Scholarlink

<p>The convergence of Artificial Intelligence (AI), Machine Learning (ML), and Internet of Things (IoT) technologies has revolutionized unobtrusive mental health monitoring by leveraging sensor-generated time series data. However, the complexity and subjectivity inherent in labeling this data render self-supervised machine learning frameworks particularly well-suited for its analysis. In this context, quantum machine learning has emerged as a powerful tool for processing large-scale, high-dimensional time series data with intricate patterns, effectively overcoming the computational limitations of traditional methods. This work introduces a novel quantum self-supervised relational reasoning framework that enhances a learner’s ability to extract meaningful insights from unlabeled time series data through temporal relational learning. By integrating quantum gates into a long short-term memory (LSTM) model, our approach significantly improves relational reasoning and representation efficiency. Furthermore, quantum transfer learning is employed to fine-tune the model on a labeled dataset, resulting in an F1-score of 0.89 on the Wesad-HRV (heart rate variability) dataset, as validated by a paired t-test at a 95% confidence level. These results highlight the framework’s superior predictive power compared to conventional models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Self-supervised quantum relational reasoning (S2QR2) of time series data for mental health monitoring

  • 期刊论文

  • 发表日期：

    2025年4月23日

查看全文
  • Anupama Padha,
  • Anita Sahoo

摘要

The convergence of Artificial Intelligence (AI), Machine Learning (ML), and Internet of Things (IoT) technologies has revolutionized unobtrusive mental health monitoring by leveraging sensor-generated time series data. However, the complexity and subjectivity inherent in labeling this data render self-supervised machine learning frameworks particularly well-suited for its analysis. In this context, quantum machine learning has emerged as a powerful tool for processing large-scale, high-dimensional time series data with intricate patterns, effectively overcoming the computational limitations of traditional methods. This work introduces a novel quantum self-supervised relational reasoning framework that enhances a learner’s ability to extract meaningful insights from unlabeled time series data through temporal relational learning. By integrating quantum gates into a long short-term memory (LSTM) model, our approach significantly improves relational reasoning and representation efficiency. Furthermore, quantum transfer learning is employed to fine-tune the model on a labeled dataset, resulting in an F1-score of 0.89 on the Wesad-HRV (heart rate variability) dataset, as validated by a paired t-test at a 95% confidence level. These results highlight the framework’s superior predictive power compared to conventional models.