NON-FINAL REJECTION, FIRST DETAILED ACTION
Status of Prosecution
The present application 18/299,679, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
The application was filed in the Office on April 12, 2023 and claims priority to provisional application 63/438,227 filed on Jan. 10, 2023.
Claims 1-22 are pending and are all objected to or rejected in this rejection. Claims 1, 15 and 21 are independent claims.
Status of Claims
Claims 1, 8-17 and 19-22 are rejected under 35 U.S.C. § 103 as being unpatentable over non-patent literature, Rajendran et al., (“Rajendran”) “Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors,” published in 2018 in view of Lin et al. (“Lin”), “Multi-Signal Detection Framework: A Deep Learning Based Carrier Frequency and Bandwidth Estimation” published March 2022.
Claim 2 is rejected under 35 U.S.C. § 103 as being unpatentable over Rajendran in view of Lin in further view of Ye et al. (“Ye”), “Acoustic Scene Classification Using Efficient Summary Statistics and Multiple Spectro-Temporal Descriptor Fusion,” published in February 2018.
Claims 6, 7 and 18 are rejected under 35 U.S.C. § 103 as being unpatentable over Rajendran in view of Lin and in further view of Tran et al., (“Tran”), United States Patent Application Publication 2021/0280239, published Sep. 9, 2021.
Allowable Subject Matter
Claims 3-5 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
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 of this title, 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.
A.
Claims 1, 8-17 and 19-22 are rejected under 35 U.S.C. § 103 as being unpatentable over non-patent literature, Rajendran et al., (“Rajendran”) “Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors,” published in 2018 in view of Lin et al. (“Lin”), “Multi-Signal Detection Framework: A Deep Learning Based Carrier Frequency and Bandwidth Estimation” published March 2022.
As to Claim 1: Rajendran teaches: An event-based signal detection and classification system comprising:
a signal converter operable with an input, and operable to receive and convert one or more input signals; at least one processor (Rajendran: Sec. II, “A general representation for the received signal is given by eq. 1,” received signal r(t), IQ/amplitude-phase representation);
at least one processor; memory including instructions that, when executed by the at least one processor (Rajendran: Sec. IV-E, “Deep learning models are processor intensive”), cause the system to:
receive, via the input, an input signal of the one or more input signals (Rajendran: Sec. II);
convert the input signal to input data (Rajendran: Sec. II);
input the input data to an event-based detection and classification component (Rajendran: Sec. IV-B, LSTM/CNN models);
transform, periodically, the input data from the temporal domain into transformed input data in the frequency domain in a plurality of frequency domain bins (Rajendran: Sec. VI-A, FFT magnitude spectrum bins, Fig. 2);
output the event data for further processing to produce analysis output data (Rajendran: Sec. I, VI, Fig. 2).
PNG
media_image1.png
530
373
media_image1.png
Greyscale
Rajendran may not explicitly teach: monitor each of the frequency domain bins for magnitude changes that meet or exceed a predetermined threshold value;
detect an event when a magnitude change meeting or exceeding a predetermined threshold value is monitored;
generate event data for the event, wherein the event data corresponds to a point in time at which a magnitude change that meets or exceeds the predetermined threshold value is detected in one of the frequency domain bins.
Lin teaches in general concepts related to a deep learning-based framework withch takes the power spectrum as the network’s input to localize spectral locations of the signals (Lin: Abstract). Specifically, Lin teaches input signals are transformed into a power spectrum which have frequency domain bins (Lin: Sec. 3.1, Welch’s power spectrum, equations 4-9). Detecting the exceeding a threshold value is well known and has been used in various ways for detecting an event (Lin: Sec. 1.1, discussion of threshold-based detection algorithms, applying equations 20-22). Once the threshold is detected, appropriate processing and event data is generation corresponding to the time (Lin: segmented time processing via Welch method, Sec. 3.1).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Rajendran disclosures and teachings of temporal processing by monitoring threshold detections for the event trigger tracking as taught by Lin. Such a person would have been motivated to do so with a reasonable expectation of success to allow for the capturing of relevant temporal spectral data with certain events of interest with reduced burden to the interested users.
As to Claim 8, Rajendran and Lin teach the limitations of claim 1.
Lin further teaches: wherein the memory device further includes instructions that, when executed by the at least one processor, cause the system to designate one or more initial processing parameters including at least one of:
a band selection defining one or more frequency bands of the input signal to analyze (Lin: Sec. 5.1, frequency resolution and FFT parameters);
a temporal resolution defining a predetermined time interval for sampling the input data;
an analysis interval defining a rate at which the input data is processed by the event-based detection and classification component; and
the predetermined threshold value defining the magnitude change value for detecting the event.
As to Claim 9, Rajendran and Lin teach the limitations of Claim 1.
Lin further teaches: alter the one or more initial processing parameters based on at least one of the analysis output data (Lin: 4.2 the parameters settings are adjusted per the training process) and the salient data parameter tuning.
As to Claim 10, Rajendran and Lin teach the limitations of claim 1.
Lin further teaches: wherein monitoring each of the frequency domain bins for magnitude changes that meet or exceed the predetermined threshold value comprises:
detecting a first magnitude in a first frequency domain bin; and
monitoring magnitudes in the first frequency domain bin subsequent to the first frequency domain bin for a second magnitude representing a magnitude change that meets or exceeds the predetermined threshold value compared to the first magnitude (Lin: Sec. 3.1, segmented periodograms segmented time processing and comparison of spectral magnitudes across segments).
As to Claim 11, Rajendran and Lin teach the limitations of claim 10.
Lin further teaches: wherein the memory device further includes instructions that, when executed by the at least one processor, cause the system to:
monitor magnitudes in the first frequency domain bin subsequent to the second magnitude for a third magnitude representing a magnitude change that meets or exceeds the predetermined threshold value compared to the second magnitude (Lin: Sec. 3.1, teaches continuous processing across segments and detection over multiple intervals).
As to Claim 12, Rajendran and Lin teach the limitations of claim 1.
Rajendran and Lin further teach: wherein the memory device further includes instructions that, when executed by the at least one processor, cause the system to:
output the event data to a saliency-classifier Convolutional Neural Network (CNN) to classify the event data as salient data or non-salient data; and
output the salient data for processing by a downstream processor to produce the analysis output data. (Rajendran: Sec. IV, CNN-based classification; Lin: Sec 3.3, encoder-decoder CNN for signal detection).
As to Claim 13, Rajendran and Lin teach the limitations of claim 1.
Lin further teaches: wherein the memory device further includes instructions that, when executed by the at least one processor, cause the system to:
monitor each of the frequency domain bins for magnitude changes in the transformed input data relative to an initial magnitude value that are below the predetermined threshold value; and
update the initial magnitude value to an updated magnitude value that tracks magnitude changes in the transformed input data below the predetermined threshold value;
monitor each of the frequency domain bins for magnitude changes in the transformed input data relative to the updated magnitude value that meet or exceed the predetermined threshold value;
detect an event when a magnitude change meeting or exceeding the predetermined threshold value is monitored;
generate event data for the event, wherein the event data corresponds to a point in time at which a magnitude change that meets or exceeds the predetermined threshold value is detected in one of the frequency domain bins; and
output the event data for further processing to produce analysis output data (Examiner asserts that these steps are similar to the parent claim’s steps, but are triggered when it is less than a magnitude threshold rather than more. As the exceeding or below feature would be a design choice, it is similarly taught and disclosed).
As to Claim 14, Rajendran and Lin teach the limitations of claim 1.
Lin further teaches: wherein the frequency domain bins comprise at least one of wavelet transform bins, Fourier transform bins, discrete Fourier transform bins, or a non-uniform discrete Fourier transform bins (Lin: teaches PSD estimation techniques including Welch method (FFT-based) (Sec. 3.1)).
As to Claim 15, it is rejected for similar reason as a claim 1.
As to Claim 16, it is rejected for similar reason as a claim 12.
As to Claim 17, it is rejected for similar reason as a claim 8.
As to Claim 19, it is rejected for similar reason as a claim 10.
As to Claim 20, it is rejected for similar reason as a claim 11.
As to Claim 21, it is rejected for similar reason as a claim 1.
As to Claim 22, it is rejected for similar reason as a claim 12.
B.
Claim 2 is rejected under 35 U.S.C. § 103 as being unpatentable over non-patent literature, Rajendran et al., (“Rajendran”) “Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors,” published in 2018 in view of Lin et al. (“Lin”), “Multi-Signal Detection Framework: A Deep Learning Based Carrier Frequency and Bandwidth Estimation” published March 2022 and further in further view of Ye et al. (“Ye”), “Acoustic Scene Classification Using Efficient Summary Statistics and Multiple Spectro-Temporal Descriptor Fusion,” published in February 2018.
As to Claim 2, Rajendran and Lin teach the limitations of claim 1.
Rajendran and Lin may not explicitly teach: wherein event data for each event is stored in an event plane comprising:
one or more rows each representing a point in time at which the event corresponding to the event data occurred; and
one or more columns each representing a frequency domain bin of the plurality of frequency domain bins.
Ye teaches in general concepts related to acoustic scene classification using acoustic feature extraction using spectro-temporal descriptors fusion (Ye: Abstract). Specifically, Ye teaches that a time-frequency plane is used as a local structure to characterize the acoustic information (Yeh: Sec. 3.2.1., the equation S(r ) denotes time frequency representation(TFR)).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Rajendran-Lin disclosures and teachings by representing the event data in the TFR with the rows and columns of a matrix as taught by Yeh. Such a person would have been motivated to do so with a reasonable expectation of success to allow for an efficient capture of the acoustic information (Ye: Abstract).
C.
Claims 6, 7 and 18 are rejected under 35 U.S.C. § 103 as being unpatentable over non-patent literature, Rajendran et al., (“Rajendran”) “Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors,” published in 2018 in view of Lin et al. (“Lin”), “Multi-Signal Detection Framework: A Deep Learning Based Carrier Frequency and Bandwidth Estimation” published March 2022 and in further view of Tran et al., (“Tran”), United States Patent Application Publication 2021/0280239, published Sep. 9, 2021.
As to Claim 6, Rajendran and Lin teach the limitations of Claim 1.
Rajendran and Lin may not explicitly teach: wherein event data is stored in separate channels of the event plane based on differences in one or more characteristics of the event data, the separate channels comprising:
a first channel that stores event data representing positive magnitude changes; and
a second channel that stores event data representing negative magnitude changes.
Tran teaches in general concepts related to analog neural memory arrays with appropriate weight mapping adaptively performed for optimal performance in power and noise (Tran: Abstract). Specifically, Tran teaches that memory cell arrays may be arranged in a manner to allow for matrix multiplication to take place (Tran: par. 0006, VMM arrays). For efficiency and optimization purposes, the weights for the network may be separated by signs (Tran: par. 0140, the positive weights are implemented a first array [2111] and the negative weights in a second array [2112]).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Rajendran-Lin disclosures and teachings by implementing separate channels based on the parity of the magnitudes as taught by Tran. Such a person would have been motivated to do so with a reasonable expectation of success to perform optimized arithmetic operations.
As to Claim 7, Rajendran and Lin teach the limitations of claim 1.
Rajendran and Lin may not explicitly teach: wherein event data is stored in separate channels of the event plane based on differences in one or more characteristics of the event data, the separate channels comprising two or more of:
a first channel that stores event data representing positive sine magnitude changes;
a second channel that stores event data representing negative sine magnitude changes;
a third channel that stores event data representing positive cosine magnitude changes;
a fourth channel that stores event data representing negative cosine magnitude changes.
Tran teaches in general concepts related to analog neural memory arrays with appropriate weight mapping adaptively performed for optimal performance in power and noise (Tran: Abstract). Specifically, Tran teaches that memory cell arrays may be arranged in a manner to allow for matrix multiplication to take place (Tran: par. 0006, VMM arrays). For efficiency and optimization purposes, the weights for the network may be separated by signs (Tran: par. 0140, the positive weights are implemented a first array [2111] and the negative weights in a second array [2112]).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Rajendran-Lin disclosures and teachings by implementing separate channels based on the parity of the magnitudes as well as the type of sinusoidal curves as taught and suggested by Tran. Such a person would have been motivated to do so with a reasonable expectation of success to perform optimized arithmetic operations and to better increase access and lookup by magnitude change types.
As to Claim 18, it is rejected for similar reason as a claim 6.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAMES T TSAI whose telephone number is (571)270-3916. The examiner can normally be reached M-F 8-5 Eastern.
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, Viker Lamardo can be reached on 571-270-5871. 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./JAMES T TSAI/ /JAMES T TSAI/Primary Examiner, Art Unit 2147
Prosecution Insights