With the increasing interconnectedness of communications and social networks, graph-based learning techniques offer valuable information extraction from data. Traditional centralized learning methods faced challenges, including data privacy violations and costly maintenance in a centralized environment. To address these, decentralized learning approaches like Federated Learning have emerged. This study explores the significant attention Federated Learning has gained in graph classification and investigates how Model Agnostic Meta-Learning (MAML) can improve its performance, especially concerning non-IID (Non-Independent Identically Distributed) data distributions.In real-world scenarios, deploying Federated Learning poses challenges, particularly in tuning client parameters and structures due to data isolation and diversity. To address this issue, this study proposes an innovative approach using Genetic Algorithms (GA) for automatic tuning of structures and parameters. By integrating GA with MAML-based clients in Federated Learning, various aspects, such as graph classification structure, learning rate, and optimization function type, can be automatically adjusted. This novel approach yields improved accuracy in decentralized learning at both the client and server levels.

One of the most famous visual manifestations of Mamlukid administration system is the symbolic use of motifs of animals, plants and everyday life tools as heraldry signs (rank; pl. Runuk) in various forms, among which the symbol of lion was used widely for the sultans, emirs and high rank officials. Historical evidences, conceptual framework, cultural context and developments of such uses of symbol of lion in Mamlukid heraldry system are investigated in the present article. The author also suggests that it may be possible (or at least it is worth for studying) that some of uses of this symbol could be based on supposed talismanic power of this ancient symbol.

Over the past few decades, democratic procedures have been raised as main core of most urban planning methods. In this regard, the present research adopts Descriptive-Evaluation methods and uses meta-analysis method so as to review the democratic procedures at the heart of planning theories and democracy and to explore their paradigmatic interaction. The main challenge is the emergence of planning Practices based on public interest and in alignment with democratic nature of it, so the results of present research suggest that transition to post-modern era of planning perspective is accompanied by association between democratic procedures and certain subjects such as public interest, consensus, pluralism, uncertainty and agonistic arenas. In this regard, the theory of planning has experienced a paradigmatic shift towards agonistic planning which is a democratic accountability mechanism premised on intellectual support of agonistic democracy. So this article tries to recognize and set up a platform for emergence of new democratic theories, especially appearance the agonistic planning theory in Iran, and consequently the formation of social discourse due to turning hostility into agnostic and replacing enmity by disagreement or aggression by competition.

One of the important elements which provided Selim I with the preliminaries of comprehensive military attack against the territory of Mamlū ks, was the bringing together of the Madrasa educators, the jurisprudents (Mufties) and the Ilmiye class elders. In examining the issue of Ottoman invasion against the Mamlū ks, although it is referred to the Ulema and Muftis’ permission to fight with the Mamlū ks, it often does not pay close attention to the complexity of the issue of this fatwas (legal opinions) and the considerations of the Madrasa educators and jurisprudents in this matter. This study shows that, according to the Mulla Arab’ s fatwa, the Sheikh al-Islam during the reign of Bayazid II, on the illegitimacy of two Muslim rulers’ conflicts that, led to the end of the Ottoman-Mamlū ks five-year wars, also because of the Mamluk Sultans were Sunni, declaring Jihad against them was simply not possible. Knowing this, by the conventional way in asking the fatwa, Selim I made a request for fatwa about the legitimation of the military attack against Mamlū ks vaguely and without reference to the case consciously and deliberately. Considering all the problems ahead in issuing the Fatwa of jihad against the Sunni Mamlū k rulers, The Madrasa educators and the Muftis issued a multi-stage fatwas. These fatwas, on the one hand, realized the objective purpose of the Ottoman Sultan to attack on the Mamluks, and on the other, in appearance, there was no contradiction with the Mulla arab’ previous fatwa.

In his book "The God delusion" Richard Dawkins has denied the existence of the God of Abrahamic religions, including Islam. In order to prove his point of view, in addition to presenting the reasons he tried to remove everything that is considered as an obstacle. The point of view of agnosticism is one of these obstacles that Dawkins, by accepting its principle, believes that the probability of the non-existence of God is greater than his existence; therefore, one should not be agnostic about the existence of God. He has based his belief on the basis of the division of " agnosticism " into temporary and permanent, Knowing the existence of God as a scientific hypothesis, the principle of the impossibility of definitively proving the absence of a thing, criticism of Bayesian reasoning and improbable reasoning. In this article, Dawkins' point of view and reasons are first introduced in a descriptive way, and then the success rate of the reasons presented in proving his claim is analyzed by a critical method. The result of the research shows that these reasons cannot prove his claim and their ultimate efficiency is to prove theoretical agnosticism.

The escalating use of networks and the internet has led to a surge in cyber threats, making it imperative to develop sophisticated intrusion detection systems (IDS) capable of safeguarding against these malicious intrusions. While machine learning techniques have been extensively employed to enhance IDS, challenges persist, notably in handling imbalanced datasets and rare attack detection such as R2L and U2R due to the small number of their samples in the training dataset. Imbalanced datasets, a common challenge in IDS evaluation, often skew toward majority classes, hindering the detection of minority class attacks. Existing machine learning classifiers, primarily accuracy-driven, struggle to excel at identifying rare attacks, which are often more catastrophic. Moreover, overlapping classes complicate feature selection, further impeding accurate detection. To tackle these challenges, this article proposes a solution rooted in Few-Shot Learning, particularly MAML. Traditional MAML has limitations, including slow convergence and computational demands. To enhance MAML's performance, the article introduces the Node Decoupled Extended Kalman Filter (NDEKF) as an alternative to gradient descent in the inner loop. NDEKF optimizes MAML training, offering faster convergence and improved generalization. The DEKF (Decoupled Extended Kalman Filter) variant simplifies calculations, making it suitable for deep neural networks. The combination of MAML and NDEKF, termed NDEKF-based MAML, is applied to address the imbalanced data problem in IDS. The proposed approach is evaluated on the NSL-KDD dataset, demonstrating its potential to improve rare attack detection in intrusion detection systems. By adopting this approach, we achieved improved convergence speed, enhanced ability to generalize, and higher accuracy compared to the original MAML algorithm when dealing with a sparse and unstable dataset such as NSL-KDD. Particularly, our framework demonstrated significant advancements in accurately detecting rare U2R and R2L attacks. The accuracy rates for R2L and U2R attacks using our proposed framework surpassed those of the original MAML, increasing from 61% to 75% and from 51% to 66%, respectively, even with a reduced number of training epochs.

Background and Objectives: Identifying pregnant women who are at risk of premature birth and determining its risk factors is essential because it affects their health. This study aimed to use an interpretable machine-learning model to predict premature birth. Methods: In this study, data from 149,350 births in Tehran in 2019 were utilized from the Iranian Mothers and Babies Network (IMaN) dataset. Various factors related to the mother and the fetus, such as the mother's demographic variables and health status, medical history, pregnancy conditions, childbirth, and associated risks, were considered. The machine learning models, including multilayer neural networks, random forest, and XGBoost, were employed to predict the occurrence of preterm birth after data preprocessing. The models were evaluated based on accuracy, sensitivity, specificity, and area under the ROC curve. The Python programming language version 3.10.0 was applied to analyze the data. Results: About 8.67% of births were premature. The XGBoost algorithm achieved the highest prediction accuracy (90%). According to the model output, multiple births, which account for 46% of pregnant women's births, had the highest importance score. Delivery risk factors had a score of 41%, and other variables, including neurological and mental illness, preeclampsia, and cardiovascular disease, were subsequently ranked in order of importance for this particular individual. Conclusion: Using an interpretable machine learning method could predict the occurrence of premature birth. Based on risk factors, the interpretable machine learning method can provide personalized preventive recommendations for every pregnant woman, aiming to reduce the risk of preterm birth.