scholarly journals Transfer Learning: Video Prediction and Spatiotemporal Urban Traffic Forecasting

Algorithms ◽  
2020 ◽  
Vol 13 (2) ◽  
pp. 39 ◽  
Author(s):  
Pavlyuk
Keyword(s):  
Time Series ◽  
Transfer Learning ◽  
Prediction Models ◽  
Urban Traffic ◽  
Modern Concept ◽  
Time Series Models ◽  
Traffic Data ◽  
Data Set ◽  
Traffic Forecasting ◽  
Video Prediction

Transfer learning is a modern concept that focuses on the application of ideas, models, and algorithms, developed in one applied area, for solving a similar problem in another area. In this paper, we identify links between methodologies in two fields: video prediction and spatiotemporal traffic forecasting. The similarities of the video stream and citywide traffic data structures are discovered and analogues between historical development and modern states of the methodologies are presented and discussed. The idea of transferring video prediction models to the urban traffic forecasting domain is validated using a large real-world traffic data set. The list of transferred techniques includes spatial filtering by predefined kernels in combination with time series models and spectral graph convolutional artificial neural networks. The obtained models’ forecasting performance is compared to the baseline traffic forecasting models: non-spatial time series models and spatially regularized vector autoregression models. We conclude that the application of video prediction models and algorithms for urban traffic forecasting is effective both in terms of observed forecasting accuracy and development, and training efforts. Finally, we discuss problems and obstacles of transferring methodologies and present potential directions for further research.

scholarly journals Video based Traffic Forecasting using Convolution Neural Network Model and Transfer Learning Techniques

2020 ◽  
Vol 2 (3) ◽  
pp. 128-134 ◽  
Author(s):  
Dr. T. Senthil Kumar
Keyword(s):  
Time Series ◽  
Transfer Learning ◽  
Large Data ◽  
Urban Traffic ◽  
Modern Concept ◽  
Time Series Models ◽  
Data Set ◽  
Smart Systems ◽  
Traffic Forecasting ◽  
Video Prediction

The ideas, algorithms and models developed for application in one particular domain can be applied for solving similar issues in a different domain using the modern concept termed as transfer learning. The connection between spatiotemporal forecasting of traffic and video prediction is identified in this paper. With the developments in technology, traffic signals are replaced with smart systems and video streaming for analysis and maintenance of the traffic all over the city. Processing of these video streams requires lot of effort due to the amount of data that is generated. This paper proposed a simplified technique for processing such voluminous data. The large data set of real-world traffic is used for prediction and forecasting the urban traffic. A combination of predefined kernels are used for spatial filtering and several such transferred techniques in combination will convolutional artificial neural networks that use spectral graphs and time series models. Spatially regularized vector autoregression models and non‐spatial time series models are the baseline traffic forecasting models that are compared for forecasting the performance. In terms of training efforts, development as well as forecasting accuracy, the efficiency of urban traffic forecasting is high on implementation of video prediction algorithms and models. Further, the potential research directions are presented along the obstacles and problems in transferring schemes.

Deep Learning Based Classification of Time Series of Chaotic Systems over Graphic Images

2021 ◽  
Author(s):  
Süleyman UZUN ◽  
Sezgin KAÇAR ◽  
Burak ARICIOĞLU
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Transfer Learning ◽  
Chaotic Systems ◽  
Initial Conditions ◽  
Step Size ◽  
Learning Methods ◽  
Data Set ◽  
Graphic Images ◽  
Different Chaotic Systems

Abstract In this study, for the first time in the literature, identification of different chaotic systems by classifying graphic images of their time series with deep learning methods is aimed. For this purpose, a data set is generated that consists of the graphic images of time series of the most known three chaotic systems: Lorenz, Chen, and Rossler systems. The time series are obtained for different parameter values, initial conditions, step size and time lengths. After generating the data set, a high-accuracy classification is performed by using transfer learning method. In the study, the most accepted deep learning models of the transfer learning methods are employed. These models are SqueezeNet, VGG-19, AlexNet, ResNet50, ResNet101, DenseNet201, ShuffleNet and GoogLeNet. As a result of the study, classification accuracy is found between 96% and 97% depending on the problem. Thus, this study makes association of real time random signals with a mathematical system possible.

scholarly journals A Period-Aware Hybrid Model Applied for Forecasting AQI Time Series

2020 ◽  
Vol 12 (11) ◽  
pp. 4730 ◽  
Author(s):  
Ping Wang ◽  
Hongyinping Feng ◽  
Guisheng Zhang ◽  
Daizong Yu
Keyword(s):  
Time Series ◽  
Air Quality ◽  
Hybrid Model ◽  
Prediction Models ◽  
Time Series Prediction ◽  
Input Vector ◽  
Period Function ◽  
Data Set ◽  
Luenberger Observer ◽  
Extraction Algorithm

An accurate, reliable and stable air quality prediction system is conducive to the public health and management of atmospheric ecological environment; therefore, many models, individual or hybrid, have been implemented widely to deal with the prediction problem. However, many of these models do not take into consideration or extract improperly the period information in air quality index (AQI) time series, which impacts the models’ learning efficiency greatly. In this paper, a period extraction algorithm is proposed by using a Luenberger observer, and then a novel period-aware hybrid model combined the period extraction algorithm and tradition time series models is build to exploit the comprehensive forecasting capacity to the AQI time series with nonlinear and non-stationary noise. The hybrid model requires a multi-phase implementation. In the first step, the Luenberger observer is used to estimate the implied period function in the one-dimensional AQI series, and then the analyzed time series is mapped to the period space through the function to obtain the period information sub-series of the original series. In the second step, the period sub-series is combined with the original input vector as input vector components according to the time points to establish a new data set. Finally, the new data set containing period information is applied to train the traditional time series prediction models. Both theoretical proof and experimental results obtained on the AQI hour values of Beijing, Tianjin, Taiyuan and Shijiazhuang in North China prove that the hybrid model with period information presents stronger robustness and better forecasting accuracy than the traditional benchmark models.

MACHINE LEARNING ON CONGESTION ANALYSIS BASED REAL-TIME NAVIGATION SYSTEM

2011 ◽  
Vol 20 (04) ◽  
pp. 753-781
Author(s):  
KAI CHEN ◽  
KIA MAKKI ◽  
NIKI PISSINOU
Keyword(s):  
Machine Learning ◽  
Travel Time ◽  
Real Time ◽  
Navigation System ◽  
Prediction Models ◽  
Urban Traffic ◽  
Route Guidance ◽  
Highway Traffic ◽  
Data Set ◽  
Guidance Systems

In the metropolitan region, most congestion or traffic jams are caused by the uneven distribution of traffic flow that creates bottleneck points where the traffic volume exceeds the road capacity. Additionally, unexpected incidents are the next most probable cause of these bottleneck regions. Moreover, most drivers are driving based on their empirical experience without awareness of real-time traffic situations. This unintelligent traffic behavior can make the congestion problem worse. Prediction based route guidance systems show great improvements in solving the inefficient diversion strategy problem by estimating future travel time when calculating accurate travel time is difficult. However, performances of machine learning based prediction models that are based on the historical data set degrade sharply during a congestion situation. This paper develops a new navigation system for reducing travel time of an individual driver and distributing the flow of urban traffic efficiently in order to reduce the occurrence of congestion. Compared with previous route guidance systems, the results reveal that our system, applying the advanced multi-lane prediction based real-time fastest path (AMPRFP) algorithm, can significantly reduce the travel time especially when drivers travel in a complex route environment and face frequent congestion problems. Unlike the previous system,1 it can be applied either for single lane or multi-lane urban traffic networks where the reason for congestion is significantly complex. We also demonstrate the advantages of this system and verify the results using real highway traffic data and a synthetic experiment.

scholarly journals Prediction of Traffic Generated by IoT Devices Using Statistical Learning Time Series Algorithms

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Shilpa P. Khedkar ◽  
R. Aroul Canessane ◽  
Moslem Lari Najafi
Keyword(s):  
Time Series ◽  
Network Traffic ◽  
Prediction Models ◽  
Forecast Model ◽  
Congestion Management ◽  
Traffic Prediction ◽  
Traffic Forecasting ◽  
Highly Sensitive ◽  
Iot Devices ◽  
Prediction Techniques

An IoT is the communication of sensing devices linked to the Internet in order to communicate data. IoT devices have extremely critical reliability with an efficient and robust network condition. Based on enormous growth in devices and their connectivity, IoT contributes to the bulk of Internet traffic. Prediction of network traffic is very important function of any network. Traffic prediction is important to ensure good system efficiency and ensure service quality of IoT applications, as it relies primarily on congestion management, admission control, allocation of bandwidth to the system, and the identification of anomalies. In this paper, a complete overview of IoT traffic forecasting model using classic time series and artificial neural network is presented. For prediction of IoT traffic, real network traces are used. Prediction models are evaluated using MAE, RMSE, and R -squared values. The experimental results indicate that LSTM- and FNN-based predictive models are highly sensitive and can therefore be used to provide better performance as a timing sequence forecast model than the conventional traffic prediction techniques.

scholarly journals Forecasting the COVID-19 Outbreak: An Application of Arima and Fuzzy Time Series Models

2020 ◽  
Author(s):  
Prashant Verma ◽  
Mukti Khetan ◽  
Shikha Dwivedi ◽  
Shweta Dixit
Keyword(s):  
Time Series ◽  
Health Care Systems ◽  
Medical Personnel ◽  
Fuzzy Time Series ◽  
Time Series Models ◽  
Data Set ◽  
Care Systems ◽  
Novel Coronavirus ◽  
Time Series Methodology ◽  
Near Future

Abstract Purpose: The whole world is surfaced with an inordinate challenge of mankind due to COVID-19, caused by 2019 novel coronavirus (SARS-CoV-2). After taking hundreds of thousands of lives, millions of people are still in the substantial grasp of this virus. This virus is highly contagious with reproduction number R0, as high as 6.5 worldwide and between 1.5 to 2.6 in India. So, the number of total infections and the number of deaths will get a day-to-day hike until the curve flattens. Under the current circumstances, it becomes inevitable to develop a model, which can anticipate future morbidities, recoveries, and deaths. Methods: We have developed some models based on ARIMA and FUZZY time series methodology for the forecasting of COVID-19 infections, mortalities and recoveries in India and Maharashtra explicitly, which is the most affected state in India, following the COVID-19 statistics till “Lockdown 3.0” (17th May 2020). Results: Both models suggest that there will be an exponential uplift in COVID-19 cases in the near future. We have forecasted the COVID-19 data set for next seven days. The forecasted values are in good agreement with real ones for all six COVID-19 scenarios for Maharashtra and India as a whole as well.Conclusion: The forecasts for the ARIMA and FUZZY time series models will be useful for the policymakers of the health care systems so that the system and the medical personnel can be prepared to combat the pandemic.

scholarly journals Influence of the range of data on the performance of ANN- and SVM- based time series models for reproducing groundwater level observations

2019 ◽  
Author(s):  
Heesung Yoon ◽  
Yongcheol Kim ◽  
Soo-Hyoung Lee ◽  
Kyoochul Ha
Keyword(s):  
Time Series ◽  
Groundwater Level ◽  
Model Building ◽  
Model Performance ◽  
Support Vector ◽  
Time Series Models ◽  
Ann Model ◽  
Data Set ◽  
Groundwater Level Fluctuations ◽  
Numerical Tests

In the present study, we designed time series models for predicting groundwater level fluctuations using an artificial neural network (ANN) and a support vector machine (SVM). To estimate the model sensitivity to the range of data set for the model building, numerical tests were conducted using hourly measured groundwater level data at a coastal aquifer of Jeju Island in South Korea. The model performance of the two models is similar and acceptable when the range of input variable lies within the data set for the model building. However, when the range of input variables is beyond it, both the models showed abnormal prediction results: an oscillation for the ANN model and a constant value for SVM. The result of the numerical tests indicates that it is necessary to obtain various types of input and output variables and assign them to the model building process for the success of design time series models of groundwater level prediction.

Forecasting Website Traffic Using Prophet Time Series Model

2019 ◽  
Vol 1 (1) ◽  
pp. 56-63
Author(s):  
A Subashini ◽  
Sandhiya K ◽  
S Saranya ◽  
U Harsha
Keyword(s):  
Time Series ◽  
Big Data ◽  
Traffic Flow ◽  
Prediction Models ◽  
Internet Traffic ◽  
Time Series Model ◽  
Traffic Data ◽  
Traffic Flow Prediction ◽  
Flow Monitoring ◽  
Flow Prediction

Web traffic is the amount of data sent and received by visitors to a website and it has been the largest portion of Internet traffic. Internet traffic flow prediction heavily depends on historical and real-time traffic data collected from various internet flow monitoring sources. With the widespread traditional traffic sensors and new emerging traffic sensor technologies, traffic data are exploding, and we have entered the era of big data internet traffic. Internet traffic management and control driven by big data is becoming a new trend. Although there have been already many internet traffic flow prediction systems and models, most of which use shallow traffic models and are still somewhat unsatisfying. This inspires us to reconsider the internet traffic flow prediction model based on deep architecture models with such rich amount of internet traffic data. ARIMA is a existing forecasting technique that predicts the future values of a series based entirely on its own inertia. Existing traffic flow prediction methods mainly use simple traffic prediction models and are still unsatisfying for many real-world applications. Now we proposed the prophet time series model to forecasting website traffic.

Continuous ACO in a SVR Traffic Forecasting Model

2011 ◽  
pp. 410-417
Author(s):  
Wei-Chiang Samuelson Hong
Keyword(s):  
Time Series ◽  
Travel Time ◽  
Traffic Flow ◽  
Urban Traffic ◽  
Forecasting Model ◽  
Risk Minimization ◽  
Minimization Principle ◽  
Traffic Forecasting ◽  
Proposed Model ◽  
Fuel Costs

The effective capacity of inter-urban motorway networks is an essential component of traffic control and information systems, particularly during periods of daily peak flow. However, slightly inaccurate capacity predictions can lead to congestion that has huge social costs in terms of travel time, fuel costs and environment pollution. Therefore, accurate forecasting of the traffic flow during peak periods could possibly avoid or at least reduce congestion. Additionally, accurate traffic forecasting can prevent the traffic congestion as well as reduce travel time, fuel costs and pollution. However, the information of inter-urban traffic presents a challenging situation; thus, the traffic flow forecasting involves a rather complex nonlinear data pattern and unforeseen physical factors associated with road traffic situations. Artificial neural networks (ANNs) are attracting attention to forecast traffic flow due to their general nonlinear mapping capabilities of forecasting. Unlike most conventional neural network models, which are based on the empirical risk minimization principle, support vector regression (SVR) applies the structural risk minimization principle to minimize an upper bound of the generalization error, rather than minimizing the training errors. SVR has been used to deal with nonlinear regression and time series problems. This investigation presents a short-term traffic forecasting model which combines SVR model with continuous ant colony optimization (SVRCACO), to forecast inter-urban traffic flow. A numerical example of traffic flow values from northern Taiwan is employed to elucidate the forecasting performance of the proposed model. The simulation results indicate that the proposed model yields more accurate forecasting results than the seasonal autoregressive integrated moving average (SARIMA) time-series model.

Sign in / Sign up

Export Citation Format

Share Document