BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Biomedical Mathematics Group - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.ibs.re.kr/bimag
X-WR-CALDESC:Events for Biomedical Mathematics Group
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:20220101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20230203T140000
DTEND;TZID=Asia/Seoul:20230203T160000
DTSTAMP:20260426T012446
CREATED:20230126T234906Z
LAST-MODIFIED:20230130T080459Z
UID:7274-1675432800-1675440000@www.ibs.re.kr
SUMMARY:Hyukpyo Hong\, Estimating and Assessing Differential Equation Models with Time-Course Data
DESCRIPTION:We will discuss about “Estimating and Assessing Differential Equation Models with Time-Course Data”\, Wong\, Samuel WK\, Shihao Yang\, and S. C. Kou\, arXiv preprint arXiv:2212.10653 (2022). \nAbstract \n\nOrdinary differential equation (ODE) models are widely used to describe chemical or biological processes. This article considers the estimation and assessment of such models on the basis of time-course data. Due to experimental limitations\, time-course data are often noisy and some components of the system may not be observed. Furthermore\, the computational demands of numerical integration have hindered the widespread adoption of time-course analysis using ODEs. To address these challenges\, we explore the efficacy of the recently developed MAGI (MAnifold-constrained Gaussian process Inference) method for ODE inference. First\, via a range of examples we show that MAGI is capable of inferring the parameters and system trajectories\, including unobserved components\, with appropriate uncertainty quantification. Second\, we illustrate how MAGI can be used to assess and select different ODE models with time-course data based on MAGI’s efficient computation of model predictions. Overall\, we believe MAGI is a useful method for the analysis of time-course data in the context of ODE models\, which bypasses the need for any numerical integration.
URL:https://www.ibs.re.kr/bimag/event/2023-02-03-jc/
LOCATION:B378 Seminar room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20230210T140000
DTEND;TZID=Asia/Seoul:20230210T160000
DTSTAMP:20260426T012446
CREATED:20230126T235218Z
LAST-MODIFIED:20230208T015345Z
UID:7276-1676037600-1676044800@www.ibs.re.kr
SUMMARY:Dongju Lim\, Predicting Chronic Stress among Healthy Females Using Daily-Life Physiological and Lifestyle Features from Wearable Sensors
DESCRIPTION:We will discuss about “Predicting Chronic Stress among Healthy Females Using Daily-Life Physiological and Lifestyle Features from Wearable Sensors”\, Magal\, Noa\, et al.\, Chronic Stress 6 (2022): 24705470221100987. \nAbstract \n\n\n\n\nBackground: Chronic stress is a highly prevalent condition that may stem from different sources and can substantially impact physiology and behavior\, potentially leading to impaired mental and physical health. Multiple physiological and behavioral lifestyle features can now be recorded unobtrusively in daily-life using wearable sensors. The aim of the current study was to identify a distinct set of physiological and behavioral lifestyle features that are associated with elevated levels of chronic stress across different stress sources. \nMethods: For that\, 140 healthy female participants completed the Trier inventory for chronic stress (TICS) before wearing the Fitbit Charge3 sensor for seven consecutive days while maintaining their daily routine. Physiological and lifestyle features that were extracted from sensor data\, alongside demographic features\, were used to predict high versus low chronic stress with support vector machine classifiers\, applying out-of-sample model testing. \nResults: The model achieved 79% classification accuracy for chronic stress from a social tension source. A mixture of physiological (resting heart-rate\, heart-rate circadian characteristics)\, lifestyle (steps count\, sleep onset and sleep regularity) and non-sensor demographic features (smoking status) contributed to this classification. \nConclusion: As wearable technologies continue to rapidly evolve\, integration of daily-life indicators could improve our understanding of chronic stress and its impact of physiology and behavior.
URL:https://www.ibs.re.kr/bimag/event/2023-02-10-jc/
LOCATION:B378 Seminar room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20230217T140000
DTEND;TZID=Asia/Seoul:20230217T160000
DTSTAMP:20260426T012446
CREATED:20230127T011541Z
LAST-MODIFIED:20230214T144610Z
UID:7278-1676642400-1676649600@www.ibs.re.kr
SUMMARY:Hyeontae Jo\, Characterizing possible failure modes in physics-informed neural networks
DESCRIPTION:We will discuss about “Characterizing possible failure modes in physics-informed neural networks”\, Krishnapriyan\, Aditi\, et al.\, Advances in Neural Information Processing Systems 34 (2021): 26548-26560. \nAbstract \n\n\n\n\n\n\nRecent work in scientific machine learning has developed so-called physics-informed neural network (PINN) models. The typical approach is to incorporate physical domain knowledge as soft constraints on an empirical loss function and use existing machine learning methodologies to train the model. We demonstrate that\, while existing PINN methodologies can learn good models for relatively trivial problems\, they can easily fail to learn relevant physical phenomena for even slightly more complex problems. In particular\, we analyze several distinct situations of widespread physical interest\, including learning differential equations with convection\, reaction\, and diffusion operators. We provide evidence that the soft regularization in PINNs\, which involves PDE-based differential operators\, can introduce a number of subtle problems\, including making the problem more ill-conditioned. Importantly\, we show that these possible failure modes are not due to the lack of expressivity in the NN architecture\, but that the PINN’s setup makes the loss landscape very hard to optimize. We then describe two promising solutions to address these failure modes. The first approach is to use curriculum regularization\, where the PINN’s loss term starts from a simple PDE regularization\, and becomes progressively more complex as the NN gets trained. The second approach is to pose the problem as a sequence-to-sequence learning task\, rather than learning to predict the entire space-time at once. Extensive testing shows that we can achieve up to 1-2 orders of magnitude lower error with these methods as compared to regular PINN training. \n 
URL:https://www.ibs.re.kr/bimag/event/2023-02-17-jc/
LOCATION:B378 Seminar room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
END:VCALENDAR