ComfRide A Smartphone based Comfortable Public Route Recommendation Authors Rohit Verma Surjya Ghosh Mahankali Saketh Niloy Ganguly Bivas Mitra Sandip Chakraborty Indian Institute of Technology ID: 766612
Download Presentation The PPT/PDF document "ComfRide - A Smartphone based Comfortabl..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
ComfRide - A Smartphone based Comfortable Public Route Recommendation Authors: Rohit Verma, Surjya Ghosh, Mahankali Saketh, Niloy Ganguly, Bivas Mitra, Sandip Chakraborty Indian Institute of Technology Kharagpur, India
Understanding Commuter Comfort Different people have different comfort preferences which is seen all over the world. Survey reveals importance of different features for commuters’ comfort Countries Delay in Reaching No seat Bad Road Traffic Jam Re O R Re O R VB B M N Re O R India 40.7 43.5 15.8 47.8 37.2 15 24.9 42.3 30 2.8 67.6 26.5 5.9 Nepal 80 20 0 40 60 0 40 20 40 0 60 40 0 Iran 12.5 62.5 25 62.5 25 12.5 0 12.5 75 12.5 62.5 37.5 0 Sri 66.7 16.7 16.6 83.3 16.7 0 16.7 33.3 50 0 83.3 16.7 0 USA 0 42.9 57.1 14.2 42.9 42.9 14.3 42.9 28.6 14.3 28.6 14.3 57.1 France 0 25 75 75 25 0 0 75 25 0 25 25 50
But Is this a Major Problem? More than 60% of the source, destination pairs have at least 4 routes between them Approximately 25% have more than 8 routes Cumulative Distribution of number of bus routes between random (source, destination) pairs calculated For every number of routes there is considerable variation in trip distance For none of number of routes, the mean value of standard deviation exceeds 15 minutes
Objective Develop an end-to-end smartphone based personalized bus route recommender system, which recommends the most comfortable bus route based on commuters’ comfort choices.
5 Data Collection: Road Information Speed Breakers Turns Bus Stops Etc.
6 Data Collection: Route Information 0.6 0.68 0.5 0.7 0.37 0.62 0.7 0.57 Congestion Jerkiness of Bus Probability of getting seat Etc.
7 Annotated City Map 0.6 0.6 0.5 0.7 0.3 0.6 0.7 0.5 0.8
8 Selecting the best route 0.6 0.6 0.5 0.7 0.3 0.6 0.7 0.5 0.8 Source
9 Selecting the best route 0.6 0.6 0.5 0.7 0.3 0.6 0.7 0.5 0.8 Source Destination
10 Selecting the best route 0.6 0.6 0.5 0.7 0.3 0.6 0.7 0.5 0.8 Source Destination Comfort Parameters Probability of sitting Waiting time at bus stop
11 Selecting the best route 0.6 0.6 0.5 0.7 0.3 0.6 0.7 0.5 0.8 Source Destination Comfort Parameters Probability of sitting Congestion Recommend the best Route!
Selecting the best route S3 S4 S5 S6 S7 S2 S1 0.6 0.5 0.5 0.6 0.3 0.5 0.4 0.6 0.6 0.4 0.6 0.4 0.6 0.5 S3 S4 S5 S6 S7 S2 S1 2.1 1.6 1.1 1.4 1.6 1.6 1.7 0.4 0.5 0.6 0.5 1.3 1.7 6.3 7.8
A Major Challenge Such systems, e.g. FAVOUR [1] and PaRE[2], have very high memory requirement and computation time. This is not permissible for mobile application [1] Paolo Campigotto , Christian Rudloff , Maximilian Leodolter , and Dietmar Bauer. 2017. Personalized and situation-aware multimodal route recommendations: the FAVOUR algorithm. IEEE Transactions on Intelligent Transportation Systems 18, 1 (2017), 92–102. [2] Yaguang Li, Han Su , Ugur Demiryurek , Bolong Zheng, Tieke He, and Cyrus Shahabi . 2017. PaRE: A System for Personalized Route Guidance. In Proceedings of the 26th International Conference on World Wide Web. 637–646
A Major Challenge Such systems have very high memory requirement and computation time. This is not permissible for mobile application Solution: Using DIOA Utilize Dynamic Input Output Automata (DIOA) which prunes and updates the graph dynamically based on the context of a query. DIOA has a set of internal actions which dynamically includes only those nodes and edges of the route graph which are required as per the query.
DIOA Advantages: Explained 1. State space reduction:For any graph based approach the state space would be;S = T * NC 2 * FCf where, T is no. of time zones, N is number of stops, F is total number of features and f is the features used. But for SIOA, the state space would be; S = 1 * N C 2 * f
T1 T2 B4 B1, B4 B1, B4, B2 B1, B4, B2 B1 B2, B3 B2 B2 B3 B3 B3 B3 FAVOUR : 3 x x
T1 T2 B4 B1, B4 B1, B4, B2 B1, B4, B2 B1 B2, B3 B2 B2 B3 B3 B3 B3 FAVOUR : 3 x x PaRE : 3 x 10 x
T1 T2 B4 B1, B4 B1, B4, B2 B1, B4, B2 B1 B2, B3 B2 B2 B3 B3 B3 B3 FAVOUR : 3 x x PaRE : 3 x 10 x ComfRide : 1 x 10 x 5
FAVOUR : 3 x x PaRE : 3 x 10 x ComfRide : 1 x 10 x 5
System Architecture Optimized graph generation by pruning unwanted nodes User Input Feature Ordering Recommended Route
Working of the DIOA
Break Journey: A Special Scenario We utilize Dynamic Programming approach.Let Then a DAG is G(V,E) is constructed as follows; and The optimal substructure for n breaks is thus given as So, if a commuter prefers β breaks, then the maximum RCI is given as; Consider the breakpoints during a travel
Experiment setup 50 volunteers were recruited for data collection across three cities, Kolkata, Bhubaneswar, DurgapurSome volunteers were given specific routes while others followed their regular routes Every trip was taken by a group of volunteers on different days at various time of the day. They travelled through both the ComfRide recommended route as well as the Google Maps (G-Maps) recommended route (least expected time). Durgapur Kolkata Bhubaneswar ODISHA
Evaluation - Deployed at Kolkata, 4 S-D Pairs S,D Pair Source Destination Distance (km) Average Travel Time (min) 1 2 3 1 2 3 P1 KM RH 10 10 15 55 55 65 P2 SC RH 6 6 6 30 30 30 P3 SC Gh 8 8 - 45 50 - P4 KM JP 15 15 - 70 65 -
Evaluation: Contd.. ComfRide recommended routes differ from G-Maps recommended routes for many instances, which is as high as 70% for P2 and P3 FAVOUR gives priority to the general choices of the commuters over a route, and so, fails to capture the personal choices of a commuter PaRE gives priority to the personal choices , and thus ignores environmental impacts Sitting Probability Number of breakers Number of bus stops Congestion Jerkiness of road Personalized Features ( PaRe ) General Features (FAVOUR)
ConclusionThe key concept behind ComfRide is to embed the general awareness and intelligence used by a regular commuter to choose the best (comfortable) bus route to reach her desired destination.ComfRide recommended routes have on average 30% better comfort level than Google navigation based recommended routes.
Thank you!ComfRide: http://rohit246.github.io/sites/comfride/Follow the work of Complex Network Research Group (CNeRG), IIT KGP at:Web: http://www.cnergr.org/ Facebook: https://web.facebook.com/iitkgpcnergTwitter: https://www.twitter.com/cnerg