Study Objectives: Sleep loss can cause cognitive impairments that increase the risk of mistakes and accidents. However, existing guidelines to counteract the effects of sleep loss are generic and are not designed to address individual-specific conditions, leading to suboptimal alertness levels. Here, we developed an optimization algorithm that automatically identifies sleep schedules and caffeine-dosing strategies to minimize alertness impairment due to sleep loss for desired times of the day.
Methods: We combined our previous algorithms that separately optimize sleep or caffeine to simultaneously identify the best sleep schedules and caffeine doses that minimize alertness impairment at desired times. The optimization algorithm uses the predictions of the well-validated Unified Model of Performance to estimate the effectiveness and physiological feasibility of a large number of possible solutions and identify the best one. To assess the optimization algorithm, we used it to identify the best sleep schedules and caffeine-dosing strategies for four studies that exemplify common sleep-loss conditions and compared the predicted alertness-impairment reduction achieved by using the algorithm's recommendations against that achieved by following the U.S. Army caffeine guidelines.
Results: Compared to the alertness-impairment levels in the original studies, the algorithm's recommendations reduced alertness impairment on average by 63%, an improvement of 24 percentage points over the U.S. Army caffeine guidelines.
Conclusions: We provide an optimization algorithm that simultaneously identifies effective and safe sleep schedules and caffeine-dosing strategies to minimize alertness impairment at user-specified times.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1093/sleep/zsae133 | DOI Listing |
Sci Rep
January 2025
Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, 80-233, Gdansk, Poland.
Computational tools, particularly electromagnetic (EM) solvers, are now commonplace in antenna design. While ensuring reliability, EM simulations are time-consuming, leading to high costs associated with EM-driven procedures like parametric optimization or statistical design. Various techniques have been developed to address this issue, with surrogate modeling methods garnering particular attention due to their potential advantages.
View Article and Find Full Text PDFSci Rep
January 2025
Department of Communication Engineering, School of Electronics Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, 632014, India.
The detection of exons is an important area of research in genomic sequence analysis. Many signal-processing methods have been established successfully for detecting the exons based on their periodicity property. However, some improvement is still required to increase the identification accuracy of exons.
View Article and Find Full Text PDFSci Rep
January 2025
Department of Networks and Cybersecurity, Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman, Jordan.
Diabetic retinopathy stands as a leading cause of blindness among people. Manual examination of DR images is labor-intensive and prone to error. Existing methods to detect this disease often rely on handcrafted features which limit the adaptability and classification accuracy.
View Article and Find Full Text PDFSci Rep
January 2025
Nanoelectronics Integrated Systems Center (NISC), Nile University, Giza, 12677, Egypt.
Due to its enormous influence on system functionality, researchers are presently looking into the issue of task scheduling on multiprocessors. Establishing the most advantageous schedules is often regarded as a difficult-to-compute issue. Genetic Algorithm is a recent tool employed by researchers to optimize scheduling tasks and boost performance, although this field of research is yet mostly unexplored.
View Article and Find Full Text PDFThe classification of chronic diseases has long been a prominent research focus in the field of public health, with widespread application of machine learning algorithms. Diabetes is one of the chronic diseases with a high prevalence worldwide and is considered a disease in its own right. Given the widespread nature of this chronic condition, numerous researchers are striving to develop robust machine learning algorithms for accurate classification.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!