SVM Intersection Driving Decision Time Scaling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional support vector machine training processes for intelligent driving decisions at intersections fail to accurately consider time series data, leading to insufficient accuracy in driving decisions such as acceleration, deceleration, or maintaining constant speed.
Innovation Solution
The intelligent driving method employs a support vector machine trained with a dataset processed through a dimensionality reducing module and a time scaling module, converting original features into new features and forming scaled sequences to account for time dependencies, improving the accuracy of driving decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional support vector machine training process is used, then the training is simple and fast, but the accuracy of driving decision is insufficient due to not considering time series data
Solution Approach 1:
The patent applies preliminary action by pre-processing the training dataset before feeding it to the support vector machine. Specifically, the original dataset is pre-processed to add time series information and construct scaled sequences that represent temporal relationships. This preliminary transformation of the data ensures that when the SVM performs classification, it already has access to time-dependent patterns, thereby improving driving decision accuracy without adding complexity during the actual decision-making process
Solution Approach 2:
The patent introduces an intermediary data processing layer between the raw sensor data and the support vector machine classifier. This intermediary layer includes modules for adding time series information, constructing scaled sequences, and transforming the original dataset. These intermediary processing steps act as a bridge that converts raw data into a format that preserves temporal relationships while remaining compatible with the SVM classifier, thus improving accuracy without requiring changes to the core SVM algorithm
2Reliability
If time series data is considered in training, then the accuracy of driving decision is improved, but the data processing complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the data processing into distinct modular components: (1) adding time series information module, (2) scaled sequence construction module, and (3) support vector machine classification module. Each module performs a specific function independently, making the overall complex process more manageable and maintainable. The segmentation allows the system to handle time series data systematically while keeping each processing stage relatively simple and well-defined
Data Source
AI summary
The intelligent driving method applied to a vehicle includes a support vector machine providing step in which the support vector machine is provided. The support vector machine has been trained by a training process. In the training process, a training dataset is provided to the support vector machine. The training dataset is obtained after an original dataset processed by a dimensionality reducing module and a time scaling module. The intelligent driving method includes a dataset processing step in which p features from an environment sensing unit are processed by the dimensionality reducing module and the time scaling module, and the processed dataset will be provided to the support vector machine. The intelligent driving method further includes a deciding step for providing a driving decision for the vehicle according to a classed result of the support vector machine.