Introduction
Surigao City is a 3rd class component city and capital of the province of Surigao Del Norte, Philippines According to the 2015 census, it has a population of 154,137 people.â
In this City Traffic congestion is normal issue in any street organization. At the point when the quantity of vehicles surpasses the furthest reaches of the street, it causes traffic congestion having various degrees of seriousness. Noticing and oversight of traffic for constant just as broadened term judgment is alluring both for strategy making and the overall population. The developing population in huge urban communities causing the consistently high requests of public vehicle has been one of the major contributing elements of traffic bottleneck issues throughout the long term. Commuters are suffering longer traveling time and having a problem related to planning their journey smoothly.
Save your time!
We can take care of your essay
- Proper editing and formatting
- Free revision, title page, and bibliography
- Flexible prices and money-back guarantee
There has been intriguing exploration on traffic congestion forecast dependent on constant traffic acquired through Google Maps API. With the fast extension of sensor advancements and remote organization foundation, innovative work of traffic related applications, such as real-time traffic maps, on-request travel course reference and traffic forecasting are acquiring considerably more consideration than before. In this paper we take Surigao City as a case study and present real-time traffic congestion results.Â
In this paper, our proposed system includes:
- Integrates ETA and weather data
- Labels data in accordance with ETA trends
- Identifies congestion index with time slot
- Applies machine learning techniques of Random Forest, Logistic regression and Naïve bayes, XGBoost, GradientBoost and KNN.
- And finally provides analysis of traffic patterns.
The execution can add to lessening the traffic and can help in free-streaming rush hour traffic congestion. It can likewise help in traffic light administration.
Review Related Literature
Urbanization in developing countries has been rapid during the past 20 years [1]. Increased vehicle usage has enhanced mobility for human activities but has also raised several serious issues, such as traffic congestion excessive fossil fuel consumption, climate change and air pollution [2].Vehicle emissions have created severe air pollution problems for global megacities, which are a major sector of urban emissions of carbon dioxide [3] and nitrogen oxide (NOX) [4].
An increasing number of vehicles and population density have created excessive demand for urban infrastructure. These trends pose a challenge to urban planners and policymakers as they need to plan land use in order to decrease traffic congestion with limited space in inner cities [5]. Understanding the complex interplay between extemporization patterns of traffic congestion and their drivers has been a particular challenge in urban management. Road networks provide accessibility for citizens, but congestion leads to increased gas consumption, traffic-related pollution [6]. and time delay [7]. Due to congestion, people in Beijing spend twice as much time travelling as they would otherwise [8].
Despite the abundance of studies on route optimization and planning, there is still insufficient knowledge of the factors governing congestion and its pattern. This highlights a need to study the potential drivers of traffic congestion and systematical solutions how to reduce congestion.
In their search for ways to alleviate traffic congestion, previous studies have focused on road design and construction [9], congestion prediction [10], traffic light realignment [11], and reducing car dependency [12] .
Many studies have generated conflicting results, most likely because the impact factors of traffic congestion have not been systematically studied. For instance, both positive and negative relationships have been found between population density and commuting time [13]. Job density and population were not found to be statistically significantly related to commuting time.However, more recently, access to real-time traffic data has enabled in-depth analyses of traffic congestion [14]. Real-time data from location-based services (LBS) provide new insights into traffic and urban challenges, e.g., avoiding city emergencies and land use planning [15]. Large multi-source datasets can be applied in urban and traffic studies. For instance, data on population mobility and traffic can be acquired from hand-held non-differential global positioning system (GPS) devices [16], mobile phones [17] ,smart cards [18], and floating car data [19], which can be utilized to study the spatio- temporal characteristics of individual behavior and traffic congestion.Video-based multiple-time remote-sensing imagery has also been used to track vehicles [20].
With the assistance of high-performance computing technology, fusing and mining multi-source data in a closed-loop system enables the quantification of fundamental spatio-temporal patterns to potentially gain a better understanding of human mobility and traffic congestion in urban areas [21], thus supporting the dynamic redistribution of resources in real-time [22].
For the past many years, one of the most important objectives on ITS research has been the development of systems that reduce incidents and traffic jams in urban traffics. It is said that half of all incidents can be avoided if drivers can become aware of potential dangerous situations 0.5 seconds before the moments of incidents. And if drivers can be aware of the occurred incidents, they will be able to avoid secondary incidents.They employed multiple video cameras, where one camera is facing in-coming vehicles and the other camera is facing vehicles inside the crossroad waiting to turn spot sensors such as loop detectors for local traffic monitoring [23].
Many related works employed image sensors for traffic monitoring. PATH project is well known for such kind of research [24]. Employed line-scan camera for traffic volume acquisition [25]. [26] performed experiments on detection of traffic congestion, obstacles, and fire or smoke utilizing images from video camera installed throughout tunnels.In addition, [27][28] attempted to monitor traffic precisely by using vehicle tracking algorithms from traffic images . And [1] applied a method of traffic rule reasoning to images of simple traffic conditions on a single lane straight road.
However, the occlusion problem had impeded object tracking from being put into practical use for many years. To resolve the problem, some previous works employed stereo vision method, and some other works employed shape models of objects to estimate texture matching with images[30].
References
- Cohen, B. (2006). Urbanization in developing countries: Current trends, future projections, and key challenges for sustainability. Technology in Society, 28, 63-80.
- https:doi.org10.1016j.techsoc.2005.10.005.
- Shindell D, Faluvegi G, Walsh M, Anenberg SC, Dingenen RV, Muller NZ, et al. Climate, health, agricultural and economic impacts of tighter vehicle-emission standards. Nat Clim Change 2011;1(1):59-66.
- Wu Y, Zhang S, Hao J, Liu H, Wu X, Hu J, et al. On-road vehicle emissions and their control in China: a review and outlook. Sci Total Environ 2017;574:332-49.
- U.S. Environmental Protection Agency (USEPA). National multipollutant emissions comparison by source sector. In: U.S. Environmental Protection Agency, Washington, DC; 2011.
- Alberti, M. (2008). Advances in urban ecology: integrating humans and ecological processes in urban ecosystems (No. 574.5268 A4). New York: Springer. Arai, K.,
Stuck on your essay?
