BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Colombo BEGIN:DAYLIGHT DTSTART:20380119T084407 TZOFFSETFROM:+0530 TZOFFSETTO:+0530 RRULE:FREQ=YEARLY;BYDAY=3TU;BYMONTH=1 TZNAME:+0530 END:DAYLIGHT BEGIN:STANDARD DTSTART:20060415T000000 TZOFFSETFROM:+0600 TZOFFSETTO:+0530 RRULE:FREQ=YEARLY;BYDAY=3SA;BYMONTH=4 TZNAME:+0530 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220203T110407Z UID:AA67B6FB-44A2-43C5-8C2D-E95CE0C80C51 DTSTART;TZID=Asia/Colombo:20220131T190000 DTEND;TZID=Asia/Colombo:20220131T200000 DESCRIPTION:Wireless technology has changed the way we communicate today an d has enormous potential to change the way we live over the next several d ecades. Future wireless will support high throughput low latency wireless access for emerging applications like Virtual Reality (VR)\, Industrial In ternet of Things (IoT)\, 3D broadcast video\, tele-surgery\, etc. These ap plications require significant increase in data rates and lower latency\, with better coverage and spectral efficiency\, often in a new communicatio n channel\, like Terahertz (THz) spectrum and UAV channels. Furthermore\, it is expected that the spectrum access will be congested\, competitive\, and vulnerable to malicious intents of strong adversaries. This motivates us to innovate in novel machine learning models to tackle the challenges p osed in new channels as well as to secure wireless communication. This tal k will have two parts. The first part of the talk will discuss development of neural network (NN) models for OFDM receiver\, where expert knowledge of wireless communication is infused in different stages of the model to c reate a practical receiver. The parameters of the NN are derived from unde rlying theory and can be adapted to different wireless environments. The m odels are trained with over-the-air captured OFDM signals\, transmitted in THz band with 10GHz bandwidth. The results show significant improvement i n bit error rate (BER) for different modulation orders compared to existin g signal processing based receiver designs. The second part of the talk wi ll discuss a cross-layer solution for addressing wireless security in pres ence of a strong adversary. A novel NN model pair is created for encryptio n and decryption that generates an encrypted waveform\, which remains unde ciphered by the adversary while the intended receiver can recover the secr et message. Cooperative learning is introduced to enable the trusted pair to defeat the adversary and learn the encryption and modulation jointly. T he NN model can encode any modulation order and improves both reliability and secrecy capacity compared to prior work.\n\nSpeaker(s): Prof.Dola Saha \, \n\nVirtual: https://events.vtools.ieee.org/m/299064 LOCATION:Virtual: https://events.vtools.ieee.org/m/299064 ORGANIZER:ieeecomsocuop@gmail.com SEQUENCE:3 SUMMARY:Guest Talk on Machine Learning for Wireless Communications URL;VALUE=URI:https://events.vtools.ieee.org/m/299064 X-ALT-DESC:Description: <br /><p>Wireless technology has changed the way we communicate today and has enormous potential to change the way we live ov er the next several decades. Future wireless will support high throughput low latency wireless access for emerging applications like Virtual Reality (VR)\, Industrial Internet of Things (IoT)\, 3D broadcast video\, tele-su rgery\, etc. These applications require significant increase in data rates and lower latency\, with better coverage and spectral efficiency\, often in a new communication channel\, like Terahertz (THz) spectrum and UAV cha nnels. Furthermore\, it is expected that the spectrum access will be conge sted\, competitive\, and vulnerable to malicious intents of strong adversa ries. This motivates us to innovate in novel machine learning models to ta ckle the challenges posed in new channels as well as to secure wireless co mmunication. This talk will have two parts. The first part of the talk wil l discuss development of neural network (NN) models for OFDM receiver\, wh ere expert knowledge of wireless communication is infused in different sta ges of the model to create a practical receiver. The parameters of the NN are derived from underlying theory and can be adapted to different wireles s environments. The models are trained with over-the-air captured OFDM sig nals\, transmitted in THz band with 10GHz bandwidth. The results show sign ificant improvement in bit error rate (BER) for different modulation order s compared to existing signal processing based receiver designs. The secon d part of the talk will discuss a cross-layer solution for addressing wire less security in presence of a strong adversary. A novel NN model pair is created for encryption and decryption that generates an encrypted waveform \, which remains undeciphered by the adversary while the intended receiver can recover the secret message. Cooperative learning is introduced to ena ble the trusted pair to defeat the adversary and learn the encryption and modulation jointly. The NN model can encode any modulation order and impro ves both reliability and secrecy capacity compared to prior work.</p> END:VEVENT END:VCALENDAR