Daily activity pattern recognition by using support vector machines with multiple classes

The focus of this paper is to learn the daily activity engagement patterns of travelers using Support Vector Machines (SVMs), a modeling approach that is widely used in Artificial intelligence and Machine Learning. It is postulated that an individual’s choice of activities depends not only on socio-demographic characteristics but also on previous activities of individual on the same day. In the paper, Markov Chain models are used to study the sequential choice of activities. The dependencies among activity type, activity sequence and socio-demographic data are captured by employing hidden Markov models. In order to learn model parameters, we use sequential multinomial logit models (MNL) and multiclass Support Vector Machines (K-SVM) with two different dependency structures. In the first dependency structure, it is assumed that type of activity at time ‘t’ depends on the last previous activity and socio-demographic data, whereas in the second structure we assume that activity selection at time ‘t’ depends on all of the individual’s previous activity types on the same day and socio-demographic characteristics. The models are applied to data drawn from a set of California households and a comparison of the accuracy of estimation of activity types and their sequence in the agenda, indicates the superiority of K-SVM models over MNL. Additionally, we show that accuracy in estimating activity patterns increases using different sets of explanatory variables or tuning parameters of the kernel function in K-SVM.     

高职高专电子商务专业双语教学刍议

本文首先从社会需求、专业改革、人才培养等角度论述了高职高专电子商务专业双语教学的必要性,并从语言学的角度论述了其理论基础。然后分析了适合我国高职高专电子商务专业双语教学的教学模式,最后分析了存在的问题及对策。     

路基工程最优化计算数学模型研究

提出了以路基变坡点为变量，路基工程费用为目标函数的路基工程最优化设计数学模型，并给出了解析形式的目标函数和约束矩阵。为河道，公路及铁路路基最优化设计奠定了理论基础。     

航运服务业集聚模式的生成机理及要素研究——推进上海国际航运中心建设的思考

为了研究航运服务业集聚的生成模式和生成要素,本文在对服务业集聚理论研究的基础上,根据市场和政府对航运服务业集聚的作用,将其生成模式划分为自然生成模式、政府主导型生成模式和混合推动型生成模式,并分别结合伦敦、新加坡和上海三个城市的航运服务业集聚模式的生成要素进行了系统研究。     

A comprehensive study on the stability analysis of vehicle dynamics with pure/combined-slip tyre models

In this paper, a vehicle's lateral dynamic model is developed based on the pure and the combined-slip LuGre tyre models. Conventional vehicle's lateral dynamic methods derive handling models utilising linear tyres and pure-slip assumptions. The current article proposes a general lateral dynamic model, which takes the linear and nonlinear behaviours of the tyre into account using the pure and combined-slip assumptions separately. The developed methodology also incorporates various normal loads at each corner and provides a proper tyre–vehicle platform for control and estimation applications. Steady-state and transient LuGre models are also used in the model development and their responses are compared in different driving scenarios. Considering the fact that the vehicle dynamics is time-varying, the stability of the suggested time-varying model is investigated using an affine quadratic stability approach, and a novel approach to define the critical longitudinal speed is suggested and compared with that of conventional lateral stability methods. Simulations have been conducted and the results are used to validate the proposed method.     

Leveraging social networks for efficient hurricane evacuation

One of the important factors affecting evacuation performance is the departure time choices made by evacuees. Simultaneous departures of evacuees can lead to overloading of road networks causing congestion. We are especially interested in cases when evacuees subject to little or no risk of exposure evacuate along with evacuees subject to higher risk of threat (also known as shadow evacuation). One of the reasons for correlated evacuee departures is higher perceived risk of threat spread through social contacts. In this work, we study an evacuation scenario consisting of a high risk region and a surrounding low risk area. We propose a probabilistic evacuee departure time model incorporating both evacuee individual characteristics and the underlying evacuee social network. We find that the performance of an evacuation process can be improved by forcing a small subset of evacuees (inhibitors) in the low risk area to delay their departure. The performance of an evacuation is measured by both average travel time of the population and total evacuation time of the high risk evacuees. We derive closed form expressions for average travel time for ER random network. A detailed experimental analysis of various inhibitor selection strategies and their effectiveness on different social network topologies and risk distribution is performed. Results indicate that significant improvement in evacuation performance can be achieved in scenarios where evacuee social networks have short average path lengths and topologically influential evacuees do not belong to the high risk regions. Additionally, communities with stronger ties improve evacuation performance.     

Towards a more equitable distribution of resources: Using activity-based models and subjective well-being measures in transport project evaluation

In this paper, we develop an innovative and comprehensive transport evaluation criterion to better account for equity considerations in transport project evaluation. This work explores transportation benefits from the consumer’s perspective to accessibility as a key benefit generated by any transportation project. To assess the full benefits of transportation project implementation for various consumers and calculate the improvement in accessibility, it is best to use Activity-Based Models (ABM). ABMs have two important advantages for equity analysis, which have not been utilized in the literature so far: first, ability to analyze results by various groups of the population; second, these models can utilize the Activity Based Accessibility (ABA) measure to estimate the overall benefits from transport investments and policies. The ABA measure allows one person to have different accessibilities for different choice situations, depending on his/her characteristics. We suggest including social and spatial factors in social welfare assessment by introducing the concept of accessibility gains to key social activities. Specifically, it is suggested to incorporate subjective well-being consideration into a new evaluation framework “Equity Benefit Analysis” (EBA). we use an alternative measure, “Subjective Value of Accessibility gains” (SVOA), which is based on the ABM accessibility measure as well as on Subjective Well-Being (SWB) measure, as the key benefit taken into account in the evaluation process. The SVOA is not intended to replace the current practice of analyzing equity by comparing various impacts on different groups of the population, but can aid by providing policymakers with a single measure advancing both equity and efficiency considerations and facilitating comparison among alternatives. Initial case study results indicate the SVOA can show higher benefits to policies focusing on the needs of vulnerable social groups that compared traditional measures.     

Ability of a “minimum” microbial food web model to reproduce response patterns observed in mesocosms manipulated with N and P, glucose, and Si

We compared an idealised mathematical model of the lower part of the pelagic food web to experimental data from a mesocosm experiment in which the supplies of mineral nutrients (nitrogen and phosphorous), bioavailable dissolved organic carbon (BDOC, as glucose), and silicate were manipulated. The central hypothesis of the experiment was that bacterial consumption of BDOC depends on whether the growth rate of heterotrophic bacteria is limited by organic-C or by mineral nutrients. In previous work, this hypothesis was examined qualitatively using a conceptual food web model. Here we explore the extent to which a “simplest possible” mathematical version of this conceptual model can reproduce the observed dynamics. The model combines algal–bacterial competition for mineral nutrients (phosphorous) and accounts for alternative limitation of bacterial and diatom growth rates by organic carbon and by silicate, respectively. Due to a slower succession in the diatom–copepod, compared to the flagellate–ciliate link, silicate availability increases the magnitude and extends the duration of phytoplankton blooms induced by mineral nutrient addition. As a result, Si interferes negatively with bacterial consumption of BDOC consumption by increasing and prolonging algal–bacterial competition for mineral nutrients. In order to reproduce the difference in primary production between Si and non-Si amended treatments, we had to assume a carbon overflow mechanism in diatom C-fixation. This model satisfactorily reproduced central features observed in the mesocosm experiment, including the dynamics of glucose consumption, algal, bacterial, and mesozooplankton biomass. While the parameter set chosen allows the model to reproduce the pattern seen in bacterial production, we were not able to find a single set of parameters that simultaneously reproduces both the level and the pattern observed for bacterial production. Profound changes in bacterial morphology and stoichiometry were reported in glucose-amended mesocosms. Our “simplest possible” model with one bacterial population with fixed stoichiometry cannot reproduce this, and we suggest that a more elaborate representation of the bacterial community is required for more accurate reproduction of bacterial production.     

价格管制模型对成本的依赖性研究

通过对各种价格管制模型的分析,揭示其对成本的依赖性,探讨了在价格管制模型的运用中,加强成本管理的重要性。