Traffic Time Prediction Using Normalized Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting time in traffic are limited in accuracy and adaptability, particularly for routing purposes, as they rely on average vehicle tracking data and fail to account for varying traffic patterns across different times and locations.
Innovation Solution
A computerized method using machine learning models, specifically Deep Neural Networks and Random Forests, is employed to collect and normalize traffic feature values, such as road distance, average speed, and time of day, to predict traffic time by training these models with normalized data and applying them to determine target times for delivery routes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are trained with normalized traffic features, then prediction accuracy improves, but model complexity increases
Solution Approach 1:
The patent applies feature normalization as a preliminary action before training the machine learning model. By pre-processing the traffic features (scaling, standardization, or normalization) before inputting them to the model, the training process becomes more efficient and accurate without requiring complex model architectures. This resolves the contradiction by improving prediction accuracy through data preparation rather than model complexity.
2Adaptability or versatility
If machine learning models are used to predict traffic time, then adaptability to different traffic patterns improves, but computational resources required increase
Solution Approach 1:
The patent changes the parameters of the input data (normalization, standardization, scaling) to make them suitable for machine learning processing. By transforming the raw traffic features into normalized forms, the model can adapt to different traffic patterns more efficiently with reduced computational requirements. This resolves the contradiction by improving adaptability through parameter transformation rather than increasing computational resources.
Data Source
AI summary
In one aspect, a computerized method for using machine learning methods for modeling for time in traffic for a vehicle on a delivery route includes the step of collecting a set of traffic feature values from a database. The method includes the step of normalizing the set of traffic feature values. The method includes the step of providing a machine learning model. The method includes the step of inputting the set of normalized traffic features into the machine learning model. The method includes the step of training the machine learning model with the set of normalized traffic features. The method includes the step of determining a target time for the vehicle on the delivery route.