BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Denver BEGIN:DAYLIGHT DTSTART:20190310T030000 TZOFFSETFROM:-0700 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:MDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20181104T010000 TZOFFSETFROM:-0600 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:MST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20181106T134028Z UID:3FCCB091-C38D-4755-B0B1-C37395E54EB2 DTSTART;TZID=America/Denver:20181105T123000 DTEND;TZID=America/Denver:20181105T133000 DESCRIPTION:Machine learning and Deep Learning are powerful tools for solvi ng complex modeling problems across a broad range of industries. The benef its of machine learning are being realized in applications everywhere\, in cluding predictive maintenance\, health monitoring\, financial portfolio f orecasting\, and advanced driver assistance. However\, developing predicti ve models for signals obtained from sensors is not a trivial task. Moreove r\, there is an increasing need for developing smart sensor signal process ing algorithms which can be either deployed on edge nodes / embedded devic es or on the cloud depending on the application.\n\nCo-sponsored by: BYU E lectrical Engineering Department & Mathworks\n\nAgenda: \nn this session w e will explore how you can use MATLAB for developing predictive models for real world sensor analytics using machine learning and deep learning work flows. Using real data we will explore the following topics:\n\nWe will ex plore the following:\n\n- How advanced signal processing techniques can be used to obtain deep insights into signal data\n- Signal Pre-processing te chniques to increase sensor signal quality.\n- Feature detection and extra ction techniques for machine learning workflows\n- Developing predictive m odels quickly for signals using Deep Learning workflows\n- Leverage high-p erformance computing resources\, such as multicore computers\, GPUs\, comp uter clusters to scale up the performance\n\nRoom: 402\, Bldg: Engineering Building (New Building)\, Engineering Building\, Brigham Young University \, Provo\, Utah\, United States\, 84604 LOCATION:Room: 402\, Bldg: Engineering Building (New Building)\, Engineerin g Building\, Brigham Young University\, Provo\, Utah\, United States\, 846 04 ORGANIZER:ckidder@ieee.org SEQUENCE:2 SUMMARY:Deep Learning for Sensor Data URL;VALUE=URI:https://events.vtools.ieee.org/m/176068 X-ALT-DESC:Description: <br /><p>Machine learning and Deep Learning are pow erful tools for solving complex modeling problems across a broad range of industries. The benefits of machine learning are being realized in applica tions everywhere\, including predictive maintenance\, health monitoring\, financial portfolio forecasting\, and advanced driver assistance. However\ , developing predictive models for signals obtained from sensors is not a trivial task. Moreover\, there is an increasing need for developing smart sensor signal processing algorithms which can be either deployed on edge n odes / embedded devices or on the cloud depending on the application.</p>< br /><br />Agenda: <br /><p>n this session we will explore how you can use MATLAB for developing predictive models for real world sensor analytics u sing machine learning and deep learning workflows. Using real data we will explore the following topics:</p>\n<p>We will explore the following:</p>\ n<p>&nbsp\;- How advanced signal processing techniques can be used to obta in deep insights into signal data<br />&nbsp\;- Signal Pre-processing tech niques to increase sensor signal quality.<br />&nbsp\;- Feature detection and extraction techniques for machine learning workflows<br />&nbsp\;- Dev eloping predictive models quickly for signals using Deep Learning workflow s<br />&nbsp\;- Leverage high-performance computing resources\, such as mu lticore computers\, GPUs\, computer clusters to scale up the performance</ p> END:VEVENT END:VCALENDAR