Recent Advances in Electrical & Electronic Engineering - Volume 18, Issue 9, 2025

Deep learning models often face challenges in achieving optimal accuracy when classifying multiclass datasets, particularly when the dataset size is limited. This study introduces Contrast Based Learning (CBL), a novel data augmentation technique designed to address data scarcity.

CBL innovatively concatenates multiple images and uses contrast learning to generate enriched datasets that exhibit a higher diversity of complex features. By focusing on the contrasts between various images, this method enhances the model's ability to learn nuanced features, thereby improving generalization and reducing overfitting.

Unlike traditional data augmentation methods, which rely on basic transformations, CBL dynamically concatenates images from different classes, creating complex inputs that provides the model with a more comprehensive training dataset. Experimental results show that CBL significantly improves classification accuracy and outperforms state-of-the-art methods across multiple small-scale multiclass datasets.

The findings highlight the robustness of CBL in addressing data limitations, demonstrating its potential to advance the classification performance of deep learning models.

Patients’ electronic health records (EHRs) stored in the cloud are more likely to suffer from data breaches. Data security risks arise from EHRs rely on centralised databases, as this approach places the responsibility for data protection on the user. Indeed, it leaves data security to a single organisation, leaving it open to intrusion by its employees. Maintaining the privacy and integrity of patient information is of utmost importance when interacting with and integrating with EHR systems.

Therefore, in order to find the best blockchain framework for trustworthy electronic health records (EHRs), a precise method for comparing the effects of several current blockchain systems is required. Data from electronic health record applications is encrypted and saved in the cloud using IPFS off-chain as part of this study, following a design that is consistent with patient data management. To secure electronic health record data, the system uses a hierarchical interdependency approach for block construction and framework design.

This research is focused on finding a solution to the issue of privacy leaking in data sharing. To ensure the privacy of user’s data, the healthcare system utilises a multilevel authentication mechanism and an encryption technique that is based on hierarchical interdependency attributes. Smart contracts have been used to establish hierarchical access control for various Internet of Things systems, guaranteeing control over data access. This paper describes about improve the system's scalability, transaction latency, and throughput by implementing a modified proof-of-stake (POS) security protocol in healthcare application 5.0. This helps to secure users' privacy and security.

In comparison to more conventional blockchain solutions, the experimental results demonstrate improvements in efficiency and security in terms of variables such as block size, upload time, transaction range, and evaluation metrics such as transaction delay.

With the advancement in Alzheimer's disease (AD) brain, cells start to deteriorate, which eventually creates physical dependency and mental instability that interferes with daily living. Presently, this disease is immedicable. Therefore, the only suitable treatment is early detection and prevention.

Although many studies have investigated the usefulness of deep learning in AD detection, relatively few have focused on the necessary image preprocessing processes, which are essential to any computer-aided diagnostic system. Furthermore, an optimal classification strategy that takes into account a diverse handful of prominent features is required.

This paper focuses on improving MRI-based AD detection by incorporating image enhancement approaches and deep hybrid learning into a fused framework to harness the power of multiple Deep Learning (DL) architectures and Machine Learning (ML) classifiers. The deep features extracted from three heterogeneous CNN architectures, namely, VGG16, DensetNet169, and MobileNetV1, are fused to produce a more informative and discriminative hybrid feature. Furthermore, the mRMR approach was used to optimise the acquired features, followed by classification via a stack of multiple ML classifiers to predict the target class.

The proposed architecture based on feature fusion strategy and ensemble learning resulted in 99.53%(Accuracy), 99.73%(Precision),99.70%(Recall), and 99.72% (F1 score). The presented model outperformed individual deep CNN architectures.

Lastly, we present a sobol-based sensitivity analysis that illustrates the concentration of the presented technique upon significant regions of the image and can assist medical professionals in decoding the decisions. The presented technique exeplifies the potency and constancy of categorizing Alzheimer's disease.