Machine Learning Model Development System for Test and Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Testing and measurement of electronic devices face challenges in accessing customer data for machine learning model development, and existing tools lack flexibility for fast experimentation and deployment across different environments, leading to cumbersome and expensive customized solutions.
Innovation Solution
A machine learning model development system that enables faster prototyping and experimentation, featuring a reusable execution model, signal processing, and feature extraction modules, integrated with external data sources and cloud storage, using ONNX standard for model portability across various applications like oscilloscopes and automation tools.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If machine learning models are developed using customized solutions for different environments, then model accuracy and suitability for specific applications is improved, but device complexity and development cost increase
Solution Approach 1:
The patent implements a universal machine learning model development platform that can deploy models across multiple environments (oscilloscopes, automation tools, cloud) using a common architecture. The system uses standardized data interfaces and a unified model training framework that adapts to different target environments without requiring separate customized development processes for each platform.
2Adaptability or versatility
If machine learning models are customized for different environments and applications, then adaptability to specific use cases is improved, but ease of manufacture and deployment deteriorates
Solution Approach 1:
The system segments the machine learning development process into modular components: data collection module, feature extraction module, model training module, and deployment module. Each module can be independently configured and reused across different applications. The segmented architecture allows users to assemble customized solutions by combining pre-built modules rather than developing entire systems from scratch for each environment.
3Productivity
If fast experimentation tools are developed for machine learning model deployment, then productivity and experimentation speed are improved, but device complexity increases
Solution Approach 1:
The system performs preliminary actions by pre-processing data into standardized formats, pre-training feature extraction pipelines, and pre-configuring deployment templates for different environments. These preliminary preparations are done once and can be reused across multiple experimentation iterations, enabling fast prototyping and model development without repeating complex setup procedures for each new model or environment.
Data Source
AI summary
A test and measurement machine learning model development system includes a user interface, one or more ports to allow the system to connect to one or more data sources, one or more memories, and one or more processors configured to execute code to cause the one or more processors to: display on the user interface one or more application user interfaces, the application user interfaces to allow a user to provide user inputs; use and application programming interface to configure the system based on the user inputs; receive data from the one or more data sources; apply one or more modules from a library of signal processing and feature extraction modules to the data to produce training data; apply one or more machine learning models to the training data; provide monitoring of the one or more machine learning models; and save the one or more machine learning models to at least one of the one or more memories. A method for operating a machine learning model development system includes displaying, on a user interface, one or more application user interfaces, the application user interfaces allowing a user to provide user inputs, configuring the system based on the user inputs through an application programming interface, receiving data from one or more data sources, applying one or more modules from a library of signal processing and feature extraction modules to the data to produce training data, applying one or more machine learning models to the training data, providing monitoring of the one or more machine learning models, and saving the one or more machine learning models to at least one of the one or more memories.