BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Canada/Pacific BEGIN:DAYLIGHT DTSTART:20210314T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20211107T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20210421T174206Z UID:CF8E2C75-E82E-451D-961B-1D68FFDCCAE0 DTSTART;TZID=Canada/Pacific:20210414T113000 DTEND;TZID=Canada/Pacific:20210414T124500 DESCRIPTION:Speaker: Angela Bonifati\n\nOne of the key principles of data a nalytics in data science pipelines is that the quality of the results is d ependent on the quality of the input data analyzed. Data collection and ac quisition in scientific domains\, such as for instance in healthcare and l ife sciences domains\, tend to often introduce errors into the data\, such as violations of business rules\, typos\, missing values and replicated e ntries. Moreover\, data collected for the patients' signals might exhibit peculiar features that need to be taken into account within the analytical and inference processes.\n\nI will present our latest results on enhancin g the quality of querying and inference processes on scientific data and b eyond. Among the others\, we operate on real-life data of patients from se veral hospitals in the EU and provide the domain experts with useful data management and learning techniques that can help them with their diagnoses and analyses. First\, inconsistency-aware annotations can enhance the dat a input to analytical processes. These annotations are further exploited d uring query processing in order to enhance the output of queries with inco nsistency degrees. Second\, feature-based similarities among time series c orresponding to patients’ signals help to better identify groups of pati ents and to assess their risks. Third\, logic-based declarative privacy-pr eserving data integration allows to migrate clinical data from one hospita l to another while ensuring privacy guarantees. In all cases\, our researc h aims at providing the caregivers with a better understanding of their cl inical data thanks to the improved outcomes of the performed analytics. In the talk\, I will overview the research performed in my group on this top ic as well as the related work and the future directions of investigation. \n\nThe video recordings and the slides of the previous seminars in this s eries are now available at the webinar series webpage <http://data.cs.sfu. ca/tdsa.html>\n\nZoom Registration is required for access to the meeting l ink. This way we can ensure quality discussions of participants from indus try and education.\n\nVirtual: https://events.vtools.ieee.org/m/269435 LOCATION:Virtual: https://events.vtools.ieee.org/m/269435 ORGANIZER:Bob_Gill@bcit.ca SEQUENCE:3 SUMMARY:SEMINAR SERIES ON TRUSTWORTHY DATA SCIENCE AND AI: QUALITY-DRIVEN A NALYTICS ON SCIENTIFIC DATA URL;VALUE=URI:https://events.vtools.ieee.org/m/269435 X-ALT-DESC:Description: <br /><p>Speaker:&nbsp\;Angela Bonifati&nbsp\;</p>\ n<p>One of the key principles of data analytics in data science pipelines is that the quality of the results is dependent on the quality of the inpu t data analyzed. Data collection and acquisition in scientific domains\, s uch as for instance in healthcare and life sciences domains\, tend to ofte n introduce errors into the data\, such as violations of business rules\, typos\, missing values and replicated entries. Moreover\, data collected f or the patients' signals might exhibit peculiar features that need to be t aken into account within the analytical and inference processes. <br /> <b r /> I will present our latest results on enhancing the quality of queryin g and inference processes on scientific data and beyond. Among the others\ , we operate on real-life data of patients from several hospitals in the E U and provide the domain experts with useful data management and learning techniques that can help them with their diagnoses and analyses. First\, i nconsistency-aware annotations can enhance the data input to analytical pr ocesses. These annotations are further exploited during query processing i n order to enhance the output of queries with inconsistency degrees. Secon d\, feature-based similarities among time series corresponding to patients &rsquo\; signals help to better identify groups of patients and to assess their risks. Third\, logic-based declarative privacy-preserving data integ ration allows to migrate clinical data from one hospital to another while ensuring privacy guarantees. In all cases\, our research aims at providing the caregivers with a better understanding of their clinical data thanks to the improved outcomes of the performed analytics. In the talk\, I will overview the research performed in my group on this topic as well as the r elated work and the future directions of investigation.</p>\n<p>The video recordings and the slides of the previous seminars in this series are now available at the webinar series webpage &lt\;<a href="http://data.cs.sfu.c a/tdsa.html">http://data.cs.sfu.ca/tdsa.html</a>&gt\;</p>\n<div class="dc- content">\n<div class="dc-modules">\n<div class="dc-modules__item">\n<div class="eds-l-mar-bot-12 eds-l-lg-mar-bot-14">\n<div class="dc-modules__ite m--text">\n<p><strong>Zoom Registration is required for access to the meet ing link.</strong>&nbsp\;This way we can ensure quality discussions of par ticipants from industry and education.</p>\n</div>\n</div>\n</div>\n</div> \n</div> END:VEVENT END:VCALENDAR