As the COVID-19 pandemic rapidly spreads across the world, regrettably, misinformation and fake news related to COVID-19 have also spread remarkably. Such misinformation has confused people. To be able to detect such COVID-19 misinformation, an effective detection method should be applied to obtain more accurate information. This will help people and researchers easily differentiate between true and fake news. The objective of this research was to introduce an enhanced evolutionary detection approach to obtain better results compared with the previous approaches. The proposed approach aimed to reduce the number of symmetrical features and obtain a high accuracy after implementing three wrapper feature selections for evolutionary classifications using particle swarm optimization (PSO), the genetic algorithm (GA), and the salp swarm algorithm (SSA). The experiments were conducted on one of the popular datasets called the Koirala dataset. Based on the obtained prediction results, the proposed model revealed an optimistic and superior predictability performance with a high accuracy (75.4%) and reduced the number of features to 303. In addition, by comparison with other state-of-the-art classifiers, our results showed that the proposed detection method with the genetic algorithm model outperformed other classifiers in the accuracy.
Due to the availability of several social media platforms and their use in sending text messages, it is necessary to provide an easy and safe way to protect messages from being hacked especially in the presence of intruders and data thieves, and taking into consideration that most of those messages are confidential and personal, it is necessary to provide an easy and safe way to protect messages from being hacked. In this research paper, a simple and easy method of message cryptography will be proposed. The method divides a message into blocks with fixed sizes. The block size ranges from 2 to 60. The method uses a secret color image to generate an array with a size equal to the number of resulted blocks. The array will then be used as a private key. Each element of the private key will be used to calculate the number of rotation digits for the associated block in order to apply block rotation left operation. The proposed method will be examined using the parameter's Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Correlation Coefficient (CC), and throughput. The proposed method will be compared with other standard methods of message cryptography, such as Data Encryption Standard (DES), Triple-DES (3DES), Advanced Encryption Standard (AES), and Blow Fish (BF). Experimental results show that the proposed method is secured enough based on using secret image, block size, and calculated Rotation Left Digits (RLD) for each block.
Colored digital images are one of the most important types of digital data to be used in many vital applications, which require a safe way to protect them from hacking operations and the danger of intruders and data thieves. This paper presents an effective and safe method for storing digital colored images (CASDC). A high level of protection is provided through a complex secret key agreed upon between the sender and the receiver. The secret key consists of nine decimal digits (and can be increased as needed). These digits are processed to extract three values for each color of the three color channels. A left rotation process is performed for the value of each color to produce three new values, where an exclusion process is performed between them to obtain the encrypted value for the color. CASDC is evaluated against a wide range of images to calculate its throughput to show the extent to which this method fulfills encryption and decryption requirements. The Mean Square Error (MSE) values, Peak Signal to Noise Ratio (PSNR), and Correlation Coefficient for the three primary channels of the RGB coloring system were analyzed. The practical results of the proposed method are compared with other standard methods such as Data Encryption Standard (DES), Tripple-DES (3DES), Advanced Encryption Standard (AES), and Blow Fish (BF). According to the obtained results, CASDC outperforms all standard methods in terms of efficiency by reducing the time of encryption and decryption and increasing the throughput of the corresponding process. Besides, CASDC is robust against breaks, as the attempts to break the private key will require hundreds of years in the best case.
Abstract-Inter-requirements traceability refers to finding the relationships between requirements. Several approaches have been identified cooperative, conflicting, and irrelevant relationships between requirements. However, the current solutions have a lack of capturing the syntactic and semantic aspects of requirements, and less attention has been paid to relating security requirements with functional requirements.To overcome these limitations, we propose to use a domain ontology based approach, in which a domain ontology can be used as a domain knowledge to discover relationships between requirements. Our proposed solution is a hybrid approach which uses: 1) a syntactic parsing technique to decompose the requirements statements into Subject, Verb, and Complement constructs, 2) a domain ontology to create a knowledge repository about security and functional requirements concepts, and 3) a rule based system to build several detection rules that identify security requirements effects upon functional requirements. We evaluate our approach in a case study of requirements for an online medical database system that shows how the effect types can be determined.
Software defect prediction enables software developers to estimate the most defective code parts in order to reduce testing efforts. As the size of software project becomes larger, software defect prediction becomes an urgent need. While static product metrics have been extensively investi gated as a static means to predict software defects, coverage analysis of the software has been abandoned due to the expected complexities. This paper proposed a novel hybrid approach that leverages code coverage metrics to improve software defect prediction. We build and compare software defect prediction results for four distinct scenarios: static product, code coverage, hybrid, and feature selection. First scenario resembles static analysis and acts as baseline model. Second scenario addresses coverage issues of the associated test cases for the source code. Third and fourth scenarios are derived from combinations of stati c product and code coverage scenarios. Each scenario has been modeled and examined using thirteen different machine learning classifiers. Two rounds of experiments have been done. First round employs real data extracted from 23 successive releases of Apache Lucene, whereas second round applies oversampling technique for the same releases. The results indicate that code coverage scenario a ttains a significant improvement in software defect prediction, especially when there is a high-coverage ratio for software modules. In general, hybrid scenario outperforms the other three scenarios. Naive Bayes classifier attains the best results among all classifiers at the first round, while IBK performs well for the second round. The second round experiment exhibits a superior performance compared to the first round because it approaches two times better recall. Further, we notice a steady improvement in the latest releases of Apache Lucene project compared to the earlier ones.
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.