Dual Neural Network Pattern Identifier for Interval Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Machine learning models struggle to identify multiple patterns at the same data point or multiple patterns of the same type during different intervals in data analysis.
Innovation Solution
A system utilizing two trained neural network models processes data points with x-values and y-values to generate output node data, identifying start and stop times for pattern types that exceed a predefined threshold, allowing for the detection of patterns across intervals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single trained neural network model is used to identify patterns in data, then the model can process data points, but it cannot identify multiple patterns at the same data point or multiple patterns of the same type during different intervals
Solution Approach 1:
The patent divides the pattern identification task into multiple specialized neural network models, where each model is trained to identify a specific pattern type. This segmentation allows the system to detect multiple patterns simultaneously by combining the outputs of individual pattern-specific models, resolving the limitation of single-model approaches that can only identify one pattern type at a time.
Solution Approach 2:
The patent creates a universal pattern identification system that can detect multiple pattern types through a ensemble of specialized models. Each neural network model serves multiple functions by being part of the larger system that processes different pattern types, allowing the overall system to achieve multi-functionality while individual models maintain specialized expertise in specific pattern recognition.
2Adaptability or versatility
If multiple neural network models are used to identify different pattern types, then multiple patterns can be detected, but the system complexity increases
Solution Approach 1:
The patent segments the complex pattern recognition problem into smaller, manageable sub-problems handled by individual neural network models. Each model focuses on a specific pattern type, reducing the complexity burden on any single model while the collective ensemble achieves comprehensive pattern detection capability.
Solution Approach 2:
The patent introduces an intermediary layer that aggregates and coordinates the outputs from multiple specialized neural network models. This intermediary mechanism manages the complexity of having multiple models by providing a standardized interface for combining their results, thus handling the system complexity while maintaining multiple pattern detection capability.
Data Source
AI summary
A computing device identifies a pattern in a dataset. A first neural network model is executed using data points as input to input nodes of the first neural network model to generate first output node data. A second neural network model is executed using the first output node data as input to input nodes of the second neural network model to generate second output node data. The second output node data includes a plurality of output values for each x-value of the plurality of data points. For each x-value, an output value of the plurality of output values is associated with a single pattern type of a plurality of predefined pattern types. For each pattern type of the plurality of predefined pattern types, a start time and a stop time is identified when the output value for the associated pattern type exceeds a predefined pattern window threshold value.