Electronic Sensing System for Olfactory Product Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional electronic sensing systems for olfactory products are plagued by unstable and non-quantitative results, producing erroneous outputs due to their inability to accurately detect and classify odors and flavors, particularly in hedonic evaluations which are subjective and dependent on human opinions.
Innovation Solution
A processor-implemented method and system that utilizes a sensing module to extract smell characteristics, a comparison module to analyze these characteristics against historic training data, and neural network models to generate reports including type, name, status, age, and decaying index of olfactory products, enabling classification into categories based on freshness and consumability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional electronic sensing systems are used for olfactory detection, then the system structure is simple, but the measurement precision and reliability are poor due to unstable and non-quantitative results
Solution Approach 1:
The sensing system is divided into multiple functional modules: sensing module (with sensor array), signal processing module, data analysis module, and classification module. Each module performs a specific function in the odor detection chain, improving measurement precision through specialized processing at each stage while keeping individual modules relatively simple.
Solution Approach 2:
The system performs preliminary actions by collecting historical training data and establishing reference odor profiles before actual detection. The neural network models are pre-trained with extensive odor data, enabling the system to achieve high measurement precision during actual operation without requiring complex real-time processing.
2Reliability
If conventional sensing devices are used, then the device complexity is low, but the reliability of results is poor due to erroneous outputs and instability
Solution Approach 1:
The system implements feedback mechanisms where detection results are continuously compared with historical training data and reference profiles. The neural network models learn from past detections and adjust their parameters, providing feedback that improves reliability over time. The system also provides feedback on detection confidence levels to indicate result reliability.
Solution Approach 2:
The patent replaces conventional mechanical/electronic sensing approaches with neural network-based pattern recognition. Instead of relying on simple threshold comparisons or rule-based systems, the neural networks process sensor signals to identify odor patterns, significantly improving reliability by capturing complex nonlinear relationships in odor data.
3Measurement precision
If neural network models and historical data comparison are implemented, then measurement precision and classification accuracy improve, but the loss of time for data processing and analysis increases
Solution Approach 1:
The system performs preliminary actions by pre-processing and normalizing historical training data before actual detection. Reference odor profiles are established in advance, and neural network models are pre-trained with extensive odor datasets. This preliminary preparation enables rapid classification during actual operation, reducing the time loss during real-time detection.
Solution Approach 2:
The system dynamically adjusts its processing based on detection needs. For routine detections, the system uses optimized neural network inference that is computationally efficient. The processing depth and complexity are dynamically adjusted based on the confidence level of preliminary analysis, allowing the system to achieve high accuracy while minimizing unnecessary processing time.
Data Source
AI summary
Electronic sensing systems and methods are disclosed. The electronic sensing system (ESS) receive an olfactory product and one or more smell characteristics of the olfactory product are detected and extracted by identifying a headspace of the olfactory product. A comparison of the extracted smell characteristics with one or more smell characteristics associated with a historic training data stored in a database is performed and a match between the extracted smell characteristics and the one or more smell characteristics associated with the historic training data is determined using machine learning technique(s). Further, the ESS generates a report for the olfactory product comprising at least one of type of the consumable, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index, and classifies the olfactory product into one or more categories based on the report and/or the historic training data.