Traffic Flows Forecasting Based on Machine Learning

Deart, Vladimir; Mankov, Vladimir; Krasnova, Irina A.

doi:10.4018/ijertcs.289198

Cited by 4 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised learning methods are fast and accurate but can only predict classes known to the model initially. For unsupervised learning methods, class values are not defined, which complicates the task and reduces prediction accuracy, but it is possible to detect new classes (Deart et al, 2022). Implementing such resources can be expensive and demanding in previously analyzed technical parameters and difficult to achieve in IoE/IoT smart environment.…”

Section: Existing Methodsmentioning

confidence: 99%

One Approach to Improving Smart Environment Communication via the Security Parameter

Behlilovic¹

2022

International Journal of Embedded and Real-Time Communication Systems

View full text Add to dashboard Cite

Improving smart environment communication remains a final unachievable destination. Continuous optimization in smart environment communication is mandatory because of an emerging number of connected devices. Carefully observing its parameters and demands leads to acknowledging existing challenges and boundaries regarding areas covered with signal and possibilities of approaching network architecture, limited battery resources in certain nodes of network architecture, privacy, and security of existing data transfer. One approach to dealing with these communication challenges and boundaries is focusing on important technical parameters respectively, signal processing speed, communication nodes distance, and communication channel security. The aim of this article is to point out these most important communication parameters in smart environments and how changing those can affect communication. Its original contribution is represented in establishing principles for governing security parameters by using permanent magnets in order to produce Faraday's rotation and thus manipulate the whole process of communication in a smart environment.

show abstract

Section: Existing Methodsmentioning

confidence: 99%

One Approach to Improving Smart Environment Communication via the Security Parameter

Behlilovic¹

2022

International Journal of Embedded and Real-Time Communication Systems

View full text Add to dashboard Cite

show abstract

“…Although there are some known works on the problems of traffic forecasting, their effectiveness depends largely on the collected traffic data. Deart et al (2022) aimed to develop a model for predicting the traffic based on the classification using the random forest regression. Li et al (2022) developed an ensemble approach to learning or adaptive enhancement to reduce error.…”

Section: Literature Reviewmentioning

confidence: 99%

Optimization of Media Strategy via Marketing Mix Modeling in Retailing

Fareniuk

Chornous

2023

ECO

View full text Add to dashboard Cite

The paper describes the marketing mix modeling results for companies in nonfood retailing. The main objectives of the research are to demonstrate the viable way of making effective recommendations for optimizing the media strategy by modeling offline and online traffic to the stores based on econometric modeling and to develop a decision support system, which enhance the effective growth of business KPIs and an effective decision-making process. Econometric modeling, deeper data analysis, decision support were implemented on the data of one of the main retailers in Ukraine in a period before the full-scale Russian invasion. Estimating the impact of different communication channels on business results made basis for ROI calculations and optimization of media investments allocation among media channels by periods, video durations, type of advertising and with optimal weekly media pressure. ROMI calculation was based on the results of regression modeling, which estimate the level of traffic and sales generated by each media channel. The information-analytical decision support system based on an interactive dashboard has been developed for improvement of day-by-day business planning and management. The developed framework of regional strategy selection facilitates to the formation of a strategic vision on a regional scale and improves the quality of a regional media strategy.

show abstract

“…In recent years, with the extensive application of artificial intelligence methods such as machine learning and deep learning in the field of transportation, the prediction of traffic flow has achieved good research results in terms of a nonlinear relationship. Machine learning methods [ 8 ] (2022) can analyze complex and diverse data in-depth without any assumptions about the data. Understanding how to deeply analyze complex and diverse data through machine learning and make efficient use of information has become one of the main problems paid attention to by big data.…”

Section: Literature Reviewmentioning

confidence: 99%

Multi-Section Traffic Flow Prediction Based on MLR-LSTM Neural Network

Shi

2022

Sensors

View full text Add to dashboard Cite

As the aggravation of road congestion leads to frequent traffic crashes, it is necessary to relieve traffic pressure through traffic flow prediction. As well, the traffic flow of the target road section to be predicted is also closely related to the adjacent road sections. Therefore, in this paper, a prediction method based on the combination of multiple linear regression and Long-Short-Term Memory (MLR-LSTM) is proposed, which uses the incomplete traffic flow data in the past period of time of the target prediction section and the continuous and complete traffic flow data in the past period of time of each adjacent section to jointly predict the traffic flow changes of the target section in a short time. The accurate prediction of future traffic flow changes can be solved based on the model supposed when the traffic flow data of the target road section is partially missing in the past period of time. The accuracy of the prediction results is the same as that of the current mainstream prediction results based on continuous and non-missing target link flow data. Meanwhile, there is a small-scale improvement when the data time interval is short enough. In the case of frequent maintenance of cameras in actual traffic sections, the proposed prediction method is more feasible and can be widely used.

show abstract

Traffic Flows Forecasting Based on Machine Learning

Cited by 4 publications

References 16 publications

One Approach to Improving Smart Environment Communication via the Security Parameter

One Approach to Improving Smart Environment Communication via the Security Parameter

Optimization of Media Strategy via Marketing Mix Modeling in Retailing

Multi-Section Traffic Flow Prediction Based on MLR-LSTM Neural Network

Contact Info

Product

Resources

About