Time-Series Data Analysis Device Using Variation Coefficients
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for comparing and analyzing time-series data require decompression and re-expansion of numerical data sequences, leading to inefficient calculations and long analysis times due to the need for repeated comparisons at each sampling period.
Innovation Solution
An analysis device with computation units that calculate variation coefficients for linear variation in time-series data, allowing for integrated difference value calculations between paired time points without decompressing the data, thereby efficiently determining similarity between multiple time-series data sets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If time-series data are decompressed and expanded for comparison, then comparison accuracy between model data and sensor data is improved, but calculation time and computational burden increase significantly
Solution Approach 1:
The patent extracts only the necessary comparison information (maximum values, minimum values, and their time points) from the compressed time-series data without performing full decompression. This selective extraction maintains comparison accuracy while avoiding the computational burden of expanding the entire data sequence, directly resolving the contradiction between accuracy and calculation time.
Solution Approach 2:
The patent performs preliminary processing by pre-calculating and storing key statistical values (maximum, minimum, and their time points) during the data compression phase. These pre-computed values are then directly used for comparison operations, eliminating the need for time-consuming decompression and expansion during actual analysis, thus reducing calculation time while preserving accuracy.
2Loss of information
If full decompression is performed for detailed analysis, then data completeness is improved, but productivity and analysis efficiency deteriorate
Solution Approach 1:
The patent applies partial action by performing decomposition and expansion only on specific segments of time-series data that contain the maximum and minimum values requiring comparison, rather than processing the entire data sequence. This selective partial processing maintains data completeness for critical analysis points while dramatically improving analysis efficiency by avoiding unnecessary processing of other data portions.
3Measurement precision
If comparison is performed at each sampling period with time point shifting, then comparison precision is improved, but computational complexity increases enormously
Solution Approach 1:
The patent extracts only the essential comparison elements (maximum values, minimum values, and their corresponding time points) from the compressed data structure. By working with these extracted key values rather than the complete decompressed time-series, the method maintains comparison precision while avoiding the enormous computational complexity of full decompression and point-by-point comparison at each sampling period.
Data Source
AI summary
A first computation unit acquires a first variation coefficient representing characteristics of linear variation of first time-series data, and calculates a value of a start time point and a value of an end time point of the first time-series data. A second computation unit acquires a second variation coefficient representing characteristics of linear variation of second time-series data, and calculates a commencing time point in the second time-series data, and a completing time point obtained by adding a time width between the start time point and the end time point to the commencing time point. A difference integrated value is calculated between paired time points which are in the same positional relationship in a range from the start time point to the end time point and in a range from the commencing time point to the completing time point, without calculating values of intervening time points.