Segmentation of vehicle detector data for improved k‐nearest neighbours‐based traffic flow prediction

Bernaś, Marcin; Płaczek, Bartłomiej; Porwik, Piotr; Pamuła, T.

doi:10.1049/iet-its.2013.0164

Cited by 50 publications

(31 citation statements)

References 21 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parametric approach includes the historical average (HA) method, autoregressive moving average method (ARIMA) [6,7], seasonal autoregressive integrated moving average method (SARIMA) [8][9][10], and Kalman filter (KF) [11,12]. The nonparametric approach includes artificial neural networks (ANNS) [13][14][15][16][17], k-nearest neighbor (KNN) [18][19][20][21][22], support vector regression (SVR) [23,24], and the Bayesian model [25,26]. The hybrid approach mainly combines the parametric approach with the nonparametric approach [27][28][29][30][31][32][33][34][35].…”

Section: Introductionmentioning

confidence: 99%

Traffic Flow Prediction during the Holidays Based on DFT and SVR

Luo

Zhang

2019

Journal of Sensors

View full text Add to dashboard Cite

With the implementation of the freeway free policy during the holidays, traffic congestion in the freeway becomes a common phenomenon. In order to alleviate traffic pressure, traffic flow prediction during the holidays has become a problem of great concern. This paper proposes a hybrid prediction methodology combining discrete Fourier transform (DFT) with support vector regression (SVR). The common trend in the traffic flow data is extracted using DFT by setting an appropriate threshold, which is predicted by extreme extrapolation of the historical trend. The SVR method is applied to predict the residual series. The experimental results with measured data collected from the toll stations in Jiangsu province of China show that the proposed algorithm has higher accuracy compared with the traditional method, and it is an efficient method for traffic flow prediction during the holidays.

show abstract

Section: Introductionmentioning

confidence: 99%

Traffic Flow Prediction during the Holidays Based on DFT and SVR

Luo

Zhang

2019

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Most of cases researchers have implemented KNN method for prediction of financial products. The main motto of this algorithm is to classify the objects using majority voting procedure among neighbour data points and took the class which is getting major votes among all [23][24][25][26].…”

Section: B K-nearest Neighbors Algorithmmentioning

confidence: 99%

Forecasting Foreign Currency Exchange Price using Long Short-Term Memory with K-Nearest Neighbor Method

Nayak,

Pavitra,

Tripathy

et al. 2019

IJEAT

View full text Add to dashboard Cite

With the growing population in the world, economic stability varies day by day. In case of India all banking transaction rules and regulations are taken by Reserve bank of India (RBI) whereas for other countries it is different. Therefore numerous academicians have projected their research on forecasting the currency exchange rate for diverse countryside. Foreign currency exchange rate prediction is a very pivotal task for international market. Hence researchers have explored different methods for predicting foreign currency exchange rate. In this work, we have taken Indian rupees (INR) with two different country’s data set such as Japanese yen (JPY) andChinese Yuan (CNY)for daily, weekly and monthlyprediction beforehand. We implemented a hybrid model oflong short-term memory (LSTM) with K-nearest neighbour (KNN) which gives better opening price prediction accuracy on our dataset. The accuracy of the prediction results are measured by the help of performance standards such as mean absolute percentage error (MAPE) and root mean square error (RMSE).

show abstract

“…An important characteristic of time series is correlation and continuous change on the time scale. A possible approach to make use of such a characteristic is to use window based shifting, which have been used for kNN based time series prediction [20], [21]. Though this approach works well, it has not been used for imputation.…”

Section: Background and Related Workmentioning

confidence: 99%

An improved k-nearest neighbours method for traffic time series imputation

Sun

Cheng

et al. 2017

2017 Chinese Automation Congress (CAC)

View full text Add to dashboard Cite

Abstract-Intelligent transportation systems (ITS) are becoming more and more effective, benefiting from big data. Despite this, missing data is a problem that prevents many prediction algorithms in ITS from working effectively. Much work has been done to impute those missing data. Among different imputation methods, k-nearest neighbours (kNN) has shown excellent accuracy and efficiency. However, the general kNN is designed for matrix instead of time series so it lacks the usage of time series characteristics such as windows and weights that are gap-sensitive. This work introduces gap-sensitive windowed kNN (GSW-kNN) imputation for time series. The results show that GSW-kNN is 34% more accurate than benchmarking methods, and it is still robust even if the missing ratio increases to 90%.

show abstract

Segmentation of vehicle detector data for improved k‐nearest neighbours‐based traffic flow prediction

Cited by 50 publications

References 21 publications

Traffic Flow Prediction during the Holidays Based on DFT and SVR

Traffic Flow Prediction during the Holidays Based on DFT and SVR

Forecasting Foreign Currency Exchange Price using Long Short-Term Memory with K-Nearest Neighbor Method

An improved k-nearest neighbours method for traffic time series imputation

Contact Info

Product

Resources

About