Viavi Solutions has been granted a patent for a device that can determine the accuracy of spectroscopic measurements performed on unknown samples. The device uses a configurable parameter to establish a decision boundary for a quantification model and calculates distance metrics to determine if the measurement corresponds to the model. The patent also covers a method for training a global classification model and providing multiple quantification models. GlobalData’s report on Viavi Solutions gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Viavi Solutions, Document anti-counterfeiting was a key innovation area identified from patents. Viavi Solutions's grant share as of September 2023 was 61%. Grant share is based on the ratio of number of grants to total number of patents.
The patent is granted for a method of training and verifying a global classification model using spectroscopic measurements
A recently granted patent (Publication Number: US11775616B2) describes a method and device for performing spectroscopic measurements and generating quantification models. The method involves providing instructions to a spectrometer to perform spectroscopic measurements and receiving sets of spectra based on these instructions. The device then trains a global classification model using a hier-support vector machine (SVM)-linear classifier and a first set of spectra. The global classification model is verified using a hier-SVM-linear classifier and a second set of spectra. After verification, the device provides multiple quantification models.
The patent also discloses that the multiple quantification models can be provided to different devices associated with different spectrometers. Additionally, the method includes training and verifying multiple local quantification models associated with the global classification model. These local quantification models can be included in the multiple quantification models.
The multiple quantification models can correspond to different classes of the global classification model or a local classification model generated based on the global classification model. For example, the quantification models can be used to determine the concentration of a particular protein in different types of meat using in-situ local modeling.
The device described in the patent includes one or more memories and processors. The processors receive sets of spectra from a spectrometer and train a global classification model using a hier-SVM-linear classifier and a first set of spectra. The global classification model is then verified using a hier-SVM-linear classifier and a second set of spectra. After verification, the device provides multiple quantification models.
Similar to the method, the device can provide the multiple quantification models to different devices associated with different spectrometers. The device can also train multiple local quantification models associated with the global classification model, which can be included in the multiple quantification models.
The patent also includes a non-transitory computer-readable medium storing a set of instructions that can be executed by a device. These instructions cause the device to provide instructions to a spectrometer for spectroscopic measurements, receive sets of spectra, train a global classification model, verify the global classification model, and provide multiple quantification models.
Overall, this patent presents a method, device, and computer-readable medium for performing spectroscopic measurements and generating quantification models, which can be used in various applications such as protein concentration determination in different types of meat.
To know more about GlobalData’s detailed insights on Viavi Solutions, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
