Assessing transport related social exclusion using a capabilities approach to accessibility framework: A dynamic Bayesian network approach
Assessing transport related social exclusion using a capabilities approach to accessibility framework: A dynamic Bayesian network approach
复制标题
DOI：
10.1016/j.jtrangeo.2020.102673
复制
发表时间：
2020-04-01
影响因子：
6.1
通讯作者：
Haworth, James
中科院分区：
文献类型：
--
作者：
Bantis, Thanos;Haworth, James
无障碍被认为是一个有价值的概念，可用于深入了解由于交通选择有限而造成的社会排斥问题。最近，研究人员试图将无障碍与社会正义的流行理论联系起来，如Amartya Sen的能力方法（CA）。这些研究为通过保护性行动表达无障碍性的方式奠定了理论基础，然而，将这一方法付诸实施的尝试仍然是零散的，而且主要是定性的。在这项研究中，提出了一个新的框架，表达在个人层面上的可及性，基于CA的基本要素。特别是，动态贝叶斯网络用于表达能力，功能，个人和环境特征之间的因果关系。这是通过引入信息Dirichlet先验分布构建使用传统的流动性调查的数据，建模的转移概率与数据相关的基于位置的特性，并定义一个观察模型，从未标记的流动性数据和感兴趣的地方（POI）。我们证明了拟议的框架的有用性，通过评估的平等水平和他们的联系，以运输相关的社会排斥不同的人口群体在伦敦，使用无标签，服务提供商生成的流动性数据。
Accessibility is considered to be a valuable concept that can be used to generate insights on issues related to social exclusion due to limited access to transport options. Recently, researchers have attempted to link accessibility with popular theories of social justice such as Amartya Sen's Capabilities Approach (CA). Such studies have set the theoretical foundations on the way accessibility can be expressed through the CA, however, attempts to operationalise this approach remain fragmented and predominantly qualitative in nature. In this study, a novel framework of expressing accessibility at the level of an individual is proposed, based on the basic elements of the CA. In particular, dynamic Bayesian networks are used to express the causal relationship between capabilities, functionings, personal and environmental characteristics. This is done by introducing informative Dirichlet prior distributions constructed using data from traditional mobility surveys, modelling the transition probabilities with data related to place based characteristics and defining an observation model from unlabelled mobility data and places of interest (POI). We demonstrate the usefulness of the proposed framework by assessing the equality levels and their link to transport related social exclusion of different population groups in London, using unlabelled, service provider generated mobility data.