Since models of transport demand have shifted from trip-based to activity-based approaches, prediction of activities and their duration has gained further importance. Activity duration is an important component of activity participation behavior of individuals, and therefore, an important determinant of individual travel behavior. Since duration data is non-negative and often censored, it follows non-normal distributions, hence, linear regression is not a suitable model. Duration models offer vaster suitability for this kind of data and thus have been used for behavioral analysis of individual trips. Since for the past two decades, shopping has been under spotlight as indispensable diurnal activities for human, the current paper has tried to compare the results of several approaches with their different modeling assumptions, by modeling duration shopping activity concurrent with recognition of influential factors on duration variable and proper distributions for such data. case study of this research, is the shopping trips of 2 and 3 home-based trip tours data obtained from inquiry a sample of Qazvin residents comprising personal and household information, the characteristics of transport networks and the features of susceptible sites for doing shopping activity which constitute 99 percent of Qazvin's citizen's daily travels. The analysis and analogy of modeling results indicate estimation of parametric approach with regard to goodness of fit, is better than other approaches and suitable distributions has used for shopping activity duration data is log-logistic distribution. Considering that scale parameter estimated of model is lower than one, the hazard curve is non-monotonic and an inverted U-shape. Worker's female than male and male than other, has associated lower duration to shop with significant difference (p=0.005). Non- motoric travel modes has positive influence to reduction of shopping duration (p<0.05). In addition, covariates such as distance and commercial destination travel attraction, are significant portion to increase of shopping activity duration (p<0.05).

Survival analysis is the statistical method for the study of time to an event, but there are various models to fit the data so the important question is which of these models are the most appropriate. In survival analysis, like all regression models, we can use residuals for assessment of the model fitness. There are varieties of residuals and each of them can be used for an especial purpose.Methods: In this study to compare different models in the study of factors associated with duration of breastfeeding, we used the data collected on women in Mazandaran Province, Iran during 2003-2004.Results: For determination of factors associated with breastfeeding duration, we fitted Cox proportional hazard, exponential, Weibull, Gompertz, log-normal, log-logistic and gamma generalized models to the data. The assumptions of the above models were also checked.Conclusion: Cox-Snell residuals were used for assessment of the fitness of each model. Then a method was suggested to compare different models on the basis of these residuals. It was concluded that Cox proportional hazard model was the most appropriate.

The increasing rate of traffic congestion, air pollution especially in developing countries, in addition to, the decreasing levels of physical activity have motivated walking as a non-motorized mode choice to decision makers. The study aimed to explore predictors of influencing factors on walking time duration and its choice among individuals in daily trips. For this reason, logit and duration models have been applied. The data used in this study have been gathered for updating the comprehensive transportation plan of Mashhad. The results indicate that various variables such as larger household size, younger people, and higher residential density have a positive relationship with longer walking duration and higher share of walking trips among all daily trips. Findings also indicate that men and well-educated people walk more compared to the competing groups (women and low-educated people, respectively). The results for various groups of occupations show that in general, students tend to walk more than others. Provision of required infrastructures and setting incentive policies to encourage walking in governmental organizations and private firms can promote walking especially among employees.

Evaluating the cutting rate (CR) of stones is important in the cost estimation and the planning of the stone processing plants. This research used regression models to estimate the stones’ CR based on their physico-mechanical characteristics. Stone processing factories in Mahallat City (Markazi province, Iran) were visited, and the CR of diamond circular saws was recorded on six different travertine stones. Next, the stone block samples were collected from the quarries for laboratory tests. Stones’ porosity (n), uniaxial compressive strength (UCS), and Schmidt hammer hardness (SH) were determined in the laboratory as their physico-mechanical characteristics. Correlation relationships of CR with physico-mechanical characteristics were evaluated using simple and multiple regression analyses, and estimator models were developed. Results showed that multiple regression models are more reliable than simple regression for estimating the stones’ CR. The validity of the developed multiple regression models was verified with the published data of one researcher. The findings indicated that these models are accurate enough for estimating the CR of stones. Consequently, the multiple regression models provide practical advantages for estimating the CR and save time and cost during the planning and design of the stone processing factories.

Automatic topic detection seems unavoidable in social media analysis due to big text data which their users generate. Clustering-based methods are one of the most important and up-to-date categories in topic detection. The goal of this research is to have a wide study on this category. Therefore, this paper aims to study the main components of clustering-based-topic-detection, which are embedding methods, distance metrics, and clustering algorithms. Transfer learning and consequently pretrained language models and word embeddings have been considered in recent years. Regarding the importance of embedding methods, the efficiency of five new embedding methods, from earlier to recent ones, are compared in this paper. To conduct our study, two commonly used distance metrics, in addition to five important clustering algorithms in the field of topic detection, are implemented by the authors. As COVID-19 has turned into a hot trending topic on social networks in recent years, a dataset including one-month tweets collected with COVID-19-related hashtags is used for this study. More than 7500 experiments are performed to determine tunable parameters. Then all combinations of embedding methods, distance metrics and clustering algorithms (50 combinations) are evaluated using Silhouette metric. Results show that T5 strongly outperforms other embedding methods, cosine distance is weakly better than other distance metrics, and DBSCAN is superior to other clustering algorithms.

There is a relationship between choosing an activity and its duration, especially for non-mandatory activities. A number of studies have analyzed the decisions about an activity type and its duration independently, while some others have used joint models. This paper contributes to the body of knowledge using nested-logit and copula-based models for assessing the existence of interdependency between, or a hierarchy of, the choice of non-mandatory activity and its relative duration. In the case of the nestedlogit model, it is assumed that error terms of these decisions are interrelated, although one is in uenced by another. In contrast, the copula-based model can facilitate making a spatial error correlation between observational units without imposing the assumption of restrictive distribution on the dependency structures between the error components. The data available from Qazvin, a city in Iran, were used for estimating both nested-logit and copula-based models and the best variables explaining both choices for each model were selected. The Final models were compared in terms of log-likelihood at convergence and adjusted likelihood ratio index. The results indicated that there were some common in uential observed and unobserved factors between these decisions. Also, the copula-based joint model with  2 0 equal to 0. 134 outperformed nested-logit models and provided better explanatory power.

Iran's economy as a developing and oil economy, needs to choose appropriate exchange rate regime is to achieve its economic goals. Some characteristics such as little diversity in production and trade, weak and underdevelopment financial markets and other features of the Iranian economy, Requires the choice of exchange rate regime be based on the features of the country. However, the choice of exchange rate regime a country, many variables affect that regardless of their choice of currency regime will be difficult and illogical. Hence, in this study using survival analysis and use of Reinhart and Rogoff approach to investigate the role of political and economic factors on the choice of a fixed exchange regime in Iran based on monthly data during the period 1980-2017. The advantage of survival analysis method it is time dependence that may exist in the occurrence of an event be included and the time can be used as a proxy for structural factors and unobservable variable in country. The results showed that political and economic variables affect the choice of the fixed exchange system in the country. The impact of political variables on the country's exchange rate regime shows that only economists are not involved in the decision on the exchange rate in Iran, and the preferences of political officials have a significant impact on foreign exchange policies.

Leaf Wetness Duration (LWD) is a key parameter in agricultural meteorology. Because of difficulties involved in LWD being readily measured, several methods have been developed to estimate it from weather data. Among the employed to estimate LWD, those that use physical principles of dew formation plus dew and/or rain evaporation have shown to be especially transmittable and of sufficiently accurate results, but their complexity is a disadvantage for operational use. Alternatively, empirical models have been utilized despite their limitations. The simplest empirical models use only relative humidity data. The objective of this study was to evaluate the performance of an RH-based empirical model and a Penman-Monteith physical model to estimate LWD in Sarvestan automatic station located in Fars province. The results indicated that both models during warm seasons underestimate LWD, while during cold seasons, the physical and empirical models show overestimation and underestimation, respectively. The Mean Absolute Error (MAE) in empirical model was recorded to be less than that in physical model's estimations. An adjusted optimum threshold value of relative humidity was suggested for the study which improved the estimations. Using an RH-based empirical model led to more accurate LWD estimations with less errors as compared with the previous published data. Hourly comparisons also showed that the optimum threshold model was of a more acceptable performance as compared with the other models.