Twitter social media data generally uses ambiguous text that can cause difficulty in identifying positive or negative sentiments. There are more than one billion social media messages that need to be stored in a proper database and processed correctly to analyze them. In this paper, an ensemble majority vote classifier to enhance sentiment classification performance and accuracy is proposed. The proposed classification model is combined with four classifiers, using varying techniques—naive Bayes, decision trees, multilayer perceptron and logistic regression—to form a single ensemble classifier. In addition to these, a comparison is drawn among the four classifiers to evaluate the performance of the individual classifiers. The result shows that in terms of an individual classifier, the naive Bayes classifier is optimal as compared to the others. However, for comparing the proposed ensemble majority vote classifier with the four individual classifiers, the result illustrates that the performance of the proposed classifier is better than the independent one.
<span>In several aspects, interest in IoT has become considerable by researchers and academics in recent years. Data security becomes one of the important challenges facing development of IoT environment. Many algorithms were proposed to secure the IoT applications. The traditional public key cryptographic are inappropriate because it requires high computational. Therefore, lattice-based public-key cryptosystem (LB-PKC) is a favorable technique for IoT security. NTRU is one of a LB-PKC that based on truncated polynomial ring, it has good features, which make it to be an effective alternative to the RSA and ECC algorithms. But, there is LLL algorithm can success to attack it under certain conditions. This paper proposes modifications to NTRU public key cryptosystem to be secure against the lattice-based attack by using LLL algorithm, as well as a method for generating a new keys sequence dynamically. The results from simulations show that the performance of these modifications gives more secure from NTRU. </span>
The color images are used widely as a cover in hiding of the information. Since the variety of applications of the color image there are several color models of color image. Most color models consist of three layers. The nature of the color mode of the cover plays a main role in determining the robustness and security of hiding algorithm.
The objective of this paper tests the layers, components, of the color models of cover color images, to figure out which color layer of each color model is best (less affected) to use as a cover to hide information within each color model in the hiding process. The experiments concentrate on the hiding texts in two positions of each layer, 7th bits and 8th bits (LSB). Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR) were used to measure the affected of hidden text in layers. The tests were done on nine colors models: RGB, HSV, HIS, HSL, HSB, YCbCr, La*b*, LUV and CMYK.
The results show that some of color models have best layer to hide text such as YCbCr, HSI, CMYK, HSL and LUV . In other color models which have been tested, there is not a distinctive layer. The layer H is the worst because any hiding leaves a clear impact on the cover image.
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.