BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Berlin BEGIN:DAYLIGHT DTSTART:20260329T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20261025T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260906T163158Z UID:A14F8280-07E2-4996-9204-8D5CD3D703FF DTSTART;TZID=Europe/Berlin:20260906T173000 DTEND;TZID=Europe/Berlin:20260906T181500 DESCRIPTION:Abstract:\n\nSmartphone time-to-empty (TTE) prediction is hinde red by the interplay of cell electrochemistry\, heterogeneous peripheral p ower draw\, and variable user workloads. Existing methods address these fa ctors in isolation: statistical approaches fail under non-stationary loads \, data-driven methods suffer distributional shift\, and physics-based mod els neglect the screen\, CPU\, and radios that dominate runtime discharge. To bridge these gaps\, we propose a hybrid framework that couples a secon d-order Thevenin equivalent circuit model with component-level power decom position and temperature/aging modulation. Backtesting on three devices an d nine scenarios shows that the proposed model achieves the lowest TTE MAE in seven of nine cases (4.0%–43.1% reduction over the best baseline) an d ranks first or second across all scenarios. Subsequent ablation reveals workload-dependent subsystem contributions: temperature correction aids mi xed-use but introduces noise under stable thermal conditions\, while ECM d ynamics benefit pulsed loads but add variance under near-constant-current discharge. Further sensitivity analysis identifies nominal capacity\, scre en and CPU coefficients\, and baseline draw as dominant parameters\, with GPS and audio coefficients being negligible.\n\nSpeaker(s): Yujie Zhang\n\ nAgenda: \nThe webinar will take place on the sidelines of the 15th IEEE I nternational Conference on Consumer Electronics (ICCE Berlin 2026)\, held on 5–7 September 2026 in Berlin\, Germany.\n\nGreetings and Introduction : 5 minutes\nPresentation: 15-20 minutes\nQ&A: 3-5 minutes\n\nChapter time : 15 minutes\n\nRoom: Corinth\, Bldg: Hilton Hotel\, Anton-Wilhelm-Amo-Str aße 30\, Berlin\, Berlin\, Germany\, 10117\, Virtual: https://events.vtoo ls.ieee.org/m/574222 LOCATION:Room: Corinth\, Bldg: Hilton Hotel\, Anton-Wilhelm-Amo-Straße 30\ , Berlin\, Berlin\, Germany\, 10117\, Virtual: https://events.vtools.ieee. org/m/574222 ORGANIZER:mbhattac@gmx.de SEQUENCE:39 SUMMARY:A Hybrid Physics-Informed and Data-Driven Framework for Component-L evel Smartphone Battery Life Prediction URL;VALUE=URI:https://events.vtools.ieee.org/m/574222 X-ALT-DESC:Description: <br /><div style="font-family: Aptos \, Aptos_Embed dedFont \, Aptos_MSFontService \, Calibri \, Helvetica \, sans-serif\; fon t-size: 12.0pt\; color: rgb(0\,0\,0)\;">Abstract:</div>\n<div style="font- family: Aptos \, Aptos_EmbeddedFont \, Aptos_MSFontService \, Calibri \, H elvetica \, sans-serif\; font-size: 12.0pt\; color: rgb(0\,0\,0)\;">&nbsp\ ;</div>\n<div style="font-family: Aptos \, Aptos_EmbeddedFont \, Aptos_MSF ontService \, Calibri \, Helvetica \, sans-serif\; font-size: 12.0pt\; col or: rgb(0\,0\,0)\;">Smartphone time-to-empty (TTE) prediction is hindered by the interplay of cell electrochemistry\, heterogeneous peripheral power draw\, and variable user workloads. Existing methods address these factor s in isolation: statistical approaches fail under non-stationary loads\, d ata-driven methods suffer distributional shift\, and physics-based models neglect the screen\, CPU\, and radios that dominate runtime discharge. To bridge these gaps\, we propose a hybrid framework that couples a second-or der Thevenin equivalent circuit model with component-level power decomposi tion and temperature/aging modulation. Backtesting on three devices and ni ne scenarios shows that the proposed model achieves the lowest TTE MAE in seven of nine cases (4.0%&ndash\;43.1% reduction over the best baseline) a nd ranks first or second across all scenarios. Subsequent ablation reveals workload-dependent subsystem contributions: temperature correction aids m ixed-use but introduces noise under stable thermal conditions\, while ECM dynamics benefit pulsed loads but add variance under near-constant-current discharge. Further sensitivity analysis identifies nominal capacity\, scr een and CPU coefficients\, and baseline draw as dominant parameters\, with GPS and audio coefficients being negligible.</div>\n<div style="font-fami ly: Aptos \, Aptos_EmbeddedFont \, Aptos_MSFontService \, Calibri \, Helve tica \, sans-serif\; font-size: 12.0pt\; color: rgb(0\,0\,0)\;">&nbsp\;</d iv><br /><br />Agenda: <br /><p>The webinar will take place on the sidelin es of the 15th IEEE International Conference on Consumer Electronics (ICCE Berlin 2026)\, held on 5&ndash\;7 September 2026 in Berlin\, Germany.</p> \n<p>&nbsp\;</p>\n<p><strong data-start="56" data-end="86">Greetings and I ntroduction: </strong>5 minutes<br data-start="86" data-end="89"><strong d ata-start="89" data-end="106">Presentation:</strong> 15-20 minutes<br data -start="117" data-end="120"><strong data-start="120" data-end="128">Q&amp\ ;A:</strong> 3-5 minutes</p>\n<p><strong>Chapter time:</strong> 15 minutes </p> END:VEVENT END:VCALENDAR