Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 09/24/2024 was being considered by the examiner.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 5 - 11, 15 – 18 and 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mayor et al. (US Patent 7,582,127 B1) in view of Cho et al. (WO 2017/210781 A1) and Ren et al. (Prediction of Aerosol Particle Size Distribution Based on Neural Network, Advances in Meteorology, 2020, 5074192, 11 pages, 2020. https://doi.org/10.1155/2020/5074192).
With regards to claims 1,11 and 18, Mayor discloses a polarimetric light field imaging system for an aerosol plume (Figure 1) comprising:
a plurality of laser sources operating at different wavelengths and configured to generate a plurality of laser beams (Figure 1; Col. 3, Lines 1 – 20; Col. 6, Lines 20 – 29 and Cool. 6, Lines 11-18);
an optical arrangement downstream from the plurality of laser sources and configured to transmit the plurality of laser beams toward the aerosol plume, and receive backscatter images therefrom (Figure 1; Col. 3, Lines 1 – 20, Col. 4, Lines 60 – 65);
a spectral polarization filter downstream from the optical arrangement (Figure 1; Col. 3, Lines 1 – 20, Col. 6, Lines 11 – 18);
acquiring parallel and perpendicular polarization components (Figure 1; Col. 3, Lines 212-38, Col. 5, Lines 1 – 22) and
processing backscatter/polarization data to determine aerosol/particles characteristics using conventional detectors for polarization channels, basically Mayor teaches polarimetric backscatter sensing for aerosols (Col. 4, Lines 1- 12) (Col. 6, Lines 13 – 19; Col. 6, Lines 20 – 41; Col. 14, Lines 1 – 18).
Mayor fails to expressly disclose a light field sensor downstream from the spectral polarization filter and configured to capture a plurality of backscatter images of the aerosol plume at different polarizations; and
a processor coupled to the light field image sensor and configured to use a Machine Learning (ML) model to determine a particle density and a particle size distribution of the aerosol plume.
Cho relates to imaging systems and methods and, more particularly, to a light field imaging device and method for depth acquisition and three- dimensional (3D) imaging including light ray directions and spectral information [0082] – [0084], [0088]. Cho basically teaches capturing angular as in directional, information in a compact light field sensor including spectral and angular information (Abstract) [0003] [0018].
Ren discloses a trained BP neutral network predicting aerosol particle number concentration distribution, as in size distribution /particle density vs size, using multi-wavelength optical inputs; the output layer includes 52 channels corresponding to aerosol particle number concentration (Pages 6-7 &10, Figure 3, Conclusion). Ren basically teaches ML PSD/density output (Abstract) (Page 1, Lines 44-46; page 6) .
It would have been obvious to a person of ordinary skill in the art at the time the invention was made to modify Mayor to include the teachings such as that taught by Cho (Cho’s light sensor in Mayor receivers path to obtain angle-resolved backscatter data for improved aerosol characterization) and Ren (Ren’s ML approach to the multi-wavelength, polarization and angle resolved backscatter imaged by Mayor and Cho to obtain particle density and assize distribution with speed and robustness) in order to improve imaging system as needed.
With regards to claims 5 and 15, Mayor discloses the ML model comprises an artificial neural network but fails to expressly disclose a deep artificial neural network. The examiner takes Official Notice that both of these neutral networks are well known and conventional in the arts. "Deep" describes the successive layers of representations that allow models to solve problems that shallow networks simply cannot handle. In this instance, increasing the number of layers (depth) is a logical optimization of a "result-effective variable", which comes down to discovering the optimum or workable models that is considered only to involve only routine skill in the art. Recognizing that adding layers to these models, typically improves the network's ability to model complex relationships, which is well known and conventional knowledge.
As such, in view of the utility, to increase depth to optimize model accuracy using known tools, it would have been obvious to a person of ordinary skill in the art at the time the invention was made to modify Mayor modified (i.e., Ren teaches the neural networking) to include the DNN with additional multiple hidden layers as oppose to the shallow ANN such as that that is well known and conventional in the art to improve the imaging system.
With regards to claim 6 and 16, Mayor modified discloses the processor is configured to control the spectral polarization for co-polarized and cross-polarized backscatter images (Figure 1, Col. 3, Line 3 to Col. 5, Line 3). Notice how Mayor teaches receiving and separating parallel/perpendicular polarizations components of backscatter. See parallel (Co-polarized) and perpendicular (cross-polarized) and rotatable ½ wave plate in the receiver path for selecting (Col. 5, Lines 57 – 65).
With regards to claims 7 and 17, Mayor discloses the claimed invention according to claim 1, but fails to expressly disclose that the light field sensor is configured to perform hyperspectral wavelength discrimination.
Cho relates to imaging systems and methods and, more particularly, to a light field imaging device and method for depth acquisition and three- dimensional (3D) imaging including light ray directions and spectral information [0019]. [0028], [0033], [0082] – [0084], [0088].
Cho further discloses teaches wavelength discrimination using dispersive optics and/or filtering (Abstract) [0094], [0093] (Claims 3 – 5).
In view of the utility, to increase depth to optimize model accuracy using known tools, it would have been obvious to a person of ordinary skill in the art at the time the invention was made to modify Mayor modified (i.e., Ren teaches the neural networking) to include the DNN with additional multiple hidden layers as oppose to the shallow ANN such as that that is well known and conventional in the art to improve the imaging system.
With regards to claims 8 and 21, Mayor modified discloses the claimed invention according to claims 1 and 18, and further Mayor teaches wavelength shifting/multi-wavelength operation (i.e., see Raman shifting; 1064 nm to 1543 nm) (Col. 5, Line 19 – 27; Col. 14, Lines 1 – 4).
Mayor modified fails to expressly disclose the light field sensor is configured to perform measurements of both angular independence and wavelength shift of backscatter images.
Cho discloses capturing directional/wave-vector (k), supporting angular resolved measurements [0002], [0003].
In view of the utility, using both angularly resolved and multi-wavelength measurements as features for aerosol property determination to improve PSD/number concentration prediction and/or sensory, it would have been obvious to a person of ordinary skill in the art at the time of the invention to modify Mayor to include the teaching such as that taught by Cho.
With regards to claim 9, Mayor modified discloses a plurality of laser sources is known (i.e., Col. 24, Line 43) and further Mayor teaches that the source and/or laser are near infrared laser source and a shortwave infrared laser source (Col. 14, Lines 1 – 18).
With regards to claim 10, Mayor modified discloses the spectral polarization filter comprises a rotatable spectral polarization filter (Col. 5, Lines 57 - 66.).
Claim(s) 2, 3,12, 13, 19 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mayor et al. (US Patent 7,582,127 B1), Cho et al. (WO 2017/210781 A1) and Ren et al. (Prediction of Aerosol Particle Size Distribution Based on Neural Network, Advances in Meteorology, 2020, 5074192,11 pp, 2020. https://doi.org/10.1155/2020/5074192) in view of Yorks et al. (Aerosol and Cloud Detection Using Machine Learning Algorithms & Space-Based Lidar Data. Atmosphere 2021,12, 606 https://doi.org/10.3390/atmos12050606).
With regards to claims 2, 3,12, 13, 19 and 20, Mayor modified provide teachings of a ML model (see the rejection of claim 1), but Mayor modified fail to teach that the ML model is completely tied to training backscatter images or comprises CNN (i.e., claims 3/13/20).
Ren does teach determining important aerosol property parameters using neutral network algorithms and adopting such systems to predict aerosol parameters as needed (Abstract) (2.2. Mie Scattering Theory) (4. Experiment and Results Analysis). Notice how Figure 3 shows the structure diagram of the BP neural network prediction model (Page 6). Still, Mayor modified fail to teach expressly the ML completely tied to training backscatter images.
Yorks teaches a remote sensing device for detecting aerosols (Abstract). More importantly, Yorks teaches a ML Model was based upon a plurality of training back scatter images. In addition to teaching that CNNs are known and effective architecture for image-based inputs; thus, an obvious implementing of the ML model as a CNN model when operation on backscatter images (Abstract; Pages 1 and 11).
In view of the utility, applying a CNN model for improved cloud-aerosol discrimination and sensing, it would have been obvious to a person of ordinary skill in the art at the time of the invention to modify Mayor to include the teaching such as that taught by Yorks.
Claim(s) 4 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mayor et al. (US Patent 7,582,127 B1), Cho et al. (WO 2017/210781 A1) and Ren et al. (Prediction of Aerosol Particle Size Distribution Based on Neural Network, Advances in Meteorology, 2020, 5074192,11 pp, 2020. https://doi.org/10.1155/2020/5074192) in view of Yu et al. (Use of machine learning to reduce uncertainties in particle number concentration and aerosol indirect radiative forcing predicted by climate models. Geophysical Research Letters, (2022), 49, e2022GL098551. https://doi.org/10.1029/2022GL098551).
With regards to claims 4 and 14, Mayor modified discloses the ML model as claimed according to claim 1, but fails to expressly disclose the ML model comprises a random forest.
Yu teaches Random Forest ML model for concentration and other parameter interest with regards to aerosol remote sensing.
In view of the utility, applying a random forest model for improved cloud-aerosol sensing as needed, it would have been obvious to a person of ordinary skill in the art at the time of the invention to modify Mayor to include the teaching such as that taught by Yu.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DJURA MALEVIC whose telephone number is (571)272-5975. The examiner can normally be reached M-F (9-5).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Uzma Alam can be reached at 571.272.3995. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/DJURA MALEVIC/Examiner, Art Unit 2884
/UZMA ALAM/Supervisory Patent Examiner, Art Unit 2884