Vehicle Sensor Data Extraction Using Time-Window Distribution Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information processing devices fail to capture data characteristics beyond vehicle speed, limiting their ability to extract relevant features from original data collected by multiple sensors on a vehicle.
Innovation Solution
An information processing device that extracts a portion of data using a search process involving clustering, time windows, and error calculation to reduce data amount while maintaining feature capture, employing machine learning to classify data into clusters and setting time windows to minimize error.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data compression is performed by extracting data based only on vehicle speed, then data amount is reduced, but data characteristics beyond vehicle speed are lost
Solution Approach 1:
The patent segments the original data into multiple feature quantities (vehicle speed, acceleration, steering angle, etc.) and applies different extraction criteria to each feature quantity. This allows comprehensive capture of data characteristics across multiple dimensions while reducing overall data volume through selective extraction based on relative frequency distribution for each segment.
Solution Approach 2:
The patent changes the extraction parameters by calculating relative frequency distribution for multiple feature quantities simultaneously rather than relying on a single parameter (vehicle speed). This multi-parameter approach enables the system to identify and extract data points that are significant across different feature dimensions, preserving comprehensive data characteristics while reducing data amount.
2Loss of information
If all original data is used for analysis, then data characteristics are fully captured, but data processing time and computational load increase
Solution Approach 1:
The patent extracts only the essential data points needed for analysis by calculating relative frequency distribution and identifying data points that deviate from the distribution pattern. This extraction process removes redundant data while preserving critical information, achieving both comprehensive data characteristic capture and reduced processing time.
Solution Approach 2:
The patent applies partial action by extracting a selective subset of data points rather than processing all original data. The extraction is based on relative frequency distribution analysis, which identifies the minimum necessary data points that represent the overall data characteristics, thereby reducing computational load while maintaining analysis accuracy.
3Device complexity
If data extraction focuses on single feature quantity, then extraction process is simple, but multiple data characteristics cannot be captured
Solution Approach 1:
The patent implements a universal extraction framework that handles multiple feature quantities (vehicle speed, acceleration, steering angle, engine RPM, etc.) through a unified relative frequency distribution calculation process. This multi-functional approach allows the same extraction methodology to be applied across different feature types, capturing comprehensive data characteristics without proportionally increasing process complexity.
Data Source
AI summary
The processing device of the information processing device includes: a first step of calculating a relative frequency distribution of target data excluding data of an initial prescribed period from the original data; a second step of setting a plurality of time windows for cutting out data of a part of the period of the target data; a third step of cutting out data from the target data; a fourth step of calculating a relative frequency distribution in the extracted data; and a fifth step of calculating an error between the relative frequency distribution of the target data and the relative frequency distribution of the extracted data; and a search process of repeatedly executing the trial from the second step to the fifth step by changing the setting of the plurality of time windows.