Revolutionizing Sleep Research: University of Houston Unveils New At-Home Sleep Study Method
- Written by Kiara Fabbri Former Tech News Writer
- Fact-Checked by Justyn Newman Former Lead Cybersecurity Editor
The University of Houston engineers has just published a new sleep study technique that utilizes a single-lead electrocardiogram (ECG) and deep learning, potentially replacing the traditional sleep lab experience.
Traditionally, polysomnography is currently the primary method for studying sleep patterns. This method involves multiple cables and sensors attached to the body, monitoring brain activity, heart rate, and other vital signs. This setup often makes it difficult for patients to sleep naturally. Sheth and Jones’s new method utilizes a single-lead electrocardiography-based deep learning neural network, drastically simplifying the process.
Empowered by AI deep learning, this simple method holds the promise as a convenient at-home sleep study solution. This means that the technology can collect and analyze vast amounts of data, revolutionizing sleep monitoring.
Commercial devices( like Apple Watch, Fitbit, and Oura Ring track sleep) have a lower accuracy than polysomnography.The new ‘at-home’ method bridges the gap, offering high-quality sleep analysis outside clinical settings. Accessible testing could increase sleep research data.
The implications of this development are significant for both sleep medicine and neuroscience research. Reliable classification of sleep stages is crucial for diagnosing and understanding various sleep disorders and brain states. Adam Jones emphasized the potential reach of their innovation: “It makes less-expensive, higher-quality studies accessible to a broader community, enabling improved sleep research and more personalized, accessible sleep-related healthcare interventions.”
The researchers have made the complete source code for their model freely available, encouraging further development and refinement.
10 AI-Created Avatars Compete as Beauty Pageants
- Written by Kiara Fabbri Former Tech News Writer
- Fact-Checked by Justyn Newman Former Lead Cybersecurity Editor
Organized by the World AI Creators Awards (WAICAS), the Miss AI pageant features 10 finalists created by artists around the globe. These artists used advanced AI programs ( like DALL-E, Midjourney, or Stable Diffusion) to generate images of women.The winner will be announced on July 8th and will receive a $5,000 cash prize along with public relations support. The contestants are judged on three criteria: aesthetics, technical skill used in creation, and online influence.
For example, Kenza Layli , who has almost 200,000 followers, was noted for “contributing to the empowerment of women in Morocco and the Middle East.” Olivia C from Portugal, is a “traveler” showcasing how technology can “enhance the human experience, not replace it.” Meanwhile, Aiyana Rainbow has been shortlisted for representing a message of inclusivity, showcasing LGBTQIA+ pride.
Despite these claims, a 2024 research paper casts a shadow on these seemingly progressive concepts. The researchers warn that AI models used to generate images can perpetuate unrealistic beauty standards and gender biases. The study found that these models tend to depict women in stereotypical ways, both in terms of appearance and profession.
In response to criticisms on this subject, in an email to TIME WAICAS team emphasized their focus on “celebrating diversity and realism.” They stated, “This isn’t about pushing unrealistic standards, but realistic creators that represent real people. Traditional pageantry took decades to evolve and be more representative—whilst AI can do this in fast forward which is really exciting”.
Whether AI-generated beauty pageants signal the future of the industry remains to be seen. However, the Miss AI pageant undeniably marks a turning point, raising questions about beauty standards and the role of AI in creative fields.
