VITAL-ECG : a de-bias algorithm embedded in a gender-immune device

被引:0
|
作者
Paviglianiti, Annunziata [1 ]
Pasero, Eros [1 ]
机构
[1] Politecn Torino, Dept Elect & Telecommun, Turin, Italy
关键词
arterial bloodpressure; ECG; electrocardiogram; fairness; gender bias; machine learning; plethysmogram; photo-plethysmogram; PPG; VITAL-ECG; HEART-DISEASE; RISK;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Artificial intelligence, sensors technology and sensors networks influence people behavior in everyday life. The diffusion of mobile devices, based on Internet of Things (IoT) paradigms, has created specific solutions for applications, in which physical objects are connected to Internet system. Wearable IoT (WIoT) represents a new IoT area, concerning detection, processing and communication capabilities in the field of healthcare. Vital-ECG is a smart device, related to health monitoring, which complies with gender equality. The wearable device takes the form of a smartwatch, which monitors heart activity and the most important vital parameters: blood oxygen saturation, skin temperature and fatigue level. Electrocardiogram and plethysmogram signals are acquired from Vital-ECG, which is able to track the blood pressure values, through a deep learning implementation. The neural algorithm has been implemented avoiding the "Gender Bias". The gender balance in machine learning, especially in biomedical application, is a crucial point to prevent algorithms from making a distorted prediction, disadvantaging women.
引用
收藏
页码:314 / 317
页数:4
相关论文
共 2 条
  • [1] Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model
    Amrhein, Chantal
    Schottmann, Florian
    Sennrich, Rico
    Laubli, Samuel
    PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, VOL 1, 2023, : 4486 - 4506
  • [2] Does AI De-Bias Recruitment?: Race, Gender and AI's 'Eradication of Differences Between Groups'
    Drage, Eleanor
    Mackereth, Kerry
    PROCEEDINGS OF THE 2022 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY, AIES 2022, 2022, : 237 - 237