BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20251114T190930Z UID:4C15FD04-7B87-44E0-B6DE-F8D19953FABE DTSTART;TZID=America/Los_Angeles:20251112T173000 DTEND;TZID=America/Los_Angeles:20251112T183000 DESCRIPTION:In this talk\, Dr. Yadav will be talking about his research on Edge Artificial Intelligence (Edge AI).\n\nEdge Artificial Intelligence (E dge AI) is ushering in a new paradigm where computation moves closer to da ta sources\, enabling real-time perception\, privacy-preserving analytics\ , and autonomous decision-making in the physical world. Central to this ev olution is context-aware computing\, where systems sense\, interpret\, and respond to environmental\, behavioral\, and temporal cues. From gesture-d riven interfaces to health monitoring\, robotics\, and smart infrastructur e\, tomorrow’s intelligent edge systems must dynamically adapt to changi ng context rather than operate as static inference engines. However\, sele cting optimal hardware platforms for these applications remains a non-triv ial challenge\, given diverse constraints in compute\, memory\, power\, la tency\, and privacy. To address this\, we introduce Edge-X\, a cost-factor evaluation workflow that enables systematic selection and deployment of A I models on edge platforms (Conley\,Yadav et al.\, 2025). Edge-X formalize s a step-by-step method to profile resource needs\, map workload character istics\, and rapidly deploy applications across heterogeneous devices. Dem onstrated through gesture recognition on three hardware tiers\, Edge-X pro vides actionable insights into balancing capability\, energy efficiency\, and integration complexity.\n\nThis talk extends the Edge-X foundation to explore the future of context-aware edge intelligence - where devices evol ve from inference units to modelers\, adaptive learners\, and federated pa rticipants capable of on-device personalization and collaborative learning across distributed ecosystems. We examine emerging processor architecture s\, context-aware model design\, low-power continual-learning approaches\, and federated protocols that respect privacy while enabling collective in telligence. The presentation will deliver a grounded deployment framework and a forward-looking roadmap toward self-training\, situationally-aware\, and cooperative Edge AI systems powering next-generation interactive\, in telligent environments.\n\nSpeaker(s): Nikhil Yadav\n\nAgenda: \n- Invited talk from Dr. Nikhil Yadav\, Associate Professor and Chair of Computer Sc ience at the University of San Diego\, San Diego.\n- Q/A Session\n\nVirtua l: https://events.vtools.ieee.org/m/512707 LOCATION:Virtual: https://events.vtools.ieee.org/m/512707 ORGANIZER:mislam@sandiego.edu SEQUENCE:66 SUMMARY:Adaptive Edge Intelligence: Context-Aware and Federated Systems URL;VALUE=URI:https://events.vtools.ieee.org/m/512707 X-ALT-DESC:Description: <br /><p>In this talk\, Dr. Yadav will be talking a bout his research on Edge Artificial Intelligence (Edge AI).</p>\n<p>Edge Artificial Intelligence (Edge AI) is ushering in a new paradigm where comp utation moves closer to data sources\, enabling real-time perception\, pri vacy-preserving analytics\, and autonomous decision-making in the physical world. Central to this evolution is context-aware computing\, where syste ms sense\, interpret\, and respond to environmental\, behavioral\, and tem poral cues. From gesture-driven interfaces to health monitoring\, robotics \, and smart infrastructure\, tomorrow&rsquo\;s intelligent edge systems m ust dynamically adapt to changing context rather than operate as static in ference engines. However\, selecting optimal hardware platforms for these applications remains a non-trivial challenge\, given diverse constraints i n compute\, memory\, power\, latency\, and privacy. To address this\, we i ntroduce Edge-X\, a cost-factor evaluation workflow that enables systemati c selection and deployment of AI models on edge platforms (Conley\,Yadav e t al.\, 2025). Edge-X formalizes a step-by-step method to profile resource needs\, map workload characteristics\, and rapidly deploy applications ac ross heterogeneous devices. Demonstrated through gesture recognition on th ree hardware tiers\, Edge-X provides actionable insights into balancing ca pability\, energy efficiency\, and integration complexity.<br><br>This tal k extends the Edge-X foundation to explore the future of context-aware edg e intelligence - where devices evolve from inference units to modelers\, a daptive learners\, and federated participants capable of on-device persona lization and collaborative learning across distributed ecosystems. We exam ine emerging processor architectures\, context-aware model design\, low-po wer continual-learning approaches\, and federated protocols that respect p rivacy while enabling collective intelligence. The presentation will deliv er a grounded deployment framework and a forward-looking roadmap toward se lf-training\, situationally-aware\, and cooperative Edge AI systems poweri ng next-generation interactive\, intelligent environments.</p><br /><br /> Agenda: <br /><ul>\n<li>Invited talk from Dr. Nikhil Yadav\, Associate Pro fessor and Chair of Computer Science at the University of San Diego\, San Diego.</li>\n<li>Q/A Session</li>\n</ul> END:VEVENT END:VCALENDAR