Human Trajectory Forecasting with RNN-Based Hybrid Models: LSTM, GRU, and SimpleRNN Combinations

International Journal of Electrical and Electronics Engineering

© 2025 by SSRG - IJEEE Journal

Volume 12 Issue 9

Year of Publication : 2025

Authors : Ahmad Zaki Aiman Abdul Rashid, Azita Laily Yusof, Norsuzila Ya’acob

10.14445/23488379/IJEEE-V12I9P101

How to Cite?

Ahmad Zaki Aiman Abdul Rashid, Azita Laily Yusof, Norsuzila Ya’acob, "Human Trajectory Forecasting with RNN-Based Hybrid Models: LSTM, GRU, and SimpleRNN Combinations," SSRG International Journal of Electrical and Electronics Engineering, vol. 12,  no. 9, pp. 1-10, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I9P101

Abstract:

For 5G aerial base station (UAV-BS) networks to have a smooth and dependable handover, human trajectory prediction is crucial. Although the majority of research focuses on individual architectures rather than hybrid approaches, deep learning models such as SimpleRNN, GRU and LSTM demonstrated potential in modeling sequential data. There are currently few comparative studies of hybrid designs, especially when dropout regularization is used. The SimpleRNN-Dropout-LSTM-Dropout model produced the best results out of all of them after 50 epochs of training with Tanh activation, Adam optimizer, learning rate of 0.001, 64 hidden units, and batch size of 32. With little training and validation loss (0.0007 each), it recorded the lowest errors across all metrics: MSE (0.0003), MAE (0.0146), ADE (0.0207), FDE (0.0434), RMSE (0.0168), and MAPE (0.0157). These results demonstrate how well hybrid deep recurrent networks - in particular, SimpleRNN-LSTM combinations - perform in accurately predicting short-term human trajectories.

Keywords:

Coordinate, Deep Learning, Hybrid, Human, Trajectory Prediction.

References:

[1] Yusheng Peng et al., “MRGTraj: A Novel Non-Autoregressive Approach for Human Trajectory Prediction,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 4, pp. 2318-2331, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Parth Kothari, Sven Kreiss, and Alexandre Alahi, “Human Trajectory Forecasting in Crowds: A Deep Learning Perspective,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 7, pp. 7386-7400, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Renata K.G. Dos Reis, Maria G.L. Damasceno, and Jussif J.A. Arnez, “Trajectory-Based Handover Cell Selection Algorithm using GRU Model in 5G Networks,” 2024 20th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), Paris, France, pp. 603-606, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Jianjing Zhang et al., “Recurrent Neural Network for Motion Trajectory Prediction in Human-Robot Collaborative Assembly,” CIRP Annals, vol. 69, no. 1, pp. 9-12, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Xin Xu, “Context-based Trajectory Prediction with LSTM Networks,” CIIS '20: Proceedings of the 2020 3rd International Conference on Computational Intelligence and Intelligent Systems, Tokyo, Japan, pp. 100-104, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yanbo Zhang, and Liying Zheng, “Pedestrian Trajectory Prediction with MLP-Social-GRU,” ICMLC '21: Proceedings of the 2021 13th International Conference on Machine Learning and Computing, Shenzhen, China, pp. 368-372, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Xin Li, Xiaowen Ying, and Mooi Choo Chuah, “GRIP: Graph-based Interaction-Aware Trajectory Prediction,” 2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand, pp. 3960-3966, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Lei Zhang, Xuefei Chen, and Yuxiang Ma, “A Handover Scheme Based on Mobility Prediction for Autonomous Moving Platforms in 5G Networks,” 2022 International Wireless Communications and Mobile Computing, (IWCMC), Dubrovnik, Croatia, pp. 104-109, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Anna Prado, Hansini Vijayaraghavan, and Wolfgang Kellerer, “ECHO: Enhanced Conditional Handover Boosted by Trajectory Prediction,” 2015 IEEE Global Communications Conference (GLOBECOM), Madrid, Spain, pp. 1-6, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Zhongliang Zhao et al., “Mobility Management with Transferable Reinforcement Learning Trajectory Prediction,” IEEE Transactions on Network and Service Management, vol. 17, no. 4, pp. 2102-2116, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Guo Xie et al., “Motion Trajectory Prediction Based on a CNN-LSTM Sequential Model,” Science China Information Sciences, vol. 63, no. 11, pp. 1-21, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Bang Cheng et al., “Pedestrian Trajectory Prediction Via the Social-Grid LSTM Model,” The Journal of Engineering, vol. 2018, no. 16, pp. 1468-1474, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Juan Chen et al., “KGCN‐LSTM: A Graph Convolutional Network Considering Knowledge Fusion of Point of Interest for Vehicle Trajectory Prediction,” IET Intelligent Transport Systems, vol. 17, no. 6, pp. 1087-1103, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Huu-Tu Dang et al., “TTC-SLSTM: Human Trajectory Prediction Using Time-to-Collision Interaction Energy,” 2023 15th International Conference on Knowledge and Systems Engineering (KSE), Hanoi, Vietnam, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Lucas B.V. de Amorim, George D.C. Cavalcanti, and Rafael M.O. Cruz, “The Choice of Scaling Technique Matters for Classification Performance,” Applied Soft Computing, vol. 133, pp. 1-37, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Basilio Gregori Chepino et al., “Effect of MinMax Normalization on ORB Data for Improved ANN Accuracy,” Journal of Electrical Engineering Energy and Information Technology (J3EIT), vol. 11, no. 2, pp. 29-35, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Joel Wolfrath, and Abhishek Chandra, “A Biased Estimator for MinMax Sampling and Distributed Aggregation,” arXiv Preprint, pp. 1-4, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Jida Huang, and Tsz-Ho Kwok, “Normalization and Dimension Reduction for Machine Learning in Advanced Manufacturing,” International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC/CIE), St. Louis, Missouri, USA, pp. 1-8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Shuo Zhao et al., “An Integrated Framework for Accurate Trajectory Prediction Based on Deep Learning,” Applied Intelligence, vol. 54, no. 20, pp. 10161-10175, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Chujie Wang et al., “Exploring Trajectory Prediction through Machine Learning Methods,” IEEE Access, vol. 7, pp. 101441-101452, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Yang Li et al., “Pedestrian Trajectory Prediction Combining Probabilistic Reasoning and Sequence Learning,” IEEE Transactions on Intelligent Vehicles, vol. 5, no. 3, pp. 461-474, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Scott M. Robeson, and Cort J. Willmott, “Decomposition of the Mean Absolute Error (MAE) into Systematic and Unsystematic Components,” PLOS ONE, vol. 18, no. 2, pp. 1-8, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Andik Adi Suryanto, and Asfan Muqtadir “Application of the Mean Absolute Error (MEA) Method in the Linear Regression Algorithm for Rice Production Prediction,” Saintekbu Journal of Science and Technology, vol. 11, no. 1, pp. 78-83, 2019. [CrossRef] [Google Scholar] [Publisher Link]
[24] Jun Qi et al., “On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression,” IEEE Signal Processing Letters, vol. 27, pp. 1485-1489, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Mark D. Schluchter, “Mean Square Error,” Encyclopedia of Biostatistics, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Sean Reiter, and Steffen W.R. Werner, “Interpolatory Model Reduction of Dynamical Systems with Root Mean Squared Error,” IFAC-PapersOnLine, vol. 59, no. 1, pp. 385-390, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[27] T. Chai, and R.R. Draxler, “Root Mean Square Error (RMSE) or Mean Absolute Error (MAE)? - Arguments Against Avoiding RMSE in the Literature,” Geoscientific Model Development, vol. 7, no. 3, pp. 1247-1250, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Timothy O. Hodson, “Root-Mean-Square Error (RMSE) or Mean Absolute Error (MAE): When to use Them or Not,” Geoscientific Model Development, vol. 15, no. 14, pp. 5481-5487, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Robert Gilmore Pontius Jr, Olufunmilayo Thontteh, and Hao Chen, “Components of Information for Multiple Resolution Comparison Between Maps that Share A Real Variable,” Environmental and Ecological Statistics, vol. 15, no. 2, pp. 111-142, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Arnaud de Myttenaere et al., “Mean Absolute Percentage Error for Regression Models,” Neurocomputing, vol. 192, pp. 38-48, 2016.
[CrossRef] [Google Scholar] [ Publisher Link]
[31] Sungil Kim, and Heeyong Kim, “A New Metric of Absolute Percentage Error for Intermittent Demand Forecasts,” International Journal of Forecasting, vol. 32, no. 3, pp. 669-679, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[32] S.K. Morley, T.V. Brito, and D.T. Welling, “Measures of Model Performance Based on the Log Accuracy Ratio,” Space Weather, vol. 16, no. 1, pp. 69-88, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Ummul Khair et al., “Forecasting Error Calculation with Mean Absolute Deviation and Mean Absolute Percentage Error,” Journal of Physics: Conference Series, vol. 930, pp. 1-6, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Bohao Shen, and Jianzhi Li, “Displacement-Sensing Method Based on Residual Scaling for One-Shot MMF Specklegram Prediction,” Sensors, vol. 25, no. 5, no. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Yang Zhang, Peng Liu, and Xuefeng Zhao, “Structural Displacement Monitoring Based on Mask Regions with Convolutional Neural Network,” Construction and Building Materials, vol. 267, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Qiaode Jeffrey Ge et al., “On the Computation of the Average of Spatial Displacements,” International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, St. Louis, Missouri, USA, vol. 7, no. 46, pp. 1-33, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Abduallah Mohamedet al., “Social-Implicit: Rethinking Trajectory Prediction Evaluation and the Effectiveness of Implicit Maximum Likelihood Estimation,” Computer Vision - European Conference on Computer Vision 2022, Tel Aviv, Israel, pp. 463-479, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Jing Yang et al., “IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Prediction,” IEEE Transactions on Cybernetics, vol. 54, no. 7, pp. 3904-3917, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[39] Alon Lerner, Yiorgos Chrysanthou, and Dani Lischinski, “Crowds by Example,” Computer Graphics Forum, vol. 26, no. 3, pp. 655-664, 2007.
[CrossRef] [Google Scholar] [Publisher Link]
[40] Ning Ye et al., “Vehicle Trajectory Prediction Based on Hidden Markov Model,” KSII Transactions on Internet and Information Systems, vol. 10, no. 7, pp. 3150-3170, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[41] Ling-Xiao Li, Guang-Li Sun, and Jiang-Peng Song, “Target Trajectory Prediction Based on Neural Network and Kalman Filtering,” Proceedings Volume 11342 Applied Optics and Photonics China (Aopc2019), AOPC 2019: AI in Optics and Photonics, Beijing, China, pp. 127-135, 2019.
[CrossRef ] [Google Scholar] [Publisher Link]
[42] Zhixian Yan, “Traj-ARIMA: A Spatial-Time Series Model for Network-Constrained Trajectory,” IWCTS '10: Proceedings of the Third International Workshop on Computational Transportation Science, San Jose, California, pp. 11-16, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[43] Dingyi Yin, “Road Traffic Prediction Based on Base Station Location data by Random Forest,” 2018 3rd International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, pp. 264-270, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[44] Qun Lim, Kritika Johari, and U-Xuan Tan, “Gaussian Process Auto Regression for Vehicle Center Coordinates Trajectory Prediction,” TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), Kochi, India, pp. 25-30, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[45] Ranjeet Singh Tomar, Shekhar Verma, and Geetam Singh Tomar, “SVM Based Trajectory Predictions of Lane Changing Vehicles,” 2011 International Conference on Computational Intelligence and Communication Networks, Gwalior, India, pp. 716-721, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[46] Shiji Huang et al., “Interpretable Interaction Modeling for Trajectory Prediction Via Agent Selection and Physical Coefficient,” arXiv Preprint, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]