In our everyday lives, the IoT is everywhere. They are used for the monitoring and documentation of environmental improvements, fire safety and even other useful roles in our homes, hospitals and the outdoors. IoT-enabled devices that are linked to the internet transmit and receive a large amount of essential data over the network. This provides an opportunity for attackers to infiltrate IoT networks and obtain sensitive data. However, the risk of a loss of privacy and security could outweigh any of these benefits. Many tests have been carried out in order to solve these concerns and find a safer way to minimize or remove the effect of IoT technologies on privacy and security practices in order to protect them. The issue with IoT devices is that they have small output modules, making it impossible to adapt current protection methods to them. This constraint necessitates the presentation of lightweight algorithms that enable IoT devices. In this article, investigated the context and identify different safety, protection, and approaches for securing components of IoT-based ecosystems and systems, as well as evolving security solutions. In addition, several proposed algorithms and authentication methods in IoT were discussed in order to avoid various types of attacks while keeping the limitations of the IoT framework in mind. Also discuss some hardware security in IoT devices.
Recently, emotion analysis has become widely used. Therefore, increasing the accuracy of existing methods has become a challenge for researchers. The proposed method in this paper is a hybrid model to improve the accuracy of emotion analysis; Which uses a combination of convolutional neural network and ensemble learning. In the proposed method, after receiving the dataset, the data is pre-processed and converted into process able samples. Then the new dataset is split into two categories of training and test. The proposed model is a structure for machine learning in the form of ensemble learning. It contains blocks consisting of a combination of convolutional networks and basic classification algorithms. In each convolutional network, the base classification algorithms replace the fully connected layer. Evaluate the proposed method, in IMDB, PL04 and SemEval dataset with accuracy, precision, recall and F1 criteria, shows that, on average, for all three datasets, the precision of polarity detection is 90%, the recall of polarity detection is 93%, the F1 of polarity detection is 91% and finally the accuracy of polarity detection is 92%.
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.