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 .
DETAILED ACTION
This action is in response to the application filed 19 February 2026. Claims 2, 7, 9, and 16-23 were previously cancelled. Claims 1, 3, 8, 10, and 12 are amended. Claims 24-25 are newly added. Claims 1, 3-6, 8, 10-15, 24, and 25 are pending and have been examined.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 19 February 2026 has been entered.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 19 February 2026 is being considered by the examiner.
Response to Arguments
Applicant' s arguments, see page 7-10, filed 19 December 2025, with respect to the rejections of Claims 1, 3-6, 8, and 10-15 under 35 U.S.C. 101 have been fully considered but they are not persuasive.
APPLICANT'S ARGUMENT: Applicant argues (page 8, paragraph 3) that "The human mind is not equipped or capable of determining heat energy collected by an infrared (IR) sensor; generating commands to control a controlled appliance of a building, such as an HVAC appliance, based on the heat energy; and then transmitting the commands to the controlled appliance (e.g., HVAC appliance) via a communication interface. Moreover, the human mind is not equipped or capable of implementing 'several fully connected layers implementing an auto-encoding functionality' as recited in independent claims 1 and 8. Moreover, the human mind is not capable of implementing a pooling layer as recited in dependent claims 6 and 15 to reduce the size of the 2D matrix generated by the convolutional layer of the neural network."
EXAMINER'S RESPONSE: Examiner respectfully disagrees. At the claimed level of generality, use of a sensor to receive measurements and transmitting commands amount to steps of mere data gathering under Step 2A Prong 2 of the Alice/Mayo test, and are well-understood, routine, conventional activities under Step 2B, due to being steps of merely receiving or transmitting data over a network. Generating commands based on heat energy appears to recite a mental process step, such as an evaluation or judgement. The additional elements of temperature measurements, an infrared sensor, and an HVAC system generally link the mental processes recited by the claim to a particular field of use.
APPLICANT'S ARGUMENT: Applicant argues (page 9, paragraph 3) that "the claimed auto-encoder is 'to perform a compression of the data at the central layer(s).' Thus, claims 1 and 8 reflect an improvement to the functioning of a technology because the claims are directed towards improving the performance of the computing device by compressing data at the central layer(s)."
EXAMINER'S RESPONSE: Examiner respectfully disagrees. As indicated in the rejection of amended Claim 1 below, executing a predictive neural network by using fully connected layers implementing autoencoding functionality appears merely to invoke a computer or other machinery merely as a tool to perform an existing process at the claimed level of generality.
APPLICANT'S ARGUMENT: Applicant argues (page 10, continued paragraph) that "claims 6 and 15 reflect an improvement to the functioning of a technology because the claims are directed towards improving the performance of the computing device processing temperatures of the infrared sensor (e.g., thermal or heat sensors) by reducing the size of the 2D matrix generated by the convolutional layer via the claimed one more pooling layers."
EXAMINER'S RESPONSE: Examiner respectfully disagrees. The amended claims do not appear to recite or reflect the argued improvement of reducing the size of the matrix of measurements. Examiner notes that although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims.
APPLICANT'S ARGUMENT: Applicant argues (page 10, paragraph 1) that "the claims, when viewed as an ordered combination, amount to significantly more than the alleged abstract idea, at least because the claims are directed to 'specific limitations or combinations of limitations that are not well-understood, routine, conventional activity in the field."
EXAMINER'S RESPONSE: Examiner respectfully disagrees. Amended Claim 1 recites a number of additional elements, but examination of the additional elements in combination with the mental process steps recited by the claim indicate that the claim amounts to well-understood, routine, conventional activity under Step 2B of the Alice/Mayo test as given in the 35 U.S.C. 101 rejection below.
Applicant' s arguments, see pages 10-12, filed 19 December 2025, with respect to the rejections of Claims 1, 3-6, 8, and 10-15 under 35 U.S.C. 103 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
APPLICANT'S ARGUMENT: Applicant argues (page 12, paragraph 2) that "the applied prior art does not teach or suggest to 'generate ... one or more commands for controlling operations of a controlled appliance, the controlled appliance and the computing device being part of an environment control system of a building' and 'transmit the one or more commands to the controlled appliance...' as recited in amended independent claims 1 and 8."
EXAMINER'S RESPONSE: Examiner notes that Applicant's arguments are moot. Amended Claims 1, 3, 4-6, 8, 10-15, 24, and 25 are now rejected under 35 U.S.C. 103 as being unpatentable over Cao in view of Luo in view of Brahimi.
Claim Objections
Claim 6 is objected to because of the following informalities: the claim is indicated as being "(Original)" but contains the amendments "s." Appropriate correction or clarification is required. For the purposes of examination, Claim 6 has been interpreted not to have been amended, similarly to Claim 15.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1, 3-6, 8, 10-15, 24, and 25 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding Claim 1
Step 1
Claim 1 recites a computing device, and thus the claimed manufacture falls within a statutory category of invention.
Step 2A Prong 1
The claim recites generating outputs based on inputs, the inputs comprising the 2D matrix of ... measurements, the outputs comprising a 2D matrix of inferred ..., the 2D matrix of inferred ... having M lines and N columns, which is a mental process. The claim recites select a subset of S values of the 2D matrix of ... measurements, S being an integer greater than 1 and lower than M * N, which is a mental process. The claim recites determine that the subset of S values of the 2D matrix ... is anomalous based on a result of the comparison algorithm being applied to the subset of S values of the 2D matrix of ... measurements and the corresponding subset of S values of the 2D matrix of inferred ..., which is a mental process. The claim recites generate, based at least on the determination that the subset of S values of the 2D matrix of ... measurements ... is anomalous, one or more commands, which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2
The additional elements a communication interface, memory for storing a predictive model generated by a neural network training engine, and a processing unit comprising one or more processors invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element receive via the communication interface a two-dimensional (2D) matrix of ... measurements from an ... sensor, the 2D matrix of ... measurements having M lines and N columns, M and N being integers greater than 1 amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering"). The additional element temperature measurements and temperature measurements from the infrared sensor does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element execute a neural network inference engine, the neural network inference engine implementing a neural network using the predictive model invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element the neural network comprises several fully connected layers implementing an auto-encoding functionality invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element apply a comparison algorithm to the subset of S values of the 2D matrix of ... measurements and a corresponding subset of S values of the 2D matrix of inferred invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element commands for controlling operations of a controlled appliance, the controlled appliance and the computing device being part of an environment control system of a building does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element transmit the one or more commands to the controlled appliance of the building via the communication interface to control operations of the controlled appliance amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering").
Step 2B
The additional elements a communication interface, memory for storing a predictive model generated by a neural network training engine, and a processing unit comprising one or more processors invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element receive via the communication interface a two-dimensional (2D) matrix of ... measurements from an ... sensor, the 2D matrix of ... measurements having M lines and N columns, M and N being integers greater than 1 is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network"). The additional element temperature measurements and temperature measurements from the infrared sensor does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element execute a neural network inference engine, the neural network inference engine implementing a neural network using the predictive model invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element the neural network comprises several fully connected layers implementing an auto-encoding functionality invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element apply a comparison algorithm to the subset of S values of the 2D matrix of ... measurements and a corresponding subset of S values of the 2D matrix of inferred invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element commands for controlling operations of a controlled appliance, the controlled appliance and the computing device being part of an environment control system of a building does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element transmit the one or more commands to the controlled appliance of the building via the communication interface to control operations of the controlled appliance is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 3
Step 1
Regarding Claim 3, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
Claim 3 recites the abstract ideas recited by parent Claim 1.
Step 2A Prong 2
The additional element receive via the communication interface a two-dimensional (2D) matrix of temperature measurements from an infrared (IR) sensor (as recited in the rejection of Claim 1), wherein the IR sensor includes an IR camera amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering").
Step 2B
The additional element receive via the communication interface a two-dimensional (2D) matrix of temperature measurements from an infrared (IR) sensor (as recited in the rejection of Claim 1), wherein the IR sensor consists of an IR camera is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 4
Step 1
Regarding Claim 4, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
The claim recites select a subset of S values of the 2D matrix of temperature measurements, S being an integer greater than 1 and lower than M * N (as recited in the rejection of Claim 1), wherein the determination that the subset of values of the 2D matrix of temperature measurements is anomalous is indicative of ... a ... temperature higher than usual, which is a mental process, which is a mental process. Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The additional element the subset of values of the 2D matrix of temperature measurements comprises at least some of the body temperature measurements of the human being, does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element the human being having a body temperature higher than usual, does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element the 2D matrix of temperature measurements comprises body temperature measurements of a human being, does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 5
Step 1
Regarding Claim 5, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
Claim 5 recites the abstract ideas recited by parent Claim 1.
Step 2A Prong 2, Step 2B
The additional element execute a neural network inference engine, the neural network inference engine implementing a neural network using the predictive model (as recited in the rejection of Claim 1), wherein the neural network comprises several fully connected layers implementing an auto-encoding functionality invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 6
Step 1
Regarding Claim 6, the rejection of Claim 5 is incorporated.
Step 2A Prong 1
Claim 6 recites the abstract ideas recited by parent Claim 5.
Step 2A Prong 2, Step 2B
The additional element execute a neural network inference engine, the neural network inference engine implementing a neural network using the predictive model (as recited in the rejection of Claim 1) wherein the neural network comprises several fully connected layers implementing an auto-encoding functionality (as recited in the rejection of Claim 5), wherein the neural network further comprises at least one two-dimension (2D) convolutional layer, optionally one or more pooling layer, the first among the at least one 2D convolutional layer applying a 2D convolution to the 2D matrix of temperature measurements invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 8
Step 1
Claim 8 recites a method using a neural network to analyze temperature measurements of an infrared (IR) sensor, and thus the claimed process falls within a statutory category of invention.
Step 2A Prong 1
The claim recites generating outputs based on inputs, the inputs comprising the 2D matrix of ... measurements, the outputs comprising a 2D matrix of inferred ..., the 2D matrix of inferred ... having M lines and N columns, which is a mental process. The claim recites select a subset of S values of the 2D matrix of ... measurements, S being an integer greater than 1 and lower than M * N, which is a mental process. The claim recites determine that the subset of S values of the 2D matrix ... is anomalous based on a result of the comparison algorithm being applied to the subset of S values of the 2D matrix of ... measurements and the corresponding subset of S values of the 2D matrix of inferred ..., which is a mental process. The claim recites generate, based at least on the determination that the subset of S values of the 2D matrix of ... measurements ... is anomalous, one or more commands, which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2
The additional element storing a predictive model generated by a neural network training engine in a memory of a computing device amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering"). The additional element by the processing unit of the computing device invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element receiving ... a two-dimensional (2D) matrix of ... measurements from an ... sensor, the 2D matrix of ... measurements having M lines and N columns, M and N being integers greater than 1 amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering"). The additional element temperature measurements and temperature measurements from the infrared sensor does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element executing ... a neural network inference engine, the neural network inference engine implementing a neural network using the predictive model invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element the neural network comprises several fully connected layers implementing an auto-encoding functionality invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element applying ... a comparison algorithm to the subset of S values of the 2D matrix of ... measurements and a corresponding subset of S values of the 2D matrix of inferred invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element commands for controlling operations of a controlled appliance, the controlled appliance and the computing device being part of an environment control system of a building does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element transmitting ... the one or more commands to the controlled appliance of the building via the communication interface to control operations of the controlled appliance amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering").
Step 2B
The additional element storing a predictive model generated by a neural network training engine in a memory of a computing device is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network"). The additional element by the processing unit of the computing device invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element executing ... a neural network inference engine, the neural network inference engine implementing a neural network using the predictive model invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element the neural network comprises several fully connected layers implementing an auto-encoding functionality invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element applying ... a comparison algorithm to the subset of S values of the 2D matrix of ... measurements and a corresponding subset of S values of the 2D matrix of inferred invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element commands for controlling operations of a controlled appliance, the controlled appliance and the computing device being part of an environment control system of a building does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element transmitting ... the one or more commands to the controlled appliance of the building via the communication interface to control operations of the controlled appliance is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Claims 10 and 13-15, dependent on Claim 8, incorporate the rejection of Claim 8. Claims 10 and 13-15 incorporate substantively all the limitations of Claims 3-6, respectively, in method form and are rejected under the same rationales.
Regarding Claim 11
Step 1
Regarding Claim 11, the rejection of Claim 8 is incorporated.
Step 2A Prong 1
The claim recites determining that the subset of S values of the 2D matrix of temperature measurements is anomalous based on a result of the comparison algorithm (as recited in the rejection of Claim 8), wherein the 2D matrix of temperature measurements is received from the IR sensor via a communication interface of the computing device, which is a mental process. Thus, the claim recites an abstract idea.
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 12
Step 1
Regarding Claim 12, the rejection of Claim 8 is incorporated.
Step 2A Prong 1
Claim 12 recites the abstract ideas recited by parent Claim 8.
Step 2A Prong 2
The additional element receiving by a processing unit of the computing device a two-dimensional (2D) matrix of temperature measurements generated by the IR sensor (as recited in the rejection of Claim 8), wherein the computing device includes the IR sensor, and the 2D matrix of temperature measurements is received from an IR sensing component of the IR sensor amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering").
Step 2B
The additional element receiving by a processing unit of the computing device a two-dimensional (2D) matrix of temperature measurements generated by the IR sensor (as recited in the rejection of Claim 8), wherein the computing device consists of the IR sensor, and the 2D matrix of temperature measurements is received from an IR sensing component of the IR sensor is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 24
Step 1
Regarding Claim 24, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
Claim 24 recites the abstract ideas recited by parent Claim 8.
Step 2A Prong 2, Step 2B
The additional element the controlled appliance includes a light or a heating, ventilation, and air-conditioning (HVAC) appliance invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it")
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Claims 25, dependent on Claim 8, incorporates the rejection of Claim 8. Claim 25 incorporates substantively all the limitations of Claim 24 in method form and is rejected under the same rationale.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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 1, 3, 4-6, 8, 10-15, 24, and 25 are rejected under 35 U.S.C. 103 as being unpatentable over Cao, et al., "Smart Sensing for HVAC Control: Collaborative Intelligence in Optical and IR Cameras" (hereinafter "Cao") in view of Luo, et al., "Temporal and spatial deep learning network for infrared thermal defect detection" (hereinafter "Luo") in view of Brahimi, et al., "Deep Interpretable Architecture For Plant Diseases Classification" (hereinafter "Brahimi").
Regarding Claim 1, Cao teaches:
A computing device comprising: a communication interface; memory for storing a predictive model ...; and a processing unit comprising one or more processors (Cao, p. 9786, II. Platform description: "Our prototype sensor comprises ... an IR camera (Flir2.5), an embedded processor for image processing (Raspberry Pi)" and p. 9786, Fig. 2. "(b) Hardware setup," depicting IR camera device connected to the processor by a communication cable) ... a predictive model generated by a neural network training engine (Cao, p. 9787, A. Overview, 3) Classification: "Classification is the final step of detection, which takes extracted feature descriptor as an input, compares it with a trained template, and outputs scores .... Among different classification methods ... a three-layer ANN is selected" and p. 9787, 4) OP/IR Database: "to demonstrate realistic results and avoid sample testing, training data and testing data are populated separately with totally different human foreground and OP/IR backgrounds," which reasonably suggests Cao's classifier ANN is generated by training using training data) ... configured to:
receive via the communication interface a two-dimensional (2D) matrix (Cao, p. 9786, III. Occupancy Detection Via Collaborative Intelligence: "The platform captures OP/IR images simultaneously, aligns them by image registration, fuses the information collected from the registered images, and determines the room’s occupancy/vacancy from the fused data" and p. 9787, A. Overview, 1) Image Alignment: "We apply a rigid translation and the three-dimensional (3-D) translation can, hence, be decomposed into 2-D by ... [Eq. 1] ... where a 2-D point
X
,
Y
in an OP image is transformed to a 2-D point
X
'
,
Y
'
in an IR image") of temperature measurements from an infrared (IR) sensor Cao, p. 9786, III. Occupancy Detection Via Collaborative Intelligence: "an IR camera perceives heat emissions"), the 2D matrix of temperature measurements having M lines and N columns, M and N being integers greater than 1 (Cao, p. 9787, A. Overview, 2) Feature Extraction: "Among all feature extractors, histogram of gradient (HOG) is chosen for its excellent performance [11]–[12]. HOG first divides the input image matrix evenly into M × N cells ... where M and N stand for the number of rows and columns of cells," where Cao's even division into cells reasonably suggests M and N being greater than 1);
execute a neural network inference engine, the neural network inference engine implementing a neural network (Cao, p. 9787, A. Overview: "In the proposed occupancy detection system, data-level fusion refers to integrating aligned OP and IR with different weights into a combined single frame, extracting HOG features from combined data, and classifying the feature with the ANN [artificial neural network] template") using the predictive model for generating outputs based on inputs (Cao, p. 9787, A. Overview, 3) Classification: "Classification is the final step of detection, which takes extracted feature descriptor as an input, compares it with a trained template, and outputs scores indicating the likelihood of a detection (occupied versus unoccupied). Among different classification methods ... a three-layer ANN is selected for its improved performance in classification and linear computation cost"), the inputs comprising the 2D matrix of temperature measurements (Cao, p. 9787, A. Overview, 2) Feature Extraction: "Feature extraction derives informative and nonredundant values to facilitate the subsequent stages to generate better classification results. It is a key stage in performing classification with high accuracy. ... Among all feature extractors, histogram of gradient (HOG) is chosen for its excellent performance [11]–[12]. HOG first divides the input image matrix evenly into M × N cells. ... Then, the spatially connected cells form a block of size (M − 1) × (N − 1) to be locally normalized to account for changes in illumination and contrast where M and N stand for the number of rows and columns of cells") ... ;
select a subset of S values of the 2D matrix of temperature measurements, S being an integer greater than 1 and lower than M * N (Cao, p. 9787, A. Overview, 2) Feature Extraction: "Among all feature extractors, histogram of gradient (HOG) is chosen for its excellent performance [11]–[12]. HOG first divides the input image matrix evenly into M × N cells. ... Then, the spatially connected cells form a block of size (M − 1) × (N − 1) to be locally normalized to account for changes in illumination and contrast where M and N stand for the number of rows and columns of cells");
apply a comparison algorithm to the subset of S values of the 2D matrix of temperature measurements (Cao, p. 9787, A. Overview, 3) Classification: "Classification is the final step of detection, which takes extracted feature descriptor as an input, compares it with a trained template, and outputs scores indicating the likelihood of a detection (occupied versus unoccupied). Among different classification methods ... a three-layer ANN is selected") ... ;
determine (Cao, p. 9787, A. Overview, 3) Classification: "Classification is the final step of detection, which takes extracted feature descriptor as an input, compares it with a trained template, and outputs scores indicating the likelihood of a detection (occupied versus unoccupied). Among different classification methods ... a three-layer ANN is selected for its improved performance in classification and linear computation cost") that the subset of S values of the 2D matrix of temperature measurements from the infrared sensor (Cao, p. 9787, A. Overview, 2) Feature Extraction: "Different feature descriptors are available, including ... HOG. Among all feature extractors, histogram of gradient (HOG) is chosen for its excellent performance [11]–[12]. HOG first divides the input image matrix evenly into M × N cells. ... Then, the spatially connected cells form a block of size (M − 1) × (N − 1) to be locally normalized to account for changes in illumination and contrast where M and N stand for the number of rows and columns of cells" and and 3) Classification: "Classification is the final step of detection, which takes extracted feature descriptor as an input, compares it with a trained template, and outputs scores indicating the likelihood of a detection (occupied versus unoccupied)") is anomalous (Cao, p. 9792, V. System Measurements: "In both summer and winter, occupancy-based HVAC control outperforms schedule-based control in sampling 'unusual' human arrivals, as is shown in the highlighted region where the resident unexpectedly (1) comes back home at noon and stays for a while and (2) arrives home later than usual") ... ;
generate ... one or more commands for controlling operations of a controlled appliance (Cao, p. 9786, II. Platform Description: "The sensed output, including occupancy/vacancy transient or motion vector, is transmitted to the HVAC controller ... using a narrow bandwidth LoRa," where Cao's transient vector reasonably suggests a command for control, as in p. 9792, V. System Measurements: "occupancy-based HVAC control outperforms schedule-based control in sampling 'unusual' human arrivals, as is shown in the highlighted region where the resident unexpectedly (1) comes back home at noon and stays for a while .... In case (1), HVAC is dynamically turned ON to provide comfortable environment" and p. 9790, A. Intelligent LoRa Front End: "the LoRa-based sensor consumes the least amount of battery energy ... for HVAC control") ... based at least on the determination that the subset of S values of the 2D matrix of temperature measurements from the infrared sensor is anomalous (Cao, p. 9792, V. System Measurements: "In both summer and winter, occupancy-based HVAC control outperforms schedule-based control in sampling 'unusual' human arrivals, as is shown in the highlighted region where the resident unexpectedly (1) comes back home at noon and stays for a while and (2) arrives home later than usual") ... the controlled appliance and the computing device being part of an environment control system of a building (Cao, p. 9786, II. Platform Description: "The sensed output, including occupancy/vacancy transient or motion vector, is transmitted to the HVAC controller" and p. 9791, V. System Measurements: "To best evaluate the sensor performance with diverse HVAC systems, two sets of occupancy patterns are randomly generated to simulate an office HVAC environment and a residential HVAC environment"); and
transmit the one or more commands to the controlled appliance of the building via the communication interface to control operations of the controlled appliance (Cao, p. 9786, II. Platform description: "The sensed output, including occupancy/vacancy transient or motion vector, is transmitted to the HVAC controller, often at the basement of an office building, using a narrow bandwidth LoRa").
Cao teaches executing a predictive model for generating a determination that values are anomalous based a 2D matrix of temperature measurements, and generating commands for controlling an environment control system of a building.
Cao does not explicitly teach the outputs comprising a 2D matrix of inferred temperatures, the 2D matrix of inferred temperatures having M lines and N columns, wherein the neural network comprises several ... layers implementing an auto-encoding functionality; apply a comparison algorithm to the subset of S values of the 2D matrix of temperature measurements and a corresponding subset of S values of the 2D matrix of inferred temperatures; determine that the subset of S values of the 2D matrix of temperature measurements from the infrared sensor is anomalous based on a result of the comparison algorithm being applied to the subset of S values of the 2D matrix of temperature measurements and the corresponding subset of S values of the 2D matrix of inferred temperatures.
However, Luo teaches
the outputs comprising a 2D matrix of inferred temperatures (Luo, p. 6, 2.2.1. Thermal spatial characteristic in deep learning structure: "in the decoding process, in order to emphasis the high-resolution features, the feature map of the encoder is connected to the upsampled feature map. ... At the same time, the edge of the defect is more obvious and the influence of the heat diffusion is getting weakened" and p. 4, 2.2.1. Thermal spatial characteristic in deep learning structure: "for the thermal conductivity defect, since the thermal conductivity of the defect is smaller, the reflected wave of the area is reduced and a cold zone is formed on the surface. ... The properties of this hot zone and cold zone can be used in space model to detect defects," where Luo's sharpened hot/cold zones correspond to the instant inferred temperatures, and p. 10, 3.1. Experiment platform and sample preparation: "The platform used to acquire the data is optical pulsed thermography including ... IR camera"), the 2D matrix of inferred temperatures having M lines and N columns (Luo p. 5, Fig. 4. Structure of spatial model, depicting the input dimension 512 x 512 and output dimension of the predicted result with 512 x 512 dimension), wherein the neural network comprises several ... layers implementing an auto-encoding functionality (Luo p. 5, Fig. 4. Structure of spatial model, depicting an encoder-decoder model with multiple layers corresponding to the instant autoencoding neural network);
apply a comparison algorithm to the subset of S values of the 2D matrix of temperature measurements and a corresponding subset of S values of the 2D matrix of inferred temperatures (Luo, p. 5, Fig. 4. Structure of spatial model, depicting decoder processing of input and output features using concatenation, p. 6, 2.2.1. Thermal spatial characteristic in deep learning structure: "An upsampling layer is added after each convolutional layer to increase the resolution of the image in decoder. The convolution operation is performed on the layer to impose a high dimensional feature. As shown in Fig. 4, in the decoding process, in order to emphasis the high-resolution features, the feature map of the encoder is connected to the upsampled feature map. Under the guidance of labels and high-resolution features, the model can learn more accurate shape, size and localization information of defects through multiple iterations. At the same time, the edge of the defect is more obvious and the influence of the heat diffusion is getting weakened");
determine that the subset of S values of the 2D matrix of temperature measurements from the infrared sensor is anomalous based on a result of the comparison algorithm being applied to the subset of S values of the 2D matrix of temperature measurements and the corresponding subset of S values of the 2D matrix of inferred temperatures (Luo, p. 4, 2.2.1. Thermal spatial characteristic in deep learning structure: "for the thermal conductivity defect, since the thermal conductivity of the defect is smaller, the reflected wave of the area is reduced and a cold zone is formed on the surface. ... The properties of this hot zone and cold zone can be used in space model to detect defects," where Luo's defect zone corresponds to the instant anomaly).
The Cao/Luo combination teaches use of an autoencoder to identify defect anomalies based on 2D infrared images.
The Cao/Luo combination does not explicitly teach the neural network comprises several fully connected layers implementing an auto-encoding functionality.
However, Brahimi teaches:
the neural network comprises several fully connected layers implementing an auto-encoding functionality (Brahimi, p. 3, 3.2 Reversed fully connected layers: "Convolutional autoencoders reverse only convolution layers to do reconstruction task. Here, the decoder requires discriminant features from fully connected layers. Therefore, two fully connected layers are used to reverse the Teacher’s fully connected layers").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the the Cao/Luo combination regarding a neural network comprising layers implementing an auto-encoding functionality with those of Brahimi regarding a neural network comprising several fully connected layers implementing an auto-encoding functionality.
The motivation to do so would be to support use of discriminative features by the decoder of the autoencoder (Brahimi, p. 3, 3.2 Reversed fully connected layers: "Convolutional autoencoders reverse only convolution layers to do reconstruction task. Here, the decoder requires discriminant features from fully connected layers. Therefore, two fully connected layers are used to reverse the Teacher’s fully connected layers. Furthermore, a skip connection (red arrow) is used to reinforce the decoder by adding the vector of the Teacher’s first fully connected layer").
Regarding Claim 8, Cao teaches:
A method using a neural network to analyze temperature measurements of an infrared (IR) sensor (Cao, p. 9786, Fig. 2(a), "System architecture of the platform prototype," depicting an infrared camera, Fig. 3, "Demonstration of the algorithm," and Fig. 4(d), "the proposed collaborative, hierarchical, and adaptive template (CHAT) algorithm. Here, FE and CL denote feature extraction and classification, respectively"), the method comprising: precisely those steps recited in the rejection of Claim 1. Claim 8 is rejected under the same rationale as Claim 1.
Regarding Claim 3, the rejection of Claim 1 is incorporated. The Cao/Luo/Brahimi combination teaches:
wherein the IR sensor consists of an IR camera (Cao, p. 9785, Abstract: "This paper presents a novel wireless device platform and prototype development that incorporates an infrared (IR) camera with an optical (OP) camera to provide collaborative intelligence at low power and enhanced accuracy").
Claim 10 incorporates substantively all the limitations of Claim 3 in method form and is rejected under the same rationale.
Regarding Claim 4, the rejection of Claim 1 is incorporated. The Cao/Luo/Brahimi combination teaches:
wherein the 2D matrix of temperature measurements comprises body temperature measurements of a human being, the subset of S values of the 2D matrix of temperature measurements comprises at least some of the body temperature measurements of the human being (Cao, p. 9786, Fig. 3, "Demonstration of the algorithm," depicting human occupancy detection in a region of the captured image, and p. 9787, 4) OP/IR Database: "to demonstrate realistic results and avoid sample testing, training data and testing data are populated separately with totally different human foreground and OP/IR backgrounds" and p. 9792, V. System Measurements: "In both summer and winter, occupancy-based HVAC control outperforms schedule-based control in sampling 'unusual' human arrivals, as is shown in the highlighted region where the resident unexpectedly (1) comes back home at noon and stays for a while and (2) arrives home later than usual"), and the determination that the subset of values of the 2D matrix of temperature measurements is anomalous is indicative of the human being having a body temperature higher than usual (Cao, p. 9785, Fig. 1(c), "Impact of miss/false positive on latency of occupancy detection/energy waste, respectively," depicting the periods of occupancy detection corresponding directly to periods of higher temperature measurements than those usually occurring for the residential or commercial space over the depicted timeframe).
Claim 13 incorporates substantively all the limitations of Claim 4 in method form and is rejected under the same rationale.
Regarding Claim 5, the rejection of Claim 1 is incorporated. The Cao/Luo/Brahimi combination has been shown to teach:
wherein the neural network comprises several fully connected layers implementing an auto-encoding functionality (as recited in the rejection of Claim 1, Brahimi, p. 3, 3.2 Reversed fully connected layers: "Convolutional autoencoders reverse only convolution layers to do reconstruction task. Here, the decoder requires discriminant features from fully connected layers. Therefore, two fully connected layers are used to reverse the Teacher’s fully connected layers").
Claim 14 incorporates substantively all the limitations of Claim 5 in method form and is rejected under the same rationale.
Regarding Claim 6, the rejection of Claim 5 is incorporated. Luo further teaches teaches:
wherein the neural network further comprises at least one two-dimension (2D) convolutional layer ... (Luo, p. 5, Fig. 4, "Structure of spatial model," depicting an input image and a first convolutional layer, and p. 6, 2.2.1. Thermal spatial characteristic in deep learning structure: "For the encoder-decoder model, they can capture several basic information of the tested object, such as background noise, texture, and shape etc., in the first few layers of the encoder. Advanced information will be extracted in the following deep layers. ... The convolution operation is performed on the layer to impose a high dimensional feature"), the first among the at least one 2D convolutional layer applying a 2D convolution to the 2D matrix of temperature measurements (Luo, p. 5, Fig. 4, "Structure of spatial model," depicting an input image and the first network layer being a convolutional layer, and p. 4, 2.2.1. Thermal spatial characteristic in deep learning structure: "The spatial models are all encoder-decoder models. ... In the encoder stage, different features such as noise, defects, and defect edges can be extracted through different kernels") ... optionally one or more pooling layer (Luo does not teach one or more pooling layers).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Cao/Luo/Brahimi combination regarding the neural network comprising several fully connected layers implementing an auto-encoding functionality with the further teachings of Luo regarding wherein the neural network further comprises at least one two-dimension (2D) convolutional layer, optionally one or more pooling layer, the first among the at least one 2D convolutional layer applying a 2D convolution to the 2D matrix of temperature measurements.
The motivation to do so would be to facilitate training a model that captures basic information of the tested object, such as background noise, texture, and shape etc. (Luo, p. 4, 2.2.1. Thermal spatial characteristic in deep learning structure: "The output of the model can be expressed as (7), where
Y
^
is an image predicted by the model, and
W
is the weight of
X
. In the encoder stage, different features such as noise, defects, and defect edges can be extracted through different kernels. In the training process, adjust the weight
W
of different features to make
Y
^
closer to
Y
adaptively through the guidance of the label. ... ¶ For the encoder-decoder model, they can capture several basic information of the tested object, such as background noise, texture, and shape etc., in the first few layers of the encoder").
Claim 15 incorporates substantively all the limitations of Claim 6 in method form and is rejected under the same rationale.
Regarding Claim 11, the rejection of Claim 8 is incorporated. The Cao/Luo/Brahimi combination teaches:
wherein the 2D matrix of temperature measurements is received from the IR sensor via a communication interface of the computing device (Cao, p. 9786, II. Platform description: "Our prototype sensor comprises ... an IR camera (Flir2.5), an embedded processor for image processing (Raspberry Pi)" and p. 9786, Fig. 2. "(b) Hardware setup," depicting IR camera device connected to the processor by a communication cable).
Regarding Claim 12, the rejection of Claim 8 is incorporated. The Cao/Luo/Brahimi combination teaches:
wherein the computing device consists of the IR sensor, and the 2D matrix of temperature measurements is received from an IR sensing component of the IR sensor (Cao, p. 9786, III. Occupancy Detection Via Collaborative Intelligence: "The platform captures OP/IR images simultaneously" and p. 9787, A. Overview, 1) Image Alignment: "We apply a rigid translation ... where a 2-D point
X
,
Y
in an OP image is transformed to a 2-D point
X
'
,
Y
'
in an IR image" and p. 9786, III. Occupancy Detection Via Collaborative Intelligence: "an IR camera perceives heat emissions").
Regarding Claim 24, the rejection of Claim 1 is incorporated. The Cao/Luo/Brahimi combination teaches:
wherein the controlled appliance includes a light or a heating, ventilation, and air-conditioning (HVAC) appliance (Cao, p. 9786, II. Platform Description: "The sensed output, including occupancy/vacancy transient or motion vector, is transmitted to the HVAC controller ... using a narrow bandwidth LoRa," where Cao's transient vector reasonably suggests a command for control, as in p. 9792, V. System Measurements: "occupancy-based HVAC control outperforms schedule-based control in sampling 'unusual' human arrivals, as is shown in the highlighted region where the resident unexpectedly (1) comes back home at noon and stays for a while .... In case (1), HVAC is dynamically turned ON to provide comfortable environment" and p. 9790, A. Intelligent LoRa Front End: "the LoRa-based sensor consumes the least amount of battery energy ... for HVAC control").
Claim 25 incorporates substantively all the limitations of Claim 24 in method form and is rejected under the same rationale.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROBERT N DAY whose telephone number is (703)756-1519. 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, Kakali Chaki can be reached at (571) 272-3719. 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.
/R.N.D./Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122
Prosecution Insights