Deep Neural Network Graph with Reinforcement Learning for Test Case Prioritization

Shankar; E. K.

doi:https://doi.org/10.54216/JISIoT.180225

International Journal of Neutrosophic Science | 2026

On Graded Weakly Jgr-classical Prime Submodules

Let 0 be a group, Υ be a 0-graded commutative ring with unity 1 and M a graded Υ-module. Our goal in this paper, introducing the concept of graded weakly Jgr -classical prime submodule as a generalization of graded weakly classical prime submodule and offering several results pertinent of graded weakly Jgr - classical prime submodules. For instance, we give characterizations of graded weakly Jgr -classical prime submodule. Also, we give some restrictions for graded submodule to be a graded weakly Jgr -classical prime submodule. A proper graded submodule V of M is said to be a graded weakly Jgr -classical prime submodule of M if, whenever 0̸ = abx ∈ V where a, b ∈ h(Υ) and x ∈ h(M), then either ax ∈ V + Jgr (M) or bx ∈ V + Jgr (M), The symbol Jgr (M) indicates the graded Jacobson radical of Υ-module M.

groups

Malak Alnimer mail -

Khaldoun Al-Zoubi mail

link https://doi.org/10.54216/IJNS.270225

Volume & Issue

Vol. Volume 27 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2026

Interval-Valued Picture Fuzzy Almost Ideals in Semigroups

An interval-valued neutrosophic set is a type of neutrosophic sets where the membership, indeterminacy, and non-membership degrees are represented by closed intervals within the unit interval [0, 1]. An interval-valued picture fuzzy set is one of special cases of interval-valued neutrosophic sets. In this paper, we apply interval- valued picture fuzzy sets on almost ideals of semigroups. Moreover, we study a relationship between each almost ideal in a semigroup and their interval-valued picture fuzzifications.

groups

Winita Yonthanthum mail -

Anusorn Simuen mail -

Ronnason Chinram mail

link https://doi.org/10.54216/IJNS.270226

Volume & Issue

Vol. Volume 27 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2026

Solution of Intuitionistic Fuzzy System of Linear Volterra Integro-differential Equations by a Novel Hybrid Method

Our study addresses the intuitionistic fuzzy system of linear Volterra-integro-differential equations of the second kind. Intuitionistic fuzzy General Transform (I-F-G-transform) method has been used to find the exact solution of these systems. We present two numerical examples for illustrating the applicability of the Intuitionistic fuzzy General integral transform method.

groups

Guelfen hanane mail

link https://doi.org/10.54216/IJNS.270227

Volume & Issue

Vol. Volume 27 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2026

Cryptanalysis In Block Ciphers: A Comprehensive Review and Future Directions

This paper examines the use of cryptography in block ciphers and assesses their security, with a focus on the Advanced Encryption Standards (AES). The study reviews key cryptanalytic techniques, including differential cryptanalysis (8.3%), linear cryptanalysis (4.2%), and integral cryptanalysis (4.2%). They give their share (in percentage) regarding the relative frequency in the cryptanalysis research literature from 2015 to 2024 according to their literature survey. Side-channel attacks showed the highest practical success rates, with some studies showing up to 50.0% effectiveness. Additionally, the study examines more sophisticated attack techniques such as meet-in-the-middle attacks, quantum-related threats, and biclique cryptanalysis (16.0%).The entire round AES is resistant to a wide range of attack techniques thanks to its strong diffusion and confusion mechanisms and reliable key schedule. The study concludes that cryptanalysis is essential for strengthening encryption schemes against emerging threats, particularly those resulting from quantum computing.

groups

Lama Al-Ghamdi mail -

Mawada Al-Sari mail -

Monir Abdullah mail -

Ghassan Ahmed Ali mail

link https://doi.org/10.54216/FPA.210211

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2026

Development of an Efficient Cluster-Based Hybrid LEACH+TEEN Protocol for Time-Critical WSN Application

Wireless Sensor Networks (WSNs) play a crucial role in monitoring and data collection for various real-time applications, including environmental surveillance, industrial automation, and smart cities. However, achieving energy efficiency and timely data delivery remains a critical challenge, especially in time-sensitive scenarios. This research presents the development of an efficient cluster-based hybrid routing protocol that combines the strengths of Low-Energy Adaptive Clustering Hierarchy (LEACH) and Threshold-sensitive Energy Efficient Network (TEEN) protocols to address these challenges. The proposed Hybrid LEACH-TEEN protocol dynamically adapts to both periodic and event-driven data transmission needs by integrating LEACH’s randomized cluster-head selection and TEEN’s threshold- based data transmission mechanism. This hybrid approach significantly reduces redundant transmissions and optimizes energy consumption across the network. Extensive simulations were conducted to evaluate the protocol’s performance in terms of network lifetime, stability period, energy consumption, and the number of alive nodes over time. Results demonstrate that the Hybrid protocol outperforms traditional LEACH and TEEN protocols, particularly in time- critical applications, by ensuring prompt response to critical events while maintaining energy-efficient operation. This work contributes to the design of intelligent and adaptive routing strategies for next- generation WSNs.

groups

Basim Jamil Ali mail -

Mohanad Ali Meteab Al-Obaidi mail

link https://doi.org/10.54216/FPA.210212

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2026

A Systematic Review on Classification Techniques of Microorganisms: Challenges and Recommendations – Towards Medical Intelligent Systems

Microorganisms are commonly found in our daily living environments and play a crucial role in environmental pollution control, disease prevention, and treatment, as well as food and drug production. To fully utilize the diverse functions of microorganisms, their analysis is essential using Intelligent Systems. Traditional analysis methods can be labor- intensive and time-consuming. As a result, image analysis using Intelligent Systems i.e. machine learning or deep learning have been introduced to improve efficiency. Deep learning networks algorithms such as CNN contain a stack of multi-layer, the first layer and the last are the input and output layers, between them are the hidden layers to extract and learn many features in images, recurrent network algorithms (RNN) combined with convolution neural network (CNN), these networks allow to process a series of images to extract the crucial information from images and also these algorithms help to minimize the size of images and reduce the redundancy in microrganisms images According to previous studies, these algorithms are the most used to classify the images of microorganisms. However, the classification of microorganism images presents several challenges these include the need for robust algorithms due to varying application contexts, the presence of insignificant features, along various analysis tasks that need to be addressed. The research summarizes significant advancements that tackle these challenges through deep learning and machine learning methods. Current obstacles, gaps in knowledge, unresolved issues, limitations, and difficulties in classification techniques are also discussed.

groups

Marwa T. Albayati mail -

Mohd Ezanee Bin Rusli mail -

Moamin A. Mahmoud mail -

Aws A. Abdulsahib mail -

Mohammed F. Alomari mail -

Sallar S. Murad mail

link https://doi.org/10.54216/JISIoT.180224

Volume & Issue

Vol. Volume 18 / Iss. Issue 2

Details open_in_new

Prospects for Applied Mathematics and Data Analysis | 2025

Some Special Types of Neutrosophic Domains

The neutrosophic ring cannot be an integral domain, but the pseudo-neutrosophic ring could be an integral domain. The main objective of this paper is to present and study some special types of neutrosophic domains, which has not been studied before, such as integral domains.

groups

Shawqi Al-lkami mail -

Adel Al-odhari mail

link https://doi.org/10.54216/PAMDA.050103

Volume & Issue

Vol. Volume 5 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2026

On Division of Symbolic n-Plithogenic Numbers

The main goal of this article is to study the division of symbolic n-plithogenic numbers using the identification method and n-plithogenic AH-isometry. In particular, we discuss the division of symbolic 2-plithogenic numbers and 3-plithogenic numbers, and we generalize these divisions. Additionally, we prove the validity of the formulas using AH-isometry and provide four worked examples to enhance understanding.

groups

P. Arulpandy mail -

S. Kalaiselvan mail -

M. Sundar mail -

G. Govindharaj mail -

P. Sugapriya mail

link https://doi.org/10.54216/IJNS.270228

Volume & Issue

Vol. Volume 27 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2026

Optimizing Navigation: Adaptive Map Reshaping and Shortest Path Analysis for Mobile Robots

To facilitate the practical deployment of robotics, efficient path planning is essential to ensure that robotic movement is accurate, safe, and goal-oriented. This study explores new approaches to map adaptation and path optimization for robot navigation between specified locations. The initial phase of the research involves designing an environment that enables the safe operation of robots. Subsequently, the collected data is processed to construct a graph using Dijkstra’s algorithm, which is employed to determine the shortest path between key points. When multiple paths are available, the algorithm selects the most efficient one, while ensuring safety in point-to-point transitions and when navigating around obstacles. In addition to this, a reinforced method is introduced to enhance the security of path planning. This approach expands the original trajectory to incorporate a safety buffer equal to half of the robot’s safety radius, thus maintaining a safe distance along the traveled route. The key contribution of this work lies in the development of novel maps featuring secure pathways, which can be utilized by optimization algorithms to improve navigation in unfamiliar terrains. Experimental results using PRM* and RRT* validate the accuracy of these maps, especially in complex, maze-like environments.

groups

Mohammed Rabeea Hashim Al-Dahhan mail -

Mahmood Abdulrazzaq Alsaadi mail -

Ruqayah R. Al-Dahhan mail -

Salah A. Aliesawi mail -

Omar Q. Mohsin mail

link https://doi.org/10.54216/FPA.210213

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2026

Deep Neural Network Graph with Reinforcement Learning for Test Case Prioritization

Recently, Deep learning (DL) models are increasingly used in Test Case Prioritization (TCP) tasks combining partial and imperfect test case (TC) information into accurate prediction models. Various DL algorithms have been created to improve TC failure prediction and prioritization in CI settings. Among them, Deep Reinforcement Prioritizer (DeepRP) model is developed using Deep Reinforcement Learning (DRL) and Deep Neural Network (DNN) for efficient TCP on huge test suites. But, the model's labelling task is interrupted early, creating difficulty in learning TC features for unlabeled training TCs due to limited resources. To solve this, Deep Graph Reinforcement Prioritizer (DeepGRP) is proposed in this paper to learn the TC features from unlabeled training data for efficient TCP in Regression Testing (RT). In this method, graph neuron stimulation attributes for TCs are created to retrieve the activation graph across DNN layers of DeepRP. The connectivity neuron link defines the activation graph. The proposed deep graph (DG) recognizes the DNN neurons as nodes and the adjacency matrix as the connectivity link among the nodes. Also, the message passing mechanism is applied to aggregate the structural information from the adjacency matrix with neighbouring node features to enhance TCP. By applying this mechanism, DeepGRP captures the high-order dependencies among neurons for efficient activation features which overcomes the traditional activation models and improves the TCP at large scale RT.  The DG model prioritizes TCs using Learning-to-Rank (L2R) which learns node attributes from TCs. This enables for better DNN testing efficiency by detecting vulnerabilities early and lower development time for efficient TCP and tackling the difficulty of learning TC characteristics for efficient TCP. Finally, the testing findings suggest that the DeepRP can improve the TCP for large TSs when compared to other common algorithms.

groups

Shankar Ramakrishnan mail -

E. K. Girisan mail

link https://doi.org/10.54216/JISIoT.180225

Volume & Issue

Vol. Volume 18 / Iss. Issue 2

Details open_in_new