Call For Paper Volume: V, Issue: 08 | AUGUST 2026 | International Journal of Advanced Trends in Engineering and Management (IJATEM)
Volume V | Issue 5 | 2026 | Paper ID: IJATEM-V05I05P2

Advanced Traffic Flow Prediction Using Transformer-BiLSTM Networks with Particle Swarm Optimization

, Ramya R R

Accurate Traffic Flow Prediction (TFP) is very important for Intelligent Transportation Systems (ITS), but it faces challenges of missing data, inconsistent feature values and inefficient model optimization. This paper proposes an Advanced TFP framework using Transformer-BiLSTM Networks with Particle Swarm Optimization (PSO) and evaluate it on the GTFS Traffic Prediction Dataset. The data pre-processing includes the removal of inconsistencies and null entries. The correlation analysis includes the identification of significant feature relationships. The Min–Max Scaler scales the input data to improve the stability of training. The Transformer-BiLSTM network effectively learns the global dependencies of features and temporal patterns of traffic for accurate congestion prediction. The novelty of the proposed framework is to integrate the Transformer-BiLSTM with PSO to acquire improved feature learning, parameter optimization and accurate traffic flow prediction. The network parameters are optimized using the PSO to improve convergence and predictive performance. The experimental outcomes show that proposed model attains 98% accuracy, precision, recall and F1-score, which are better than CNN (92%), LSTM (90%) and LR (92%). This makes it a reliable solution for intelligent traffic management.

Data Pre-processing, Correlation analysis, Min-Max Scaling, Transformer BiLSTM, PSO, DL.

  • [1] Xueyan Yin; Genze Wu; Jinze Wei; Yanming Shen; Heng Qi; Baocai Yin, Year: 2021, “Deep learning on traffic prediction: Methods, analysis, and future directions”, IEEE Transactions on Intelligent Transportation Systems, Vol: 23, No: 6, pp. 4927-4943.

  • [2] S. Narmadha; V. Vijayakumar, Year: 2023, “Spatio-Temporal vehicle traffic flow prediction using multivariate CNN and LSTM model”, Materials today: proceedings, Vol: 81, pp. 826-833.

  • [3] Fouzi Harrou; Abdelhafid Zeroual; Farid Kadri; Ying Sun, Year: 2024, “Enhancing road traffic flow prediction with improved deep learning using wavelet transforms”, Results in Engineering, Vol: 23, pp. 102342.

  • [4] Sura Mahmood Abdullah; Muthusamy Periyasamy; Nafees Ahmed Kamaludeen; S. K. Towfek; Raja Marappan; Sekar Kidambi Raju; Amal H. Alharbi; Doaa Sami Khafaga, Year: 2023, “Optimizing traffic flow in smart cities: Soft GRU-based recurrent neural networks for enhanced congestion prediction using deep learning”, Sustainability, Vol: 15, No: 7, pp. 5949.

  • [5] Noor Afiza Mat Razali; Nuraini Shamsaimon; Khairul Khalil Ishak; Suzaimah Ramli; Mohd Fahmi Mohamad Amran; Sazali Sukardi, Year: 2021, “Gap, techniques and evaluation: traffic flow prediction using machine learning and deep learning”, Journal of Big Data, Vol: 8, No: 1, pp. 152.

  • [6] Mahmuda Akhtar; Sara Moridpour, Year: 2021, “A review of traffic congestion prediction using artificial intelligence”, Journal of Advanced Transportation, Vol: 2021, No: 1, pp. 8878011.

  • [7] Mouna Zouari Mehdi; Habib M. Kammoun; Norhene Gargouri Benayed; Dorra Sellami; Alima Damak Masmoudi, Year: 2022, “Entropy-based traffic flow labeling for CNN-based traffic congestion prediction from meta-parameters”, IEEE Access, Vol: 10, pp. 16123-16133.

  • [8] Sura Mahmood Abdullah; Muthusamy Periyasamy; Nafees Ahmed Kamaludeen; S. K. Towfek; Raja Marappan; Sekar Kidambi Raju; Amal H. Alharbi; Doaa Sami Khafaga, Year: 2023, “Optimizing traffic flow in smart cities: Soft GRU-based RNN for enhanced congestion prediction using DL”, Sustainability, Vol: 15, No: 7, pp. 5949.

  • [9] Babalola Eyitemi Akilo; Samuel Abiodun Oyedotun; Godfrey Perfectson Oise; Onyemaechi Clement Nwabuokei; Nkem Belinda Unuigbokhai, Year: 2024, “Intelligent traffic management system using ant colony and deep learning algorithms for real-time traffic flow optimization”, Journal of Science Research and Reviews, Vol: 1, No: 2, pp. 63-71.

  • [10] Junxi Zhang; Shiru Qu; Zhiteng Zhang; Shaokang Cheng, Year: 2022, “Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction”, PeerJ Computer Science, Vol: 8, pp. e1048.

  • [11] Rusul Abduljabbar; Hussein Dia; Sohani Liyanage, Year: 2025, “Machine learning traffic flow prediction models for smart and sustainable traffic management”, Infrastructures, Vol: 10, No: 7, pp. 155.

  • [12] Ganglong Duan; Yutong Du; Yanying Shang; Hongquan Xue; Ruochen Zhang, Year: 2025, “Research on Support Vector Regression Short-Time Traffic Flow Prediction Model for Secondary Roads Based on Associated Road Analysis”, Appl. Sci., Vol: 15, pp. 1779.

  • [13] Xingyu Tao; Lan Cheng; Ruihan Zhang; W. K. Chan; Huang Chao; Jing Qin, Year: 2024, “Towards Green Innovation in Smart Cities: Leveraging Traffic Flow Prediction with Machine Learning Algorithms for Sustainable Transportation Systems”, Sustainability, Vol: 16, pp. 251.

  • [14] P. Kumar; M. Manur; A. K. Pani, Year: 2022, “Road Traffic Prediction and Optimal Alternate Path Selection Using HBI-LSTM and HV-ABC”, Indian J. Sci. Technol, Vol: 15, pp. 689-699.

  • [15] Samar M. Zayed; Samah Alshathri; Walid El-Shafai, Year: 2026, “Firefly algorithm optimized hybrid deep learning framework for intrusion detection in IoT environments”, International Journal of Computational Intelligence Systems, Vol: 19, No: 1, pp. 158.