Arman Process Journal (APJ)

Abstract Background and Objectives: Multiple sclerosis is a brain disease where early diagnosis is crucial for treatment. One of the ways to diagnose this disease is by observing lesions caused by it in MRI scans. Most previous approaches have issues such as low diagnostic accuracy, a high number of features, time-consuming analysis, and a lack of certainty in achieving optimal answers.
Methods: In this article, for the first time, a feature vector set is formed by aggregating results from image MRI texture descriptors such as wavelet transform, chaotic features (fractal), and local binary patterns. The presentation of a selected feature set using a differential evolutionary algorithm has not been utilized in this area of identification before, so our proposed technique is based on this approach. Additionally, the proposed classifier will be an improved model combining three types of neural networks. Moreover, improvements in accuracy, sensitivity, and the ability to verify the correctness of the classification results are also considered innovative aspects.
Findings: The data used in this article was obtained from two datasets. After K-fold cross-validation, the experimental accuracy for both image datasets were found to be 95% and 97%, respectively, which represents a 2% improvement over a method that used wavelet transform along with principal component analysis and support vector machines, while also addressing the uncertainty issue.
Conclusion: Our integrated algorithm introduced greater diagnostic accuracy compared to previous methods and takes into account the accuracy factor that was not considered in past approaches. This algorithm not only reduces processing time but also enables simultaneous processing from different channels, aligning better with the opinions of specialized doctors. Despite the lack of a simultaneous separation-processing technique, the rates of false positives and negatives in identifying MS disease are very low. For future work, recommendations include noise removal in the preprocessing stage, combining feature selection techniques to increase accuracy, and using parallel processing as the primary tool in separation software.

Abstract Central Bank Digital Currencies (CBDCs) represent a new generation of digital money, created and supported under the authority of central banks. This cutting-edge technology, with its potential to bring transformative changes to traditional payment infrastructures and to revolutionize global payment systems, has captured the attention of researchers and financial industry professionals alike.

This study examines the challenges and opportunities associated with CBDCs during the 2018–2024 period. To this end, a systematic search was conducted across eight reputable academic databases, resulting in the identification of 62 relevant articles. After applying screening criteria, 53 articles were selected for final analysis and for the development of this review paper.

An analysis of these articles reveals a significant increase in interest in CBDCs in recent years. Central banks around the globe are actively exploring or piloting their own digital currency projects. The potential benefits of CBDCs include enhanced efficiency and inclusivity in payments, strengthened financial stability, and innovation in financial services. However, challenges such as privacy concerns, cybersecurity risks, and the potential for misuse also persist. Consequently, further research and comprehensive regulatory frameworks are essential to fully understand and manage the benefits and risks of CBDCs.

Abstract In this article, a method is proposed for diagnosing children with Attention Deficit Hyperactivity Disorder (ADHD) using deep learning concepts and analyzing the correlation between segmented areas of functional brain images. The proposed method includes preprocessing medical images to remove distorted, noisy, incomplete, and problematic images, generating new functional brain images using autoencoders, which are applicable in artificial intelligence and deep learning, to assist in better analysis of medical images and address the limitations of medical image availability. It also involves segmenting images and creating separate networks to enhance the diagnostic accuracy of the condition and calculate the correlation between regions, ultimately leading to an effective diagnosis of ADHD in children. The conclusion of this study indicates that this combined method has a high capability for timely and accurate diagnosis of this condition in children and can serve as an effective tool in the field of child neurology and psychiatry.

Abstract Distributed operating systems are a very important part of the software design and implementation work for managing systems with a large number of processors. On the other hand, research in the areas of computer science research on distributed systems has increased significantly in the past few decades. One of the topics discussed in such operating systems is the discussion of resource management through process management. For process management in a distributed operating system, there are mechanisms that allow process transfer, download, remote debugging, state vectoring, and remote emulation of the operating system. Process management facilities can be realized by the distributed operating system kernel, and resource utilization improvement is possible through this. In this research, we intend to examine the evolution of distributed operating systems, how to manage processes, migration, clustering, how to transact messages, and other topics about distributed operating systems. We also consider an example of such operating systems called Amoeba, and we examine process management, inter-process communication, and its efficient mechanisms for improving resource management.

Abstract With the rising demand for high-quality video services such as live streaming, virtual reality, and UHD videos, efficient video coding methods have become increasingly critical. Standards like H.264, H.265, and H.266 aim to reduce data volume while preserving image quality, yet they face challenges such as computational complexity, bandwidth management, and compression resilience. This paper provides a comprehensive review of neural network-based approaches for optimizing video coding. The reviewed methods include convolutional neural networks (CNNs) for intra-mode prediction, LSTM and Seq2Seq models for video traffic modeling, and inverse neural networks (INNs) for robust video hiding. Findings indicate that these techniques can reduce encoding time by up to 70%, enhance frame size prediction accuracy to 13.6%, and improve the resilience of stego videos against compression. Practical applications in bandwidth management, coding optimization for resource-constrained devices, and video security are explored. This study underscores the significant potential of deep learning in advancing video coding standards and suggests future research directions.

Abstract One of the most important applications of the Internet of Things in the field of health is remote monitoring of patients. This technology allows doctors to check the health status of patients in real time, which is especially vital for people suffering from or prone to heart diseases. Prediction of cardiovascular diseases is known to be a complex challenge that faces low accuracy in existing models. In this research, a new recommender system for predicting cardiovascular diseases is proposed that uses a convolutional neural network to analyze physiological data of patients. Physiological data from patients are collected remotely through four biological sensors including ECG sensor, blood pressure sensor, heart rate sensor and blood sugar sensor. These data are then processed by an Arduino controller and the convolutional neural network model is used to predict cardiovascular disease. With outstanding capabilities in extracting local features and without the need for complex time sequence analysis, this model can effectively use fixed numerical data such as blood pressure, heart rate, and blood sugar to diagnose heart diseases. The experimental results showed that the convolutional neural network was able to effectively extract local and non-temporal features of the data and help the model achieve a prediction accuracy of 98.90%.