{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:49:07Z","timestamp":1782452947327,"version":"3.54.5"},"reference-count":49,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T00:00:00Z","timestamp":1687564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human activity recognition (HAR) is essential for the development of robots to assist humans in daily activities. HAR is required to be accurate, fast and suitable for low-cost wearable devices to ensure portable and safe assistance. Current computational methods can achieve accurate recognition results but tend to be computationally expensive, making them unsuitable for the development of wearable robots in terms of speed and processing power. This paper proposes a light-weight architecture for recognition of activities using five inertial measurement units and four goniometers attached to the lower limb. First, a systematic extraction of time-domain features from wearable sensor data is performed. Second, a small high-speed artificial neural network and line search method for cost function optimization are used for activity recognition. The proposed method is systematically validated using a large dataset composed of wearable sensor data from seven activities (sitting, standing, walking, stair ascent\/descent, ramp ascent\/descent) associated with eight healthy subjects. The accuracy and speed results are compared against methods commonly used for activity recognition including deep neural networks, convolutional neural networks, long short-term memory and convolutional\u2013long short-term memory hybrid networks. The experiments demonstrate that the light-weight architecture can achieve a high recognition accuracy of 98.60%, 93.10% and 84.77% for seen data from seen subjects, unseen data from seen subjects and unseen data from unseen subjects, respectively, and an inference time of 85 \u03bcs. The results show that the proposed approach can perform accurate and fast activity recognition with a reduced computational complexity suitable for the development of portable assistive devices.<\/jats:p>","DOI":"10.3390\/s23135854","type":"journal-article","created":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T05:11:54Z","timestamp":1687756314000},"page":"5854","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["A Light-Weight Artificial Neural Network for Recognition of Activities of Daily Living"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5721-8866","authenticated-orcid":false,"given":"Samer A.","family":"Mohamed","sequence":"first","affiliation":[{"name":"Department of Electronic and Electrical Engineering, Faculty of Engineering and Design, University of Bath, Bath BA2 7AY, UK"},{"name":"Mechatronics Engineering Department, Faculty of Engineering, Ain Shams University, Cairo 11566, Egypt"},{"name":"Multimodal Inte-R-Action Lab, University of Bath, Bath BA2 7AY, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9922-7912","authenticated-orcid":false,"given":"Uriel","family":"Martinez-Hernandez","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, Faculty of Engineering and Design, University of Bath, Bath BA2 7AY, UK"},{"name":"Multimodal Inte-R-Action Lab, University of Bath, Bath BA2 7AY, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,24]]},"reference":[{"key":"ref_1","unstructured":"Debnath, B., O\u2019brien, M., Kumar, S., and Behera, A. (2023). Multimodal AI in Healthcare, Springer."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"105129","DOI":"10.1016\/j.jstrokecerebrovasdis.2020.105129","article-title":"Quality of life and resilience of patients with juvenile stroke: A systematic review","volume":"29","author":"Winter","year":"2020","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1177\/17474930221123175","article-title":"Global stroke statistics 2022","volume":"17","author":"Thayabaranathan","year":"2022","journal-title":"Int. J. Stroke"},{"key":"ref_4","unstructured":"Chrysanthou, M. (2020). The Effect of a Novel Orthosis on Ankle Kinematics in Simulated Sprain. [Master\u2019s Thesis, University of Twente]."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1007\/s12369-020-00662-9","article-title":"Development of active lower limb robotic-based orthosis and exoskeleton devices: A systematic review","volume":"13","author":"Kalita","year":"2021","journal-title":"Int. J. Soc. Robot."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"10719","DOI":"10.1109\/JSEN.2022.3167686","article-title":"Motion Intention Prediction and Joint Trajectories Generation Towards Lower Limb Prostheses Using EMG and IMU Signals","volume":"22","author":"Wang","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4238","DOI":"10.1017\/S0263574722000881","article-title":"Development of portable robotic orthosis and biomechanical validation in people with limited upper limb function after stroke","volume":"40","author":"Ferreira","year":"2022","journal-title":"Robotica"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Voicu, R.A., Dobre, C., Bajenaru, L., and Ciobanu, R.I. (2019). Human physical activity recognition using smartphone sensors. Sensors, 19.","DOI":"10.3390\/s19030458"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Akada, H., Wang, J., Shimada, S., Takahashi, M., Theobalt, C., and Golyanik, V. (2022, January 23\u201327). UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20068-7_1"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1143248","DOI":"10.3389\/fbioe.2023.1143248","article-title":"A multi-sensor wearable system for the assessment of diseased gait in real-world conditions","volume":"11","author":"Salis","year":"2023","journal-title":"Front. Bioeng. Biotechnol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2103694","DOI":"10.1002\/advs.202103694","article-title":"Wearable Triboelectric Sensors Enabled Gait Analysis and Waist Motion Capture for IoT-Based Smart Healthcare Applications","volume":"9","author":"Zhang","year":"2022","journal-title":"Adv. Sci."},{"key":"ref_12","first-page":"3","article-title":"IMU gyroscopes are a valid alternative to 3D optical motion capture system for angular kinematics analysis in tennis","volume":"235","author":"Vanrenterghem","year":"2021","journal-title":"Proc. Inst. Mech. Eng. Part J. Sport. Eng. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kim, B.H., Hong, S.H., Oh, I.W., Lee, Y.W., Kee, I.H., and Lee, S.Y. (2021). Measurement of ankle joint movements using imus during running. Sensors, 21.","DOI":"10.20944\/preprints202105.0771.v1"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Bangaru, S.S., Wang, C., and Aghazadeh, F. (2020). Data quality and reliability assessment of wearable emg and imu sensor for construction activity recognition. Sensors, 20.","DOI":"10.3390\/s20185264"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zheng, X., Wang, M., and Ordieres-Mer\u00e9, J. (2018). Comparison of data preprocessing approaches for applying deep learning to human activity recognition in the context of industry 4.0. Sensors, 18.","DOI":"10.3390\/s18072146"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/10.204774","article-title":"A new strategy for multifunction myoelectric control","volume":"40","author":"Hudgins","year":"1993","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Cui, J.W., Li, Z.G., Du, H., Yan, B.Y., and Lu, P.D. (2022). Recognition of Upper Limb Action Intention Based on IMU. Sensors, 22.","DOI":"10.3390\/s22051954"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Karakish, M., Fouz, M.A., and ELsawaf, A. (2022). Gait Trajectory Prediction on an Embedded Microcontroller Using Deep Learning. Sensors, 22.","DOI":"10.3390\/s22218441"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Krichen, M., Mihoub, A., Alzahrani, M.Y., Adoni, W.Y.H., and Nahhal, T. (2022, January 9\u201311). Are Formal Methods Applicable to Machine Learning and Artificial Intelligence?. Proceedings of the 2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH), Riyadh, Saudi Arabia.","DOI":"10.1109\/SMARTTECH54121.2022.00025"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1002\/inst.12434","article-title":"Framework for Formal Verification of Machine Learning Based Complex System-of-Systems","volume":"26","author":"Raman","year":"2023","journal-title":"Insight"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A review of recurrent neural networks: LSTM cells and network architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"14","DOI":"10.3389\/frobt.2018.00014","article-title":"Benchmark datasets for bilateral lower-limb neuromechanical signals from wearable sensors during unassisted locomotion in able-bodied individuals","volume":"5","author":"Hu","year":"2018","journal-title":"Front. Robot. AI"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Caruso, M., Sabatini, A.M., Knaflitz, M., Della Croce, U., and Cereatti, A. (2021). Extension of the rigid-constraint method for the heuristic suboptimal parameter tuning to ten sensor fusion algorithms using inertial and magnetic sensing. Sensors, 21.","DOI":"10.3390\/s21186307"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.robot.2014.09.032","article-title":"Review of assistive strategies in powered lower-limb orthoses and exoskeletons","volume":"64","author":"Yan","year":"2015","journal-title":"Robot. Auton. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.jbiomech.2009.09.030","article-title":"Invariant ankle moment patterns when walking with and without a robotic ankle exoskeleton","volume":"43","author":"Kao","year":"2010","journal-title":"J. Biomech."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"6211","DOI":"10.1109\/LRA.2022.3167065","article-title":"A Discrete Non-Linear Series Elastic Actuator for Active Ankle-Foot Orthoses","volume":"7","author":"DeBoer","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"102426","DOI":"10.1016\/j.jelekin.2020.102426","article-title":"Tutorial: Analysis of motor unit discharge characteristics from high-density surface EMG signals","volume":"53","author":"Holobar","year":"2020","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_28","unstructured":"Yu, T. (2019). On-Line Decomposition of iEMG Signals Using GPU-Implemented Bayesian Filtering. [Ph.D. Thesis, \u00c9cole Centrale de Nantes]."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1109\/TNSRE.2020.3043368","article-title":"Wearable MMG-plus-one armband: Evaluation of normal force on mechanomyography (MMG) to enhance human-machine interfacing","volume":"29","author":"Castillo","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1109\/RBME.2020.2969915","article-title":"A review on machine learning for EEG signal processing in bioengineering","volume":"14","author":"Hosseini","year":"2020","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"De Fazio, R., Mastronardi, V.M., Petruzzi, M., De Vittorio, M., and Visconti, P. (2022). Human\u2013Machine Interaction through Advanced Haptic Sensors: A Piezoelectric Sensory Glove with Edge Machine Learning for Gesture and Object Recognition. Future Internet, 15.","DOI":"10.3390\/fi15010014"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Mohsen, S., Elkaseer, A., and Scholz, S.G. (2021, January 15\u201317). Human activity recognition using K-nearest neighbor machine learning algorithm. Proceedings of the International Conference on Sustainable Design and Manufacturing, Split, Croatia.","DOI":"10.1007\/978-981-16-6128-0_29"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tran, D.N., and Phan, D.D. (2016, January 25\u201327). Human Activities Recognition in Android Smartphone Using Support Vector Machine. Proceedings of the 2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS), Bangkok, Thailand.","DOI":"10.1109\/ISMS.2016.51"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Jmal, A., Barioul, R., Meddeb Makhlouf, A., Fakhfakh, A., and Kanoun, O. (2020, January 24\u201326). An embedded ANN raspberry PI for inertial sensor based human activity recognition. Proceedings of the International Conference on Smart Homes and Health Telematics, Hammamet, Tunisia.","DOI":"10.1007\/978-3-030-51517-1_34"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Martinez-Hernandez, U., Rubio-Solis, A., and Dehghani-Sanij, A.A. (2018, January 26\u201329). Recognition of walking activity and prediction of gait periods with a CNN and first-order MC strategy. Proceedings of the 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob), Enschede, The Netherlands.","DOI":"10.1109\/BIOROB.2018.8487220"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1109\/ICIT46573.2021.9453672","article-title":"Recognition of human activity and the state of an assembly task using vision and inertial sensor fusion methods","volume":"Volume 1","author":"Male","year":"2021","journal-title":"Proceedings of the 2021 22nd IEEE International Conference on Industrial Technology (ICIT)"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"23964","DOI":"10.1109\/ACCESS.2022.3154775","article-title":"MS-DLD: Multi-Sensors Based Daily Locomotion Detection via Kinematic-Static Energy and Body-Specific HMMs","volume":"10","author":"Ghadi","year":"2022","journal-title":"IEEE Access"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1007\/s42235-022-00230-z","article-title":"Integral real-time locomotion mode recognition based on GA-CNN for lower limb exoskeleton","volume":"19","author":"Wang","year":"2022","journal-title":"J. Bionic Eng."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1186\/s12984-021-00945-w","article-title":"Long short-term memory (LSTM) recurrent neural network for muscle activity detection","volume":"18","author":"Ghislieri","year":"2021","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Marcos Mazon, D., Groefsema, M., Schomaker, L.R., and Carloni, R. (2022). IMU-Based Classification of Locomotion Modes, Transitions, and Gait Phases with Convolutional Recurrent Neural Networks. Sensors, 22.","DOI":"10.3390\/s22228871"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2132138","DOI":"10.1155\/2020\/2132138","article-title":"Wearable sensor-based human activity recognition using hybrid deep learning techniques","volume":"2020","author":"Wang","year":"2020","journal-title":"Secur. Commun. Netw."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"e12743","DOI":"10.1111\/exsy.12743","article-title":"Deep ensemble learning approach for lower extremity activities recognition using wearable sensors","volume":"39","author":"Jain","year":"2022","journal-title":"Expert Syst."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Caruso, M., Sabatini, A.M., Laidig, D., Seel, T., Knaflitz, M., Della Croce, U., and Cereatti, A. (2021). Analysis of the accuracy of ten algorithms for orientation estimation using inertial and magnetic sensing under optimal conditions: One size does not fit all. Sensors, 21.","DOI":"10.3390\/s21072543"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Farooq, F., Tandon, S., Parashar, S., and Sengar, P. (2016, January 4\u20136). Vectorized code implementation of Logistic Regression and Artificial Neural Networks to recognize handwritten digit. Proceedings of the 2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), Delhi, India.","DOI":"10.1109\/ICPEICES.2016.7853346"},{"key":"ref_45","first-page":"149","article-title":"A new stepsize for the steepest descent method","volume":"24","author":"Yuan","year":"2006","journal-title":"J. Comput. Math."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/S0167-8655(98)00120-2","article-title":"A comparative study of neural network based feature extraction paradigms","volume":"20","author":"Lerner","year":"1999","journal-title":"Pattern Recognit. Lett."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3090076","article-title":"Ensembles of deep lstm learners for activity recognition using wearables","volume":"Volume 1","author":"Guan","year":"2017","journal-title":"ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhong, K., Zhang, J., Sun, Q., and Zhao, X. (2016, January 24\u201325). LSTM networks for mobile human activity recognition. Proceedings of the 2016 International Conference on Artificial Intelligence: Technologies and Applications, Bangkok, Thailand.","DOI":"10.2991\/icaita-16.2016.13"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"56855","DOI":"10.1109\/ACCESS.2020.2982225","article-title":"LSTM-CNN architecture for human activity recognition","volume":"8","author":"Xia","year":"2020","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/13\/5854\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:59:36Z","timestamp":1760126376000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/13\/5854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,24]]},"references-count":49,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["s23135854"],"URL":"https:\/\/doi.org\/10.3390\/s23135854","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,24]]}}}