpe, U., Kanarachos, S., Palade, V., and Christopoulos, S.-R.G. (2020, January 14\u201317). Learning uncertainties in wheel odometry for vehicular localisation in GNSS deprived environments. Proceedings of the International Conference on Machine Learning Applications (ICMLA), Miami, FL, USA.","DOI":"10.1109\/ICMLA51294.2020.00121"},{"key":"ref_31","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J.L. (2013, January 24\u201326). A public domain dataset for human activity recognition using smartphones. Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1109\/TNNLS.2012.2183613","article-title":"Generalization characteristics of complex-valued feedforward neural networks in relation to signal coherence","volume":"23","author":"Hirose","year":"2012","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"ref_33","first-page":"1099","article-title":"On the critical points of the complex-valued neural network","volume":"Volume 3","author":"Nitta","year":"2002","journal-title":"Proceedings of the ICONIP 2002 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age, Singapore, 18\u201322 November 2002"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1016\/j.epsr.2017.03.004","article-title":"GPS signal loss in the wide area monitoring system: Prevalence, impact, and solution","volume":"147","author":"Yao","year":"2017","journal-title":"Electr. Power Syst. Res."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Luo, L., Feng, H., and Ding, L. (2010, January 29\u201331). Color image compression based on quaternion neural network principal component analysis. Proceedings of the 2010 International Conference on Multimedia Technology, ICMT 2010, Ningbo, China.","DOI":"10.1109\/ICMULT.2010.5631456"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Greenblatt, A., Mosquera-Lopez, C., and Agaian, S. (2013, January 13\u201316). Quaternion neural networks applied to prostate cancer gleason grading. Proceedings of the 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013, Manchester, UK.","DOI":"10.1109\/SMC.2013.199"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"5693","DOI":"10.1109\/TGRS.2013.2291940","article-title":"Quaternion neural-network-based PolSAR land classification in poincare-sphere-parameter space","volume":"52","author":"Shang","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Parcollet, T., Morchid, M., and Linares, G. (2018). Deep quaternion neural networks for spoken language understanding. Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017, Okinawa, Japan, 16\u201320 December 2017, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/ASRU.2017.8268978"},{"key":"ref_39","unstructured":"Parcollet, T., Morchid, M., and Linar\u00e8s, G. (2020, December 30). Quaternion Denoising Encoder-Decoder for Theme Identification of Telephone Conversations. Available online: https:\/\/hal.archives-ouvertes.fr\/hal-02107632."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1007\/s11263-019-01245-6","article-title":"Modeling human motion with quaternion-based neural networks","volume":"128","author":"Pavllo","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Comminiello, D., Lella, M., Scardapane, S., and Uncini, A. (2019). Quaternion convolutional neural networks for detection and localization of 3D sound events. Proceedings of the ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Brighton, UK, 12\u201317 May 2019, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/ICASSP.2019.8682711"},{"key":"ref_42","unstructured":"Zhu, X., Xu, Y., Xu, H., and Chen, C. (2020, December 30). Quaternion Convolutional Neural Networks. Available online: https:\/\/arxiv.org\/abs\/1903.00658."},{"key":"ref_43","unstructured":"Tay, Y., Zhang, A., Tuan, L.A., Rao, J., Zhang, S., Wang, S., Fu, J., and Hui, S.C. (August, January 28). Lightweight and efficient neural natural language processing with quaternion networks. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy."},{"key":"ref_44","unstructured":"Parcollet, T., Ravanelli, M., Morchid, M., Linar\u00e8s, G., and De Mori, R. (2018). Speech recognition with quaternion neural networks. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Parcollet, T., Morchid, M., Linares, G., and De Mori, R. (2019). Quaternion convolutional neural networks for theme identification of telephone conversations. Proceedings of the 2018 IEEE Spoken Language Technology Workshop, SLT 2018, Athens, Greece, 18\u201321 December 2018, Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/SLT.2018.8639676"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Tran, T., You, D., and Lee, K. (2020). Quaternion-based self-attentive long short-term user preference encoding for recommendation. Proceedings of the International Conference on Information and Knowledge Management, Galway, Ireland, 19\u201323 October 2020, Association for Computing Machinery.","DOI":"10.1145\/3340531.3411926"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"6907","DOI":"10.3934\/mbe.2019346","article-title":"Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field","volume":"16","author":"Chen","year":"2019","journal-title":"MBE"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Jin, L., Zhou, Y., Liu, H., and Song, E. (2020). Deformable quaternion gabor convolutional neural network for color facial expression recognition. Proceedings of the International Conference on Image Processing, ICIP, Abu Dhabi, United Arab Emirates, 25\u201328 October 2020, IEEE Computer Society.","DOI":"10.1109\/ICIP40778.2020.9191349"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Qiu, X., Parcollet, T., Ravanelli, M., Lane, N., and Morchid, M. (2020, January 14\u201318). Quaternion neural networks for multi-channel distant speech recognition. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Shanghai, China.","DOI":"10.21437\/Interspeech.2020-1682"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Kumar, D., Kumar, N., and Mishra, S. (2020). QUARC: Quaternion multi-modal fusion architecture for hate speech classification. arXiv, Available online: https:\/\/github.com\/smlab-niser\/quaternionFusion.","DOI":"10.1109\/BigComp51126.2021.00075"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014, January 25\u201329). Learning phrase representations using RNN encoder-decoder for statistical machine translation. Proceedings of the EMNLP 2014\u20142014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_52","first-page":"229","article-title":"Vehicular localisation at high and low estimation rates during GNSS outages: A deep learning approach","volume":"Volume 1232","author":"Wani","year":"2020","journal-title":"Deep Learning Applications, Volume 2. Advances in Intelligent Systems and Computing"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1179\/sre.1975.23.176.88","article-title":"Direct and inverse solutions of geodesics on the ellipsoid with application of nested equations","volume":"23","author":"Vincenty","year":"1975","journal-title":"Surv. Rev."},{"key":"ref_54","unstructured":"Pietrzak, M. (2019, April 12). Vincenty \u00b7 PyPI. Available online: https:\/\/pypi.org\/project\/vincenty\/."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"106885","DOI":"10.1016\/j.dib.2021.106885","article-title":"IO-VNBD: Inertial and odometry benchmark dataset for ground vehicle positioning","volume":"35","author":"Onyekpe","year":"2021","journal-title":"Data Br."},{"key":"ref_56","unstructured":"Gal, Y., and Ghahramani, Z. (2016). A theoretically grounded application of dropout in recurrent neural networks. arXiv."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/12\/3\/117\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:35:40Z","timestamp":1760160940000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/12\/3\/117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,9]]},"references-count":56,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,3]]}},"alternative-id":["info12030117"],"URL":"https:\/\/doi.org\/10.3390\/info12030117","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,9]]}}}