Browse by author
Lookup NU author(s): Shamil Al-Ameen, Dr Tejal Shah, Professor Raj Ranjan
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Accurate mobility prediction has become pivotal for a wide range of smart city applications including optimizing electric vehicles (EV) charging management, traffic management, infrastructure planning, etc. However, traditional mobility prediction models face significant challenges including ineffective integration of geographical information, inability to dynamically adapt to changing location popularity, and struggle with longterm dependency. Furthermore, these models are susceptible to catastrophic forgetting, losing previously learned knowledge when exposed to new data.To overcome these challenges, we propose the Lifelong Edgecloud Adaptive Prediction (LEAP) framework, a fresh approach that integrates lifelong learning into mobility prediction. LEAP improves prediction accuracy and reliability in dynamic realworld environments by fusing a central cloud model for capturing long-term trends with multiple local edge models that process real-time data. LEAP employs Spatially Adaptive LSTM (SA-LSTM) and Temporal Adjustment LSTM (TA-LSTM) to incorporate dynamic spatio-temporal patterns, along with Global Context Operations (GC Ops) to manage long-term dependencies. To prevent catastrophic forgetting, LEAP uses Learning without Forgetting (LwF), enabling on device continuous learning and adaptation at the edge.Extensive evaluations demonstrate that LEAP surpasses ten state-of-the-art methods, including Scikit-Learn’s LSTM, with average improvements of 2.61x in Recall-5, 2.35x in Recall-10, 2.80x in NDCG-5, and 3.06x in NDCG-10. These results highlight LEAP’s superior effectiveness, accuracy, and adaptability, proving it a worthy choice for dynamic real-world mobility prediction tasks while effectively addressing catastrophic forgetting.
Author(s): Al-Ameen S, Sudharsan B, Al-Taie R, Shah T, Ranjan R
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: 2024 IEEE International Conference on Big Data (IEEE BigData 2024)
Year of Conference: 2025
Online publication date: 18/12/2024
Acceptance date: 22/10/2024
Date deposited: 08/01/2025
Publisher: IEEE
URL: https://www3.cs.stonybrook.edu/~ieeebigdata2024/
ePrints DOI: 10.57711/dnj3-xx32
