Traffic emissions are considered one of the leading causes of environmental impact in megacities and their dangerous effects on human health. This paper presents a hybrid model based on data mining and GIS models designed to predict vehicular Carbon Monoxide (CO) emitted from traffic on the New Klang Valley Expressway, Malaysia. The hybrid model was developed based on the integration of GIS and the optimized Artificial Neural Network algorithm that combined with the Correlation based Feature Selection (CFS) algorithm to predict the daily vehicular CO emissions and generate prediction maps at a microscale level in a small urban area by using a field survey and open source data, which are the main contributions to this paper. The other contribution is related to the case study, which represents the spatial and quantitative variations in the vehicular CO emissions between toll plaza areas and road networks. The proposed hybrid model consists of three steps: the first step is the implementation of the correlation-based Feature Selection model to select the best model’s predictors; the second step is the prediction of vehicular CO by using a multilayer perceptron neural network model; and the third step is the creation of micro scale prediction maps. The model was developed using six traffic CO predictors: number of vehicles, number of heavy vehicles, number of motorbikes, temperature, wind speed and a digital surface model. The network architecture and its hyperparameters were optimized through a grid search approach. The traffic CO concentrations were observed at 15-min intervals on weekends and weekdays, four times per day. The results showed that the developed model had achieved validation accuracy of 80.6 %. Overall, the developed models are found to be promising tools for vehicular CO simulations in highly congested areas.
Transportation infrastructures play a significant role in the economy as they provide accessibility services to people. Infrastructures such as highways, road networks, and toll plazas are rapidly growing based on changes in transportation modes, which consequently create congestions near toll plaza areas and intersections. These congestions exert negative impacts on human health and the environment because vehicular emissions are considered as the main source of air pollution in urban areas and can cause respiratory and cardiovascular diseases and cancer. In this study, we developed a hybrid model based on the integration of three models, correlation-based feature selection (CFS), support vector regression (SVR), and GIS, to predict vehicular emissions at specific times and locations on roads at microscale levels in an urban areas of Kuala Lumpur, Malaysia. The proposed model comprises three simulation steps: first, the selection of the best predictors based on CFS; second, the prediction of vehicular carbon monoxide (CO) emissions using SVR; and third, the spatial simulation based on maps by using GIS. The proposed model was developed with seven road traffic CO predictors selected via CFS (sum of vehicles, sum of heavy vehicles, heavy vehicle ratio, sum of motorbikes, temperature, wind speed, and elevation). Spatial prediction was conducted based on GIS modelling. The vehicular CO emissions were measured continuously at 15 min intervals (recording 15 min averages) during weekends and weekdays twice per day (daytime, evening-time). The model's results achieved a validation accuracy of 80.6%, correlation coefficient of 0.9734, mean absolute error of 1.3172 ppm and root mean square error of 2.156 ppm. In addition, the most appropriate parameters of the prediction model were selected based on the CFS model. Overall, the proposed model is a promising tool for traffic CO assessment on roads.
Urban trees have the potential to mitigate some of theharm brought about by rapid urbanization and population growth, as well as serious environmental degradation (e.g. soil erosion, carbon pollution and species extirpation), in cities. This paper presents a novel urban tree extraction modelling approach that uses discrete laser scanning point clouds and object-based textural analysis to (1) develop a model characterised by four sub-models, including (a) height-based split segmentation, (b) feature extraction, (c) texture analysis and (d) classification, and (2) apply this model to classify urban trees. The canopy height model is integrated with the objectlevel local binary pattern algorithm (LBP) to achieve high classification accuracy.The results of each sub-model reveal that the classification of urban trees based on the height at 47.14 (high) and 2.12 m (low), respectively, while based on crown widths were highest and lowest at 22.5 and 2.55 m, respectively. Results also indicate that the proposed algorithm of urban tree modelling is effective for practical use.
During the past decade, deep learning-based classification methods (e.g., convolutional neural networks—CNN) have demonstrated great success in a variety of vision tasks, including satellite image classification. Deep learning methods, on the other hand, do not preserve the precise edges of the targets of interest and do not extract geometric features such as shape and area. Previous research has attempted to address such issues by combining deep learning with methods such as object-based image analysis (OBIA). Nonetheless, the question of how to integrate those methods into a single framework in such a way that the benefits of each method complement each other remains. To that end, this study compared four integration frameworks in terms of accuracy, namely OBIA artificial neural network (OBIA ANN), feature fusion, decision fusion, and patch filtering, according to the results. Patch filtering achieved 0.917 OA, whereas decision fusion and feature fusion achieved 0.862 OA and 0.860 OA, respectively. The integration of CNN and OBIA can improve classification accuracy; however, the integration framework plays a significant role in this. Future research should focus on optimizing the existing CNN and OBIA frameworks in terms of architecture, as well as investigate how CNN models should use OBIA outputs for feature extraction and classification of remotely sensed images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.