CRII: SCH: Semi-Supervised Physics-Based Generative Model for Data Augmentation and Cross-Modality Data Reconstruction
CRII:SCH:基于半监督物理的数据增强和跨模态数据重建生成模型
基本信息
- 批准号:1755695
- 负责人:
- 金额:$ 16.87万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2018
- 资助国家:美国
- 起止时间:2018-06-01 至 2021-05-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Deep learning approaches have been rapidly adopted across a wide range of fields because of their accuracy and flexibility, but require large labeled training sets. This presents a fundamental problem for applications with limited, expensive or private data, such as in healthcare. One example of these applications with the small data challenges is human in-bed pose and pressure estimation. In-bed pose estimation can be a critical part of prevention, prediction, and management of movement-related problems like pressure ulcers. These pressure ulcers often lead to costly and painful conditions such as bedsores. In this research, we propose a semi-supervised generative model based on novel data augmentation and cross-modality data reconstruction techniques to expand the use of powerful deep learning approaches to the in-bed pose and pressure estimation problems. This grant will directly fund the education and mentorship of graduate students involved in researching these problems. In addition, middle school and high school students will be engaged through summer school mentorship programs at Northeastern University.The educational outreach funded by this grant will be used to mentor at schools primarily serving minority student populations. This comprehensive mentorship from middle school to PhD creates a pipeline of experienced students in this important area. The PI actively maintains a diverse research group which includes 50% women and other members of under-represented groups. This proposed research explores the use of semi-supervised physics-based generative models to bridge the gap between state-of-the-art deep learning techniques and the small data problem common in personalized healthcare and other data-limited domains. The use of a physics-based approach to generate image data from a low-dimensional parameter space is unique and transformative. This proposal organizes the research to two Thrusts: (I) data augmentation, which synthesizes the large training set required to train a deep learning model to recognize the in-bed pose from an image; and (II) cross-modality data reconstruction, which extracts pose parameters from one image modality to generate data in another image modality. The success of the data augmentation will be measured by using the synthesized image data to train a network, which will be tested against deep and non-deep models trained on publicly-available pose datasets. The accuracy of the pressure image reconstruction will be tested by comparing the results to pressure images taken from a high-resolution pressure sensing mat. The successful completion of this project enables (1) the use of high-accuracy deep learning techniques for robustly recognizing objects and object poses for which articulated 3D models are available or can be generated; and (2) generating highly realistic images of posable figures in one sensory domain using data from another, when one sensory domain is cheaper or easier to gather data in than others.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
深度学习方法由于其准确性和灵活性而在广泛的领域中迅速被采用,但需要大量的标记训练集。这对于具有有限、昂贵或私有数据的应用(例如医疗保健)来说是一个根本问题。这些具有小数据挑战的应用程序的一个例子是人类在床上的姿势和压力估计。床上姿势估计可以是预防、预测和管理与运动相关的问题(如压疮)的关键部分。这些压力性溃疡往往导致昂贵和痛苦的条件,如褥疮。在这项研究中,我们提出了一种基于新的数据增强和跨模态数据重建技术的半监督生成模型,以将强大的深度学习方法扩展到床内姿势和压力估计问题。这笔赠款将直接资助研究这些问题的研究生的教育和指导。此外,初中和高中学生将通过东北大学的暑期学校辅导计划参与。这笔赠款资助的教育推广活动将用于主要为少数民族学生服务的学校的辅导。这种从中学到博士的全面指导在这一重要领域创造了一个有经验的学生管道。PI积极维持一个多样化的研究小组,其中包括50%的妇女和代表性不足群体的其他成员。这项拟议的研究探索了使用基于半监督物理的生成模型来弥合最先进的深度学习技术与个性化医疗保健和其他数据有限领域中常见的小数据问题之间的差距。使用基于物理的方法从低维参数空间生成图像数据是独特的和变革性的。该提案将研究组织为两个重点:(I)数据增强,其合成训练深度学习模型以从图像中识别床上姿势所需的大型训练集;以及(II)跨模态数据重建,其从一种图像模态中提取姿势参数以生成另一种图像模态中的数据。数据增强的成功将通过使用合成图像数据来训练网络来衡量,该网络将针对在公开可用的姿势数据集上训练的深度和非深度模型进行测试。将通过将结果与从高分辨率压力传感垫拍摄的压力图像进行比较来测试压力图像重建的准确性。该项目的成功完成使得(1)能够使用高精度深度学习技术来鲁棒地识别对象和对象姿态,其中关节式3D模型可用或可以生成;以及(2)使用来自另一个感觉域的数据在一个感觉域中生成可摆姿势的人物的高度逼真的图像,该奖项反映了NSF的法定使命,并被认为值得通过使用基金会的智力价值和更广泛的影响进行评估来支持审查标准。
项目成果
期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
A Semi-Supervised Data Augmentation Approach using 3D Graphical Engines
- DOI:10.1007/978-3-030-11012-3_31
- 发表时间:2018-08
- 期刊:
- 影响因子:0
- 作者:Shuangjun Liu;S. Ostadabbas
- 通讯作者:Shuangjun Liu;S. Ostadabbas
In-Bed Pose Estimation: Deep Learning With Shallow Dataset
- DOI:10.1109/jtehm.2019.2892970
- 发表时间:2019-01-01
- 期刊:
- 影响因子:3.4
- 作者:Liu, Shuangjun;Yin, Yu;Ostadabbas, Sarah
- 通讯作者:Ostadabbas, Sarah
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Sarah Ostadabbas其他文献
Vision-Based Treatment Localization with Limited Data: Automated Documentation of Military Emergency Medical Procedures
有限数据下基于视觉的治疗定位:军事紧急医疗程序的自动记录
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
Trevor Powers;Elaheh Hatamimajoumerd;William Chu;Vishakk Rajendran;Rishi Shah;Frank Diabour;Marc Vaillant;Richard Fletcher;Sarah Ostadabbas - 通讯作者:
Sarah Ostadabbas
Intelligent Care Management for Diabetic Foot Ulcers: A Scoping Review of Computer Vision and Machine Learning Techniques and Applications.
糖尿病足溃疡的智能护理管理:计算机视觉和机器学习技术及应用的范围审查。
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:5
- 作者:
Cynthia Baseman;Maya Fayfman;Marcos C Schechter;Sarah Ostadabbas;G. Santamarina;Thomas Ploetz;R. Arriaga - 通讯作者:
R. Arriaga
Computational complexity reduction of an adaptive congestion control in Active Queue Management
主动队列管理中自适应拥塞控制的计算复杂度降低
- DOI:
10.1109/ccdc.2008.4598030 - 发表时间:
2008 - 期刊:
- 影响因子:0
- 作者:
Sarah Ostadabbas;M. Haeri - 通讯作者:
M. Haeri
Sarah Ostadabbas的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Sarah Ostadabbas', 18)}}的其他基金
Collaborative Research: Development of a precision closed loop BCI for socially fearful teens with depression and anxiety
合作研究:为患有抑郁症和焦虑症的社交恐惧青少年开发精确闭环脑机接口
- 批准号:
2327066 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant
CAREER: Learning Visual Representations of Motor Function in Infants as Prodromal Signs for Autism
职业:学习婴儿运动功能的视觉表征作为自闭症的前驱症状
- 批准号:
2143882 - 财政年份:2022
- 资助金额:
$ 16.87万 - 项目类别:
Continuing Grant
CHS: Small: Collaborative Research: A Graph-Based Data Fusion Framework Towards Guiding A Hybrid Brain-Computer Interface
CHS:小型:协作研究:基于图的数据融合框架指导混合脑机接口
- 批准号:
2005957 - 财政年份:2020
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant
SCH: INT: Collaborative Research: Detection, Assessment and Rehabilitation of Stroke-Induced Visual Neglect Using Augmented Reality (AR) and Electroencephalography (EEG)
SCH:INT:合作研究:使用增强现实 (AR) 和脑电图 (EEG) 检测、评估和康复中风引起的视觉忽视
- 批准号:
1915065 - 财政年份:2019
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant
NRI: EAGER: Teaching Aerial Robots to Perch Like a Bat via AI-Guided Design and Control
NRI:EAGER:通过人工智能引导设计和控制教导空中机器人像蝙蝠一样栖息
- 批准号:
1944964 - 财政年份:2019
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant
SBIR Phase I: Pressure Map Analytics for Ulcer Prevention
SBIR 第一阶段:预防溃疡的压力图分析
- 批准号:
1248587 - 财政年份:2013
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant
相似国自然基金
基于生物类芬顿的LA/Sch@BB耦合系统去除水产养殖尾水中抗生素的效果与机制研究
- 批准号:42377063
- 批准年份:2023
- 资助金额:49 万元
- 项目类别:面上项目
具有低聚合收缩和生态防龋双功能的埃洛石纳米管@SCH-79797改性复合树脂的研究
- 批准号:82170950
- 批准年份:2021
- 资助金额:52 万元
- 项目类别:面上项目
一类稳态Schödinger-Poisson-Slater方程标准化解的研究
- 批准号:11501137
- 批准年份:2015
- 资助金额:18.0 万元
- 项目类别:青年科学基金项目
锥中修改的Poisson-Sch积分在无穷远点处的渐近行为及其应用
- 批准号:U1304102
- 批准年份:2013
- 资助金额:30.0 万元
- 项目类别:联合基金项目
酵母中Sch9蛋白激酶信号途径调控衰老的分子机理
- 批准号:30671181
- 批准年份:2006
- 资助金额:24.0 万元
- 项目类别:面上项目
相似海外基金
Open Access Block Award 2024 - London Sch of Hygiene & Tropic. Medicine
2024 年开放访问区块奖 - 伦敦卫生学院
- 批准号:
EP/Z532368/1 - 财政年份:2024
- 资助金额:
$ 16.87万 - 项目类别:
Research Grant
CRII: SCH: Towards Smart Patient Flow Management: Real-time Inpatient Length of Stay Modeling and Prediction
CRII:SCH:迈向智能患者流程管理:实时住院患者住院时间建模和预测
- 批准号:
2246158 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant
SCH: Dementia Early Detection for Under-represented Populations via Fair Multimodal Self-Supervised Learning
SCH:通过公平的多模式自我监督学习对代表性不足的人群进行痴呆症早期检测
- 批准号:
10816864 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
Collaborative Research: SCH: Improving Older Adults' Mobility and Gait Ability in Real-World Ambulation with a Smart Robotic Ankle-Foot Orthosis
合作研究:SCH:使用智能机器人踝足矫形器提高老年人在现实世界中的活动能力和步态能力
- 批准号:
2306660 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant
Collaborative Research: SCH: A wireless optoelectronic implant for closed-loop control of bi-hormone secretion from genetically modified islet organoid grafts
合作研究:SCH:一种无线光电植入物,用于闭环控制转基因胰岛类器官移植物的双激素分泌
- 批准号:
2306708 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant
Collaborative Research: SCH: AI-driven RFID Sensing for Smart Health Applications
合作研究:SCH:面向智能健康应用的人工智能驱动的 RFID 传感
- 批准号:
2306790 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant
SCH: Computer Vision Algorithms to Detect Tics In Patients with Tourette Syndrome
SCH:用于检测抽动秽语综合征患者抽动的计算机视觉算法
- 批准号:
10817272 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
SCH: A Novel Bias-mitigated Multimodal Oxygen Monitor
SCH:一种新型的消除偏差的多模式氧监测仪
- 批准号:
10816771 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
SCH: Artificial Intelligence enabled multi-modal sensor platform for at-home health monitoring of patients
SCH:人工智能支持的多模式传感器平台,用于患者的家庭健康监测
- 批准号:
10816667 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
SCH: Neonatal Facial Coding for Pain Recognition Monitoring System (PRAMS)
SCH:新生儿面部编码疼痛识别监测系统 (PRAMS)
- 批准号:
2205472 - 财政年份:2023
- 资助金额:
$ 16.87万 - 项目类别:
Standard Grant