Crowdsourcing Labels and Explanations to Build More Robust, Explainable AI/ML Activity Models
Crowdsourcing Labels and Explanations to Build More Robust, Explainable AI/ML Activity Models
批准号:
10833847
负责人:
Diane Joyce Cook
金额:
$30.56万
依托单位国家:
美国
项目类别:
财政年份:
2020
资助国家:
美国
项目状态:
未结题
起止时间:
2020-09-30 至 2025-05-31
关键词:
Active LearningAgingAgreementAlzheimer&aposs disease related dementiaAreaBehaviorCategoriesClinicalClinical ResearchCollectionCommunitiesDataData CollectionData SetElderlyFoundationsGoalsHealthIndividualInterventionLabelLearningMachine LearningMechanicsMethodsModelingNeuropsychologyOutcomePerformancePopulationProcessResearchSamplingSeriesSoftware EngineeringTechnologyTextTimeTrainingTrustUncertaintyVisualVisualizationcitizen sciencecrowdsourcingdata toolsdata visualizationdiverse dataexperiencehealth applicationhealth assessmentlearning strategymHealthmachine learning modelmultimodalityparent projectrecruitsensorsmart watchtoolwearable sensor technology
中文摘要
项目总结/摘要
到2050年,随着65岁以上的人口从5800万增长到8800万,
患有阿尔茨海默病和相关痴呆症(ADRD)的老年人1。父项目
引入临床驱动的技术方法,以自动评估老年人的功能健康
多模态传感器数据。社区和我们的母项目中缺少的是
地面实况智能手表活动标签。如果没有足够数量的标记数据,机器学习模型
不能学习鲁棒的行为模型并将这些模型用于功能健康预测。另夕h
具有相应标签的活动类别非常倾斜,进一步限制了机器学习
因为经典的不平衡类分布问题。在这一补充请求中,我们
我建议大幅提高我们的母项目和
领域为此,我们将创建一种机制,通过Amazon Mechanical Turk众包活动标签。
此外,我们将利用众包的机会,推动母项目进入下一步,
为可解释的机器学习模型奠定基础。一旦我们的活动标签的目标数量达到
达成共识后,我们将启动第二轮众包,要求公民科学家创造一句话,
对应于活动实例的可视化数据的解释。补充项目将包括
四项任务。首先,我们将创建一个用于AmazonMechanical的可视化和数据点选择工具
土耳其人(AMT)数据收集论坛。基线主动学习策略将用于收集一组初始的
标签,并创建一个基线模型,之后,主动学习和注释器选择策略将
细化以收集活动标签的剩余部分。最后,来自每个建模类别的不同数据点
将被显示以收集用于训练解释模型的一组文本标题。本次增补的结果
该项目将是最大的一组活动标记的智能手表数据收集“在野外”。标记的
由该补充创建的数据集将为众多健康研究提供基础,
通过在真实世界研究中收集的连续可穿戴传感器读数观察到的活动信息。为
父项目,标记的数据量将增加超过10,000%。该补充还将提供一个
创建可解释的移动的健康AI/ML工具的起点。
英文摘要
PROJECT SUMMARY / ABSTRACT
As the population of individuals 65+ grows from 58 million to 88 million by 2050, so too will the number of
individuals who are aging with Alzheimer's disease and related dementias (ADRDs)1. The parent project
introduces clinically-driven technological methods to automate assessment of an older adult's functional health
from multimodal sensor data. What is lacking in the community, and in our parent project, is the availability of
ground-truth smartwatch activity labels. Without a sufficient amount of labeled data, machine learning models
cannot learn robust behavior models and use these models for functional health prediction. Additionally, the
categories of activities that have corresponding labels are very skewed, further limiting machine learning
performance because of the classical imbalanced class distribution problem. In this supplement request, we
propose to dramatically increase the availability of labeled smartwatch data for our parent project and for the
field. To do this, we will create a mechanism to crowdsource activity labels through Amazon Mechanical Turk.
Additionally, we will capitalize on the crowdsourcing opportunity to push the parent project to the next step by
laying a foundation for explainable machine learning models. Once our target number of activity labels is
reached, we will initiate a second round of crowdsourcing by asking citizen scientists to create one-sentence
explanations of the visualized data corresponding to an activity instance. The supplement project will contain
four tasks. First, we will create a visualization and data point-selection tool for use in the Amazon Mechanical
Turk (AMT) forum for data collection. A baseline active learning strategy will be used to collect an initial set of
labels and create a baseline model, after which, the active learning and annotator selection strategies will be
refined to collect the remainder of the activity labels. Finally, diverse data points from each modeled category
will be displayed to collect a set of text captions for training explanation models. The outcome of this supplement
project will be one of the largest sets of activity labeled smartwatch data collected “in the wild.” The labeled
datasets created by this supplement will offer a foundation for a multitude of health studies that can utilize
activity information observed by continuous wearable sensor readings collected in real-world studies. For the
parent project, the amount of labeled data will increase by over 10,000%. The supplement will also offer a
starting point for creating explainable mobile health AI/ML tools.
期刊论文(1)
专著(0)
科研奖励(0)
会议论文
Partnering a Compensatory Application with Activity-Aware Prompting to Improve Use in Individuals with Amnestic Mild Cognitive Impairment: A Randomized Controlled Pilot Clinical Trial.
与Action-Aware的补偿性应用合作,促使有弱化的轻度认知障碍患者的使用:一项随机对照试验临床试验。
DOI:
10.3233/jad-215022
发表时间:
2022
期刊:
JOURNAL OF ALZHEIMERS DISEASE
影响因子:
4
作者:
[Schmitter-Edgecombe, Maureen, Brown, Katelyn, Luna, Catherine, Chilton, Reanne, Sumida, Catherine A., Holder, Lawrence, Cook, Diane]
通讯作者:
Cook, Diane
Creating adaptive, wearable technologies to assess and intervene for individuals with ADRDs
-
批准号:10616670
-
项目类别:
-
资助金额:$87.5万
-
财政年份:2021
-
负责人:Diane Joyce Cook
-
依托单位:
Creating adaptive, wearable technologies to assess and intervene for individuals with ADRDs
-
批准号:10390367
-
项目类别:
-
资助金额:$89.69万
-
财政年份:2021
-
负责人:Diane Joyce Cook
-
依托单位:
Multi-modal functional health assessment and intervention for individuals experiencing cognitive decline
-
批准号:10426321
-
项目类别:
-
资助金额:$59.68万
-
财政年份:2020
-
负责人:Diane Joyce Cook
-
依托单位:
Multi-modal functional health assessment and intervention for individuals experiencing cognitive decline
-
批准号:10092007
-
项目类别:
-
资助金额:$60.04万
-
财政年份:2020
-
负责人:Diane Joyce Cook
-
依托单位:
Multi-modal functional health assessment and intervention for individuals experiencing cognitive decline
-
批准号:10662381
-
项目类别:
-
资助金额:$59.68万
-
财政年份:2020
-
负责人:Diane Joyce Cook
-
依托单位:
Multi-modal functional health assessment and intervention for individuals experiencing cognitive decline
-
批准号:10267717
-
项目类别:
-
资助金额:$60.39万
-
财政年份:2020
-
负责人:Diane Joyce Cook
-
依托单位:
Automated Health Assessment through Mobile Sensing and Machine Learning of Daily Activities
-
批准号:10683062
-
项目类别:
-
资助金额:$117.85万
-
财政年份:2019
-
负责人:Diane Joyce Cook
-
依托单位:
Automated Health Assessment through Mobile Sensing and Machine Learning of Daily Activities
-
批准号:10472075
-
项目类别:
-
资助金额:$117.85万
-
财政年份:2019
-
负责人:Diane Joyce Cook
-
依托单位:
A clinician-in-the-loop smart home to support health monitoring and intervention for chronic conditions
-
批准号:10367017
-
项目类别:
-
资助金额:$14.41万
-
财政年份:2017
-
负责人:Diane Joyce Cook
-
依托单位:
A clinician-in-the-loop smart home to support health monitoring and intervention for chronic conditions: Supplement to focus on Alzheimer's and/or other dementias
-
批准号:10086759
-
项目类别:
-
资助金额:$36.67万
-
财政年份:2017
-
负责人:Diane Joyce Cook
-
依托单位:
Development of an Online Course Suite in Tools for Analysis of Sensor-Based Behavioral Health Data (AHA!)
-
批准号:9313495
-
项目类别:
-
资助金额:$18.62万
-
财政年份:2017
-
负责人:Diane Joyce Cook
-
依托单位:
A clinician-in-the-loop smart home to support health monitoring and intervention for chronic conditions
-
批准号:10166954
-
项目类别:
-
资助金额:$35.26万
-
财政年份:2017
-
负责人:Diane Joyce Cook
-
依托单位:
Multidisciplinary undergraduate training program in Health-assistive Smart Environments
-
批准号:10602509
-
项目类别:
-
资助金额:$34.94万
-
财政年份:2014
-
负责人:Diane Joyce Cook
-
依托单位:
Multidisciplinary undergraduate training program in Health-assistive Smart Environments
-
批准号:10451494
-
项目类别:
-
资助金额:$36.13万
-
财政年份:2014
-
负责人:Diane Joyce Cook
-
依托单位:
Multi-disciplinary undergraduate training program in health-assistive smart envir
-
批准号:8917080
-
项目类别:
-
资助金额:$29.89万
-
财政年份:2014
-
负责人:Diane Joyce Cook
-
依托单位:
Smart environment technology for longitudinal behavior analysis and intervention
-
批准号:8549245
-
项目类别:
-
资助金额:$34.12万
-
财政年份:2012
-
负责人:Diane Joyce Cook
-
依托单位:
Smart environment technology for longitudinal behavior analysis and intervention
-
批准号:8402015
-
项目类别:
-
资助金额:$48.11万
-
财政年份:2012
-
负责人:Diane Joyce Cook
-
依托单位:
Smart environment technology for longitudinal behavior analysis and intervention
-
批准号:8915691
-
项目类别:
-
资助金额:$35.46万
-
财政年份:2012
-
负责人:Diane Joyce Cook
-
依托单位:
Smart environment technology for longitudinal behavior analysis and intervention
-
批准号:8715805
-
项目类别:
-
资助金额:$35.1万
-
财政年份:2012
-
负责人:Diane Joyce Cook
-
依托单位:
Smart Environment Technologies for Health Assessment and Assistance
-
批准号:8432827
-
项目类别:
-
资助金额:$29.11万
-
财政年份:2010
-
负责人:Diane Joyce Cook
-
依托单位:
海外基金