JPEG-Resistant DCT Steganography for Secure Communication

Israa Abdulkadhim Jabbar Al; Zainab A.; Rawaa.M.aljubouri

doi:https://doi.org/10.54216/FPA.210118

Journal of Cybersecurity and Information Management | 2026

Using Artificial Intelligence Techniques to Enhance the Performance of Control Systems in Solar Power Plants

This study examines the potential benefits of AI. It also addressees enhancing the performance of plants powered by solar and defending them against cyberattacks. Old controllers like PID and fuzzy logic work well in old places, and have no built in protection against cyber hackers that want to steal data, get into your control system, or obtain system access credentials. Artificial Neural Networks (ANN) and Reinforcement Learning (RL) are instances of AI-driven pattern stick to establishing fast adjustments on the fly, thus inducing non-normal behavior in controllers. This work uses AI to build models that predict solar flux on a surface and adjust input parameters in real time. In addition, it delivers security sensitive capabilities through pattern-driven analysis and alerting. MATLAB/Simulink simulations are used to demonstrate the efficacy of the approach, and it is compared with different methods in terms of power generation, time of response, power loss, stability, and quality of control. The ANN model made very good predictions, and the RL methods increased the flexibility and security of the system. According to the outcomes, the inclusion of AI into the system not only makes it more efficient in terms of producing energy but also renders it invulnerable to hackers or any other operational risks. This blog post discusses the need to secure AI-based energy systems with intelligent security. It also adds that future studies should explore the convergence of AI and cyber security in safeguarding critical infrastructure.

groups

Ahmed Abdul Mahdi Alawsi mail -

Ahmed M. Ali Ali mail

link https://doi.org/10.54216/JCIM.170105

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2026

Machine Learning Model in Satellite Data Security Analysis using Remote Sensing Network

Over uncovered and under-covered areas, satellite communication provides the potential for ubiquity, scalability, and service continuity. However, before these benefits may be fully realized, a number of obstacles need to be overcome. Satellite networks present more difficulties than terrestrial networks in terms of spectrum management, energy consumption, network control, resource management, and network security. The goal of this research is to create a novel way to remote sensing network security modelling by utilizing machine-learning techniques to analyses the security of satellite data. In order to provide an intrusion detection technique for the modern network environment, this study considers data from both terrestrial and satellite networks. Here the remote sensing network security analysis is carried out using quantum federated encryption algorithm and data security has been analysis by quantile regression adversarial convolutional neural networks. Experimental analysis has been carried out in terms of data integrity, latency, random accuracy, QoS, AUC. Proposed technique Data integrity of 93%, LATENCY of 95%, QOS of 96%, random accuracy of 98%, AUC of 92%.

groups

Gagan Kumar Koduru mail -

P. Chinnasamy mail -

S. Kalaimagal mail -

Karri Nagaraju mail -

V. Bhaskara Murthy mail -

Shivanadhuni Spandana mail -

M. Rajesh mail

link https://doi.org/10.54216/JCIM.170106

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2026

Secure Honeynet Cloud IoT Model and Machine Learning based Smart Healthcare System with Urban Management

Smart health is becoming an increasingly sensitive field because to the growing use of a variety of Internet of Medical Things (IoMT) devices as well as apps. IoMT is a well-liked technique for developing smart city solutions that eventually improve critical infrastructures, such smart healthcare. Numerous IoMT devices in smart cities employ Bluetooth technology for short-range communication because it is adaptable and resource-efficient. This research proposes novel method in urban planning in smart public healthcare system utilizing ML algorithms. The smart healthcare system is developed based on secure honeynet cloud IoT model. Here the input smart healthcare-based health monitoring data is collected and processed for missing value removal and noise removal. Then this data classified and optimized using recurrent Bi-LSTM temporal Gaussian model with whale swarm particle colony optimization. Experimental analysis is carried out in terms of detection accuracy, precision, data integrity, throughput, recall, latency. Proposed technique obtained 96% of Detection    accuracy, 97% of Precision, 95% of Throughput, 88% of RECALL, 94% of LATENCY.

groups

S. Pavithra mail -

Venkatesan S. mail -

Yerragudipadu subbarayudu mail -

Keshav Sinha mail -

Rayavarapu Sridivya mail -

Munugapati Bhavana mail

link https://doi.org/10.54216/JCIM.170107

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2026

Intelligent Arabic Writer Identification Using Artificial Immune System Algorithms: A Bio-Inspired Approach for Smart Pattern Recognition

Artificial immune systems (AIS) represent an emerging facet of artificial intelligence, offering innovative solutions to a spectrum of problems. It draws inspiration from the biological immune system's fascinating properties, mechanisms, and principles, resulting in mathematical and computer-based implementations. In this paper, we aim to assess the accuracy of artificial immune systems as classification tools in the realm of Arabic handwriting recognition. Among the repertoire of immune-computing models, we focus on the Artificial Immune Recognition System (AIRS), Immunos, Clonal Selection Algorithm (CLONALG), and Clonal Selection Classification Algorithm (CSCA), which have garnered significant attention for their prowess in pattern recognition applications. To conduct this investigation, we leverage the comprehensive IFN-INIT Arabic handwriting database, which comprises contributions from 411 distinct writers. Feature selection plays a pivotal role in enhancing classification performance, and for this purpose, we harness the grey level co-occurrence matrix. In pursuit of a thorough comparative analysis, we also employ well-established classifiers such as Support Vector Machines (SVM), k-Nearest Neighbors (KNN), and Naive Bayes. The obtained results exhibit the promising potential of AIS-based classifiers in the context of Arabic handwriting recognition, offering insights into the evolving landscape of AI solutions in this domain.

groups

Fahad Ghabban mail

link https://doi.org/10.54216/JISIoT.180125

Volume & Issue

Vol. Volume 18 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2026

Symptom-Based Detection of COVID‑19 Cases Using Machine Learning Algorithms

Mammals are susceptible to the lethal disease called coronavirus. This virus often infects humans through the aerial precipitation of any fluid released from the bodily part of the affected entity. This viral variant is deadlier than other sudden viruses. Given the ongoing thread which COVID-19 on health systems in the worldwide, there is a rising interest in development a mechanism that effective in terms of cost and classification. A mechanism for categorizing and scrutinizing the estimations derived from this virus' symptoms is proposed in this paper. The precision of various machine-learning classifiers is calculated in this study in order to determine the optimal classifier for COVID-19 identification. Because the COVID-19 dataset has the greatest precision of 100%, it was classified using AdaBoost and Bagging. Additionally, precision, recall, and F-score measures together with the ROC were deployed for evaluating detection performance to ensure the approach is capable and successful.

groups

Hussein Ibrahim Hussein mail -

Lateef Abd Zaid Qudr mail -

Weal Hasan Ali Almohammed mail

link https://doi.org/10.54216/JISIoT.180126

Volume & Issue

Vol. Volume 18 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2026

Improvement to the Gradient Projection Method Used to Find the Optimal Solution for Neutrosophic Nonlinear Models Constrained by Equality Constraints

A mathematical model consists of decision variables, a goal function, and constraints. The region of possible solutions for a nonlinear mathematical model is the set of vectors whose components satisfy all constraints. The optimal solution is the vector whose components satisfy all constraints, and at which the function reaches an optimal value (maximum or minimum). Nonlinear programming constitutes an important and fundamental part of operations research and is more comprehensive than linear programming. Its applications have spread across all branches of science, including engineering, physics, chemistry, management, economics, and military fields, among others. Nonlinear programming can also be used in forecasting, estimation, applied statistics, and determining the costs resulting from the production, purchase, and storage of goods. Given this importance, and in order to obtain a more accurate solution that takes into account all the changes that the system under study may be exposed to, we have previously presented a neutrosophic study of nonlinear models and some of the methods used to find the optimal solution. In addition to what we have previously done, in a research we present an improvement to the gradient projection method used to find the optimal solution for nonlinear models constrained by equal constraints, enabling us to obtain the optimal solution in fewer steps. We will then apply it to find the solution. Optimization of nonlinear neutrosophic models.

groups

Maissam Jdid mail -

Florentin Smarandache mail

link https://doi.org/10.54216/IJNS.270116

Volume & Issue

Vol. Volume 27 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2026

Components Reusability Optimization based on Re-Structure Monolithic Code

In modern software engineering, monolithic code structures are increasingly incompatible with the flexibility demanded by today’s platforms. These tightly coupled systems pose challenges for scalability, integration, and secure deployment. This paper presents a method for restructuring monolithic Java classes into optimized, reusable software components. We analyze each class using 19 object-oriented metrics from the CKJM suite, evaluating cohesion and coupling properties. Using our proposed framework—Good Global Optimization Dynamic Weighted Metrics (GGODWM)—we cluster interrelated classes and transform them into high-level components suitable for microservice environments. These components are evaluated within a Component Base Redesign Structure (CBRS) environment to measure reusability. Our experimental results show a 52% improvement in cohesion and coupling balance, outperforming traditional Turbo_MQ-based metrics. By enhancing component modularity and reducing interdependencies, the proposed approach contributes to more secure and maintainable code, thus supporting cybersecurity goals such as reduced attack surface and easier vulnerability management.

groups

Zeyd Saeed mail -

Mustafa Ismael Khudair mail -

Ahmed Khader Ali Ibrahim mail -

Rahman Nahi Abid mail

link https://doi.org/10.54216/JCIM.170108

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2026

Hybrid Adaptive Swarm Enhanced Vision Transformer for Accurate Corn Leaf Disease Prediction

Early and precise detection of corn leaf diseases is important for maintaining crop yield and quality. This work suggests a new end-to-end system Hybrid Adaptive Swarm-enhanced Vision Transformer (HAS-ViT) to overcome the limitations of current techniques such as poor accuracy, high computational expense, and overfitting and inefficient feature extraction. The suggested framework combines a three-stage pipeline such as segmentation, classification and optimization to overcome the issues. First, Adaptive Gradient Masking with Color Entropy (AGM-CE) is a novel segmentation technique that isolates diseased areas through an integration of local color entropy and gradient energy in the LAB color space. This guarantees accurate area selection and removal of the background. Then, a transformer model is constructed named Vision Transformer with Enhanced Visual Attention (ViT-EVA). It integrates depthwise attention layers as well as lesion-aware region concentration, enhancing separation of disease classes and model simplification. Finally, Adaptive Bio-Inspired Gradient Tuning (ABGT) optimizer integrates the Bat Algorithm, AdamW and gradient sign flipping for effective learning and convergence. The mechanism speeds up convergence, prevents local minima and maintains exploration exploitation trade-offs at training. The performance of proposed work is measured on a corn disease dataset and performs at 98.1% accuracy and 0.12 loss than conventional and current transformer-based models.

groups

Nilam Sachin Patil mail -

E. Kannan mail

link https://doi.org/10.54216/FPA.210116

Volume & Issue

Vol. Volume 21 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2026

Automated Rheumatoid Arthritis Diagnosis and Grading with KL-Grading Deepnet-X

Arthritis significantly affects mobility and quality of life due to joint inflammation and dysfunction. Its most common type, rheumatoid arthritis (RA), primarily influences multiple joints and tissues, especially in women aged 30–50. Common symptoms include pain, swelling, and stiffness. The growing prevalence of RA, projected to reach 44 million globally by 2045, underscores the need for advanced diagnostic methods. MRI offers detailed visualization of joint structures, essential for accurate diagnosis. However, current grading systems like OARSI and Kellgren-Lawrence are subjective and prone to variability. This study introduces the KL Grading DeepNetX framework, a deep learning-based model for automated RA grading and classification. The approach integrates image preprocessing and segmentation to extract key features such as joint space narrowing and cartilage thickness. Comparative analysis shows that KL Grading DeepNetX outperforms traditional methods with high precision, sensitivity, specificity, and F1-score. This framework enables earlier, more accurate and efficient detection of arthritis using knee MRI images.

groups

Govindan Rajesh mail -

Nandagopal Malarvizhi mail

link https://doi.org/10.54216/FPA.210117

Volume & Issue

Vol. Volume 21 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2026

JPEG-Resistant DCT Steganography for Secure Communication

In this work, the researchers presented an ingenious new way to conceal secret messages within images, a practice called steganography. This technique embedded secret messages within images undetectably. To embed the secret data, it applies a mathematical trick called Discrete Cosine Transform (DCT) that is commonly used to compress image files to hide the secret data in areas of the image that are not too complex or too simple. The algorithm adaptively selected embedding locations based on image texture to the appearance of the image, choosing the most appropriate places to hide the secret and the picture to appear normal. This new method of hiding data is more magical and less detectable than older methods, which modify the smallest details of an image (so-called Least Significant Bit techniques). It examines the patterns of the image such as whether it is smooth or has many details and selects obscure, secure locations to conceal the message. They tried this with 1,000 images, and in each image, they embedded a small message (a paragraph of text). The pictures came out great afterwards with just minor adjustments that most people would not have noticed. 95% of the buried messages could be dragged out flawlessly even after the images had been reduced in size with the JPEG. An artificial intelligence-based high-tech detection tool only detected the hidden data half the time 52%, a significant improvement over the older techniques where it located 85 percent or 65% of the secrets.

groups

Israa Abdulkadhim Jabbar Al Ali mail -

Zainab A. Abdulazeez mail -

Rawaa.M.aljubouri mail

link https://doi.org/10.54216/FPA.210118

Volume & Issue

Vol. Volume 21 / Iss. Issue 1

Details open_in_new