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 .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 04/16/2025 is in compliance with the provisions of 37 C.F. R 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Drawings
The drawings were received on 04/16/2025. These drawings are acceptable.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-4, 6-7, 9-13, 15 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Dong et al., (NPL titled: "Deep CNN-Based Channel Estimation for mmWave Massive MIMO Systems," in IEEE Journal of Selected Topics in Signal Processing, vol. 13, no. 5, pp. 989-1000, Sept. 2019) in view of Cheong et al. (US 20220159543 A1).
Regarding Claim 1, Dong et al. discloses;
A method for channel estimation for a wireless channel (Abstract, Section VI. CONCLUSION: method for deep CNN based channel estimation for H(τ); “deep CNN based channel estimation approaches”), comprising:
obtaining an initial channel estimation based on a wireless signal received over the wireless channel (Fig. 1, Section I, II., III, IV: obtaining by “Tentative Estimation”/initial/coarse channel estimation based on a wireless signal, Yk, received over the wireless channel H(τ). See Equations (7) , (17) and (24) used for initial/coarse channel estimation);
processing the initial channel estimation by a classifier neural network to obtain a class of the wireless channel;
selecting a refinement neural network from a plurality of refinement neural networks (Fig. 1, 2, 4, Abstract: selecting one of “a spatial-frequency CNN (SF-CNN),” “a spatial frequency- temporal CNN(SFT-CNN)” or “a spatial pilot-reduced CNN (SPR-CNN)”) based on …[a] class of the wireless channel (Fig. 1, 2, 4, Abstract, Section I., II., III., IV: selecting one of three different neural network options (see each equation (10), (18) or “Algorithm 1”) for refining the initial/coarse channel estimation, where each option depends on different wireless channel environment/type/class/condition, e.g. “spatial and frequency correlation [with] the corrupted channel, ” “temporal correlation in time-varying channels” and channel with “huge spatial pilot overhead”).
obtaining a refined channel estimation based on processing the initial channel estimation by the selected refinement neural network (Fig. 1, 2, 4: Section. I, II., III, IV: obtaining refined “tentatively estimated channel” using one of a selected refinement neural network, SF-CNN, SFT-CNN, or SPR-CNN - equations (10), (18) or “Algorithm 1, ” respectively).
Dong et al. does not teach:
“processing the initial channel estimation by a classifier neural network to obtain a class of the wireless channel;”
On the other hand, in the same field of endeavor (Abstract: “a communication system using different wireless communication protocols”) Cheong et al. teaches:
“processing the initial channel estimation by a classifier neural networkto obtain a class of the wireless channel (Fig. 3, Para. [0051]: “Wireless channel selection engine 302 may create a classifier using a machine learning algorithm such as, for example, linear classifier, quadratic classifier, naive Bayes classifier, random forest, neural network, or the like. The machine learning algorithm may include a trained classifier that analyzes the data and identifies a predefined operational context of IHS 102 that is closest (e.g., most similar) to the type that may be provided by any one available wireless channel. Wireless channel selection engine 302 may then select that wireless channel that most closely matches the operational context that IHS 102 is currently experiencing”);”
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention that the “Tentative Estimation”/initial/coarse channel estimation and the selection of one of a refinement neural network, SF-CNN, SFT-CNN, or SPR-CNN - equations (10), (18) or “Algorithm 1, ” respectively Dong et al.’s invention can further be processed and obtained by a classifier machine learning algorithm/classifier neural network as taught by Cheong et al., where doing so would (Cheong et al., Para. [0004], [0052]) allow “how quickly and efficiently the information may be processed, stored, or communicated” such as “to select one or several wireless channels from among multiple wireless channels 106.” That is, the channel selection engine 302 of Cheong et al. can be implemented in Dong et al.’s invention (e.g. between “Tenetative Estimation” unit/module and a set of “deep convolutional neural network (CNN)” include SF-CNN, SFT-CNN, or SPR-CNN) to further classify as to which of the three wireless channel environment/type/class/condition (see Abstract, Section VI. CONCLUSION) the tentative estimated signals, Rk, corresponding to and direct the classified tentative estimated signals, Rk to corresponding “refinement neural network, SF-CNN, SFT-CNN, or SPR-CNN.”
Regarding Claim 10, Dong et al. discloses;
An apparatus for channel estimation for a wireless channel (Fig. 1: Receiver - RX), configured to:
obtain an initial channel estimation based on a wireless signal received over the wireless channel (Fig. 1, Section I, II., III, IV: obtaining by “Tentative Estimation”/initial/coarse channel estimation based on a wireless signal, Yk, received over the wireless channel H(τ). See Equations (7) , (17) and (24) used for initial/coarse channel estimation);
process the initial channel estimation by a classifier neural network to obtain a class of the wireless channel;
select a refinement neural network from a plurality of refinement neural networks(Fig. 1, 2, 4, Abstract: selecting one of “a spatial-frequency CNN (SF-CNN),” “a spatial frequency- temporal CNN(SFT-CNN)” or “a spatial pilot-reduced CNN (SPR-CNN)”) based on …[a] class of the wireless channel (Fig. 1, 2, 4, Abstract, Section I., II., III., IV: selecting one of three different neural network options (see each equation (10), (18) or “Algorithm 1”) for refining the initial/coarse channel estimation, where each option depends on different wireless channel environment/type/class/condition, e.g. “spatial and frequency correlation [with] the corrupted channel, ” “temporal correlation in time-varying channels” and channel with “huge spatial pilot overhead”)
obtain a refined channel estimation based on processing the initial channel estimation by the selected refinement neural network (Fig. 1, 2, 4: Section. I, II., III, IV: obtaining refined “tentatively estimated channel” using one of a selected refinement neural network, SF-CNN, SFT-CNN, or SPR-CNN - equations (10), (18) or “Algorithm 1, ” respectively).
Dong et al. does not teach the apparatus comprising:
“processing circuitry” and
“process the initial channel estimation by a classifier neural network to obtain a class of the wireless channel:
On the other hand, in the same field of endeavor (Abstract: “a communication system using different wireless communication protocols”) Cheong et al. teaches an apparatus (Fig. 2: information handling system (IHS)) comprising:
“processing circuitry (Fig. 2: at least chip set 203)” and
“process the initial channel estimation by a classifier neural network to obtain a class of the wireless channel (Fig. 3, Para. [0051]: “Wireless channel selection engine 302 may create a classifier using a machine learning algorithm such as, for example, linear classifier, quadratic classifier, naive Bayes classifier, random forest, neural network, or the like. The machine learning algorithm may include a trained classifier that analyzes the data and identifies a predefined operational context of IHS 102 that is closest (e.g., most similar) to the type that may be provided by any one available wireless channel. Wireless channel selection engine 302 may then select that wireless channel that most closely matches the operational context that IHS 102 is currently experiencing”);”
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention that the receiver, Rx, the “Tentative Estimation”/initial/coarse channel estimation and the selection of one of a refinement neural network, SF-CNN, SFT-CNN, or SPR-CNN - equations (10), (18) or “Algorithm 1, ” respectively Dong et al.’s invention can include least chip set 203 for implementing Wireless channel selection engine 302 to obtain a classifier machine learning algorithm/classifier neural network as taught by Cheong et al., where doing so would (Cheong et al., Para. [0004], [0052]) allow “how quickly and efficiently the information may be processed, stored, or communicated” such as “to select one or several wireless channels from among multiple wireless channels 106.” That is, the channel selection engine 302 implemented by the chip set 203 of Cheong et al. can be implemented in Dong et al.’s invention (e.g. between “Tentative Estimation” unit/module and a set of “deep convolutional neural network (CNN)” include SF-CNN, SFT-CNN, or SPR-CNN) to further classify as to which of the three wireless channel environment/type/class/condition (see Abstract, Section VI. CONCLUSION) the tentative estimated signals, Rk, corresponding to and direct the classified tentative estimated signals, Rk to corresponding “refinement neural network, SF-CNN, SFT-CNN, or SPR-CNN.”
Regarding Claim 2 and 11, Dong et al. in view of Cheong et al. discloses all as applied to claim 1and 10 above, where Dong et al. further teaches;
wherein the obtaining of the initial channel estimation
processing a received pilot symbol obtained from the wireless signal (Fig. 1, 2, 4, Section II. SYSTEM MODEL: frequency domain wireless channel, Hk (Equation (4)) includes received pilot symbol Yk ( Equation (5) where “Pilots are utilized to estimate the channels of corresponding time-frequency positions”) and a reference pilot symbol to obtain the initial channel estimation (Fig. 1, Section III: SF-CNN-BASED CHANNEL ESTIMATION, Part A. Algorithm Description” “Yk [Fig. 1 -reference pilot symbol – Yk0, Yk0 + 1] goes through the tentative estimation (TE) module, which uses two matrices, GL and GR, to process Yk and outputs a coarse estimation…(Equation (7))”).
Regarding Claim 3 and 12, Dong et al. in view of Cheong et al. discloses all as applied to claim 1 and 10 above, where Dong et al. further teaches;
each refinement neural network respective channel model of a plurality of channel models of the channel (Fig. 1, 2, 4, Abstract, Section I., II., III., IV: each of three different refinement neural network, SF-CNN, SFT-CNN, or SPR-CNN, correspond to a respective channel model (see each equation (10), (18) or “Algorithm 1”) of wireless channel, Hk).
Regarding Claim 4 and 13, Dong et al. in view of Cheong et al. discloses all as applied to claim 3 and 12 above, where Dong et al. further teaches;
at least one channel model of the plurality of channel models is based on one or more of:
- an environment of the wireless network (Fig. 1, 2, 4, Abstract, Section I., II., III., IV: selecting one of three different neural network options (see each equation (10), (18) or “Algorithm 1”) for refining the initial/coarse channel estimation, where each option depends on different wireless channel environment/type/class/condition, e.g. “spatial and frequency correlation [with] the corrupted channel, ” “temporal correlation in time-varying channels” and channel with “huge spatial pilot overhead”)),
- a delay spread (See Equation (1) - based on “delay domain[spread]”), and/or
- non-line-of-sight (NLOS) conditions (Section V. NUMERICAL RESULTS, Para. A SF-CNN-Based Channel Estimation: “the proposed SF-CNN based channel estimation and MMSE channel estimation over two adjacent subcarriers in the urban micro (UMi) street non-line of sight (NLOS) scenario”) or line-of-sight (LOS) conditions”).
Regarding Claim 6 and 15, Dong et al. in view of Cheong et al. discloses all as applied to claim 1 and 10 above, where Cheong et al. further teaches;
wherein the wireless channel is one of: - an IEEE 802.11 based wireless channel (Para. [0064]: “transceivers may include Wi-Fi narrow beam” that is the wireless channel can be one of Wi-Fi/ IEEE 802.11 based wireless channel), or- a 5G New Radio (NR) based wireless channel (Para. [0064]: “cellular communications (3G, 4G, 5G, etc.), ” that is the wireless channel can be 5G based wireless channel).
Regarding Claim 7 and 16, Dong et al. in view of Cheong et al. discloses all as applied to claim 3 and 12 above, where Dong et al. further teaches;
wherein at least one refinement neural network from the plurality of refinement neural networks is trained to refine the channel estimation according to the respective channel model (Fig. 1, 2, 4, Abstract, Section II, III, IV:. “For the proposed SF-CNN, the training set consisting of Ntr samples is generated according to certain channel model in the simulation environment…”; “offline training of the SFT-CNN”; “training process of the SPRCNNs” where the train is based on the corresponding wireless channel environment/type/class/condition, e.g. “spatial and frequency correlation [with] the corrupted channel, ” “temporal correlation in time-varying channels” and channel with “huge spatial pilot overhead”).
Regarding Claim 9, Dong et al. in view of Cheong et al. discloses all as applied to claim 1 above, where Cheong et al. further teaches;
At least one non-transitory, computer-readable medium (Fig. 2: 205), comprising instructions that, when executed by at least one processor, cause the at least one processor to perform the method according to claim 1(Fig. 2, Para. [0024]: “memory 205 that is coupled to processor 201 provides processor 201 with a high-speed memory that may be used in the execution of computer program instructions by processor 201” to implement the method as taught by Dong et al.) .
Claims 5 8, 14 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Dong et al., (NPL titled: "Deep CNN-Based Channel Estimation for mmWave Massive MIMO Systems," in IEEE Journal of Selected Topics in Signal Processing, vol. 13, no. 5, pp. 989-1000, Sept. 2019) in view of Cheong et al. (US 20220159543 A1) further in view of ABDALLAH et al. (US 20230300006 A1).
Regarding Claim 5 and 14, Dong et al. in view of Cheong et al. discloses all as applied to claim 1 and 10 above, however they do not teach;
obtaining a compensated signal based on the refined channel estimation and the received wireless signal.
On the other hand, in the same field of endeavor (Abstract: “machine learning based method for channel estimation for a multiple-input multiple-output, MIMO, system”), ABDALLAH et al. teaches;
obtaining a compensated signal (Fig. 7C, Para. [0062]: step 710 - reconstructing 710 the channels [compensated signal]…) based on the refined channel estimation (Fig. 7C, Para. [0062]: step 706-708 - “reconstructing 710 the channels according to the selected dominant entries, corresponding to the supports [refined channel estimation]”’) and the received wireless signal (Fig. 7C, Para. [0062]: step 700- the received wireless pilot signals y[k]).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention that the receiver, Rx, receiving received signal Yk, and obtaining refined channel estimation ˆHk0 and ˆHk0+1, in Dong et al. in view of Cheong et al.’s invention can be used to obtain a compensated/reconstructed signal/channel as taught by ABDALLAH et al., where doing so would (ABDALLAH et al., Para. [0005], [0041]) for “a low complexity channel estimation for mmWave MIMO systems” and reconstruction of the “transmitted signal x[k]” in order to recover “data symbols s[k].”
Regarding Claim 8 and 17, Dong et al. in view of Cheong et al. discloses all as applied to claim 1 and 10 above, however they do not teach;
wherein at least one refinement neural network from the plurality of refinement neural networks and/or the classifier neural network is a feed forward neural network.
On the other hand, in the same field of endeavor (Abstract: “machine learning based method for channel estimation for a multiple-input multiple-output, MIMO, system”), ABDALLAH et al. teaches;
wherein at least one refinement neural network from the plurality of refinement neural networks and/or the classifier neural network is a feed forward neural network (Para. [0056], [0071]: “The former simultaneously estimate the supports using an offline-trained DnCNN (note that other machine learning systems may be used instead of the DnCNN, for example, a convolutional neural network, CNN, or any neural network, NN, system; also the system may not be a denoise convolutional system”; “The algorithm considers the received pilot signal as an image, and then employs a denoising convolutional neural network 400 (see, for example, [20]) for channel amplitude estimation. Thereby, the pilot signal/image denoising is treated as a discriminative learning problem, i.e., separating the noise from a noisy image by feed-forward convolutional neural networks (CNNs)”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention that the refinement neural networks, SF-CNN, SFT-CNN, or SPR-CNN or classifier 302 in Dong et al. in view of Cheong et al.’s invention can be implemented as a feed forward neural network as taught by ABDALLAH et al., where doing so would (ABDALLAH et al., Para. [0005], [0041]) for “a low complexity channel estimation for mmWave MIMO systems” and reconstruction of the “transmitted signal x[k]” in order to recover “data symbols s[k].”
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AMNEET SINGH whose telephone number is (571)272-2414. The examiner can normally be reached 9:30am to 5:30pm.
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, Sam K Ahn can be reached at 5712723044. 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.
/AMNEET SINGH/Examiner, Art Unit 2633
/SAM K AHN/Supervisory Patent Examiner, Art Unit 2633