Hi Xiaofei,
Regarding CSI feedback compression use case in pg. 5:
I suggest to remove ‘LB-SciFi’ from the above paragraph to avoid confusion, so the paragraph becomes:
In [12]
, another unsupervised learning technique, Deep Neural Network Autoencoder (DNN-AE) is applied to CSI angle vectors and further compresses the derived angles by leveraging the compression capability of DNNs. Experimental results
show that the algorithm reduces the feedback overhead by 73% and increases the network throughput by 69%, on average.
BTW: could you please change my affiliation in pg. 1 from “Samsung Cambridge Solution Center” to “Samsung Cambridge Solution Centre”?
Thanks,
Ziming
From: Xiaofei Wang <Xiaofei.Wang@xxxxxxxxxxxxxxxx>
Sent: 10 September 2023 00:44
To: STDS-802-11@xxxxxxxxxxxxxxxxx
Cc: Stephen McCann <mccann.stephen@xxxxxxxxx>; Ziming He <ziming.he@xxxxxxxxxxx>; JEON EUNSUNG <eunsung.jeon@xxxxxxxxxxx>; guoziyang <guoziyang@xxxxxxxxxx>; Liupeng (Jeremy) <jeremy.liupeng@xxxxxxxxxx>; Zinan Lin <Zinan.Lin@xxxxxxxxxxxxxxxx>; Rui Yang
<Rui.Yang@xxxxxxxxxxxxxxxx>; Ganming(Ming Gan) <ming.gan@xxxxxxxxxx>; Liangxiao Xin <xlx20190808@xxxxxxxxx>; Federico Lovison (flovison) <flovison@xxxxxxxxx>; Juan Carlos Zuniga (juzuniga) <juzuniga@xxxxxxxxx>; Szymon Szott <szott@xxxxxxxxxx>; Jerome Henry
(jerhenry) <jerhenry@xxxxxxxxx>
Subject: AIML TIG Technical report draft r10 uploaded
Dear all,
I have uploaded the r10 of 11-22/987, which is the draft AIML TIG technical report.
https://mentor.ieee.org/802.11/dcn/22/11-22-0987-10-aiml-aiml-tig-technical-report-draft.doc
It contains mostly editorial changes. Many thanks to Stephen, who has so kindly provided a very thorough editorial review of 11-22/987r8.
Since his changes were presented in one of the AIML TIG teleconferences, and there were no objections, I have accepted most of the editorial changes.
There are still a number of comments remaining in the current document, which needs to be addressed by the individual authors.
In addition, I have temporarily removed the structure Problem-AIML Benefits-Summary for each individual use case. Since we will likely have an executive summary, summary/conclusions, we may want to wait a bit to see which
structure is preferred for each use case. But I did add some summary notes for each use case.
Please let me know if you have any comments/questions.
Best regards,
Xiaofei Clement Wang
Principal Engineer | InterDigital
T: (631) 622.4028
E: Xiaofei.wang@xxxxxxxxxxxxxxxx
To unsubscribe from the STDS-802-11 list, click the following link: https://listserv.ieee.org/cgi-bin/wa?SUBED1=STDS-802-11&A=1