De Detec%ng and ec%ng and An Analyzing Urb Urban an Regions with High Imp mpact of Weather Ch Change on e on T Transpor ort Ye Ding, Yanhua Li, Ke Deng, Haoyu Tan, Mingxuan Yuan, Lionel M. Ni Presenta;on by Karan Somaiah Napanda, Suchithra Balakrishnan, Zhaoning Su
URBAN comp mpu%ng connects urban sensing, data ma manageme ment, data analy%c and service providing *Urban compu;ng with taxis, MSRA *A Cloud-Based Knowledge Discovery System for Monitoring Fine-Grained Air Quality, MSRA
URBAN comp mpu%ng connects urban sensing, data ma manageme ment, data analy%c and service providing pr viding • Focus • infer the real-;me and fine grained air quality • Traffic conges;on informa;on throughout a city • Energy consump;on • iden;fy the hot spots of moving vehicles in an • Pollu;on urban area • Based on data • propose a framework, called DRoF, to discover • traffic flow regions of different func;ons in a city • human mobility • try to sense the refueling behavior and • geographical data citywide petrol consump;on in real-;me…
The imp mpact of incleme ment weather to traffic ffic • May slow down the traffic • May cause conges;ons due to low visibility and high demand of • May influence the transport performance,
the imp mpact of incleme ment weather to traffic ffic *Changes in Climate and Weather Relevant on US Transport, “The impact of climate change and weather on transport: An overview of empirical fin”
Mo Mo%v %va%o a%on n *IBM Smarter Traveler Traffic Predic;on So^ware *Google Opera;ng System how can we identify those regions being highly influenced by weather change on transport?
Ch Challen enges es lacking of effec%ve traffic monitoring system in city-wide scale • To enable weather-traffic index throughout a city and factor analysis • extract traffic informa;on from numerous taxis driving on roads due to its availability, wide-coverage and low-cost. • A taxi tracking system con;nuously record the informa;on including loca;on, speed, occupancy status, and orienta;on of the taxis
Ch Challen enges es lacking of effec%ve traffic monitoring system in city-wide scale Vo Voronoi d diagr iagram am
Ch Challen enges es lacking of effec%ve traffic monitoring system in city-wide scale Equal-sized rectangles Ø some cells are highly dense and in others are highly sparse Voronoi diagram Ø seeds are the road intersec;ons Ø every cell include at least one road intersec;on and a number of roads connected to this intersec;on Ø if several road intersec;ons are very close to each other, for example within 50 meters, they are grouped together as a complex intersec;on *The Voronoi diagrams par;;ons in Shanghai. The under layer represents the road networks .
Qu Ques%ons • The average of taxi can reflect the traffic informa%on? In the area of residence community, everyone have their own car so they don’t need the taxi • By calcula%ng the average driving speeds of all taxis in each Voronoi cell can reflect the average speed? However maybe some cells have a lower average speed of taxis is just because people are likely get on or get off from the taxis here
Ch Challen enges es how to disclose the key factors behind the weather-traffic index density of roads number of road intersec;ons number of POIs(points of interest) traffic volume average age of the household density of buildings and more in the surrounding regions
Th The Goa e Goal of of t this p paper er To develope weather-traffic index (WTI) system The first is to set up a weather-traffic index throughout a city, which indicates the impact of weather to traffic from light to heavy. The second is to reveal the key factors behind the weather-traffic index throughout the city and their rela;ve weights. Previous works mainly focus on the analysis of road segments; on the contrary, this paper is the first study on local traffic-weather sensi;vity throughout a city and the inves;ga;on to reveal the key factors behind the sensi;vity
OVERVIEW 1. Data Prepara;on 2. Weather-traffic Index Establishment 3. Factor Analysis
1. DATA PREPARATION i. Regional Par;;oning Voronoi Diagram ii. Source Data Road Network Traffic Data Regional features Weather Report Data
DATA PREPARATION - Regional Par%%oning VORONOI DIAGRAM Par;;oning of a plane into cells/ regions based on the distance between seeds Shape and size of each cells is different from each other SEEDS- road intersec;ons ROAD- INTERSECTION- ORIENTED Par;;oning Proper;es • Even distribu;on of road networks • Potray the rela;on of weather and traffic
DATA PREPARATION – Source Data i. Road Networks ii. Traffic Data iii. Regional Features iv. Weather Report Data i. Road Networks - G(V, E) E- set of road segments V- set of road intersec;ons E- type, length, speed limit, two end points V- loca;on (la;tude and longitude), type
DATA PREPARATION – Source Data Time Mean Speed/ Average Speed- Traffic Parameter Arithme;c mean of individual spot speeds that are recorded over a selected ;me period Extracted from taxi trajectories in each cell ii. Traffic Data Split into 7 classes Traffic Parameters of interest are extracted • <10 km/h • 70- 90 km/h Average Speed • • 10- 30 km/h • 90- 110 km/h • 30- 50 km/h • >110 km/h Quan;ty measures • • 50- 70 km/h • Quality assessment measures The average speed of one road segment is subject • Movement measures to the traffic parameter of that road segment only, Composi;on/ Classifica;on measures • not comparable with other road segments
DATA PREPARATION – Source Data iv. Regional Features Four Categories a) Points of Interest c) Density b) Structure d) Community iii. Weather Report Data State of atmosphere • Degree to which it is hot or cold, wet • or dry, calm or stormy, clear or cloudy
2. WEATHER TRAFFIC INDEX ESTABLISHMENT Input – Weather data and Traffic data Indicates the impact of weather to traffic in different cells Given a cell g, its value in the weather traffic index is the correla;on between traffic and weather, denoted as ρ(g). ρ(g) takes a value from the discrete range [1, 2, 3, 4, 5]
WEATHER TRAFFIC INDEX ESTABLISHMENT Correla%on Detec%on Correla;on between traffic speed F t and weather F w. Classifier is trained with F t and F w Input - Weather as a feature vector Output - one of the seven speed classes Inference accuracy Correla;on between F t and F w in that cell Inference accuracy Correla;on between F t and F w in that cell Weakness of this method, Does not consider other reasons that affect traffic
WEATHER TRAFFIC INDEX ESTABLISHMENT Correla%on Detec%on Granger Causality test whether one ;me series is useful in forecas;ng another A ;me series X is said to Granger-cause Y if it can be shown that those X values provide sta;s;cally significant informa;on about future values of Y. A variable X that evolves over ;me Granger-cause another evolving variable Y if predic;ons of the value of Y based on its own past values and on the past values of X are beuer than predic;ons of Y based only on its own past values.
WEATHER TRAFFIC INDEX ESTABLISHMENT Correla%on Detec%on • Traffic Predic;on models are trained separately for different ;me • Weather-traffic index value ρ(g) is assigned to each cell to indicate the extent to which traffic is impacted by weather • Cells are organised in ascending order of traffic predic;on accuracy improvement and then divided into k- equal sized subsets • k- quan;les show the correla;on between traffic and weather from weak to strong
WEATHER TRAFFIC INDEX ESTABLISHMENT Traffic Predic%on • Classifica;on Problem • Methods used Support Vector Machine (SVM) Logis;c Regression (LOGIT) Perceptron • 10-fold cross valida;on • SVM is applied and LOGIT and Perceptron is used to verify the output of SVM
3. FACTOR ANALYSIS AssumpRon – weather traffic index of all cells have been certainly assigned This method iden;fies the key factors and their weights contribu;ng to the weather- traffic indices of cells. Discloses what regional features make the traffic in some cells vulnerable to inclement weather Steps: 1. Key Factor Verifica;on by Index Inference (KFVII) 2. Weight Es;ma;on of Regional Features
FACTOR ANALYSIS Key Factor Verifica%on by Index Inference (KFVII) • Intui;on • Weather- traffic index of one region can be inferred from the indices of its closely located (or adjacent) cells • Given a set of regional features F r , if the inference accuracy is sa;sfactory with F r as input, it indicates that such set of regional features are the key features • This model is not symmetric • Naïve Bayes classifier
FACTOR ANALYSIS Key Factor Verifica%on by Index Inference (KFVII) Marginal DistribuRon Probability distribu;on of the regions contained in a similarity subset Probability of one region being the index of i given one of its adjacent regions with index j, if two regions have a certain similarity Cosine Similarity is used to describe the similarity m uv between two regions g u and g v Similarity ranges of k- groups b0 is minimum similarity Bk is maximum similarity
Recommend
More recommend
