DETAILED ACTION
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 .
Priority
The pending application 18/223,688, filed on 19 JUL 2023, claims priority from provisional application 63/369,568, filed on 27 JUL 2022.
Response to Amendment
Applicant’s amendment filed on 12 NOV 2025 has been entered. Claims 1, 3, 8, 10 and 14 have been amended. Claims 2, 9 and 15 have been cancelled. Claims 1, 3-8, 10-14, and 16-20 are still pending in this application, with claims 1, 8, and 14 being independent.
Applicant’s amendments to the claims have overcome the objection(s) raised in the previous office action dated 13 AUG 2025.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1, 8 and 14 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 argues that the Crawford reference fails to disclose the limitations of “receiving a digitized radio frequency (RF) signal as a digital input signal including a series of values each including both an in-phase (I) component and a quadrature (Q) component… feeding the digital input signal into a plurality of input notes of a trained Pulse Parameter Estimation Neural Network (PPENN), the PPENN having been trained using machine learning, each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes.” As discussed below, the newly cited Farmer et al. reference is relied upon to teach the amended limitations. Therefore, applicant’s argument is moot.
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.
Claim(s) 1, 7-8, 14 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Crawford (US 10,924,308 B1, previously relied upon by the examiner) in view of Farmer et al. (US 6,366,236 B1, newly cited by the examiner).
Regarding claim 1 (Currently Amended), Crawford discloses:
[Note: what is not explicitly taught by Crawford has been struck-through]
A method of estimating pulse parameters, the method comprising:
receiving a digitized radio frequency (RF) signal as a digital input signal (Crawford via “As illustrated, antennas 302-1 to 302-N receive RF signals from one or more RF emitters, for example, radars.” – Col. 5, lines 27-29); including a series of values each including both an in-phase (I) component and a quadrature (Q) component (Crawford “Since the input signal can be received as a real value or a complex value including a real component (1) and an imaginary component (Q), the output of the CS encoders 306-1 to 306-Y and the summer 308 are in the form of I/Q data.” – Col. 6, lines 24-30);
feeding the digital input signal into a plurality of input nodes (Crawford “Known Neural Networks operate on 2-D arrays, accordingly 4096 I/Q samples are used to populate two 64 by 64 arrays.” – Col. 7, lines 30-33) of a trained Pulse Parameter Estimation Neural Network (PPENN) (Crawford “In some embodiments, machine learning pulse characterizer 600 is a deep learning pulse characterizer that employs a Convolutional Neural Network (CNN) …” – Col. 9, lines 36-39), the PPENN having been trained using machine learning (Crawford “The MLPC 314 characterizes the detected pulse, using the output signal 312 and a trained process to characterize the pulse (described in more detail with respect to FIG. 6)” – Col. 7, lines 10-13), each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes;
operating the trained PPENN to estimate a plurality of pulse parameters of a set of pulses embedded within a waveform of the digital input signal and to output the plurality of pulse parameters from the trained PPENN (Crawford “The output of the classifier 618 is a PDW that include the classical parameters of an RF emitter (e.g., a radar) pulse, including RF carrier, Time of Arrival (ToA), pulse width and modulation type.” – Col. 10, lines 23-26); and
processing the plurality of pulse parameters to further quantify the set of pulses (Crawford “pooling layer 712 then pulls the layers together. An embedded layer 714 is where the PDW parameters are embedded into the model. A soft decision classifier then classifies each separated speaker into a specific radar type, make, model and mode. This information including the emitter ID and model, along with a consolidated time of arrival list of each PDW goes into an Intercept. Intercepts across multiple platforms are compared and those with the same type, make, model and mode are used to calculate a geoposition based upon the time difference of arrival across these multiple platforms.” – Col. 10, line 61 – Col. 11, line 4).
Farmer et al. discloses:
receiving a digitized radio frequency (RF) signal as a digital input signal (Farmer et al. “a time domain signal is input to the neural network 100” – Col. 11, lines 28-29; Fig. 7) including a series of values each including both an in-phase (I) component and a quadrature (Q) component (Farmer et al. “The instant invention overcomes the above-noted problems by providing a system and method of processing a radar signal using a neural network that processes the intermediate frequency in-phase and quadrature phase signals sampled in time from a FMCW radar” – Co. 4, line 66 - Col. 5, line 3);
each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes (Farmer et al. “Responsive to a different sample of the in-phase modulated IF radar signal being fed to one of each pair of input nodes, and to a respective different sample of the quadrature-phase modulated IF radar signal being fed to the other of each pair of input nodes…” – Col. 9, lines 46-50; “The first plurality of nodes 126 comprise first 128 and second 130 subsets of nodes. An input from each of the first subset of nodes 128 is operatively connected to a sample of a first time series 132 of radar data, and each node 108 of the first subset 128 is operatively connected to a different time sample. An input from each of the second subset of nodes 130 is operatively connected to a sample of a second time series 134 of radar data and the second time series 134 is of quadrature phase to the first time series. Each node 108 of the second subset 130 is operatively connected to a different time sample, and the first 128 and second 130 subsets of the first plurality of nodes 126 correspond in time.” – Col. 12, lines 38-50);
It would have been obvious to someone with ordinary skill in the art prior to the effective filing date of the claimed invention to incorporate the features as disclosed by Farmer et al. into the invention of Crawford to yield the invention of claim 1 above. Both Crawford and Farmer et al. are considered analogous arts to the claimed invention as they both disclose the use of neural networks for processing radar signals. Crawford discloses the limitations outlined in claim 1 above. However, Crawford fails to explicitly disclose each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes. This feature is disclosed by Farmer et al. where “Responsive to a different sample of the in-phase modulated IF radar signal being fed to one of each pair of input nodes, and to a respective different sample of the quadrature-phase modulated IF radar signal being fed to the other of each pair of input nodes…” (Farmer et al. Col. 9, lines 46-50). The combination of Crawford and Farmer et al. would be obvious with a reasonable expectation of success to implement a neural network processor chip for reduced cost and improved reliability (Farmer et al. Col. 5, lines 10-11).
Regarding claim 7 (Original), Crawford discloses:
The method of claim 1 wherein operating the trained neural network to output the plurality of pulse parameters from the trained neural network includes outputting (Crawford “The output of the classifier 618 is a PDW that include the classical parameters of an RF emitter (e.g., a radar) pulse, including RF carrier, Time of Arrival (ToA), pulse width and modulation type.” – Col. 10, lines 23-26) at least two of:
pulse detection;
pulse-on-pulse detection;
intrapulse modulation (Crawford Col. 9, line 41);
start time;
stop time;
signal power;
signal-to-noise ratio;
pulse width (Crawford Col. 9, lines 41-42); and
center frequency (Crawford Col. 9, line 41).
Regarding claim 8 (Currently Amended), Crawford discloses:
[Note: what is not explicitly taught by Crawford has been struck-through]
A system (Crawford smart receiver/sensor 300, Fig. 3) comprising:
a radio frequency (RF) antenna (Crawford antennas 302, Fig. 3) configured to receive an RF signal (Crawford via “As illustrated, antennas 302-1 to 302-N receive RF signals from one or more RF emitters, for example, radars.” – Col. 5, lines 27-29);
an analog-to-digital converter (Crawford ADC 414, Fig. 4) configured to digitize the received RF signal to yield a digital input signal, the digital input signal including a series of values each including both an in-phase (I) component and a Quadrature (Q) component (Crawford “Since the input signal can be received as a real value or a complex value including a real component (I) and an imaginary component (Q), the output of the CS encoders 306-1 to 306-Y and the summer 308 are in the form of I/Q data.” – Col. 6, lines 24-30); and
processing circuitry configured to:
feed the digital input signal into a plurality of input nodes (Crawford “Known Neural Networks operate on 2-D arrays, accordingly 4096 I/Q samples are used to populate two 64 by 64 arrays.” – Col. 7, lines 30-33) of a trained Pulse Parameter Estimation Neural Network (PPENN) (Crawford “In some embodiments, machine learning pulse characterizer 600 is a deep learning pulse characterizer that employs a Convolutional Neural Network (CNN) …” – Col. 9, lines 36-39), the PPENN having been trained using machine learning (Crawford “The MLPC 314 characterizes the detected pulse, using the output signal 312 and a trained process to characterize the pulse (described in more detail with respect to FIG. 6)” – Col. 7, lines 10-13), each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes;
operate the trained PPENN to estimate a plurality of pulse parameters of a set of pulses embedded within a waveform (Crawford “The output of the classifier 618 is a PDW that include the classical parameters of an RF emitter (e.g., a radar) pulse, including RF carrier, Time of Arrival (ToA), pulse width and modulation type.” – Col. 10, lines 23-26) of the digital input signal and to output the plurality of pulse parameters from the trained PPENN (Crawford “The output of the classifier 618 is a PDW that include the classical parameters of an RF emitter (e.g., a radar) pulse, including RF carrier, Time of Arrival (ToA), pulse width and modulation type.” – Col. 10, lines 23-26); and
process the plurality of pulse parameters to further quantify the set of pulses (Crawford “pooling layer 712 then pulls the layers together. An embedded layer 714 is where the PDW parameters are embedded into the model. A soft decision classifier then classifies each separated speaker into a specific radar type, make, model and mode. This information including the emitter ID and model, along with a consolidated time of arrival list of each PDW goes into an Intercept. Intercepts across multiple platforms are compared and those with the same type, make, model and mode are used to calculate a geoposition based upon the time difference of arrival across these multiple platforms.” – Col. 10, line 61 – Col. 11, line 4).
Farmer et al. discloses:
the digital input signal including a series of values each including both an in-phase (I) component and a Quadrature (Q) component (Farmer et al. “The instant invention overcomes the above-noted problems by providing a system and method of processing a radar signal using a neural network that processes the intermediate frequency in-phase and quadrature phase signals sampled in time from a FMCW radar” – Co. 4, line 66 - Col. 5, line 3);
each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes (Farmer et al. “Responsive to a different sample of the in-phase modulated IF radar signal being fed to one of each pair of input nodes, and to a respective different sample of the quadrature-phase modulated IF radar signal being fed to the other of each pair of input nodes…” – Col. 9, lines 46-50; “The first plurality of nodes 126 comprise first 128 and second 130 subsets of nodes. An input from each of the first subset of nodes 128 is operatively connected to a sample of a first time series 132 of radar data, and each node 108 of the first subset 128 is operatively connected to a different time sample. An input from each of the second subset of nodes 130 is operatively connected to a sample of a second time series 134 of radar data and the second time series 134 is of quadrature phase to the first time series. Each node 108 of the second subset 130 is operatively connected to a different time sample, and the first 128 and second 130 subsets of the first plurality of nodes 126 correspond in time.” – Col. 12, lines 38-50);
It would have been obvious to someone with ordinary skill in the art prior to the effective filing date of the claimed invention to incorporate the features as disclosed by Farmer et al. into the invention of Crawford to yield the invention of claim 8 above. Both Crawford and Farmer et al. are considered analogous arts to the claimed invention as they both disclose the use of neural networks for processing radar signals. Crawford discloses the limitations outlined in claim 8 above. However, Crawford fails to explicitly disclose each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes. This feature is disclosed by Farmer et al. where “Responsive to a different sample of the in-phase modulated IF radar signal being fed to one of each pair of input nodes, and to a respective different sample of the quadrature-phase modulated IF radar signal being fed to the other of each pair of input nodes…” (Farmer et al. Col. 9, lines 46-50). The combination of Crawford and Farmer et al. would be obvious with a reasonable expectation of success to implement a neural network processor chip for reduced cost and improved reliability (Farmer et al. Col. 5, lines 10-11).
Regarding claim 14 (Currently Amended), Crawford discloses:
[Note: what is not explicitly taught by Crawford has been struck-through]
A computer program product comprising a non-transitory computer-readable storage medium storing a set of instructions (Crawford “One skilled in the art would realize that the machine learning devices shown in FIGS. 6 and 7 may be implemented as electronic circuits, such one or more FPGAs, one or more general-purpose or specific-purpose processors executing firmware and software. In some embodiments, the processors implementing the machine learning devices may be part of the processing hardware of the receiver.” – Col. 11, lines 4-11), which, when performed by a computing device (Crawford smart receiver/sensor 300, Fig. 3), causes the computing device to:
receive a digitized radio frequency (RF) signal as a digital input signal (Crawford via “As illustrated, antennas 302-1 to 302-N receive RF signals from one or more RF emitters, for example, radars.” – Col. 5, lines 27-29), the digital input signal including a series of values each including both an in-phase (I) component and a quadrature (Q) component;
feed the digital input signal into a plurality of input nodes (Crawford “Known Neural Networks operate on 2-D arrays, accordingly 4096 I/Q samples are used to populate two 64 by 64 arrays.” – Col. 7, lines 30-33) of a trained Pulse Parameter Estimation Neural Network (PPENN) (Crawford “In some embodiments, machine learning pulse characterizer 600 is a deep learning pulse characterizer that employs a Convolutional Neural Network (CNN) …” – Col. 9, lines 36-39), the PPENN having been trained using machine learning (Crawford “The MLPC 314 characterizes the detected pulse, using the output signal 312 and a trained process to characterize the pulse (described in more detail with respect to FIG. 6)” – Col. 7, lines 10-13), each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes;
operate the trained PPENN to estimate a plurality of pulse parameters of a set of pulses embedded within a waveform (Crawford “The output of the classifier 618 is a PDW that include the classical parameters of an RF emitter (e.g., a radar) pulse, including RF carrier, Time of Arrival (ToA), pulse width and modulation type.” – Col. 10, lines 23-26) of the digital input signal and to output the plurality of pulse parameters from the trained PPENN (Crawford “The output of the classifier 618 is a PDW that include the classical parameters of an RF emitter (e.g., a radar) pulse, including RF carrier, Time of Arrival (ToA), pulse width and modulation type.” – Col. 10, lines 23-26); and
process the plurality of pulse parameters to further quantify the set of pulses (Crawford “pooling layer 712 then pulls the layers together. An embedded layer 714 is where the PDW parameters are embedded into the model. A soft decision classifier then classifies each separated speaker into a specific radar type, make, model and mode. This information including the emitter ID and model, along with a consolidated time of arrival list of each PDW goes into an Intercept. Intercepts across multiple platforms are compared and those with the same type, make, model and mode are used to calculate a geoposition based upon the time difference of arrival across these multiple platforms.” – Col. 10, line 61 – Col. 11, line 4).
Farmer et al. discloses:
the digital input signal including a series of values each including both an in-phase (I) component and a Quadrature (Q) component (Farmer et al. “The instant invention overcomes the above-noted problems by providing a system and method of processing a radar signal using a neural network that processes the intermediate frequency in-phase and quadrature phase signals sampled in time from a FMCW radar” – Co. 4, line 66 - Col. 5, line 3);
each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes (Farmer et al. “Responsive to a different sample of the in-phase modulated IF radar signal being fed to one of each pair of input nodes, and to a respective different sample of the quadrature-phase modulated IF radar signal being fed to the other of each pair of input nodes…” – Col. 9, lines 46-50; “The first plurality of nodes 126 comprise first 128 and second 130 subsets of nodes. An input from each of the first subset of nodes 128 is operatively connected to a sample of a first time series 132 of radar data, and each node 108 of the first subset 128 is operatively connected to a different time sample. An input from each of the second subset of nodes 130 is operatively connected to a sample of a second time series 134 of radar data and the second time series 134 is of quadrature phase to the first time series. Each node 108 of the second subset 130 is operatively connected to a different time sample, and the first 128 and second 130 subsets of the first plurality of nodes 126 correspond in time.” – Col. 12, lines 38-50);
It would have been obvious to someone with ordinary skill in the art prior to the effective filing date of the claimed invention to incorporate the features as disclosed by Farmer et al. into the invention of Crawford to yield the invention of claim 14 above. Both Crawford and Farmer et al. are considered analogous arts to the claimed invention as they both disclose the use of neural networks for processing radar signals. Crawford discloses the limitations outlined in claim 14 above. However, Crawford fails to explicitly disclose each component of each value of the series of values of the digital input signal provided to different input nodes of the plurality of input nodes. This feature is disclosed by Farmer et al. where “Responsive to a different sample of the in-phase modulated IF radar signal being fed to one of each pair of input nodes, and to a respective different sample of the quadrature-phase modulated IF radar signal being fed to the other of each pair of input nodes…” (Farmer et al. Col. 9, lines 46-50). The combination of Crawford and Farmer et al. would be obvious with a reasonable expectation of success to implement a neural network processor chip for reduced cost and improved reliability (Farmer et al. Col. 5, lines 10-11).
Regarding claim 20 (Original), the same cited section and rationale as corresponding method claim 7 is applied.
Claim(s) 3, 10, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Crawford (US 10,924,308 B1, previously relied upon by the examiner) in view of Farmer et al. (US 6,366,236 B1, newly cited by the examiner) as applied to claim 1 above, and further in view of Driggs et al. (US 2009/0135052 A1, cited by applicant in IDS dated 2 JAN 2024 and previously relied upon by the examiner).
Regarding claim 3 (Currently Amended), Crawford discloses:
[Note: what is not explicitly taught by Crawford has been struck-through]
The method of claim 1 wherein:
the RF signal is a radar signal (Crawford “In some embodiments, the disclosed invention is a smart receiver with compressive sensing and machine learning that identifies and optionally locates radar signals and their characteristics, for example, what type of RF emitters or radars and whether they are friendly radars or “threat” radars.” – Col. 2, lines 41-46);
Driggs et al. discloses:
processing the plurality of pulse parameters to further quantify the set of pulses includes performing pulse deinterleaving (Driggs et al. “To deinterleave an incoming signal, it is necessary to compare one or more parameters associated with incoming signal portions with corresponding parameters stored in memory, for example, characteristics from previous pulses or expected signal characteristics.” - ¶ [0011]).
It would have been obvious to someone with ordinary skill in the art prior to the effective filing date of the claimed invention to incorporate the features as disclosed by Driggs et al. into the invention of Crawford as modified above to yield the invention of claim 3. Crawford, Farmer et al. and Driggs et al. are considered analogous arts to the claimed invention for the following reasons:
Crawford discloses a radar system that uses neural network to determine pulse parameters
Farmer et al. discloses a radar system that uses neural networks comprising a plurality of input node pairs for receiving in-phase and quadrature components of a radar signal
Driggs et al. discloses a radar system that determines radar pulse parameters and performs deinterleaving
Crawford as modified above discloses the invention of claim 1. However, Crawford fails to explicitly disclose processing the plurality of pulse parameters to further quantify the set of pulses includes performing pulse deinterleaving. This feature is disclosed by Driggs et al. where “To deinterleave an incoming signal, it is necessary to compare one or more parameters associated with incoming signal portions with corresponding parameters stored in memory, for example, characteristics from previous pulses or expected signal characteristics.” (Driggs et al. ¶ [0011]). The combination of Crawford, Farmer et al. and Driggs et al. would be obvious with a reasonable expectation of success to implement a neural network processor chip for reduced cost and improved reliability (Farmer et al. Col. 5, lines 10-11) and sort incoming pulses in order to determine the location of a signal source (Driggs et al. ¶ [0002]).
Regarding claim 10 (Currently Amended), the same cited section and rationale as corresponding method claim 3 is applied.
Regarding claim 16 (Currently Amended), the same cited section and rationale as corresponding method claim 3 is applied.
Claim(s) 4, 11, and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Crawford (US 10,924,308 B1, previously relied upon by the examiner) in view of Farmer et al. (US 6,366,236 B1, newly cited by the examiner) as applied to claim 1 above, and further in view of Shima (US 10,879,946 B1, previously relied upon by the examiner) and Paluzzie et al. (“A Comparison of SNR Estimation Techniques for the AWGN Channel,” cited by applicant in IDS dated 2 JAN 2024 and previously relied upon by the examiner).
Regarding claim 4 (Original), Crawford discloses:
[Note: what is not explicitly taught by Crawford has been struck-through]
The method of claim 1 wherein:
operating the trained PPENN to estimate the plurality of pulse parameters does not include performing thresholding (Crawford the CNN does not include thresholding, Col. 7, lines 30-42).
Shima discloses:
a signal-to-noise ratio (SNR) of the RF signal is low (Shima “In accordance with embodiments of the present disclosure, signal processing systems and methods are provided that enable signal detection, de-noising, and extraction of desired signals in noisy environments.” – Col. 2, lines 6-10; the system trained on RF spectrograms with a signal to noise ratio (SNR) of the pulses ranging from −4 to +7 dB” – Col. 7, lines 15-21)
Although Shima does not explicitly disclose a signal-to-noise ratio of the RF signal is less than a predetermined threshold, Shima does disclose that the system and method are designed for detecting signals in noisy environments where the signal-to-noise ratio of the RF signals are considered low.
Pauluzzi et al. discloses:
a signal-to-noise ratio (SNR) of the RF signal is less than a predetermined threshold value (Pauluzzi et al. “THE SEARCH for a good signal-to-noise ratio (SNR) estimation technique is motivated by the fact that various algorithms require knowledge of the SNR (see, for example, [1]–[3]) for optimal performance if the SNR is not constant. The performance of diverse systems may be improved if knowledge of the SNR is available.” - Section I. Introduction, p. 1681)
It would have been obvious to someone with ordinary skill in the art prior to the effective filing date of the claimed invention to incorporate the features as disclosed by Pauluzzi et al. into the invention of Crawford as modified above to yield the invention of claim 4. Crawford, Farmer et al., Shima and Pauluzzi et al. are considered analogous arts to the claimed invention for the following reasons:
Crawford discloses a radar system that uses neural network to determine pulse parameters
Farmer et al. discloses a radar system that uses neural networks comprising a plurality of input node pairs for receiving in-phase and quadrature components of a radar signal
Shima discloses a radar system that uses neural networks that receive in-phase and quadrature components of a radar signal and to determine pulse parameters
Pauluzzi et al. discloses using estimates of the SNR to optimize the performance of a radar system
Crawford as modified above discloses the invention of claim 1. However, Crawford fails to explicitly disclose a signal-to-noise ratio (SNR) of the RF signal is less than a predetermined threshold value. This feature is disclosed by Shima and Pauluzzi et al., where Shima discloses the radar system and algorithm for low signal-to-noise ratio pulses (Shima Col. 2, lines 6-10), and Pauluzzi et al. discloses that “various algorithms require knowledge of the SNR for optimal performance” (Pauluzzi et al. Section I. Introduction, p. 1681). The combination of Crawford, Farmer et al., Shima and Pauluzzi et al. would be obvious with a reasonable expectation of success to implement a neural network processor chip for reduced cost and improved reliability (Farmer et al. Col. 5, lines 10-11), determine the signal processing method based on the SNR threshold in order to “enable the detection of even low energy and low probability of detection, transient signals” (Shima Col. 2, lines 10-13) and optimize the performance of the system and decrease costs (Pauluzzi et al. Section I. Introduction, p. 1681).
Regarding claim 11 (Original), the same cited section and rationale as corresponding method claim 4 is applied.
Regarding claim 17 (Original), the same cited section and rationale as corresponding method claim 4 is applied.
Claim(s) 5-6, 12-13 and 18-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Crawford (US 10,924,308 B1, previously relied upon by the examiner) in view of Farmer et al. (US 6,366,236 B1, newly cited by the examiner) as applied to claim 1 above, and further in view of Shima (US 10,879,946 B1, previously relied upon by the examiner).
Regarding claim 5 (Original), Crawford discloses:
[Note: what is not explicitly taught by Crawford has been struck-through]
The method of claim 1
Shima discloses:
wherein the method further comprises, prior to feeding the digital input signal into the plurality of input nodes of the PPENN (Shima “The output 432 can be applied by receiver components included as part of the system 200, and can be provided to other systems or nodes.” – Col. 6, lines 58-60), performing a preliminary cleansing operation on the digital input signal to remove noise or channel effects (Shima “In accordance with further embodiments of the present disclosure, the de-noising network 600 can provide an output spectrogram 630 in which the de-noised signal or signals 124 have been excised from some or all of the noise that was present in the original spectrogram 614.” – Col. 8, lines 23-28).
It would have been obvious to someone with ordinary skill in the art prior to the effective filing date of the claimed invention to incorporate the features as disclosed by Shima into the invention of Crawford as modified above to yield the invention of claim 5. Both Crawford, Farmer et al. and Shima are considered analogous arts to the claimed invention for the following reasons:
Crawford discloses a radar system that uses neural network to determine pulse parameters
Farmer et al. discloses a radar system that uses neural networks comprising a plurality of input node pairs for receiving in-phase and quadrature components of a radar signal
Shima discloses a radar system that uses neural networks that receive in-phase and quadrature components of a radar signal and to determine pulse parameters
Crawford as modified above discloses the invention of claim 1. However, Crawford fails to explicitly disclose wherein the method further comprises, prior to feeding the digital input signal into the plurality of input nodes of the PPENN, performing a preliminary cleansing operation on the digital input signal to remove noise or channel effects. This feature is disclosed by Shima where the convolutional neural network filters the noise and outputs a de-noised signal that can be provided to others systems (Shima Col. 6, lines 58-60; Col. 8, lines 23-28). The combination of Crawford, Farmer et al. and Shima would be obvious with a reasonable expectation of success to implement a neural network processor chip for reduced cost and improved reliability (Farmer et al. Col. 5, lines 10-11), and “enable the detection of even low energy and low probability of detection, transient signals” (Shima Col. 2, lines 10-13).
Regarding claim 6 (Original), Crawford discloses:
[Note: what is not explicitly taught by Crawford has been struck-through]
The method of claim 5 plurality of input nodes of the trained PPENN (Crawford “Known Neural Networks operate on 2-D arrays, accordingly 4096 I/Q samples are used to populate two 64 by 64 arrays.” – Col. 7, lines 30-33).
Shima discloses:
wherein performing the preliminary cleansing operation includes feeding the digital input signal into another plurality of input nodes of a Filtering Neural Network (FiNN) that was trained to filter noise from the digital input signal (Shima “Still further embodiments of the present disclosure include a neural network that is trained to output a de-noised time series output signal.” – Col. 3, lines 57-59), the FiNN being configured to output into other nodes (Shima “The de-noised time series signal 636 can be provided to a conventional receiver implemented by or included in the signal processing system 300, or to a receiver or other nodes connected to or otherwise in communication with the signal processing system 300.” – Col. 8, lines 8-12).
It would have been obvious to someone with ordinary skill in the art prior to the effective filing date of the claimed invention to incorporate the features as disclosed by Shima into the invention of Crawford as modified above to yield the invention of claim 6. Crawford, Farmer et al. and Shima are considered analogous arts to the claimed invention for the following reasons:
Crawford discloses a radar system that uses neural network to determine pulse parameters
Farmer et al. discloses a radar system that uses neural networks comprising a plurality of input node pairs for receiving in-phase and quadrature components of a radar signal
Shima discloses a radar system that uses neural networks that receive in-phase and quadrature components of a radar signal and to determine pulse parameters
Crawford as modified above discloses the invnetion of claim 5. However, Crawford fails to explicitly disclose wherein the method further comprises, prior to feeding the digital input signal into the plurality of input nodes of the PPENN, performing a preliminary cleansing operation on the digital input signal to remove noise or channel effects. This feature is disclosed by Shima where the convolutional neural network filters the noise and outputs a de-noised signal that can be provided to others systems (Shima Col. 6, lines 58-60; Col. 8, lines 23-28). The combination of Crawford, Farmer et al. and Shima would be obvious with a reasonable expectation of success to implement a neural network processor chip for reduced cost and improved reliability (Farmer et al. Col. 5, lines 10-11), and “enable the detection of even low energy and low probability of detection, transient signals” (Shima Col. 2, lines 10-13).
Regarding claim 12 (Original), the same cited section and rationale as corresponding method claim 5 is applied.
Regarding claim 13 (Original), the same cited section and rationale as corresponding method claim 6 is applied.
Regarding claim 18 (Original), the same cited section and rationale as corresponding method claim 5 is applied.
Regarding claim 19 (Original), the same cited section and rationale as corresponding method claim 6 is applied.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NAOMI M WOLFORD whose telephone number is (571)272-3929. The examiner can normally be reached Monday - Friday, 8:30 am - 4:30 pm EST.
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, Vladimir Magloire can be reached at (571)270-5144. 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.
NAOMI M. WOLFORD
Examiner
Art Unit 3648
/N.M.W./Examiner, Art Unit 3648
14 JAN 2026
/VLADIMIR MAGLOIRE/Supervisory Patent Examiner, Art Unit 3648
Prosecution Insights