• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    Proceedings of the ... IEEE Systems and Information Engineering Design Symposium

    Proceedings of the ... IEEE Systems and Information Engineering Design Symposium

    Conference

    年发文量

    研究主题

    论文(2)

    排序
    1Exploring Themes and Bias in Art Using Machine Learning Image Analysis.
    Sudeepti Surapaneni,Sana Syed, Logan Yoonhyuk Lee

    Machine learning and computer vision have been applied for image recognition of art objects such as paintings, sculpture images etc. In particular, deep learning methods for image classification in art have been used to improve user engagement by providing access to accurately labelled and classified art objects. As an increasing number of notable museums turn towards creating open access collections, alternatives to the use of laborious human annotating methods are needed. This paper focuses on the Open Access initiative of The Metropolitan Museum of Art (The Met) which was launched in 2017 in an effort to expand The Met's reach and presence. The museum now provides a select dataset of information on more than 470,000 artworks in its collection for unrestricted commercial and noncommercial use. However, with a widely accessible collection, the Met now faces the problem of how to enhance the user experience via access to accurately labelled art. This paper focuses on machine learning methods with applicability to automated classification of images obtained from The Met's online collection. We aimed to: 1) Compare three different convolutional neural networks ResNet 50, ResNet 101, and Inception-ResNet-V2 using human annotated data, 2) Add transparency and interpretability to our models by using Gradient-weighted Class Activation Maps (Grad-CAMs) and to explore bias in gender labels and 3) Implement a multi-label classification model using ResNet 50. Future work would include the use of unsupervised clustering methods/auto-encoders to explore additional themes in the data. Other extensions of this work would include exploring methods to implement fine grained visual categorization, to mitigate bias, and to address the limitations associated with culture and stylistic interpretations. Deep learning techniques for art image classification may also help detect consistent features of bias in human annotated art.

    2020引用:19
    引用
    AI阅读
    加入学术空间
    2Design of Interactive Cancer Education Technology for Latina Farmworkers
    Ying Wu,Devan Samant,Kristen Squibbs,Alexis Chaet,Bijan Morshedi,Laura E. Barnes

    Latinas in the United States experience higher levels of cervical cancer (CC) incidence and mortality rates than the general population, and many lack access to healthcare or face communication, literacy, and knowledge barriers preventing proper CC screening. Interactive technological interventions, like embodied conversational agents (ECA)/virtual agents, are currently used in other populations, settings, and for other health topics, however, no known initiative has used culturally- and literacy-appropriate technological interventions to deliver Spanish-language CC education. This study aims to create a culturally tailored Spanish-language Virtual Patient Educator (VPE) application to augment a patient navigator (PN) intervention for increasing CC screening rates among Hispanic women in a rural agricultural community. The VPE is a computer character that can simulate face-to-face conversation with an actual person and will embody the characteristics of a PN. Through iterative interviews with the target population, key cultural design factors were identified to inform the design and implementation of a prototype VPE. This paper discusses design and usability issues associated with development of the VPE for low-literacy users in addition to a framework methodology for development of similar tools and a cultural matrix of design factors. A VPE might help close the knowledge gap between Hispanic women and the general population regarding cervical cancer screening. Incorporation of culturally tailored features in technology aids in increasing overall understanding and trust of health information presented. An iterative approach that engages the patient population in design of technology is important to identify population-specific patient preferences.

    2014引用:6
    引用
    AI阅读
    加入学术空间

    高被引作者

    作者引用发文
    Sana Syed191
    Laura Barnes61
    Samant, D.61
    Bijan Morshedi61
    Squibbs, K.61
    Alexis Chaet61
    Ying Wu61

    高产作者

    作者引用发文
    Alexis Chaet61
    Laura Barnes61
    Sana Syed191
    Samant, D.61
    Bijan Morshedi61
    Ying Wu61
    Squibbs, K.61

    相关期刊

    International Journal of Big Data Intelligence
    Journal of Digital Information Management
    Euro American Conference on Telematics and Information Systems
    European Intelligence and Security Informatics Conference
    Innovative Mobile and Internet Services in Ubiquitous Computing
    International Symposium on Independent Computing
    International Journal of Computer Science and Information Technology
    International Journal of Computer and Communication Engineering
    Journal of Advances in Computer Networks
    International Conference on Science in Information Technology