Article
Multidisciplinary Sciences
Nway Nway Aung, Junxiong Pang, Matthew Chin Heng Chua, Hui Xing Tan
Summary: This study developed a deep-learning model that uses data from the past 30 days to forecast the daily number of new COVID-19 cases 14 days later in the early stages of the pandemic. The research found that countries with more accurate forecasts had higher daily case numbers and experienced more waves of infections. The model performed well even with fewer variables.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Civil
Mosammat Tahnin Tariq, Rajib Saha, Mohammed Hadi
Summary: This study utilizes a data analytic approach to estimate the diversion rate during freeway incidents and develop special signal timing plans to manage the demand surge on diversion routes. The evaluation shows that this approach can significantly reduce delays on alternative routes.
TRANSPORTATION RESEARCH RECORD
(2022)
Article
Engineering, Civil
Mehdi Jamei, Mumtaz Ali, Anurag Malik, Masoud Karbasi, Priya Rai, Zaher Mundher Yaseen
Summary: Accurate forecasting of monthly rainfall in the Himalayan region of India was achieved using a new multi-decomposition deep learning-based technique. The rainfall signals were decomposed using time-varying filter-based empirical mode decomposition and partial autocorrelation function. The decomposed signals were further decomposed using Singular Valued Decomposition to reduce dimensionality. Hybrid forecasting models using machine learning approaches outperformed standalone models, with TVF-EMD-SVD-EDBi-LSTM achieving the best results.
JOURNAL OF HYDROLOGY
(2023)
Article
Green & Sustainable Science & Technology
Hyeonseo Kim, Kyeongjoo Kwon, Nuri Park, Juneyoung Park, Mohamed Abdel-Aty
Summary: The study aims to evaluate safety effects of altering deceleration and acceleration lane lengths at rest areas on expressways in Korea. A new framework was proposed to explore crash-based and simulation-based safety performances, with the development of safety performance function and crash modification factor. Two simulation analyses were conducted to find optimal lengths of lanes for different traffic conditions.
Article
Computer Science, Artificial Intelligence
Changlu Chen, Yanbin Liu, Ling Chen, Chengqi Zhang
Summary: Urban traffic forecasting is essential for intelligent transportation systems. This study introduces a bidirectional spatial-temporal adaptive transformer (Bi-STAT) that effectively addresses two intrinsic properties of the traffic forecasting problem. Experimental results demonstrate the superiority of Bi-STAT over existing methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Transportation
Han Liu, Ye Tian, Jian Sun, Di Wang
Summary: Traditional traffic simulation systems have limitations in performance and calibration/validation processes due to their use of independent models without considering their coupling relationship. In this study, a Data-Driven Simulation System (DDSS) framework was introduced to address this issue by defining traffic system operation processes and coordinating submodules. Experimental results showed that DDSS outperforms the widely used VISSIM simulation system in terms of accuracy and overall performance.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Engineering, Civil
Sepideh Emami Tabrizi, Kai Xiao, Jesse Van Griensven The, Muhammad Saad, Hani Farghaly, Simon X. Yang, Bahram Gharabaghi
Summary: In cold climates, road authorities apply salt on roads during winter to ensure public safety. Predicting pavement temperature can optimize road salt application, reduce costs, improve public safety, and decrease environmental impacts. This research developed a reliable and accurate pavement surface temperature prediction tool using machine learning techniques.
JOURNAL OF HYDROLOGY
(2021)
Article
Computer Science, Theory & Methods
Ke Yan, Xiaokang Zhou, Jinjun Chen
Summary: Energy consumption forecasting based on IoT data and deep learning algorithm is improved through a sophisticated multi-channel bidirectional nested LSTM framework combined with discrete stationary wavelet transform. Experimental results show the superior performance of the proposed method.
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
(2022)
Article
Automation & Control Systems
Huan Yu, Qijian Gan, Alexandre Bayen, Miroslav Krstic
Summary: This article presents a boundary observer for congested freeway traffic state estimation based on the ARZ model. The method allows the estimation of aggregated traffic states in a freeway segment from boundary measurements without knowledge of initial states, ensuring stability and convergence to zero of the estimation error system.
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY
(2021)
Article
Automation & Control Systems
Hamidreza Jahangir, Hanif Tayarani, Saleh Sadeghi Gougheri, Masoud Aliakbar Golkar, Ali Ahmadian, Ali Elkamel
Summary: The study introduces a precise forecasting method based on deep learning concept and microclustering task, which effectively handles a high volume of data in smart grids.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2021)
Article
Computer Science, Artificial Intelligence
Xiao Yan, Xianghua Gan, Rui Wang, Taojie Qin
Summary: This study proposes a video prediction model using a query-key-value self-attention mechanism in traffic flow forecasting. The model optimizes the long-term relationship by introducing self-attention mechanism from both algorithm and network architecture perspectives.
Article
Ergonomics
Xiaoxue Yang, Yajie Zou, Lei Chen
Summary: This study provides novel insights into the deployment of Connected and Autonomous Vehicles (CAVs) through the analysis of platoon strategy. The research finds that with increasing market penetration rate (MPR) of CAVs, road capacity increases and traffic oscillation reduces. However, the collision risk and severity of traffic conflicts also increase.
ACCIDENT ANALYSIS AND PREVENTION
(2022)
Article
Ergonomics
Zheng Xu, Xin Zou, Taeho Oh, Hai L. Vu
Summary: The study investigates drivers' perceptions and reactions towards freeway merging using a new approach with a multilevel simulation platform incorporating VR technology. Results show that conflict probability correlates positively with traffic flow, and the presence of ramp metering affects conflict frequency at freeway merges. The study suggests that the proposed VR simulation platform is beneficial for improving freeway merging safety and enhancing driver skills.
JOURNAL OF SAFETY RESEARCH
(2021)
Article
Chemistry, Multidisciplinary
Paweena Suebsombut, Aicha Sekhari, Pradorn Sureephong, Abdelhak Belhi, Abdelaziz Bouras
Summary: Water is essential for crop production, but becoming scarce. Proper irrigation scheduling can improve crop yield and quality. Soil Moisture (SM) is a key irrigation parameter. Predicting future soil moisture using machine learning is valuable for water optimization and crop yield.
APPLIED SCIENCES-BASEL
(2021)
Article
Astronomy & Astrophysics
Jun Tang, Dengpan Yang, Mingfei Ding
Summary: This paper presents a deep learning model based on Bidirectional long short-term memory (BiLSTM) and attention mechanism for predicting the critical frequency of the ionospheric F2 layer (foF2). The model outperforms other models and shows the best performance at high latitudes and during winter. The model's prediction performance is also improved under different geomagnetic conditions.
SPACE WEATHER-THE INTERNATIONAL JOURNAL OF RESEARCH AND APPLICATIONS
(2023)