scholarly journals Machine learning of Truck Traffic Classification groups from Weigh-in-Motion data

2021 ◽  
pp. 100178
Author(s):  
Narges Tahaei ◽  
Jidong J. Yang ◽  
Mi Geum Chorzepa ◽  
S. Sonny Kim ◽  
Stephan A. Durham
Keyword(s):  
Machine Learning ◽  
Traffic Classification ◽  
Truck Traffic ◽  
Motion Data ◽  
Weigh In Motion

scholarly journals Creation of Truck Axle Load Spectra Using Weigh-in-Motion Data

2010 ◽  
Vol 47 (4) ◽  
Author(s):  
Yi Jiang ◽  
Shuo Li ◽  
Tommy Nantung ◽  
Kirk Mangold ◽  
Scott A. MacArthur
Keyword(s):  
Design Method ◽  
Pavement Design ◽  
Smooth Transition ◽  
Traffic Information ◽  
Truck Traffic ◽  
Motion Data ◽  
Load Spectra ◽  
Weigh In Motion ◽  
Adjustment Factors ◽  
Axle Loads

To assure a smooth transition from the existing pavement design methods to the new mechanistic-empirical design method in the Indiana Department of Transportation, a study was conducted to create truck traffic inputs and axle load spectra of major interstate and state-owned highways in Indiana. The existing pavement design method is based on the equivalent single-axle loads (ESAL), which converts wheel loads of various magnitudes and repetitions to an equivalent number of "standard" or "equivalent" axle loads. The new design method uses axle load spectra as the measure of vehicle loads on pavements. These spectra represent the percentage of the total axle applications within each load interval for single, tandem, tridem, and quad axles. In this study, the truck traffic and axle load spectra were developed based on the historical traffic data collected at 47 sites with weigh-in-motion technology. The truck traffic information includes hourly, daily, and monthly distributions of various types of vehicles and corresponding adjustment factors, the distributions of the number of axles of each type of truck, the weights of the axles, the spaces between the axles, the proportions of vehicles on roadway lanes, and the proportions of vehicles in driving directions. This paper presents the truck traffic and axle load spectra generated from the weigh-in-motion sites as required by the new pavement design method.

scholarly journals Effects of Revised Toll-by-Weight Policy on Truck Overloading Behavior and Bridge Infrastructure Damage Using Weigh-in-Motion Data: A Comparative Study in China

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Haiyun Huang ◽  
Junyong Zhou ◽  
Junping Zhang ◽  
Wangxi Xu ◽  
Zhixing Chen ◽  
...  
Keyword(s):  
Transportation Network ◽  
Structural Safety ◽  
Chinese Government ◽  
Truck Traffic ◽  
Highway Infrastructure ◽  
Motion Data ◽  
Weigh In Motion ◽  
Traffic Volumes ◽  
Infrastructure Performance ◽  
Equivalent Load

Since 2000, overloaded trucks have caused more than 50 bridges to collapse in China. In an effort to ensure the structural safety and extend the service life of the highway infrastructure, the Chinese government has proposed a series of policies in the past decade to mitigate truck overloading. This study aimed at investigating the effects of China’s recently revised toll-by-weight policy on truck overloading behavior and bridge infrastructure damage using weigh-in-motion data that spanned seven years (January 2011 to March 2018) and two successive toll-by-weight policies (with the new one implemented from August 2016), wherein truck data were measured from a typical national freeway segment. We first compared truck traffic volumes, compositions, and weight distributions under the initial and revised toll-by-weight policies. Next, we compared bridge infrastructure performance with respect to safety and fatigue based on the overloaded truck traffic observed under the initial and revised toll-by-weight policies. The results indicated that the revised toll-by-weight policy, which uses a stepwise incremental fee structure based on vehicle weight, was more effective at controlling truck overloading behavior and reducing bridge infrastructure damage than the initial toll-by-weight policy. Under the current policy, average daily truck volumes, overloaded truck proportions, and maximum truck weights decreased significantly. Concurrently, extreme and equivalent load effects for safety and fatigue assessments, respectively, decreased by an average of 20% for small- to medium-span bridges. Despite these noted improvements, overloaded truck traffic persisted, with loads often exceeding bridge design levels. This study’s findings can support future efforts by the Chinese government to further refine their toll-by-weight policies and subsequently ensure a safe and viable transportation network.

Procedure to Estimate Loading from Weigh-in-Motion Data

1996 ◽  
Vol 1536 (1) ◽  
pp. 19-24
Author(s):  
Shie-Shin Wu
Keyword(s):  
Monitoring Program ◽  
Traffic Monitoring ◽  
Traffic Classification ◽  
Traffic Loading ◽  
Motion Data ◽  
Weigh In Motion ◽  
Load Factors ◽  
Different Types ◽  
Truck Load ◽  
Truck Weight

Truck weight data collected from weigh-in-motion (WIM) sites were used to develop a procedure to estimate truck load factors for pavement design purposes. A conceptual procedure that uses WIM data to derive equivalent single-axle load factors for different types of trucks is presented. Sets of load factors can be developed for different types of facilities. An example is provided to illustrate how these factors can be used by engineers to calculate project design loading. Applying these factors to traffic classification counts collected from the statewide traffic monitoring program, engineers can also compute network traffic loading history.

Mapping of truck traffic in New Jersey using weigh-in-motion data

2018 ◽  
Vol 12 (9) ◽  
pp. 1053-1061
Author(s):  
Sami Demiroluk ◽  
Kaan Ozbay ◽  
Hani Nassif
Keyword(s):  
New Jersey ◽  
Truck Traffic ◽  
Motion Data ◽  
Weigh In Motion

Research on the expression of new visual intelligence system based on machine learning technology

2021 ◽  
pp. 1-9
Author(s):  
Zuoshan Li
Keyword(s):  
Machine Learning ◽  
Intelligent System ◽  
Science And Technology ◽  
Learning Technology ◽  
3D Animation ◽  
Motion Data ◽  
Intelligence System ◽  
New Science ◽  
Continuous Progress ◽  
Internet Of Things Technology

With the continuous progress of society, the level of science and technology of the country has made a leap forward development, the research energy of various industries on new science and technology continues to deepen, greatly promoting the promotion of science and technology. At the same time, with the increase in social pressure, more and more people pursue spiritual relaxation, and appropriate leisure and entertainment activities have gradually become a part of people’s life. Film plays an irreplaceable role in leisure and entertainment. Mainly from the background of the development of the film industry towards intelligent direction, and then use machine learning technology to study the application of film animation production and film virtual assets analysis and investigation. Based on the Internet of things technology, we also vigorously develop the ways and methods of visual expression of movies, and at the same time introduce new expression modes to promote the expression effect of the intelligent system. Finally, by comparing various algorithms in machine learning technology, the results of intelligent expression of random number forest algorithm in machine learning technology are more accurate. The system is also applied to 3D animation production to observe the measurement error of 3D motion data and facial expression data.

scholarly journals Research on QoS Classification of Network Encrypted Traffic Behavior Based on Machine Learning

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1376
Author(s):  
Yung-Fa Huang ◽  
Chuan-Bi Lin ◽  
Chien-Min Chung ◽  
Ching-Mu Chen
Keyword(s):  
Machine Learning ◽  
Majority Voting ◽  
Deep Packet Inspection ◽  
Traffic Classification ◽  
K 13 ◽  
Packet Inspection ◽  
Majority Voting Method ◽  
Encrypted Traffic ◽  
Traffic Behavior

In recent years, privacy awareness is concerned due to many Internet services have chosen to use encrypted agreements. In order to improve the quality of service (QoS), the network encrypted traffic behaviors are classified based on machine learning discussed in this paper. However, the traditional traffic classification methods, such as IP/ASN (Autonomous System Number) analysis, Port-based and deep packet inspection, etc., can classify traffic behavior, but cannot effectively handle encrypted traffic. Thus, this paper proposed a hybrid traffic classification (HTC) method based on machine learning and combined with IP/ASN analysis with deep packet inspection. Moreover, the majority voting method was also used to quickly classify different QoS traffic accurately. Experimental results show that the proposed HTC method can effectively classify different encrypted traffic. The classification accuracy can be further improved by 10% with majority voting as K = 13. Especially when the networking data are using the same protocol, the proposed HTC can effectively classify the traffic data with different behaviors with the differentiated services code point (DSCP) mark.

Duration prediction of Chilean strong motion data using machine learning

2021 ◽  
Vol 109 ◽  
pp. 103253
Author(s):  
Sarit Chanda ◽  
M.C. Raghucharan ◽  
K.S.K. Karthik Reddy ◽  
Vasudeo Chaudhari ◽  
Surendra Nadh Somala
Keyword(s):  
Machine Learning ◽  
Strong Motion ◽  
Strong Motion Data ◽  
Motion Data ◽  
Duration Prediction

scholarly journals MODC: A Pareto-Optimal Optimization Approach for Network Traffic Classification Based on the Divide and Conquer Strategy

Information ◽  
2018 ◽  
Vol 9 (9) ◽  
pp. 233 ◽  
Author(s):  
Zuleika Nascimento ◽  
Djamel Sadok
Keyword(s):  
Machine Learning ◽  
Network Traffic ◽  
Machine Learning Algorithms ◽  
Divide And Conquer ◽  
Pareto Optimal ◽  
Optimization Approach ◽  
Traffic Classification ◽  
Multi Objective ◽  
Network Traffic Classification ◽  
Changes Over Time

Network traffic classification aims to identify categories of traffic or applications of network packets or flows. It is an area that continues to gain attention by researchers due to the necessity of understanding the composition of network traffics, which changes over time, to ensure the network Quality of Service (QoS). Among the different methods of network traffic classification, the payload-based one (DPI) is the most accurate, but presents some drawbacks, such as the inability of classifying encrypted data, the concerns regarding the users’ privacy, the high computational costs, and ambiguity when multiple signatures might match. For that reason, machine learning methods have been proposed to overcome these issues. This work proposes a Multi-Objective Divide and Conquer (MODC) model for network traffic classification, by combining, into a hybrid model, supervised and unsupervised machine learning algorithms, based on the divide and conquer strategy. Additionally, it is a flexible model since it allows network administrators to choose between a set of parameters (pareto-optimal solutions), led by a multi-objective optimization process, by prioritizing flow or byte accuracies. Our method achieved 94.14% of average flow accuracy for the analyzed dataset, outperforming the six DPI-based tools investigated, including two commercial ones, and other machine learning-based methods.

Sign in / Sign up

Export Citation Format

Share Document