Social influences on household location, mobility and activity choice in integrated micro-simulation models

Agent-based approaches to simulating long-term location and mobility decisions and short-term activity and travel decisions of households and individuals are receiving increasing attention in land-use and transportation interaction (LUTI) models to predict land-use changes and travel behaviour in mutual interaction. Social interactions between households and between individuals potentially have an influence on a wide range of the long-term and short-term choices involved in these systems. In this paper we identify the areas in which social interactions play a role and address the question how these influences can be modelled in the context of agent-based LUTI models. We distinguish impacts on activity participation (joint activity participation, support-and-help activities) and impacts on decision making (information exchange, social adaptation of preferences and aspirations) as the two main areas of social influence. A prototype of a LUTI model is proposed that accounts for impacts of the social network on longer-term mobility decision making through information exchange and social adaptation of preferences and aspirations. The model is demonstrated in a numerical simulation.     

A behavioral analysis of freight mode choice decisions

This paper develops a behavioral analysis of freight mode choice decisions that could provide a basis for an acceptable analytical tool for policy assessment. The paper specifically examines the way that truck and rail compete for commodity movement in the US. Two binary mode choice models are introduced in which some shipment-specific variables (e.g. distance, weight and value) and mode-specific variables (e.g. haul time and cost) are found to be determinants. The specifications of the non-selected choice are imputed in a machine learning module. Shipping cost is found to be a central factor for rail shipments, while road shipments are found to be more sensitive to haul time. Sensitivity of mode choice decisions is further analyzed under different fuel price fluctuation scenarios. A low level of mode choice sensitivity is found with respect to fuel price, such that even a 50% increase in fuel cost does not cause a significant modal shift between truck and rail.     

高速公路路网运行指数评估模型应用研究

由于高速公路路网交通流量分布不均衡,往往会造成部分节点或区域拥堵,而量化评估路网运行状态能快速确定交通拥堵位置.提出了一种基于波动率和机器学习的路网运行指数评估模型:首先选取合适的机器学习算法确定路网各节点的基准值;然后运用波动率理论构建各节点的运行指数评估模型;之后利用广东省高速公路若干节点路段的真实数据对模型进行了...     

具有无序排列管片环结构的地铁盾构隧道数字模型智能重建北大核心CSCD

运营地铁隧道的管理、健康监测及维护正逐渐趋向于数字化、智能化;但常因地铁盾构隧道管理和检测单位缺少隧道数字模型,限制了地铁隧道智能维护和管理系统的应用和发展。文章针对地铁盾构隧道中无序排列的管片环结构,提出了一种基于深度学习和机器视觉的地铁盾构隧道数字模型智能重建方法,利用检测车获取的隧道衬砌内表面高清图片,对管片特征物(螺栓孔)进行智能识别与自动分类,再根据螺栓孔群的分布特点自动推断隧道管片环的排版规律,从而结合隧道实际线路实现隧道数字模型快速重建。某地铁隧道的实例应用结果表明,该方法适用于管片无规律性错缝拼装的情况,能以100%的准确率实现地铁盾构隧道数字模型的智能重建。     

基于语音特征迁移学习的驾驶疲劳检测

针对现有方法在实际应用时的标记样本稀缺与测试样本数据分布偏移等问题,提出一种基于语音特征迁移学习的驾驶疲劳检测方法。通过基于迁移学习的特征空间变换,对源领域有标记样本与目标域无标记样本数据间的边缘分布、条件分布、流形结构进行联合适配及降维处理,以解决样本数据分布偏移和特征维度过高的问题。以半监督学习的方式来迭代优化目标域样本的伪标记,并据此不断更新特征变换方式和迁移分类器,进而提高疲劳检测模型的精度和泛化能力。通过实验将本文方法与现有常用的监督学习、半监督学习和迁移学习等方法进行对比。结果表明,在测试时间、应用场景和被试个体均发生变化的情况下,本文所提方法的驾驶疲劳检测效果显著优于现有方法,正确率最高达到86.7%,具有实际应用价值。     

Impact of an electrified parkade on the built environment: An unsupervised learning approach

Proposed legislation in British Columbia would require 30 percent of new car sales to be zero-emission vehicles by 2030, and 100 percent by 2040. The growing amount of energy demand and usage data from smart meters or internet of things (IoT) devices enables new research areas. We reporton machine learning approaches to reevaluate the impacts of battery electric vehicles (BEV) on the built environment. We developed a daily power profile analysis based on unsupervised learning, to understand the underlying structure of building and BEV charging station demand data. In addition, we have implemented a load aggregation method based on the features revealed by a clustering process. This aggregation method simulates the electricity demand of an arbitrary number of charging stations, all of which are connected to the main feeder of a building. Several scenarios are simulated using charging stations and building demand data from the University of British Columbia campus in Vancouver. Results for 150 charging stations revealed that the feeder load could increase from a peak load scenario of 300 kW to more than 1000 kW during a high-consumption weekday.     

信号博弈下的交叉口TSCA间的协调学习模型的构建

针对路网中交叉口之间交通流的关联性、动态性及不确定性,应用了信号博弈作为交叉口交通信号控制agent（TSCA）间协调的模型,以分布式Q强化学习中Q值更新来进行其效用函数的学习,通过引入记忆因子对奖惩函数进行设计,及相邻交叉口之间的影响建立权值函数,构建了协调学习的仿真实现流程,并通过实验仿真验证此模型的有效性。     

A hybrid machine learning model for short-term estimated time of arrival prediction in terminal manoeuvring area

4D trajectory prediction is the core element of future air transportation system, which is intended to improve the operational ability and the predictability of air traffic. In this paper, we introduce a novel hybrid model to address the short-term trajectory prediction problem in Terminal Manoeuvring Area (TMA) by application of machine learning methods. The proposed model consists of two parts: clustering-based preprocessing and Multi-Cells Neural Network (MCNN)-based prediction. Firstly, in the preprocessing part, after data cleaning, filtering and data re-sampling, we applied principal Component Analysis (PCA) to reduce the dimension of trajectory vector variable. Then, the trajectories are clustered into several patterns by clustering algorithm. Using nested cross validation, MCNN model is trained to find out the appropriate prediction model of Estimated Time of Arrival (ETA) for each individual cluster cell. Finally, the predicted ETA for each new flight is generated in different cluster cells classified by decision trees. To assess the performance of MCNN model, the Multiple Linear Regression (MLR) model is proposed as the comparison learning model, and K-means++ and DBSCAN are proposed as two comparison clustering models in preprocessing part. With real 4D trajectory data in Beijing TMA, experimental results demonstrate that our proposed model MCNN with DBSCAN in preprocessing is the most effective and robust hybrid machine learning model, both in trajectory clustering and short-term 4D trajectory prediction. In addition, it can make an accurate trajectory prediction in terms of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) with regards to comparison models.     

β-淀粉样蛋白诱导大鼠海马S100β表达的作用及机制

目的　探讨 β 淀粉样蛋白 (Aβ)对S10 0 β表达的影响及作用机制。 方法　采用Aβ2 5-3 5和IL 1ra ,选择大鼠海马CA1区进行定位注射 ,通过行为学测试、刚果红染色和免疫组化技术结合图像分析的方法 ,对不同时间大鼠的学习记忆、淀粉样沉积、GFAP和海马CA1区S10 0 β表达的变化进行观测。 结果　Aβ2 5-3 5注射后 ,大鼠的学习记忆能力明显下降 ;海马CA1区出现Aβ沉积 ,并有大量GFAP阳性胶质细胞包绕 ;实验组S10 0 β阳性细胞数目在 3、7、2 1d较对照组均有明显增多 ,细胞平均面积只在 2 1d才有明显增大。脑内注射IL 1ra后 3、7d,S10 0 β阳性细胞数目明显低于同组的Aβ大鼠 ,而高于对照组。结论　Aβ2 5-3 5脑内注射可建立具有类似阿尔茨海默病的局部病理改变和学习记忆损害的AD动物模型 ;Aβ2 5-3 5可上调大鼠海马CA1区S10 0 β的表达 ,实验早期以S10 0 β阳性细胞的数目增加为主 ,后期表现为细胞体积的增大 ;IL 1ra脑内注射可明显降低Aβ2 5-3 5上调S10 0 β表达的作用 ,其机制是阻断由Aβ2 5-3 5激活的小胶质细胞释放的IL 1对星形胶质细胞的活化作用。     

防抱死制动系统模糊自学习控制研究

由于车辆参数和运行工况的复杂多变，针对特定参数和路面条件所设计的防抱死制动系统往往难以适应。为解决这一问题，文中首先建立了带有盘式制动器的双轮车辆直线制动系统的数学模型；而后提出了模糊自学习控制策略，该方案通过引入模糊学习机制以调整模糊控制器的规则集，可使车辆对象输出跟踪理想参考模型的输出；接着对所设计控制算法在不同路面条件下进行了性能模拟；最后开发了模糊自学习微控制器，基于硬件在环仿真技术，对设计控制器的性能进行了实验验证。