Implementation of genetic algorithm in problem of processing GPS data
summary
Claims a genetic algorithm with dynamic time warping and dynamic programming reconstructs sparse vehicle GPS to map links, provides Python code, and beats prior methods on Belgrade data (claimed "most accurate model for sparse GPS data"). Initial population is seeded by proximity to GPS points, fitness combines shortest-path DP and DTW similarity, three generations reach 95% of solutions (max 27 before tuning), subsequence clipping cuts mean runtime to 0.3s mean runtime.
AI-written summary · about
chapters (12)
- 0:00Start
- 2:42Map Matching Practices
- 3:23Real-Time Processing
- 4:06Proposed Model
- 4:37The Genetic Algorithm
- 5:31Generate Initial Population
- 6:48Crossover Operation
- 7:15Explain Accuracy of Gps Devices
- 11:02Fitness Function
- 18:36Mutation Mechanism
- 20:40Performance
- 21:12Accuracy
related talks
39mSolving the vehicle routing problem for optimizing shipment delivery
32mRunning Every Street in Paris with Python and PostGIS
22mFishing for routes: exploring an application of pgRouting
29mAnalysing and sharing genetic data with Python
53mSpatial Programming for the Rubyist
26mBuilding a scalable genomic matching algorithm
15mUsing the GDS Steiner Algorithm for Disney's 4 Park Challenge
41mCalculating Guilt: Using open-source software in forensic DNA testing