BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern BEGIN:DAYLIGHT DTSTART:20230312T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20221106T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230209T232417Z UID:9EA12EFB-C452-4587-B4B2-9D0C6119989B DTSTART;TZID=US/Eastern:20230206T183000 DTEND;TZID=US/Eastern:20230206T200000 DESCRIPTION:Smart environments in wide-ranging applications are expected to have a large number of static/mobile IoT devices operating via machine-ty pe communications for sensing/monitoring\, actuation\, and control purpose s. For scalability and widespread adoption of such autonomous environments the IoT devices and the network need to be low-cost\, light in terms of e nergy and data footprints\, and potentially self-adaptive\, so as to minim ize human intervention. In this context\, in this talk\, we will present a data-driven approach to the performance optimization of IoT network syste ms. By application of context-aware learning of temporal and spatial dynam ic stochasticity and cross-correlation of the sensing parameters of intere st\, the multi-sensing and communication activities of the IoT nodes are o ptimized. Further\, data communication priority is dynamically adapted\, t hereby further minimizing sensing and communication-related energy and com munication bandwidth overheads. A few examples\, include smart power grid monitoring and smart sensing IoT systems\, we will demonstrate how data-dr iven\, context-aware light-weight\nmachine learning and edge computing-aid ed approaches can be utilized for more accurate system performance charact erization and optimizations\, leading to significant processing\, communic ation\, and storage resource efficiency and energy sustainability of the I oT network. We will share our experiences from field experiments\, proof-o f-concept implementations\, and campus-wide deployments\, and will highlig ht the possibilities of learning-aided networking optimizations for variou s multidisciplinary-disciplinary applications.\n\nTime: Feb 6\, 2023\, 06: 30 Eastern Time (US and Canada)\n\nJoin Zoom Meeting\nhttps://us02web.zoom .us/j/9514547039\n\nMeeting ID: 951 454 7039\n\nCo-sponsored by: IEEE Nort h Jersey Section\n\nSpeaker(s): Dr. Swades De\, \n\nVirtual: https://event s.vtools.ieee.org/m/346934 LOCATION:Virtual: https://events.vtools.ieee.org/m/346934 ORGANIZER:akpoddar@ieee.org SEQUENCE:8 SUMMARY:Smart IoT for energy sustainable environments URL;VALUE=URI:https://events.vtools.ieee.org/m/346934 X-ALT-DESC:Description: <br /><p>Smart environments in wide-ranging applica tions are expected to have a large number of static/mobile IoT devices ope rating via machine-type communications for sensing/monitoring\, actuation\ , and control purposes. For scalability and widespread adoption of such au tonomous environments the IoT devices and the network need to be low-cost\ , light in terms of energy and data footprints\, and potentially self-adap tive\, so as to minimize human intervention. In this context\, in this tal k\, we will present a data-driven approach to the performance optimization of IoT network systems. By application of context-aware learning of tempo ral and spatial dynamic stochasticity and cross-correlation of the sensing parameters of interest\, the multi-sensing and communication activities o f the IoT nodes are optimized. Further\, data communication priority is dy namically adapted\, thereby further minimizing sensing and communication-r elated energy and communication bandwidth overheads. A few examples\, incl ude smart power grid monitoring and smart sensing IoT systems\, we will de monstrate how data-driven\, context-aware light-weight<br />machine learni ng and edge computing-aided approaches can be utilized for more accurate s ystem performance characterization and optimizations\, leading to signific ant processing\, communication\, and storage resource efficiency and energ y sustainability of the IoT network. We will share our experiences from fi eld experiments\, proof-of-concept implementations\, and campus-wide deplo yments\, and will highlight the possibilities of learning-aided networking optimizations for various multidisciplinary-disciplinary applications.</p >\n<p>Time: Feb 6\, 2023\, 06:30 Eastern Time (US and Canada)</p>\n<p><str ong>Join Zoom Meeting</strong><br /><strong><span style="color: #236fa1\;" >https://us02web.zoom.us/j/9514547039</span></strong></p>\n<p><strong>Meet ing ID: 951 454 7039</strong></p> END:VEVENT END:VCALENDAR