Hasan Abdul hussein Ahmed Alshishtarli

We continue to develop our algorithms, initially designed for image encryption, to ensure they are also valid for text encryption. This is a challenging task because text encoding does not tolerate any errors, unlike image encryption, where minor numerical inaccuracies may be acceptable. The numerical values of text components must be retrieved accurately. In this study, we build upon our previous algorithm (MK-11), which used Generalized Singular Value Decomposition (GSVD) technology combined with a logistic function for image encryption with a real-number encryption key. We introduce a new algorithm that relies solely on the logistic function, employing a method of dispersal and retrieval of numerical values to encrypt text effectively. We assess the quality of this new algorithm by applying it to various text samples, as we did with our previous algorithm (MKTEXT-5). Our algorithm operates in two main steps: First, we convert the text to be encrypted into a vector of numerical values, using the ASCII values corresponding to the letters and symbols stored in the computer. Second, we disperse the numerical values of this vector using the encryption key (a real number) and the logistic function. The results we obtained are excellent and error-free, outperforming our previous algorithms in terms of quality, speed, and accuracy. We reaffirm that these algorithms are suitable for use in various fields, such as information security in banks, universities, and public and private institutions. We will detail the algorithm, results, and related readings in the subsequent sections of our research

This research presents a high-performance AI framework for intelligent internal audit automation, integrating deep learning, semantic policy embeddings, and reinforcement-driven risk optimization. Leveraging fine-tuned transformer models and structured enterprise datasets, the system was evaluated across diverse audit domains including financial transactions, procurement logs, HR records, and vendor management data. The model consistently achieved detection accuracies exceeding 98.53%, with F1-scores reaching 0.94 and compliance alignment scores up to 0.94. Compared to traditional rule-based methods, the enhanced framework reduced control oversight errors by over 25% and significantly improved interpretability through SHAP-based explanations and anomaly heatmaps. The integration of contextual text embeddings, numerical audit features, and dynamic control evaluation enabled transaction-level compliance analysis and proactive risk detection. Unlike resource-intensive neural pipelines, the model maintained sub-2 second training cycles, ensuring deployment feasibility within ERP-integrated enterprise systems. The architecture supports cross-platform generalization and is extensible to various operational domains without requiring structural reengineering.

In the present paper, Medical Image Verification using statistical factors and back propagation Neural Network is proposed. Database consists of 200 images (100 image for satisfactory skin cancer, 100 image for unsatisfactory skin), types for image .jpg , .png and .bmp image formats. Database prepared in our conditions. Indeed the images obtained (50 image for satisfactory skin cancer, 50 image for unsatisfactory skin), other images obtained from internet (50 image for satisfactory skin cancer, 50 image for unsatisfactory skin). Testing stage consists of 80 images (20 image for satisfactory skin cancer, 20 image for unsatisfactory skin cancer) from in Al-Seder Hospital and (20 image for satisfactory skin cancer, 20 image for unsatisfactory skin cancer) from internet. The experiment results confirm the effectiveness of the proposed algorithm

The two teachers from the College of Computer Science and Mathematics at the University of Kufa, Dr. Adel Al-Ramahi and Dr. Hind Rustom, and the graduate student researcher Hassan Abdel-Hussein, are participating in a joint scientific research in the work of the International Conference on Medical Imaging, which is to be held in the US state of Las Vegas during next June. Al-Ramahi stated that the research deals with a new algorithm for diagnosing cancer diseases by Through the statistical parameters of medical images within the algorithm of artificial neural networks, he indicated that the research will be published within the IEEE International Foundation.