An Improved K-nearest Neighbor Model for Short-term Traffic Flow Prediction

Zhang, Lun; Liu, Qiuchen; Yang, Wenchen; Nai, Wei; Dong, Dezun

doi:10.1016/j.sbspro.2013.08.076

Cited by 237 publications

(94 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In nonparametric models, the algorithms 'learn' from the data, thereby selecting the function that best fits the training dataset, meaning they can fit many functions to a particular dataset [16]. The k-Nearest Neighbour (k-NN) is mostly considered the easiest to implement nonparametric machine learning model [34] and has been widely explored in traffic prediction [34,40,43]. The logic driving the model is that the with the categorisation of k most similar observations in a feature space, then a new observed sample will likely belong to this category [42].…”

Section: Short-term Traffic Predictionmentioning

confidence: 99%

A deep-learning model for urban traffic flow prediction with traffic events mined from twitter

Petrounias²,

et al. 2020

View full text Add to dashboard Cite

Short-term traffic parameter forecasting is critical to modern urban traffic management and control systems. Predictive accuracy in data-driven traffic models is reduced when exposed to non-recurring or non-routine traffic events, such as accidents, road closures, and extreme weather conditions. The analytical mining of data from social networksspecifically twittercan improve urban traffic parameter prediction by complementing traffic data with data representing events capable of disrupting regular traffic patterns reported in social media posts. This paper proposes a deep learning urban traffic prediction model that combines information extracted from tweet messages with traffic and weather information. The predictive model adopts a deep Bi-directional Long Short-Term Memory (LSTM) stacked autoencoder (SAE) architecture for multi-step traffic flow prediction trained using tweets, traffic and weather datasets. The model is evaluated on an urban road network in Greater Manchester, United Kingdom. The findings from extensive empirical analysis using real-world data demonstrate the effectiveness of the approach in improving prediction accuracy when compared to other classical/statistical and machine learning (ML) state-of-the-art models. The improvement in predictive accuracy can lead to reduced frustration for road users, cost savings for businesses, and less harm to the environment.

show abstract

Section: Short-term Traffic Predictionmentioning

confidence: 99%

A deep-learning model for urban traffic flow prediction with traffic events mined from twitter

Petrounias²,

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Cruz et al 18 studied the problem of processing k-NN queries in road networks considering traffic conditions and the queries return the k-points of interest that could be reached in the minimum amount of time. Zhang et al 19 presented a method for short-term urban expressway flow prediction system with accuracy over 90% using k-NN. Lin et al 20 applied k-NN method to form the training dataset for local linear wavelet neural network instead of taking the whole historical dataset for training for short-term prediction of five minutes volume.…”

Section: Literature Reviewmentioning

confidence: 99%

Soft Computing-Based Traffic Density Estimation Using Automated Traffic Sensor Data under Indian Conditions

Raj

Bahuleyan²,

Ramesh³

et al. 2017

Current Science

View full text Add to dashboard Cite

Traffic density is an indicator of congestion and the present study explores the use of data-driven techniques for real time estimation and prediction of traffic density. Data-driven techniques require large database, which can be achieved only with the help of automated sensors. However, the available automated sensors developed for western traffic may not work for heterogeneous and lane-less traffic. Hence, the performance of available automated sensors was evaluated first to identify the best inputs to be used for the chosen application. Using the selected data, implementation was carried out and the results obtained were promising, indicating the possibility of using the proposed methodology for real time traveller information under such traffic conditions. Keywords: Automated traffic sensors, artificial neural network, k-nearest neighbour, traffic density.WITH the fast growing urban population and increasing vehicle population, it is becoming difficult to implement efficient traffic management for Indian roads. Intelligent transportation systems (ITS) is viewed as an option to handle some of these issues and is becoming more popular under this scenario. ITS enable gathering of data and providing timely feedback to traffic managers and roadusers based on the real time data. Advanced traveller information system (ATIS) is a major functional area of ITS and it deals with providing real time traffic information to travellers for making informed travel decisions. The information provided can include expected travel time, congestion condition, locations of incidents, weather and road conditions, optimal routes, recommended speeds and lane restrictions.Traffic congestion information is most sought after, followed by travel time and travel speed information. However, congestion being qualitative in nature, there is a need to identify the best measure to quantify it. As per the Highway Capacity Manual (HCM) 1 , traffic density on freeways, delays at signalized intersections and walking speed for pedestrians are examples of measures of effectiveness that characterize traffic conditions on a facility.Of these, traffic density is the primary measure for quantifying congestion on roadways, other than the intersection areas. Traffic density is the number of vehicles occupying a given length of roadway. Density being a spatial variable makes it difficult to carry out direct measurements. Aerial photography is the primary approach to measure density directly from field, which is very difficult to implement. Hence, it is usually estimated from other location-based parameters such as speed, flow or occupancy, making it a challenging research problem. This problem of estimation of density from location based parameters such as volume and time mean speed (TMS) obtained using selected sensors is considered in this study. This becomes more challenging under Indian conditions, with heterogeneous and lane less-traffic, leading to high variability and randomness. In addition, these traffic conditions make automated data collection ...

show abstract

“…K-NN algorithm accuracy is greatly influenced by the presence or absence of features that are not relevant, or if the weight of such features is not equivalent to its relevance to the classification. Research on these algorithms largely discusses how to choose and give weight to the feature, in order to become a better classification performance [6], [7].…”

Section: K-nearest Neighbor (K-nn)mentioning

confidence: 99%

Clustering and Feature Selection Technique for Improving Internet Traffic Classification Using K-NN

Wiradinata¹,

Paramita²

2016

JACN

View full text Add to dashboard Cite

Abstract-This research will use the algorithm K-Nearest Neighbour (K-NN) to classify internet data traffic, K-NN is suitable for large amounts of data and can produce a more accurate classification, K-NN algorithm has a weakness takes computing high because K-NN algorithm calculating the distance of all existing data. One solution to overcome these weaknesses is to do the clustering process before the classification process, because the clustering process does not require high computing time, clustering algorithm that can be used is Fuzzy C-Mean algorithm, the Fuzzy C-Mean algorithm does not need to be determined in first number of clusters to be formed, clusters that form on this algorithm will be formed naturally based datasets be entered, but the algorithm Fuzzy C-Mean has the disadvantage of clustering results obtained are often not the same even though the same input data, this is because the initial dataset that of the Fuzzy C-Mean is not optimal, to optimize initial datasets in this research using feature selection algorithm, after main feature of dataset selected the output from fuzzy C-Mean become consistent. Selection of the features is a method that is expected to provide an initial dataset that is optimum for the algorithm Fuzzy C-Means. Algorithms for feature selection in this study used are Principal Component Analysis (PCA). PCA reduced non significant attribute to created optimal dataset and can improve performance clustering and classification algorithm. Results in this study is an combining method of classification, clustering and feature extraction of data, these three methods successfully modeled to generate a data classification method of internet bandwidth usage that has high accuracy and have a fast performance.

show abstract

An Improved K-nearest Neighbor Model for Short-term Traffic Flow Prediction

Cited by 237 publications

References 3 publications

A deep-learning model for urban traffic flow prediction with traffic events mined from twitter

A deep-learning model for urban traffic flow prediction with traffic events mined from twitter

Soft Computing-Based Traffic Density Estimation Using Automated Traffic Sensor Data under Indian Conditions

Clustering and Feature Selection Technique for Improving Internet Traffic Classification Using K-NN

Contact Info

Product

Resources

About