scholarly journals Segmentation Effect on the Transferability of International Safety Performance Functions for Rural Roads in Egypt

Safety ◽  
2020 ◽  
Vol 6 (3) ◽  
pp. 43
Author(s):  
Sania Reyad Elagamy ◽  
Sherif M. El-Badawy ◽  
Sayed A. Shwaly ◽  
Zaki M. Zidan ◽  
Usama Elrawy Shahdah
Keyword(s):  
Constant Term ◽  
Safety Performance ◽  
Likelihood Method ◽  
Percentage Error ◽  
Segmentation Method ◽  
Local Data ◽  
Absolute Deviation ◽  
Rural Roads ◽  
Safety Performance Function ◽  
Segmentation Approach

This paper examines the transferability of the Safety Performance Function (SPF) of the Highway Safety Manual (HSM) and other 10 international SPFs for total crashes on rural multi-lane divided roads in Egypt. Four segmentation approaches are assessed in the transferability of the international SPFs, namely: (1) one-kilometer segments (S1); (2) homogenous sections (S2); (3) variable segments with respect to the presence of curvatures (S3); and (4) variable segments with respect to the presence of both curvatures and U-turns (S4). The Mean Absolute Deviation (MAD), Mean Prediction Bias (MPB), Mean Absolute Percentage Error (MAPE), Pearson χ2 statistic, and Z-score parameters are used to evaluate the performance of the transferred models. The overdispersion parameter (k) for each transferred model and each segmentation approach is recalibrated using the local data by the maximum likelihood method. Before estimating the transferability calibration factor (Cr), three methods were used to adjust the local crash prediction of the transferred models, namely: (1) the HSM default crash modification factors (CMFs); (2) local CMFs; and (3) recalibrating the constant term of the transferred model. The latter method is found to outperform the first two methods. Besides, the results show that the segmentation method would affect the performance of the transferability process. Moreover, the Italian SPFs based on the S1 segmentation method outperforms the HSM and all of the investigated international SPFs for transferring their models to the Egyptian rural roads.

scholarly journals Calibration of highway safety manual predictive models and validation of safety performance funtions for canadian urban/suburban intersections

2021 ◽  
Author(s):  
Shahzad Faisal
Keyword(s):  
Predictive Models ◽  
Safety Performance ◽  
Local Data ◽  
Performance Function ◽  
Safety Performance Function ◽  
Highway Safety Manual ◽  
Related Aspect ◽  
Crash Types ◽  
The City ◽  
Collision Models

In this research, the HSM predictive models for collisions on urban/suburban arterials are calibrated for collision data from the City of Toronto. It has been found that the use of calibration factors for applying HSM models to Toronto intersection data is not appropriate. New collision models are therefore developed by using local data. The HSM and Toronto models are then calibrated to City of Edmonton intersection collision data to determine whether it is better to calibrate HSM models for a Canadian jurisdiction or models from another Canadian jurisdiction. A related aspect of the research is the investigation of models for crash types. There is no safety performance function (SPF) available in the HSM to predict rear end collisions. Instead, rear end collisions are estimated as a proportion of predicted multivehicle collisions. To overcome this deficiency, Toronto data are used in the estimation of models for rear end collisions.

scholarly journals Calibration of highway safety manual predictive models and validation of safety performance funtions for canadian urban/suburban intersections

2021 ◽  
Author(s):  
Shahzad Faisal
Keyword(s):  
Predictive Models ◽  
Safety Performance ◽  
Local Data ◽  
Performance Function ◽  
Safety Performance Function ◽  
Highway Safety Manual ◽  
Related Aspect ◽  
Crash Types ◽  
The City ◽  
Collision Models

In this research, the HSM predictive models for collisions on urban/suburban arterials are calibrated for collision data from the City of Toronto. It has been found that the use of calibration factors for applying HSM models to Toronto intersection data is not appropriate. New collision models are therefore developed by using local data. The HSM and Toronto models are then calibrated to City of Edmonton intersection collision data to determine whether it is better to calibrate HSM models for a Canadian jurisdiction or models from another Canadian jurisdiction. A related aspect of the research is the investigation of models for crash types. There is no safety performance function (SPF) available in the HSM to predict rear end collisions. Instead, rear end collisions are estimated as a proportion of predicted multivehicle collisions. To overcome this deficiency, Toronto data are used in the estimation of models for rear end collisions.

Simple Index to Assess the Calibration Quality of Safety Performance Functions Based on Multiple Goodness-of-Fit Metrics

2021 ◽  
pp. 036119812110088
Author(s):  
Raul E. Avelar ◽  
Karen Dixon ◽  
Boniphace Kutela ◽  
Sam Klump ◽  
Beth Wemple ◽  
...  
Keyword(s):  
Goodness Of Fit ◽  
Synthetic Data ◽  
Calibration Procedure ◽  
Safety Performance ◽  
Absolute Deviation ◽  
Data Set ◽  
Safety Database ◽  
Simple Index ◽  
Safety Performance Functions

The calibration of safety performance functions (SPFs) is a mechanism included in the Highway Safety Manual (HSM) to adjust SPFs in the HSM for use in intended jurisdictions. Critically, the quality of the calibration procedure must be assessed before using the calibrated SPFs. Multiple resources to aid practitioners in calibrating SPFs have been developed in the years following the publication of the HSM 1st edition. Similarly, the literature suggests multiple ways to assess the goodness-of-fit (GOF) of a calibrated SPF to a data set from a given jurisdiction. This paper uses the calibration results of multiple intersection SPFs to a large Mississippi safety database to examine the relations between multiple GOF metrics. The goal is to develop a sensible single index that leverages the joint information from multiple GOF metrics to assess overall quality of calibration. A factor analysis applied to the calibration results revealed three underlying factors explaining 76% of the variability in the data. From these results, the authors developed an index and performed a sensitivity analysis. The key metrics were found to be, in descending order: the deviation of the cumulative residual (CURE) plot from the 95% confidence area, the mean absolute deviation, the modified R-squared, and the value of the calibration factor. This paper also presents comparisons between the index and alternative scoring strategies, as well as an effort to verify the results using synthetic data. The developed index is recommended to comprehensively assess the quality of the calibrated intersection SPFs.

scholarly journals PREDICTION OF LOG P AND SPECTRUM OF QUERCETINE, GLUCOSAMINE, AND ANDROGRAPHOLIDE AND ITS CORRELATION WITH LABORATORY ANALYSIS

2016 ◽  
Vol 8 (11) ◽  
pp. 33 ◽  
Author(s):  
Sandra Megantara ◽  
Mutakin Mutakin ◽  
Jutti Levita
Keyword(s):  
Ab Initio ◽  
1H Nmr ◽  
13C Nmr ◽  
Forecast Error ◽  
Computational Prediction ◽  
Percentage Error ◽  
Log P ◽  
P Value ◽  
Absolute Deviation ◽  
R Value

Objective: This study was aimed to confirm the result of computational prediction of log P and spectrum (ultraviolet-visible, 1H-NMR, 13C-NMR) of quercetin, glucosamine and andrographolide with laboratory analysis.Methods: Quercetine, glucosamine and andrographolide, were downloaded from ChemSpider and were geometry optimised. Log P and spectrum were calculated and predicted and the data obtained were compared with laboratory results. The correlation was calculated by employing mean absolute deviation (MAD), mean square error (MSE), mean forecast error (MFE), and mean absolute percentage error (MAPE) parameters.Results: The smallest energy value of geometry optimisation was provided by ab initio method. Log P prediction showed good accuracy, with r-value 0.995 and p-value 0.05 respectively. The error parameters were: MAD 0.19; MSE 0.06; MFE 0.16, and MAPE 8.62%, respectively. Prediction of λ maximum by ab initio, semiempirical, and molecular mechanics were respectively: MAD 2.67, 6.67, and 28.67; MSE 8.67, 45.33, and 830; MFE 2.67, 6.67, and 28.67; and MAPE 1.10%, 2.79%, and 11.99%; r-value 0.997, 0.997, and 0.979; and p-value 0.044, 0.043, and 0.129. 1H-NMR and 13C-NMR spectra prediction were: MAD 0.73 and 1.58; MSE 1.15 and 7.41; MFE 0.27 and 0.69; MAPE 18.35% and 2.68%; r-value 0.942 and 0.986; and p-value 0.001 and 0.001.Conclusion: There is a positive correlation between computational ab initio calculation method with experimental results in predicting log P and spectrum of quercetine, glucosamine, and andrographolide.

scholarly journals Crash Prediction Models for Horizontal Curve Segments on Two-Lane Rural Roads in Thailand

2021 ◽  
Vol 13 (16) ◽  
pp. 9011
Author(s):  
Nopadon Kronprasert ◽  
Katesirint Boontan ◽  
Patipat Kanha
Keyword(s):  
Prediction Models ◽  
Safety Performance ◽  
Horizontal Curve ◽  
Crash Frequency ◽  
Rural Roads ◽  
Crash Prediction ◽  
Road Crashes ◽  
Highway Safety Manual ◽  
Safety Performance Functions ◽  
Crash Prediction Models

The number of road crashes continues to rise significantly in Thailand. Curve segments on two-lane rural roads are among the most hazardous locations which lead to road crashes and tremendous economic losses; therefore, a detailed examination of its risk is required. This study aims to develop crash prediction models using Safety Performance Functions (SPFs) as a tool to identify the relationship among road alignment, road geometric and traffic conditions, and crash frequency for two-lane rural horizontal curve segments. Relevant data associated with 86,599 curve segments on two-lane rural road networks in Thailand were collected including road alignment data from a GPS vehicle tracking technology, road attribute data from rural road asset databases, and historical crash data from crash reports. Safety Performance Functions (SPFs) for horizontal curve segments were developed, using Poisson regression, negative binomial regression, and calibrated Highway Safety Manual models. The results showed that the most significant parameter affecting crash frequency is lane width, followed by curve length, traffic volume, curve radius, and types of curves (i.e., circular curves, compound curves, reverse curves, and broken-back curves). Comparing among crash prediction models developed, the calibrated Highway Safety Manual SPF outperforms the others in prediction accuracy.

scholarly journals Kajian Adaptive Neuro-Fuzzy Inference System (ANFIS) Dalam Memprediksi Penerimaan Mahasiswa Baru Pada Universitas Buana Perjuangan Karawang

2021 ◽  
Vol 6 (1) ◽  
pp. 44-54
Author(s):  
Tatang Rohana Cucu
Keyword(s):  
Error Rate ◽  
Fuzzy Inference ◽  
Percentage Error ◽  
Hybrid Technique ◽  
Mean Absolute Deviation ◽  
Absolute Deviation ◽  
Inference System ◽  
Neuro Fuzzy ◽  
New Students ◽  
The Mean

Abstract - The process of admitting new students is an annual routine activity that occurs in a university. This activity is the starting point of the process of searching for prospective new students who meet the criteria expected by the college. One of the colleges that holds new student admissions every year is Buana Perjuangan University, Karawang. There have been several studies that have been conducted on predictions of new students by other researchers, but the results have not been very satisfying, especially problems with the level of accuracy and error. Research on ANFIS studies to predict new students as a solution to the problem of accuracy. This study uses two ANFIS models, namely Backpropagation and Hybrid techniques. The application of the Adaptive Neuro-Fuzzy Inference System (ANFIS) model in the predictions of new students at Buana Perjuangan University, Karawang was successful. Based on the results of training, the Backpropagation technique has an error rate of 0.0394 and the Hybrid technique has an error rate of 0.0662. Based on the predictive accuracy value that has been done, the Backpropagation technique has an accuracy of 4.8 for the value of Mean Absolute Deviation (MAD) and 0.156364623 for the value of Mean Absolute Percentage Error (MAPE). Meanwhile, based on the Mean Absolute Deviation (MAD) value, the Backpropagation technique has a value of 0.5 and 0.09516671 for the Mean Absolute Percentage Error (MAPE) value. So it can be concluded that the Hybrid technique has a better level of accuracy than the Backpropation technique in predicting the number of new students at the University of Buana Perjuangan Karawang.   Keywords: ANFIS, Backpropagation, Hybrid, Prediction

Shadow-Free, Expeditious and Precise, Moving Object Separation from Video

2018 ◽  
Vol 18 (01) ◽  
pp. 1850005
Author(s):  
Prashant Domadiya ◽  
Pratik Shah ◽  
Suman K. Mitra
Keyword(s):  
Adaptive Learning ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Segmentation Method ◽  
False Detection ◽  
Invariant Representation ◽  
Computation Efficiency ◽  
Segmentation Approach ◽  
Background Motion ◽  
Temporal Direction

The foreground–background separation is an essential part of any video-based surveillance system. Gaussian Mixture Models (GMM) based object segmentation method accurately segments the foreground, but it is computationally expensive. In contrast, single Gaussian-based segmentation is computationally inexpensive but inaccurate because it can not handle the variations in the background. There is a trade-off between computation efficiency and precision in the segmentation approach. From the experimental observations, the variations such as lighting variations, shadows, background motion, etc., affect only a few pixels in the frames in temporal direction. So, unaffected pixel can be modeled by single Gaussian in temporal direction while the affected pixels may need GMM to handle the variations in the background. We propose an adaptive algorithm which models pixel dynamically in terms of number of Gaussians in temporal direction. The proposed method is computationally inexpensive and precise. The flexibility in terms of number of Gaussians used to model each pixel, along with adaptive learning approach, reduces the time complexity of the algorithm significantly. To resolve spacial occlusion problem, a spatial smoothing is carried out by weighted [Formula: see text] nearest neighbors which improves the overall accuracy of proposed algorithm. To avoid false detection due to illumination variations and shadows in a particular image, illumination invariant representation is used.

Safety Performance of Rural Curved Corner Intersections with Regional Effects

2021 ◽  
pp. 036119812110444
Author(s):  
Anthony Ingle ◽  
Timothy J. Gates
Keyword(s):  
Negative Binomial ◽  
Signalized Intersections ◽  
Regression Modeling ◽  
Safety Performance ◽  
Radius Of Curvature ◽  
Rural Roads ◽  
Produce Safety ◽  
Regional Effects ◽  
Random Intercept ◽  
Safety Performance Functions

This study evaluates the intersection of rural roads where a curved roadway segment connects the major flow of through traffic from orthogonal directions. A system of up to three intersections in combination can be represented singly by the situation modeled in this paper as a curved corner intersection site. This paper evaluates the application of random intercept negative binomial (NB) regression modeling to produce safety performance functions, and compares the outcome with NB models using fixed regional effects. At curved corner intersections, installing a combined/merged intersection approach near the midpoint of the curve is a potential countermeasure that by comparison with three-leg configurations experienced 20% fewer intersection crashes. A larger radius of curvature along the curved segment at these types of intersections is also very favorable for safety performance. Each 100 ft increase in the radius of a three-leg or four-leg curved corner intersection is estimated to reduce total non-animal crash occurrence by 5% and 7%, respectively. This study can help safety engineers to prioritize the improvement of rural un-signalized intersections.

scholarly journals A Multiscale CNN-CRF Framework for Environmental Microorganism Image Segmentation

2020 ◽  
Vol 2020 ◽  
pp. 1-27
Author(s):  
Jinghua Zhang ◽  
Chen Li ◽  
Frank Kulwa ◽  
Xin Zhao ◽  
Changhao Sun ◽  
...  
Keyword(s):  
Image Segmentation ◽  
State Of The Art ◽  
Conditional Random Field ◽  
Segmentation Method ◽  
Recall Accuracy ◽  
Evaluation Indexes ◽  
Segmentation Quality ◽  
Segmentation Approach ◽  
Overall Evaluation

To assist researchers to identify Environmental Microorganisms (EMs) effectively, a Multiscale CNN-CRF (MSCC) framework for the EM image segmentation is proposed in this paper. There are two parts in this framework: The first is a novel pixel-level segmentation approach, using a newly introduced Convolutional Neural Network (CNN), namely, “mU-Net-B3”, with a dense Conditional Random Field (CRF) postprocessing. The second is a VGG-16 based patch-level segmentation method with a novel “buffer” strategy, which further improves the segmentation quality of the details of the EMs. In the experiment, compared with the state-of-the-art methods on 420 EM images, the proposed MSCC method reduces the memory requirement from 355 MB to 103 MB, improves the overall evaluation indexes (Dice, Jaccard, Recall, Accuracy) from 85.24%, 77.42%, 82.27%, and 96.76% to 87.13%, 79.74%, 87.12%, and 96.91%, respectively, and reduces the volume overlap error from 22.58% to 20.26%. Therefore, the MSCC method shows great potential in the EM segmentation field.

Prediction of Daily Network Traffic based on Radial Basis Function Neural Network

2016 ◽  
Vol 3 (4) ◽  
pp. 145
Author(s):  
Haviluddin Haviluddin ◽  
Imam Tahyudin
Keyword(s):  
Neural Network ◽  
Radial Basis Function ◽  
Basis Function ◽  
Network Traffic ◽  
Good Method ◽  
Series Data ◽  
Percentage Error ◽  
Absolute Deviation ◽  
East Kalimantan ◽  
Radial Basis

This paper presents an approach for predicting daily network traffic using artificial neural networks (ANN), namely radial basis function neural network (RBFNN) method. The data is gained from 21 – 24 June 2013 (192 samples series data) in ICT Unit Universitas Mulawarman, East Kalimantan, Indonesia. The results of measurement are using statistical analysis, e.g. sum of square error (SSE), mean of square error (MSE), mean of percentage error (MPE), mean of absolute percentage error (MAPE), and mean of absolute deviation (MAD). The results show that values are the same, with different goals that have been set are 0.001, 0.002, and 0.003, and spread 200. The smallest MSE value indicates a good method for accuracy. Therefore, the RBFNN model illustrates the proposed best model to predict daily network traffic.

Sign in / Sign up

Export Citation Format

Share Document