An Enhanced Ensemble-Based Long Short-Term Memory Approach for Traffic Volume Prediction

作     者：Duy Quang Tran Huy Q.Tran Minh Van Nguyen 

作者机构：Faculty of Civil EngineeringNha Trang UniversityNha Trang650000Vietnam Robotics and Mechatronics Research GroupFaculty of Engineering and TechnologyNguyen Tat Thanh UniversityHo Chi Minh City700000Vietnam Department of Civil EngineeringHo Chi Minh City University of Technology and EducationHo Chi Minh City700000Vietnam 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第78卷第3期

页      面：3585-3602页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Ensemble empirical mode decomposition traffic volume prediction long short-term memory optimal hyperparameters deep learning 

摘      要：With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service *** volume is an influential parameter for planning and operating traffic *** study proposed an improved ensemble-based deep learning method to solve traffic volume prediction problems.A set of optimal hyperparameters is also applied for the suggested approach to improve the performance of the learning *** fusion of these methodologies aims to harness ensemble empirical mode decomposition’s capacity to discern complex traffic patterns and long short-term memory’s proficiency in learning temporal ***,a dataset for automatic vehicle identification is obtained and utilized in the preprocessing stage of the ensemble empirical mode decomposition *** second aspect involves predicting traffic volume using the long short-term memory ***,the study employs a trial-and-error approach to select a set of optimal hyperparameters,including the lookback window,the number of neurons in the hidden layers,and the gradient descent ***,the fusion of the obtained results leads to a final traffic volume *** experimental results show that the proposed method outperforms other benchmarks regarding various evaluation measures,including mean absolute error,root mean squared error,mean absolute percentage error,and *** achieved R-squared value reaches an impressive 98%,while the other evaluation indices surpass the *** findings highlight the accuracy of traffic pattern ***,this offers promising prospects for enhancing transportation management systems and urban infrastructure planning.