EdgeAI-Powered Hybrid ESN-GRU Model for High-Accuracy and Efficient Short-Term Load Forecasting in Smart Grids

Published in: IEEE ACCESS

Dec 09, 2025

With the widespread use of renewable energy sources (RES) in the smart grid, the next generation power system, short-term load forecasting (STLF) is of critical importance in grid stability and energy optimization. Traditional STLF models include issues such as high computational cost, dependency on cloud infrastructure, and latency issues, which are undesirable for real-time energy management. To solve these issues, the EdgeAI paradigm, which combines edge computing and artificial intelligence (AI), can be a promising solution. EdgeAI reduces the dependency on cloud-based systems by processing data close to the data source, offering advantages such as low latency and low bandwidth. Thus, it increases the response speed by processing data in real time, making it suitable for STLF applications. In order to benefit from all these advantages, the EdgeAI-driven Hybrid Echo State Network and Gated

Supervised methods of machine learning for email classification: a literature survey

Published in: Systems Science & Control Engineering

Nov 20, 2025

Muath AlShaikh Yasser Alrajeh Sultan Alamri suhib melhem

Intoday’sdigital landscape,email isacknowledgedasacriticalconduitforglobaldataexchanges. Withasurgeindatavolume,malefactorsexploituseridentities,leadingtodatamisuse.Cybercriminalsemployelectronictransgressionssuchasphishingandspamtoorchestratesecurityinfractions. Machinelearningcountersthesebreachesusingmyriadtechniques,demonstratingsignificantefficiencyinidentifyingphishingemails.Wecandividemachinelearningintotwotypes:supervised andunsupervised.Supervisedlearningrequirespre-trainingthemodelonlabelleddatasets,amalgamatingclassification,andregressionlearning.Notably,supervisedmethodologiessuchassupport vectormachines (SVMs),naiveBayes,decisiontrees,neuralnetworks, randomforests,anddeep learninghavebeenexploitedforspamfiltering.Thisreviewdelvesintoissuesconcerningspamfilteringandemailclassificationthroughsupervisedmachinelearningtechniques,offeringacomprehensiveevaluationofstrategies,methods,performanceindicators,andthebenefitsanddrawbacks ofdifferent research. This informationallows researchers toassess theefficiencyandeffectivenessofsupervisedlearningalgorithms, layingthefoundationforadvancedemailcategorization techniques.

An efficient semi-blind watermarking technique based on ACM and DWT for mitigating integrity attacks

Published in: Arabian Journal for Science and Engineering

Oct 15, 2025

Digital watermarking is an essential technology in multimedia and information processing, addressing the ever-mounting concerns related to data integrity and protecting intellectual property rights. In content authentication, copyright protection, and data integrity, digital watermarking plays a critical role. Nonetheless, the current application of digital watermarking faces crucial challenges, most notably adversarial attacks such as compression and noise interference, which pose substantial threats to the integrity of embedded watermarks. In this article, we introduce a semi-blind watermarking scheme that fuses the capabilities of the ACM and DWT techniques to facilitate the efficient embedding and extraction of watermarks in digital images. This approach achieves a trade-off between robustness and imperceptibility, thereby ensuring that the embedded watermark remains resilient against commonplace attacks

An OTP and watermarking based partial homomorphic approach to authenticated and integrated cloud computing

Published in: Cluster Computing

Sep 24, 2025

Cloud computing offers an ideal solution for reducing costs, time, and complexity in data management, but data security remains a critical concern. This study proposes a novel approach that combines partial homomorphic encryption (PHE) with digital watermarking to improve the authenticity and integrity of data in cloud environments. Our method employs a chaotic map for key generation, ensuring unique and non-duplicate keys, and utilizes the One-Time Pad (OTP) principle with probabilistic encryption for data protection. The watermarking technique, based on linear interpolation, enables tampering detection without compromising data privacy. We implement this approach using a symmetric linear scheme to achieve homomorphic properties, allowing specific operations on encrypted data without decryption. Experimental results demonstrate that our method achieves lower computational complexity compared to

Hierarchical Multiparty Digital Signature for Distributed Systems: Application in Intelligent Vehicle Surveillance

Published in: Journal of Cybersecurity and Privacy

May 21, 2025

The rapid expansion of distributed systems such as the Internet of Things (IoT) has increased the need for robust authentication and data integrity mechanisms to ensure public security in dynamic environments. This article presents a hierarchical multiparty digital signature (HMPS) technique designed to address the unique challenges of resource-constrained and decentralized systems. By integrating a modified ElGamal-based individual signature with linear encryption and hierarchical aggregation, HMPS delivers enhanced security through collaborative and layered signing processes. A key application is demonstrated in intelligent vehicle surveillance, where the scheme ensures the authenticity and integrity of commands and data in multi-level communication scenarios. Comprehensive security analysis confirms resistance to forgery, single points of failure, and unauthorized access. HMPS exhibits superior computational efficiency, scalability, and energy efficiency, as evidenced by comparative performance evaluations with state-of-the-art techniques. These results highlight HMPS as a highly effective solution for secure, real-time IoT applications, providing a pathway to more resilient and trustworthy distributed systems.

Robust Reversible Watermarking Technique Based on Improved Polar Harmonic Transform

Published in: Tech Science Press

May 06, 2025

Improved Resilience of Image Encryption Based on Hybrid TEA and RSA Techniques

Published in: Tech Science Press

Mar 21, 2025

Image encryption algorithm based on factorial decomposition

Published in: Multimedia Tools and Applications

Dec 16, 2024

This study proposes a highly efficient image encryption algorithm by employing a rapid key generation approach and permutation structure. The image is converted to a matrix, and then an encryption algorithm based on factorial decomposition permutation is applied. Two variants of the algorithm have been proposed in this study, where each variant is distinguished by the elements of the matrix to be permutated. The first variant is based on the permutation of the pixels of the image. In the second variant, the permutation is applied to both columns and rows of the matrix. These variants of the algorithm have been tested and compared. To create a permutation of a collection of elements, the factorial decomposition mathematical technique is applied, where the Euclidian division of a given key is obtained by adding the factorials of all the integers. The experimental results indicate that the proposed approach provides

A multi-layered security framework for medical imaging: integrating compressed digital watermarking and blockchain

Published in: IEEE ACCESS

Dec 06, 2024

In electronic healthcare, patient medical imaging data is critical for remote diagnostic procedures. The increasing demand to harness the potential of these medical images necessitates their secure sharing among various entities, including hospitals, medical institutions, and insurance companies. However, third-party access and possible manipulation make it challenging to maintain the ownership and integrity of this data. This study introduces a novel approach that combines compression, digital watermarking, symmetric encryption, and blockchain technology to protect medical images from unauthorized third-party interventions. Using the Discrete Wavelet Transform, our proposed technique embeds a compressed watermark into the host image. Specifically, the watermark is encoded into vectors and inserted into the second-level approximation, i.e., the Low-Low of the image using the Least Significant Bit

An iomt image crypto-system based on spatial watermarking and asymmetric encryption

Published in: Multimedia Tools and Applications

Nov 20, 2024

In the growing field of the Internet of Medical Things (IoMT), securing the transmission of medical images over public networks is a critical challenge. Medical images, being highly sensitive and often containing personally identifiable information, require robust protection against unauthorized access and tampering. This paper addresses this challenge by introducing a novel cryptosystem specifically tailored to the resource limitations inherent in IoMT environments. To meet the demand for protecting sensitive information in medical images, the proposed system integrates two layers of security: spatial watermarking and asymmetric encryption. At the core of our approach lies a newly developed, cost-effective spatial watermarking algorithm that seamlessly embeds watermarks within host images to facilitate tamper detection. Complementing this, we employ a resource-efficient Twin Message Fusion (TMF) encryption