DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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 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.
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.
Claims 21-30, 33-42 are rejected under 35 U.S.C. 103 as being unpatentable over Draganov, A., Brown, C., Mattei, E., Dalton, C. and Ranjit, J., 2020. Open Set Recognition through Unsupervised and Class-Distance Learning (Draganov), in view of Xie, C., Zhang, L. and Zhong, Z., 2022. Few-shot unsupervised specific emitter identification based on density peak clustering algorithm and meta-learning. IEEE Sensors Journal, 22(18), pp.18008-18020 (Xie) and in further view of Shen, G., Zhang, J., Marshall, A., Valkama, M. and Cavallaro, J., 2021, October. Radio frequency fingerprint identification for security in low-cost IoT devices. In 2021 55th Asilomar conference on signals, systems, and computers (pp. 309-313). IEEE (Shen) and Shi, Yi, et al. "Deep learning for RF signal classification in unknown and dynamic spectrum environments." 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN). IEEE, 2019 (Shi).
Regarding Claims 21, 33:
A radio frequency (RF) signal processing method, comprising: associating, by one or more processors, vector representations of a plurality of RF signals, received at one or more RF sensors, using content in dimensions of the vector representations of the plurality of RF signals, wherein the vector representations comprise outputs of one or more trained models in response to the one or more trained models receiving RF radiation data including the plurality of RF signals as input (Draganov: .Fig. 2 and 3., a system configuration to classify RF fingerprints through a ML; the system take RF signals as inputs, generate the latent features (i.e., vector representations of a plurality of RF signals) from the network encoder and other feature parameters for closed set classifier (trained through known labels), openness metric learning (3.3) and unsupervised (3.4) that both takes in unlabeled dataset; Xie: III. Fig. 3, illustrate a construct of autoencoder networks; III.D, Algorithm 3, a method of training and classification of received raw RF signals; ).
It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention was made to modify Draganov with autoencoder network as further taught by Xie. The advantage of doing so is to extract and identify radio freq fingerprints of wireless signals to establish a hardware-software dial identification system (Xie: Intro).
Draganov does not teach explicitly on classifying multi-signal interference. However, Shen teaches (Shen: III.E and IV.C).
It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention was made to modify Draganov with classifying multi-signal interference as further taught by Shen. The advantage of doing so is to provide a RFF classification method that can work well in low SNR scenarios (Shen: Abstract).
Draganov does not teach explicitly on a constrain inputted by users. However, Shi teaches Shi: III.C., If the signal is unknown, then users can record it and exchange the newly discovered label with each other).
It would have been obvious for one of ordinary skill in the art before the effective filling date of the claimed invention was made to modify Draganov with a constrain inputted by users as further taught by Shi. The advantage of doing so is a RFFI in unknown and dynamic spectrum environments to improve network security (Shi: Intro).
Regarding Claims 22 and 34, Draganov as modified teaches further teaches:
The RF signal processing method of claim 21, wherein the vector representations are compressed with respect to the RF radiation data (Xie: III. A, The initial feature vector sample is sent to the encoder for compression encoding).
Regarding Claims 23 and 35, Draganov as modified teaches further teaches:
The RF signal processing method of claim 21, wherein associating the vector representations comprises comparing a first vector representation of a first RF signal of the plurality of RF signals with a second vector representation of a second RF signal of the plurality of RF signals (Xie: III.B, Clustering analysis is performed on the basis of the optimum latent vector {Z1−opt, Z2−opt, . . . , ZN−opt} from the training of the autoencoder network, where clustering implies comparing).
Regarding Claims 24 and 36, Draganov as modified teaches further teaches:
The RF signal processing method of claim 21, wherein associating the vector representations comprises grouping a first vector representation of a first RF signal of the plurality of RF signals with a plurality of associated vector representations of a plurality of associated RF signals of the plurality of RF signals (Xie: III.B, Clustering analysis is performed on the basis of the optimum latent vector {Z1−opt, Z2−opt, . . . , ZN−opt} from the training of the autoencoder network).
Regarding Claims 25 and 37, Draganov as modified teaches further teaches:
The RF signal processing method of claim 24, wherein grouping the first vector representation of the first RF signal with the plurality of associated vector representations is based on determining that a vector-based distance between content in dimensions of the first vector representation and is within a predetermined threshold of a vector space associated with a category, and the plurality of associated vector representations are associated with the category (Daganov: 2., the model, UCDL, consolidates statistical and subspace approaches by providing both the feature vector as well as the distances to class centroids to an open set recognition module; 3.4, obtain centroids for each class in this feature space and ensure that our feature vector corresponds to one of these centroids (implies a vector threshold); Xie: III.B-C, clustering and meta-learning, e.g., calculating distance between two latent vectors and etc.).
Regarding Claims 26 and 38, Draganov as modified teaches further teaches:
The RF signal processing method of claim 24, wherein: grouping the first vector representation of the first RF signal with the plurality of associated vector representations is based on determining, using content in dimensions of the first vector representation, that a characteristic of the first RF signal satisfies a constraint; and the constraint is based on user input received via an interface (Shi: III.C., If the signal is unknown, then users can record it and exchange the newly discovered label with each other).
Regarding Claims 27 and 39, Draganov as modified teaches further teaches:
The RF signal processing method of claim 21, wherein associating the vector representations comprises determining whether a vector-based distance between content within dimensions of a first vector representation of a first RF signal of the plurality of RF signals is within a predetermined threshold of content within dimensions of a second vector representation of a second RF signal of the plurality of RF signals (Daganov: 2., the model, UCDL, consolidates statistical and subspace approaches by providing both the feature vector as well as the distances to class centroids to an open set recognition module; 3.4, obtain centroids for each class in this feature space and ensure that our feature vector corresponds to one of these centroids (implies a vector threshold)).
Regarding Claims 28 and 40, Draganov as modified teaches further teaches:
The RF signal processing method of claim 21, wherein associating the vector representations comprises inputting a first vector representation of a first RF signal of the plurality of RF signals into a trained decoder model and, based on an output from the trained decoder model, determining that a characteristic of the first RF signal satisfies a constraint also satisfied by a second vector representation of a second RF signal of the plurality of RF signals (Xie: Abstract and III: the original radio-frequency (RF) signal is preprocessed based on the Hilbert–Huang transform (HHT) to obtain the Hilbert time–frequency spectrum, which can highlight RF fingerprints (RFFs) that can be used as signal training samples. Then, the Hilbert time–frequency spectrum is input to an improved autoencoder network for training to obtain the latent vector that can represent hidden features of the received signal. Next, the clustering by fast search and find of a density peaks [i.e., density peak clustering (DPC)] algorithm is used to cluster and label the latent vector, which is later reconstructed by the improved autoencoder network to obtain training samples with labeled information. Finally, the meta-learning algorithm is used to train the few-shot SEI network under the few-shot condition, so that it can distinguish different types of RF signals, corresponding to specific emitters).
Regarding Claims 29 and 41, Draganov as modified teaches further teaches:
The RF signal processing method of claim 28, wherein the characteristic is selected from the group consisting of: modulation type of the first RF signal; pulse rate of the first RF signal; signal-to-noise ratio (SNR) of the first RF signal; type and/or location of an RF source that transmitted the first RF signal; confidence metric of the first RF signal being analog and/or digital; confidence metric of the first RF signal matching another RF signal; confidence metric of the first RF signal being amplitude modulated (AM); confidence metric of the first RF signal being frequency modulated (FM); confidence metric of the first RF signal being a chirp; confidence metric of the first RF signal being frequency-shift keyed (FSK); confidence metric of the first RF signal being amplitude-shift keyed (ASK); confidence metric of the first RF signal being phase-shift keyed (PSK); confidence metric of the first RF signal being a chirp spread spectrum (CSS); and confidence metric of the first RF signal being constellation modulated (Xie: IV., e.g., Fig. 5 with SNR, IV.D., various modulation schemes).
Regarding Claims 30 and 42, Draganov as modified teaches further teaches:
The RF signal processing method of claim 21, wherein at least some of the vector representations are stored in a database and the RF signal processing method further comprises, by the one or more processors, loading the at least some of the vector representations from the database for associating (Shen: III.E and IV.C).
Allowable Subject Matter
The Claims 31-32 and 43-44 are objected to as being dependent upon a rejected base claim, but are potentially allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZHITONG CHEN whose telephone number is (571) 270-1936. The examiner can normally be reached on M-F 9:30am - 5pm.
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, Yuwen Pan can be reached on 571-272-7855. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ZHITONG CHEN/
Primary Examiner, Art Unit 2649
Prosecution Insights