linear regression model

Surrogate safety measures make it possible to assess the level of risk and vulnerability of pedestrians. There are advantages to using these indicators: first, the independence of the accident statistics and some of its details and errors, and second, the possibility of examining risky interactions that did not lead to an accident, and third, in evaluating before and after safety policies and measures. In this research, practical surrogate safety measures related to pedestrian safety have been identified and the effective factors on these indicators have been determined. Innovations of the article includes the use of the Lane-based surrogate safety measure for pedestrians, as well as the combined examination of the Mid-block of pedestrian crossings in a street and at an intersection. Four Surrogate safety measures of Post Encroachment Time, Lane-based Post Encroachment Time, Gap Time and Time to Collision were calculated. Surrogate safety measures and extractable variables were extracted from the recorded videos in the streets of Isfahan and by linear fitting, significant variables for each surrogate safety measures as well as effective factors in increasing or decreasing each surrogate safety measures were identified. The results showed that the variables of Mid-block of pedestrian crossing, Conflict of a pedestrian with a car, presence of a SUV vehicle in the Conflict, gender of pedestrian, day light, Group crossing of pedestrian, direction of pedestrian movement, pedestrian velocity and car velocity are the most important Factors affecting safety of pedestrian and vehicle conflicts. It is important to pay attention to the mentioned variables in order to plan and predict appropriate facilities for pedestrians to cross the street.

One of the consequences of a fire is smoke. Occasionally, monitoring and detection of this smoke can be a solution to prevent occurrence or spreading a fire. On the other hand, due to the destructive effects of the smoke spreading on human health, measures can be taken to improve the level of health services by zoning and monitoring its expansion process. In this paper, an automated method is proposed to detect the dilute smoke caused by large fires in multispectral images. The main idea of this method is the impossibility of precisely reconstructing the smoke in the bands affected by smoke (blue band) using regression models from other spectral bands. In the first step of the proposed method, the absolute value of the residuals of the regression estimation of blue spectral band is transformed into a binary mask with the help of Otsu thresholding. Afterwards, in an iterative process, non-smoke areas are detected and then clustered. In the iteration process, a regression model is fitted for each cluster and for each pixel, coefficients with the least error of the blue band reconstruction is used. Through more accurate estimation of the blue band, it reduces the effect of First Positive Error and leads the mask of residuals obtained from thresholding process to the smoke areas. The final step of the proposed method is to refine and remove the incorrect image segments. This method has been successful in detecting diluted smokes and also in disregarding smoke in non-smoky images. The results show the average accuracy of  99.04 percent in several datasets with diluted smokes.

Every year, a large volume of waste materials are produced in the world, however a very small part of it take place in recycling and reusing. Recycled Asphalt Pavement (RAP) is a waste material which may have undesirable influence on its environment. Considering these materials reported characteristics, there have been introduced different strategies to reuse RAP’s. One of these applications recently noticed by the researchers is using RAP’s in cement mixtures such as concrete.As RAP is mainly gathered from roadsides and highways, so it is desirable to use them in common mixtures for roads pavement construction. Hence, Roller Compacted Concrete -a concrete mixture with unique features such as ease of application and low costs - was selected as basic mixture. In this research, after introducing two mixing ratios with two designing strengths, replacing a part of aggregates with RAPs was carried out in three states: 1-with fine and coarse aggregates, 2-with just fine aggregates, and 3-with just coarse aggregates, with ratios of 0, 10, 20, 40, and 80 %. Then, in the next step regression models with acceptable correlation coefficients were presented for prediction of compressive strength as well as allowable percentages of RAP aggregate to use in theconcrete. Valid using other types of RAPs was another work conducted in this research.