# US 12,000,773 B2 · Systems and methods for screening nutrients or chemical compositions using diversifiers for noise reduction > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,000,773 B2 - Document ID: US12000773B2 - Status: Granted - Kind: B2 - Application number: 17/645,450 - Filed: 2021-12-21 - Published: 2023-04-20 - Granted: 2024-06-04 - Earliest claimed: 2021-10-14 - Assignees: Hyperspectral Corp. - Applicants: Hyperspectral Corp. - Inventors: David M. Palacios; Harry Hopper - Web page: https://patentgrep.com/patent/US12000773B2 ## CPC - G01N 21/255: {Details, e.g. use of specially adapted sources, lighting or optical systems} - G01N 21/31: Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry {(G01N21/72 takes precedence)} - G01N 15/0606: {by collecting particles on a support} - G01N 21/314: {with comparison of measurements at specific and non-specific wavelengths (dual wavelength spectrometry G01J3/427)} - G01N 21/39: using tunable lasers - G01N 21/51: inside a container, e.g. in an ampoule (G01N21/53 takes precedence) - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G01N 15/075: by optical means - G01N 33/569: for microorganisms, e.g. protozoa, bacteria, viruses - G01N 2021/513: {Cuvettes for scattering measurements} - G06N 3/048: Activation functions - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A system comprising at least one light source configured to generate a light at specific wavelengths and project the light over an optical path, a sample device, the sample device configured to receive a sample obtained from a person, the sample device being transparent and being at least partially within the optical path, a diversifier including occlusions for scattering coherent light received from the light source along the optical path, a first detector configured to receive the light over the optical path and from at least a portion of the diversifier, the detector configured to detect spectral intensities of the light, and a second detector configured to receive at least a portion of the light form the optical path before the light passes through the diffuser, the second detector configured to detect spectral intensities of the light. ## Claims ### Claim 1 A system comprising: at least one light source configured to generate a light at specific wavelengths and project the light over an optical path; a sample device, the sample device configured to receive a sample obtained from a person, the sample device being transparent and being at least partially within the optical path; a diversifier including occlusions for scattering coherent light received from the light source along the optical path; a first detector configured to receive the light over the optical path and from at least a portion of the diversifier, the detector configured to detect spectral intensities of the light; and a second detector configured to receive at least a portion of the light form the optical path before the light passes through the diversifier, the second detector configured to detect spectral intensities of the light. ### Claim 2 (depends on 1) The system of claim 1, further comprising a processor configured to compare results of spectral detection from the first detector and results of spectral detection of the second detector in view of the specific wavelengths present in the light to recognize spectral patterns caused by scattering from the diversifier. ### Claim 3 (depends on 2) The system of claim 2, wherein the processor generates filtering information to reconstruct spectral information based on the comparison, the filtering information including spectral intensities related to the light from the light source and not including at least some noise added during projection of the light along the light path. ### Claim 4 (depends on 3) The system of claim 3, wherein the system is configured to compare results comprises performing pattern recognition using a deep neural network. ### Claim 5 (depends on 3) The system of claim 3, wherein the processor is remote from the first detector and the second detector. ### Claim 6 (depends on 5) The system of claim 5, wherein the processor is further configured to compare results of spectral detection from a third detector and results of spectral detection of a fourth detector in view of specific wavelengths present in the other light projected by an other light source along an other light path to recognize spectral patterns caused by scattering from an other diversifier, the third detector configured to receive the other light after being projected through at least a part of an other diversifier, the fourth detector configured to receive the other light before being projected through the other diversifier. ### Claim 7 (depends on 6) The system of claim 6, wherein the processor is configured to generate other filtering information to reconstruct spectral information based on comparison of the results of spectral detection from a third detector and results of spectral detection of a fourth detector, the other spectral information including spectral intensities related to the other light from the other light source and not including at least some noise added during projection of the other light along the other light path. ### Claim 8 (depends on 3) The system of claim 3, wherein the processor is further configured to utilize the filtering information for subsequent spectral detection from the first detector to remove noise when a biological sample is contained within the sample device. ### Claim 9 (depends on 8) The system of claim 8, wherein the processor is further configured to detect pathogen signatures by recognizing spectral scattering and absorption caused by known pathogens in a plurality of samples using the first detector and the filtering information to reduce noise and improve spectral detection related to pathogen detection. ### Claim 10 A method comprising: projecting a light over an optical path by at least one light source at light at specific wavelengths and project the light over an optical path; receiving, by a sample device, the light generated by the at least one light source, the sample device capable of receiving a sample obtained from a person, the sample device being transparent and being at least partially within the optical path; receiving, by a diversifier, the light after passing through the sample device; scattering at least some of the light by the diversifier, coherent light of the light being scattered by occlusions of the diversifier; receiving light along the light path by a first detector after light has scattered by the diversifier; detecting, by the first detector, spectral intensities of the light after having passed through the diversifier; generating first measurements of the spectral intensities detected by the first detector; receiving light along the light path by a second detector before light has scattered by the diversifier; detecting, by the second detector, spectral intensities of the light; and generating second measurements of the spectral intensities detected by the second detector. ### Claim 11 (depends on 10) The method of claim 10, further comprising comparing the first measurements and the second measurements in view of the specific wavelengths present in the light to recognize spectral patterns caused by scattering from the diversifier. ### Claim 12 (depends on 11) The method of claim 11, further comprising generating, by a processor, filtering information to reconstruct spectral information based on the comparison, the filtering information including spectral intensities related to the light from the light source and not including at least some noise added during projection of the light along the light path. ### Claim 13 (depends on 12) The method of claim 12, wherein comparing the first measurements and the second measurements comprises performing pattern recognition using a deep neural network. ### Claim 14 (depends on 12) The method of claim 12, wherein the processor is remote from the first detector and the second detector. ### Claim 15 (depends on 14) The method of claim 14, further comprising comparing, by the processor, third measurements of an other light by a third detector and four measurements of the light by a fourth detector in view of specific wavelengths present in the other light projected by an other light source along an other light path to recognize spectral patterns caused by scattering from an other diversifier, the third detector configured to receive the other light after being projected through at least a part of an other diversifier, the fourth detector configured to receive the other light before being projected through the other diversifier. ### Claim 16 (depends on 15) The method of claim 15, further comprising generating, by the processor, other filtering information to reconstruct spectral information based on comparison of the third measurements of spectral detection from the third detector and fourth measurements of spectral detection from the fourth detector, the other spectral information including spectral intensities related to the other light from the other light source and not including at least some noise added during projection of the other light along the other light path. ### Claim 17 (depends on 12) The method of claim 12, further comprising, utilizing, by the processor, the filtering information for subsequent spectral detection from the first detector to remove noise when a biological sample is contained within the sample device. ### Claim 18 (depends on 17) The method of claim 17, further comprising detecting pathogen signatures by recognizing spectral scattering and absorption caused by known pathogens in a plurality of samples using the first detector and the filtering information to reduce noise and improve spectral detection related to pathogen detection.