scholarly journals Air Traffic Prediction as a Video Prediction Problem Using Convolutional LSTM and Autoencoder

Aerospace ◽  
2021 ◽  
Vol 8 (10) ◽  
pp. 301
Author(s):  
Hyewook Kim ◽  
Keumjin Lee
Keyword(s):  
Loss Function ◽  
Traffic Management ◽  
Short Term Memory ◽  
Air Traffic Management ◽  
Air Traffic ◽  
Function Technique ◽  
Traffic Data ◽  
Short Term ◽  
Long Short Term Memory ◽  
New Framework

Accurate prediction of future air traffic situations is an essential task in many applications in air traffic management. This paper presents a new framework for predicting air traffic situations as a sequence of images from a deep learning perspective. An autoencoder with convolutional long short-term memory (ConvLSTM) is used, and a mixed loss function technique is proposed to generate better air traffic images than those obtained by using conventional L1 or L2 loss function. The feasibility of the proposed approach is demonstrated with real air traffic data.

scholarly journals Optimization of air traffic management efficiency based on deep learning enriched by the long short-term memory (LSTM) and extreme learning machine (ELM)

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Mahdi Yousefzadeh Aghdam ◽  
Seyed Reza Kamel Tabbakh ◽  
Seyed Javad Mahdavi Chabok ◽  
Maryam Kheyrabadi
Keyword(s):  
Deep Learning ◽  
Traffic Management ◽  
Short Term Memory ◽  
Air Traffic Management ◽  
Air Traffic ◽  
Short Term ◽  
Data Set ◽  
Term Memory ◽  
Data Mining Algorithms ◽  
Long Short Term Memory

AbstractNowadays this concept has been widely assessed due to its complexity and sensitivity for the beneficiaries, including passengers, airlines, regulatory agencies, and other organizations. To date, various methods (e.g., statistical and fuzzy techniques) and data mining algorithms (e.g., neural network) have been used to solve the issues of air traffic management (ATM) and delay the minimization problems. However, each of these techniques has some disadvantages, such as overlooking the data, computational complexities, and uncertainty. In this paper, to increase the air traffic management accuracy and legitimacy we used the bidirectional long short-term memory (Bi-LSTMs) and extreme learning machines (ELM) to design the structure of a deep learning network method. The Kaggle data set and different performance parameters and statistical criteria have been used in MATLAB to validate the proposed method. Using the proposed method has improved the criteria factors of this study. The proposed method has had a % increase in air traffic management in comparison to other papers. Therefore, it can be said that the proposed method has a much higher air traffic management capacity in comparison to the previous methods.

scholarly journals Optimization of Air Traffic Management Efficiency Based on Deep Learning Enriched by the Long Short-term Memory(LSTM) and Extreme Learning Machine(ELM)

2021 ◽  
Author(s):  
Mahdi Yousefzadeh Aghdam ◽  
Seyed Reza Kamel ◽  
Seyed Javad Mahdavi Chabok ◽  
maryam khairabadi
Keyword(s):  
Deep Learning ◽  
Traffic Management ◽  
Short Term Memory ◽  
Air Traffic Management ◽  
Air Traffic ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Learning Machine ◽  
Deep Learning Model

Abstract Air traffic management refers to the activities required for the efficient and safe management of the national air system (NAS) for each country. This concept has been widely assessed due to its complexity and sensitivity for the beneficiaries, including passengers, airlines, regulatory agencies, and other organizations. To date, various methods (e.g., statistical and fuzzy techniques) and data mining algorithms (e.g., neural network) have been used to solve the issues of air traffic management (ATM) and delay the minimization problems. However, each of these techniques has some disadvantages, such as overlooking the data, computational complexities, and uncertainty. The present study aimed to increase ATM efficiency using the deep learning approach. The main research objective was to propose a deep learning model with the application of a long short-term memory-based deep learning model in order to increase the predictive accuracy in short daily and long-term annual windows by enhancing deep learning (two-dimensional). In addition, the deep model output was transferred to the extreme learning machine fast learning deep neural machine in order to calculate the estimated time of arrival real-time based on other similar input data, including the NAS data, bureau of transportation statistics system, and automatic dependent surveillance-broadcast system. The final results indicated the increased accuracy of ATM compared to other studies.

scholarly journals Optimization of Air Traffic Management Efficiency Based on Deep Learning Enriched by the Long Short-term Memory(LSTM) and Extreme Learning Machine(ELM)

2020 ◽  
Author(s):  
Mahdi Yousefzadeh Aghdam ◽  
Seyed Reza Kamel ◽  
Seyed Javad Mahdavi Chabok ◽  
maryam khairabadi
Keyword(s):  
Deep Learning ◽  
Traffic Management ◽  
Short Term Memory ◽  
Air Traffic Management ◽  
Air Traffic ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Learning Machine ◽  
Deep Learning Model

Abstract Air traffic management refers to the activities required for the efficient and safe management of the national air system (NAS) for each country. This concept has been widely assessed due to its complexity and sensitivity for the beneficiaries, including passengers, airlines, regulatory agencies, and other organizations. To date, various methods (e.g., statistical and fuzzy techniques) and data mining algorithms (e.g., neural network) have been used to solve the issues of air traffic management (ATM) and delay the minimization problems. However, each of these techniques has some disadvantages, such as overlooking the data, computational complexities, and uncertainty. The present study aimed to increase ATM efficiency using the deep learning approach. The main research objective was to propose a deep learning model with the application of a long short-term memory-based deep learning model in order to increase the predictive accuracy in short daily and long-term annual windows by enhancing deep learning (two-dimensional). In addition, the deep model output was transferred to the extreme learning machine fast learning deep neural machine in order to calculate the estimated time of arrival real-time based on other similar input data, including the NAS data, bureau of transportation statistics system, and automatic dependent surveillance-broadcast system. The final results indicated the increased accuracy of ATM compared to other studies.

Predicting Coordinated Actuated Traffic Signal Change Times using Long Short-Term Memory Neural Networks

2021 ◽  
pp. 036119812110007
Author(s):  
Seifeldeen Eteifa ◽  
Hesham A. Rakha ◽  
Hoda Eldardiry
Keyword(s):  
Loss Function ◽  
Short Term Memory ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Loss Functions ◽  
Short Term ◽  
Mean Relative Error ◽  
Squared Error ◽  
The Mean ◽  
Long Short Term Memory

Vehicle acceleration and deceleration maneuvers at traffic signals result in significant fuel and energy consumption levels. Green light optimal speed advisory systems require reliable estimates of signal switching times to improve vehicle energy/fuel efficiency. Obtaining these estimates is difficult for actuated signals where the length of each green indication changes to accommodate varying traffic conditions and pedestrian requests. This study details a four-step long short-term memory (LSTM) deep learning based methodology that can be used to provide reasonable switching time estimates from green to red and vice versa while being robust to missing data. The four steps are data gathering, data preparation, machine learning model tuning, and model testing and evaluation. The input to the models includes controller logic, signal timing parameters, time of day, traffic state from detectors, vehicle actuation data, and pedestrian actuation data. The methodology is applied and evaluated on data from an intersection in Northern Virginia. A comparative analysis is conducted between different loss functions including the mean squared error, mean absolute error, and mean relative error used in LSTM and a new loss function that is proposed in this paper. The results show that while the proposed loss function outperforms conventional loss functions in overall absolute error values, the choice of the loss function is dependent on the prediction horizon. Specifically, the proposed loss function is slightly outperformed by the mean relative error for very short prediction horizons (less than 20 s) and the mean squared error for very long prediction horizons (greater than 120 s).

scholarly journals Data analytics for traffic flow prediction in Custom using Long Short Term Memory (LSTM) networks

2021 ◽  
Vol 2107 (1) ◽  
pp. 012006
Author(s):  
Lee Pin Loon ◽  
Elbaraa Refaie ◽  
Ahmad Athif Mohd Faudzi
Keyword(s):  
Traffic Flow ◽  
Traffic Management ◽  
Time Series Data ◽  
Short Term Memory ◽  
Series Data ◽  
Short Term ◽  
Term Memory ◽  
Traffic Flow Prediction ◽  
Flow Prediction ◽  
Long Short Term Memory

Abstract This paper proposes data analysis for traffic flow prediction of customs to help the officer in Customs, Immigration, and Quarantine (CIQ) Complex to understand more about the traffic situation in CIQ. Currently in CIQ, the traffic behaviour for car is unpredictable; sometimes the traffic is very heavy while there are times where all the lanes are cleared. There is a plan to have installation of cameras for smart traffic management system in the future. Therefore, this research aims to have prediction of traffic flow based on time and visualize the trend of traffic data for the officer. The data consist of traffic flow and the respective timestamp. To analyse it with time-series data, Long Short-Term Memory (LSTM) Recurrent Network is used as deep learning approach for prediction. The data pre-processing and training of model would be done using Python. To organize the data, Tableau Prep Builder is used and integrate with Python to publish the data to Tableau Server for storage. An interactive dashboard would be designed on Tableau and made available online for the usage of the officer.

scholarly journals The Deep 3D Convolutional Multi-Branching Spatial-Temporal-Based Unit Predicting Citywide Traffic Flow

2020 ◽  
Vol 10 (21) ◽  
pp. 7778 ◽  
Author(s):  
Zain Ul Abideen ◽  
Heli Sun ◽  
Zhou Yang ◽  
Amir Ali
Keyword(s):  
Traffic Flow ◽  
Traffic Congestion ◽  
Traffic Management ◽  
Short Term Memory ◽  
Time Estimation ◽  
External Factors ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Real World Datasets

Recently, for public safety and traffic management, traffic flow prediction is a crucial task. The citywide traffic flow problem is still a big challenge in big cities because of many complex factors. However, to handle some complex factors, e.g., spatial-temporal and some external factors in the intelligent traffic flow forecasting problem, spatial-temporal data for urban applications (i.e., travel time estimation, trajectory planning, taxi demand, traffic congestion, and the regional rainfall) is inherently stochastic and unpredictable. In this paper, we proposed a deep learning-based novel model called “multi-branching spatial-temporal attention-based long-short term memory residual unit (MBSTALRU)” for the citywide traffic flow from lower-level layers to high-level layers, simultaneously. In our work, initially, we have modeled the traffic flow with spatial correlations multiple 3D volume layers and propose the novel multi-branching scheme to control the spatial-temporal features. Our approach is useful for exploring temporal dependencies through the 3D convolutional neural network (CNN) multiple branches, which aim to merge the spatial-temporal characteristics of historical data with three-time intervals, namely closeness, daily, and weekly, and we have embedded features by attention-based long-short term memory (LSTM). Then, we capture the correlation between traffic inflow and outflow with residual layers units. In the end, we merge the external factors dynamically to predict citywide traffic flow simultaneously. The simulation results have been performed on two real-world datasets, BJTaxi and NYCBike, which show better performance and effectiveness of the proposed method than previous state-of-the-art models.

scholarly journals DistTune: Distributed Fine-Grained Adaptive Traffic Speed Prediction for Growing Transportation Networks

2021 ◽  
pp. 036119812110111
Author(s):  
Ming-Chang Lee ◽  
Jia-Chun Lin ◽  
Ernst Gunnar Gran
Keyword(s):  
Short Term Memory ◽  
Transportation Network ◽  
Traffic Data ◽  
Short Term ◽  
Fine Grained ◽  
The Past ◽  
Speed Prediction ◽  
Efficient Processing ◽  
Long Short Term Memory ◽  
Traffic Speed

Over the past decade, many approaches have been introduced for traffic speed prediction. However, providing fine-grained, accurate, time-efficient, and adaptive traffic speed prediction for a growing transportation network where the size of the network keeps increasing and new traffic detectors are constantly deployed has not been well studied. To address this issue, this paper presents DistTune based on long short-term memory (LSTM) and the Nelder-Mead method. When encountering an unprocessed detector, DistTune decides if it should customize an LSTM model for this detector by comparing the detector with other processed detectors in the normalized traffic speed patterns they have observed. If a similarity is found, DistTune directly shares an existing LSTM model with this detector to achieve time-efficient processing. Otherwise, DistTune customizes an LSTM model for the detector to achieve fine-grained prediction. To make DistTune even more time-efficient, DisTune performs on a cluster of computing nodes in parallel. To achieve adaptive traffic speed prediction, DistTune also provides LSTM re-customization for detectors that suffer from unsatisfactory prediction accuracy due to, for instance, changes in traffic speed patterns. Extensive experiments based on traffic data collected from freeway I5-N in California are conducted to evaluate the performance of DistTune. The results demonstrate that DistTune provides fine-grained, accurate, time-efficient, and adaptive traffic speed prediction for a growing transportation network.

Sign in / Sign up

Export Citation Format

Share Document