Search

In recent years, with the widespread use of digital technology and intelligent gadgets, an enormous amount of data are being generated at an alarmingly rapid rate. The quickly growing technologies and data generated by mobile and Internet of Things devices are tremendous. These data can be used to achieve sleep deprivation in users using machine learning. Multi-modal sensors and technology to detect activity, sleep, and circadian rhythms have become increasingly widespread. For the first time, large-scale sleep tracking is conceivable. In addition to large-scale epidemiological research, multi-sensor data can be used for wellness applications such as sleep coaching for chronic disease patients. Individuals, health, and research must overcome several fundamental obstacles before new technologies may ultimately benefit. We examine existing sleep-monitoring technology from data gathering through mobile data sensors to machine learning mode. We also analyze the current and emerging sensing technologies. [Display omitted] • An early alert of sleep deprivation using mobile sensor data to monitor sleep deprivation. • The Deep neural network model is developed to accumulate sensor fusion. • The categorization of sleep situations has been shown based on user data and learning. • Our model can provide monitoring throughout the night. [ABSTRACT FROM AUTHOR]

To ensure reliable Internet of Things (IoT) applications, this study provides a new intelligent deployment technique for sensor nodes. The proposed intelligent deployment technique places sensor nodes in appropriate locations to achieve high levels of connectivity and, as a result, boost the WSN's overall reliability. To generate optimal sensor node coordinate positions, a modified version of the Expectation–Maximization method is utilized as a machine learning technique. Following that, each node's neighbours are determined, and links between them are built using the K-Nearest neighbour algorithm. Then, to assess the reliability of WSN, a novel algorithm is proposed. The proposed algorithms are all well-illustrated with appropriate examples. When the algorithms provided in this research are compared to certain existing methods in terms of node positioning accuracy (10%), network connectivity (10%), and estimated dependability values (5%), it is clear that the suggested strategy outperforms them in every way. [Display omitted] • Using Modified EM algorithm to generate optimal positions of sensors of WSNs. • A new algorithm based on node disjoint minimal path to evaluate reliability of WSNs. • Positioning accuracy, connectivity, and reliability were increased significantly. • Assess the impact of transmission range and time on values of reliability of WSNs. [ABSTRACT FROM AUTHOR]