DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . The preliminary Amendment filed 19 September 2024 has been entered and considered. Claims 1-18 have been cancelled. Claims 19-38 have been added. Claims 19-38 are all the claims pending in the application.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 11/19/2024 and 03/18/2026 were considered by the examiner.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 37 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. As best understood, Claim 37 refers to [0127] of the specification, where a particular coral was examined over time. The “increase in tissue coverage” seems to be the natural result of analyzing that particular coral, and not a situation where the CNN is promoting tissue growth by the claimed amount. It is unclear how the CNN “obtains” the claimed tissue growth, or how this is a feature of the CNN or the method.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 19, 21, and 35-36 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Narayan et al. (NPL: Using Deep Learning to Monitor Coral Reef Health, hereafter referred as Narayan).
Regarding Claim 19:
Narayan teaches a method for determining or predicting coral growth, coral health, or coral resiliency (Narayan: p. 6, par. 3; coupling ML with crowd-sourced images can be used to analyze existing and new databases to identify coral disease), the method comprising:(a) obtaining one or more images of one or more corals (Narayan: p. 8, par. 2; obtained a total of 178 images of individual corals and coral reefs with the aforementioned health conditions (healthy and bleached), which corresponded to a total of 1530 individual instances of these health conditions); and (b) applying a machine learning-based classifier comprising a multi-class model on the one or more images to determine the coral growth, the coral health, or the coral resiliency of the one or more corals (Narayan: p. 9, par. 1, Table 1 and Fig. 2; the corals in the images could be classified as healthy or bleached, and the background of the image (along with any other organisms present) was left unannotated and was treated as a third class; Fig. 2 shows example of image data annotated (right) in Labelbox and used for model-training; healthy corals were outlined in green and bleached corals were annotated in purple using the polygonal selection tool) based at least on a plurality of coral growth features, coral health features, coral resiliency features, or coral environmental features (Narayan: p. 13, Fig. 3; segmentation loss (A), binding box loss (B), and class loss (C); segmentation and binding-box identifies individual coral features while class loss predicts which class those features belong to: healthy or bleached coral).
In regards to Claim 21, Narayan further teaches the method of claim 19, wherein (b) comprises using the classifier to analyze the plurality of coral health features, wherein the plurality of coral health features comprises coral bleaching, coral growth, exposed coral skeleton, coral tissue loss, or coral hygiene (Narayan: p. 9 and 13, par. 1, Table 1 and Fig. 2-3; the corals in the images could be classified as healthy or bleached, and the background of the image (along with any other organisms present) was left unannotated and was treated as a third class; Fig. 2 shows example of image data annotated (right) in Labelbox and used for model-training; healthy corals were outlined in green and bleached corals were annotated in purple using the polygonal selection tool; segmentation loss (A), binding box loss (B), and class loss (C); segmentation and binding-box identifies individual coral features while class loss predicts which class those features belong to: healthy or bleached coral).
In regards to Claim 35, Narayan further teaches the method of claim 19, wherein the classifier comprises a convolutional neural network (CNN) (Narayan: p. 7, par. 1; a CNN has now been trained on images of corals with varying degrees of health in order to create a model that can identify disease).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 36 and 37 are rejected under 35 U.S.C. 103 as being unpatentable over Narayan et al. (NPL: Using Deep Learning to Monitor Coral Reef Health, hereafter referred as Narayan).
In regards to Claim 36, Narayan further teaches the method of claim 35, wherein the CNN is trained to obtain (i) a loss function of less than 5% or (ii) an accuracy greater than 95% (Narayan: p. 14; detecting true instances of bleaching is more critical to protecting reef health than minimizing false positives, therefore the operating point of 0.8, which resulted in a recall of 0.9 and a precision of 0.7, was appropriate; at this operating point, the model achieved 85% accuracy in distinguishing between healthy and bleached corals in the test set; precision, recall, and accuracy combined provide a more complete picture of the model’s performance; the operating point is also flexible and can be changed for implementation of the model; obvious to one skilled in the art that higher accuracy is more desirable, as well as to change the operating point to further increase accuracy, at the cost of increased training time and/or operating speed).
In regard to Claim 37, see the 35 U.S.C. 112 rejection above. The increase in tissue coverage seems to be a property of the coral itself and not the CNN. To the extent this is claiming a coral with improving health, it would have been obvious to one skilled in the art to analyze a variety of corals with Narayan, some of which would have been increasing tissue coverage (with or without the CNN being present) by the claimed amount.
Claims 20 and 32 are rejected under 35 U.S.C. 103 as being unpatentable over Narayan et al. (NPL: Using Deep Learning to Monitor Coral Reef Health, hereafter referred as Narayan) in view of Guan et al. (U.S. Patent App. Pub No. 2017/0357872 A1, hereafter referred as Guan).
In regards to Claim 20, Narayan fails to further teach the method of claim 19, wherein the classifier analyzes the one or more images comprising images in the (i) visible electromagnetic (EM) spectrum, (ii) infrared (IR) EM spectrum, or (iii) ultraviolet (UV) EM spectrum.
Guan, like Narayan, is directed to environmental classifiers. Guan does teach wherein the classifier analyzes the one or more images comprising images in the (i) visible electromagnetic (EM) spectrum, (ii) infrared (IR) EM spectrum, or (iii) ultraviolet (UV) EM spectrum (Guan: Par. [0128]; the feature extractor 500 receives as input remote sensing imagery 510 and extracts features from the image for use by the high-precision pixel classifier 501, Par. [0107]; sensors may include cameras with detectors effective for any range of the electromagnetic spectrum including visible light, infrared, ultraviolet, near-infrared (NIR), and the like).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Narayan to utilize the various sensor modalities, as taught by Guan, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. As taught by Guan, the proposed modification allow for different classification schemes to work better if the features include and/or exclude specific bands from the remote sensing imagery (Guan: Par. [0128]).
In regards to Claim 32, Narayan as modified by Guan further teaches the method of claim 20, further comprising using an imaging apparatus to obtain the one or more images of the one or more corals (Narayan: p. 8, par. 2; obtained a total of 178 images of individual corals and coral reefs with the aforementioned health conditions (healthy and bleached), which corresponded to a total of 1530 individual instances of these health conditions), wherein the imaging apparatus comprises one or more sensors for imaging in (i) the visible EM spectrum, (ii) the IR EM spectrum, or (iii) the UV EM spectrum (Guan: Par. [0128]; the feature extractor 500 receives as input remote sensing imagery 510 and extracts features from the image for use by the high-precision pixel classifier 501, Par. [0107]; sensors may include cameras with detectors effective for any range of the electromagnetic spectrum including visible light, infrared, ultraviolet, near-infrared (NIR), and the like).
Claims 22-23 and 29-30 are rejected under 35 U.S.C. 103 as being unpatentable over Narayan et al. (NPL: Using Deep Learning to Monitor Coral Reef Health, hereafter referred as Narayan) in view of Stender et al. (NPL: Evaluating the feasibility and advantage of a multi-purpose submerged breakwater for harbor protection and benthic habitat enhancement at Kahului Commercial Harbor, Hawai‘i: case study, hereafter referred as Stender).
In regards to Claim 22, Narayan fails to further teach the method of claim 19, wherein (b) comprises using the classifier to analyze the plurality of coral environmental features, wherein the plurality of coral environmental features comprises pH or salinity of water in which the one or more corals are submerged.
Stender, like Narayan, is directed to the environmental analysis of coral reefs. Stender does teach wherein the plurality of coral environmental features comprises pH or salinity of water in which the one or more corals are submerged (Stender: 2.3 Water quality; water quality measurements included temperature (°C), pH, salinity (ppt), and turbidity (NTU), measurements were taken 1.5 m off the sea floor at each sampling site, variables including water temperature, salinity, turbidity, depth, dissolved oxygen, and pH were assessed for linear relationships between pairs of the variables using the scatter plot matrix).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Narayan to utilize the analysis of water quality, as taught by Stender, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. As taught by Stender, the proposed modification would allow for data analysis using an environment gradient based on the variables (Stender: 2.3 Water quality).
In regards to Claim 23, Narayan as modified by Stender further teaches the method of claim 19, wherein (b) comprises using the classifier to analyze the plurality of coral environmental features, wherein the plurality of coral environmental features comprises levels of calcium, phosphate, nitrogen, nitrate, nitrite, or dissolved oxygen in the water in which the one or more corals are submerged (Stender: 2.3 Water quality; water quality measurements included temperature (°C), pH, salinity (ppt), and turbidity (NTU), measurements were taken 1.5 m off the sea floor at each sampling site, variables including water temperature, salinity, turbidity, depth, dissolved oxygen, and pH were assessed for linear relationships between pairs of the variables using the scatter plot matrix).
In regards to Claim 29, Narayan as modified by Stender further teaches the method of claim 19, further comprising adjusting one or more environmental parameters of an environmental apparatus determined by the classifier to have a likelihood of optimizing coral growth conditions (Stender: 4.1 Reef community patterns and application of a multi-purpose submerged breakwater; engineering potentials for how a submerged breakwater at Kahului could be designed as a multi-purpose ‘reef structure’ for harbor protection, while replacing a deeper barren-disturbed soft-bottom area with an optimal shallow-water coral reef habitat).
In regards to Claim 30, Narayan as modified by Stender further teaches the method of claim 29, wherein the one or more environmental parameters comprise (i) pH or salinity of water in which the one or more corals are submerged or (ii) levels of calcium, phosphate, nitrogen, nitrate, nitrite, or dissolved oxygen in the water (Stender: 2.3 Water quality; water quality measurements included temperature (°C), pH, salinity (ppt), and turbidity (NTU), measurements were taken 1.5 m off the sea floor at each sampling site, variables including water temperature, salinity, turbidity, depth, dissolved oxygen, and pH were assessed for linear relationships between pairs of the variables using the scatter plot matrix).
Claims 24-28 and 31 are rejected under 35 U.S.C. 103 as being unpatentable over Narayan et al. (NPL: Using Deep Learning to Monitor Coral Reef Health, hereafter referred as Narayan) in view of Drury et al. (NPL: Genotype by environment interactions in coral bleaching, hereafter referred as Drury).
In regards to Claim 24, Narayan fails to further teach the method of claim 19, further comprising using the classifier to determine or predict the coral growth, the coral health, or the coral resiliency for a likelihood of successful outplanting to an in situ environment.
Drury, like Naryana, is directed to the environmental analysis of coral reefs. Drury does teach using the classifier to determine or predict the coral growth, the coral health, or the coral resiliency for a likelihood of successful outplanting to an in situ environment (Dury: 4. Discussion; the strongest residuals represent coral colonies that were more (or less) tolerant than their counterparts at greater than 85% (7 of 8) sites, meaning that predictions can account for a portion of the variation associated with interactions and provide practitioners with ‘confidence intervals' about their chance of success in a new environment).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Narayan to utilize outplanting success prediction, as taught by Dury, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. As taught by Drury, the proposed modification can alter the genetic composition of coral populations to facilitate adaptive change (Drury: 1. Introduction).
In regards to Claim 25, Narayan as modified by Drury further teaches the method of claim 19, further comprising obtaining genetic sequencing of the one more or corals to perform assisted evolution (Dury: 2. Methods; used next-generation sequencing and phenotypic assays from 668 Acropora cervicornis fragments monitored during the 2015 global bleaching event to evaluate genotype × environment interactions and genomic correlates of resilience).
In regards to Claim 26, Narayan as modified by Drury further teaches the method of claim 25, wherein the genetic sequencing is used to train the classifier for performing the assisted evolution of the one or more corals (Dury: 2. Methods; to create predictions for novel corals not used in the reciprocal transplant, we used additional samples collected as part of ongoing restoration efforts by a network of nurseries along the Florida Reef Tract that had sequencing data, aligned reads and calculated allelic probabilities using the method detailed above for the 58 loci used in the original model).
In regards to Claim 27, Narayan as modified by Drury further teaches the method of claim 25, wherein the assisted evolution comprises (i) subjecting the one or more corals to adverse growth or environmental conditions and (ii) obtaining updated genetic sequencing of the subjected one or more corals (Drury: 3 Results; all sites experienced conditions above the bleaching threshold of 30.5°C and 4 of 7 sites experienced at least 40 h above 32°C; all corals were harboured in a single in situ nursery from 1 year prior to outplanting to decrease the influence of acclimatization and isolate host genotypic effects).
In regards to Claim 28, Narayan as modified by Drury further teaches the method of claim 25, further comprising using the genetic sequencing to perform the assisted evolution of the one or more corals (Drury: 2. Methods; collected one genotype of Acropora cervicornis from each of 10 sites and propagated them in a common garden nursery for 1 year before outplanting each to 8 of the original collection sites, 3. Results; all corals were harboured in a single in situ nursery from 1 year prior to outplanting to decrease the influence of acclimatization and isolate host genotypic effects).
In regards to Claim 31, Narayan as modified by Drury further teaches the method of claim 19, further comprising outplanting at least one coral of the one or more corals determined by the classifier to have a likelihood of successful outplanting (Drury: 2. Methods; collected one genotype of Acropora cervicornis from each of 10 sites and propagated them in a common garden nursery for 1 year before outplanting each to 8 of the original collection sites, 3. Results; all corals were harboured in a single in situ nursery from 1 year prior to outplanting to decrease the influence of acclimatization and isolate host genotypic effects).
Claims 33-34 are rejected under 35 U.S.C. 103 as being unpatentable over Narayan et al. (NPL: Using Deep Learning to Monitor Coral Reef Health, hereafter referred as Narayan) in view of Akkaynak et al. (NPL: Sea-thru: A Method For Removing Water From Underwater Images, hereafter referred as Akkaynak).
In regards to Claim 33, Narayan fails to further teach the method of claim 19, further comprising processing the one or more images into one or more reconstructed phase images.
Akkaynak, like Narayan, is directed to the analysis of underwater images. Akkaynak does teach processing the one or more images into one or more reconstructed phase images (Akkaynak: 1. Introduction; reconstructing colors in underwater images using the Sea-thru revised model).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Narayan to utilize the color reconstruction technique, as taught by Akkaynak, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. As taught by Akkaynak, the proposed modification would help with better scene recovery (Akkaynak: 1. Introduction).
In regards to Claim 34, Narayan as modified by Akkaynak further teaches the method of claim 33, wherein (b) comprises using the classifier to analyze the one or more reconstructed phase images (Akkaynak: 1. Introduction; reconstructing colors in underwater images using the Sea-thru revised model) to determine coral health features comprising coral bleaching, coral growth, exposed coral skeleton, coral tissue loss, or coral hygiene (Narayan: p. 6, par. 3; coupling ML with crowd-sourced images can be used to analyze existing and new databases to identify coral disease).
Allowable Subject Matter
Claim 38 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Claim 38 recites, wherein the CNN prioritizes health-dependent phenotypes or morphological changes based at least on a frequency or a number of occurrences of the health-dependent phenotypes or the morphological changes. The cited art of record does not teach or suggest such a combination of features.
Because the cited art of record, alone or in combination, does not teach or suggest each and every feature of dependent Claims 37 and 38, these claims would be allowable.
Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Schill et al. (NPL: Site Selection for Coral Reef Restoration Using Airborne Imaging Spectroscopy) teaches using derivatives from imaging spectroscopy from the Global Airborne Observatory (GAO) to identify suitable coral outplant sites and report on the survival rates of restored coral at those sites.
Van Oppen et al. (NPL: Building coral reef resilience through assisted evolution) teaches the risks and benefits of the improvement of natural and commercial stocks in noncoral reef systems and advocate a series of experiments to determine the feasibility of developing coral stocks with enhanced stress tolerance through the acceleration of naturally occurring processes, an approach known as (human)-assisted evolution, while at the same time initiating a public dialogue on the risks and benefits of this approach.
McMillan et al. (U.S. Patent App. Pub No. 2005/0172910 A1) teaches a system and method for monitoring and controlling an aquatic environment thus regulating the aquatic environment and maximizing the stability of the aquatic ecosystem.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RENAE BITOR whose telephone number is (703)756-5563. The examiner can normally be reached Monday to Friday: 8:00 - 5:30 but off the 1st Friday of the biweek.
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, GREG MORSE can be reached on (571)272-3838. 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.
/RENAE A BITOR/Examiner, Art Unit 2663
/GREGORY A MORSE/Supervisory Patent Examiner, Art Unit 2698
Prosecution Insights