Parvaneh Asghari

Amir Masoud Rahmani, Parisa Khoshvaght, Hamid Alinejad-Rokny et al.

Acute lymphoblastic leukemia (ALL) severity is determined by the presence and ratios of blast cells (abnormal white blood cells) in both bone marrow and peripheral blood. Manual diagnosis of this disease is a tedious and time-consuming operation, making it difficult for professionals to accurately examine blast cell characteristics. To address this difficulty, researchers use deep learning and machine learning. In this paper, a ResNet-based feature extractor is utilized to detect ALL, along with a variety of feature selectors and classifiers. To get the best results, a variety of transfer learning models, including the Resnet, VGG, EfficientNet, and DensNet families, are used as deep feature extractors. Following extraction, different feature selectors are used, including Genetic algorithm, PCA, ANOVA, Random Forest, Univariate, Mutual information, Lasso, XGB, Variance, and Binary ant colony. After feature qualification, a variety of classifiers are used, with MLP outperforming the others. The recommended technique is used to categorize ALL and HEM in the selected dataset which is C-NMC 2019. This technique got an impressive 90.71% accuracy and 95.76% sensitivity for the relevant classifications, and its metrics on this dataset outperformed others.

Behbod Keshavarzi, Hamidreza Navidi, Parvaneh Asghari et al.

The capacity and security of the confidential message on the channel are two important challenges in steganography. In this paper, a new block steganography model is presented using the bargain method so that a competitive model is introduced. In this game, the blocks are the same players. The bargain is provided with the aim of embedding information without reducing capacity as well as increasing security. The proposed model shows that it can be used both of the special domain and the transform domain, which are two important methods of steganography. For this purpose, an example of a special domain model is introduced in which, In the first step, the image is divided into $n \times n$ blocks, and in the second step using the graph coloring algorithm, pixels are considered to embed confidential information in each block. In the third step, regarding the bargaining method in game theory, each block plays the role of a player, that the competition between players is based on the defined goal function, and in the best blocks in terms of two criteria of capacity and security, which here means each block has a higher security-to-capacity ratio, so it has a higher priority, which is determined based on the bargaining model. Also, information embedded in LSB two bits. An example of a conversion domain method is also shows that security increases without decreasing in capacity. The conclusion is evaluated by three criteria: PSNR, histogram, and $ε-secure$ also, 2000 standard images were evaluated and observed that the proposed method improves the block methods of embedding information.

Parviz Gharehbagheri, Sayeed Hamid Haji Sayeed Javadi, Parvaneh Asghari et al.

This article shows that any type of binary data can be defined as a collection from codewords of variable length. This feature helps us to define an Injective and surjective function from the suggested codewords to the required codewords. Therefore, by replacing the new codewords, the binary data becomes another binary data regarding the intended goals. One of these goals is to reduce data size. It means that instead of the original codewords of each binary data, it replaced the Huffman codewords to reduce the data size. One of the features of this method is the result of positive compression for any type of binary data, that is, regardless of the size of the code table, the difference between the original data size and the data size after compression will be greater than or equal to zero. Another important and practical feature of this method is the use of symmetric codewords instead of the suggested codewords in order to create symmetry, reversibility and error resistance properties with two-way decoding.

Parvaneh Asghari, Seyyed Hamid Haj Seyyed Javadi

Security is one of the main issues in Internet of Things (IoT). Encryption plays a curtail role in making these systems secure. Substitution Box (S-Box) has an effective impact in block encryption methods. Due to the restricted resource capacities of IoT nodes, providing a lightweight S-Box is a challenging problem. This paper presents a key-dependent S-Box using Hyperelliptic curve. The proposed S-Box is analytically evaluated using performance criteria including bijection, nonlinearity, strict avalanche effect, and algebraic degree. The evaluation results endorse that the offered S-Box production algorithm is considerably an effective way to generate cryptographic strong S-Box.