| Abstrakt: |
Rapid urbanization needs major cities that change into smart cities to increase our lifestyle with respect to transportation, people, government, environmental sustainability, and more. In recent times, Internet of Things (IoT) and healthcare wearables have played a vital play in the progress of smart cities by providing enhanced healthcare services and an entire standard of living. Wearables offer real-time health records to individuals and healthcare providers, permitting for proactive management of chronic conditions and early recognition of health problems. While sleep is of major importance for a healthy life, it can be required to forecast sleep quality. Insufficient sleep affects mental health, physical, and emotional, and is a solution to many illnesses like heart disease, insulin resistance, stress, heart disease, and so on. Recently, deep learning (DL) techniques can be deployed to forecast the quality of sleep dependent upon the wearables data in the awake duration. Therefore, this paper presents an automated sleep quality recognition using hunger games search optimization with deep learning (ASQR-HGSODL) technique in the IoT-assisted smart healthcare system. The ASQR-HGSODL technique allows the IoT devices to perform a data collection process, which collects the data related to sleep activity. For the feature selection process, the ASQR-HGSODL technique applies an arithmetic optimization algorithm (AOA). For the prediction of sleep quality, the ASQR-HGSODL technique implements a convolutional long short-term memory (ConvLSTM) approach. Lastly, the HGSO technique has been applied for the optimum hyper parameter selection of the ConvLSTM approach. To exhibit the effectual prediction results of the ASQR-HGSODL approach, a range of simulation can be carried out. The investigational outputs highlight the improved outcome of the ASQR-HGSODL. technique with other DL methodologies. [ABSTRACT FROM AUTHOR] |
