The aim of this study to propose a model based on Machine Learning (ML) and Internet of Things (IoT) to diagnose patients with COVID-19 in smart hospitals. In this sense, it was emphasized that by the representation for the role of ML models and IoT relevant technologies in smart hospital environment. The accuracy rate of diagnosis (classification) based on laboratory findings can be improved via light ML models. Three ML models, namely, Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM), were trained and tested on the basis of laboratory datasets. Three main methodological scenarios of COVID-19 diagnoses, such as diagnoses based on original and normalized datasets and those based on feature selection, were presented. Compared with benchmark studies, our proposed SVM model obtained the most substantial diagnosis performance (up to 95%). The proposed model based on ML and IoT can be serve as a clinical decision support system. Furthermore, the outcomes could reduce the workload for doctors, tackle the issue of patient overcrowding, and reduce mortality rate during the COVID-19 pandemic.
Modern optimisation is increasingly relying on meta-heuristic methods. This study presents a new meta-heuristic optimisation algorithm called Eurasian oystercatcher optimiser (EOO). The EOO algorithm mimics food behaviour of Eurasian oystercatcher (EO) in searching for mussels. In EOO, each bird (solution) in the population acts as a search agent. The EO changes the candidate mussel according to the best solutions to finally eat the best mussel (optimal result). A balance must be achieved among the size, calories, and energy of mussels. The proposed algorithm is benchmarked on 58 test functions of three phases (unimodal, multimodal, and fixed-diminution multimodal) and compared with several important algorithms as follows: particle swarm optimiser, grey wolf optimiser, biogeography based optimisation, gravitational search algorithm, and artificial bee colony. Finally, the results of the test functions prove that the proposed algorithm is able to provide very competitive results in terms of improved exploration and exploitation balances and local optima avoidance.
One of the most common problem in the design of robotic technology is the path planning. The challenge is choosing the robotics' path from source to destination with minimum cost. Meta-heuristic algorithms are popular tools used in a search process to get optimal solution. In this paper, we used Crow Swarm Optimization (CSO) to overcome the problem of choosing the optimal path without collision. The results of CSO compared with two meta-heuristic algorithms: PSO and ACO in addition to a hybrid method between these algorithms. The comparison process illustrates that the CSO better than PSO and ACO in path planning, but compared to hybrid method CSO was better whenever the smallest population. Consequently, the importance of research lies in finding a new method to use a new metahumanistic algorithm to solve the problem of robotic path planning.
In the age of the Internet, a lot of images are circulated among users, and some of these images contain financial or personal information that requires confidentiality. Encryption algorithms existed for a long time, and the data used was focused on the text data, while the multimedia data was neglected for a long time. In addition, there are significant shortcomings in 3D image coding techniques. This paper proposed a method for image encrypted and decrypted electronically using the Lorenz chaotic system, the supposed algorithm was developed by using the three equations of the Lorenz system, before that, the image pixels are destroyed using reversible shifting and rotating processes to increase the randomness of the encrypted pixels and thus the difficulty of cracking the cipher. Then he supposed technique gave the following results: The average entropy calculation was (7.285) before image encryption and (7.9974) after image encryption with an average NPCR of (99.65%) and UACI was (30.35%) this confirms that the proposed method is reliable and applicable. Moreover, the suggested technique gives the best outcomes when compared to other similar works.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.