Volume 3 Issue 4
Authors: F. Mokhatab Rafiei; S.M. Manzari; M. Khashei
Abstract: Corporate credit rating analysis is one of the most important financial problems, which has attracted lots of research interests in the literature. Recent studies have shown that Artificial Intelligence (AI) methods can achieve better performance than traditional statistical methods. In this paper, Multilayer Perceptrons (MLPs) and multiple statistics methods are used to carry out multi-class credit rating of listed corporations in Tehran Stock Exchange (TSE). To accomplish this goal, a sample of these corporations is randomly selected and financial ratios as independent variables are computed for them. Dependent variable is a discrete variable of four groups as the corporation's bond ratings. The sample is split into training set and test set. With training set sample, the model is constructed through Multiple Discriminant Analysis, and with the remaining, hold out sample of corporations, the model is evaluated. Financial ratios for 126 manufacturing companies quoted in TSE have been used. Two models based on artificial neural networks and multiple discriminant analysis (MDA) are utilized to bond rating of corporations. ANN model achieved 81% and 68% accuracy rates in training and holdout samples, respectively. To evaluate the reliability of the model, the data were examined with multivariate discriminate analysis method. MDA reached 65.3% correct classifications of total initial sample. Results indicate that financial characteristics of corporations are good criterion for their bond rating and the same variables as other countries are significant in Iran too.
Keywords: Multiclass Credit Rating; Financial Ratios; Artificial Neural Networks; Principal Component Analysis; Multiple Discriminant Analysis
Authors: Faramarz Sadeghi; Marjan Kuchaki Rafsanjani; Fatemeh Zarisfi Kermani
Abstract: In this study a new method has been presented in order to hide secret information on host image, in a way that the image has been steganographed and has minimum difference to host image and is based on least significant bit (LSB). As security and quality are two main factors in evaluating steganography operation and LSB is a common method and is vulnerable against attacks and noises, researchers have set their priority on finding a substitution matrix in order to improve these two important factors and increase the system's efficiency. In this article, in order to find an optimal substitution matrix, a compound meta-heuristic method has been suggested which uses two optimization algorithms: Particle Swarm Optimization and simulated annealing. Results of simulation with two optimization algorithms PSO and SA and compound meta-heuristic algorithm PSO-SA have been comprised according to PSNR value and show that the stego-image produced by PSO-SA has more quality in comparison with other existing methods.
Keywords: Steganography; LSB Substitution Matrix; Particle Swarm Optimization Algorithm; Simulated Annealing Algorithm
Authors: V. Gayoso Martinez; L. Hernandez Encinas
Abstract: Elliptic Curve Cryptography is one of the best options for protecting sensitive information. The lastest version of the Java platform includes a cryptographic provider, named SunEC, that implements some elliptic curve operations and protocols. However, potential users of this provider are limited by the lack of information available. In this work, we present an extensive review of the SunEC provider and, in addition to that, we offer to the reader the complete code of three applications that will allow programmers to generate key pairs, perform key exchanges, and produce digital signatures with elliptic curves in Java.
Keywords: Elliptic Curves; Information Security; Java; Public Key Cryptography