PES Modern College of Engineering, Pune, popularly known as Modern or MCOE, is a Private Engineering Institute located in Pune, Maharashtra. The college is approved by All India Council of Technical Education(AICTE), New Delhi, Directorate of Technical Education(DTE), and Government of Maharashtra and is permanently affiliated to University of Pune, complying to all norms and standards of Engineering education. It is UGC recognized under 2(f) and 12(B) and NAAC accredited Grade "A" college. In 2019, the Institute received an NBA accreditation for 3 years. It has also been awarded as the "Best College in the Urban area" by the University of Pune in the year 2012.
Cloud-based Healthcare 4.0 systems have research challenges with secure medical data processing, especially biomedical image processing with privacy protection. Medical records are generally text/numerical or multimedia. Multimedia data includes X-ray scans, Computed Tomography (CT) scans, Magnetic Resonance Imaging (MRI) scans, etc. Transferring biomedical multimedia data to medical authorities raises various security concerns. This paper proposes a one-of-a-kind blockchain-based secure biomedical image processing system that maintains anonymity. The integrated Healthcare 4.0 assisted multimedia image processing architecture includes an edge layer, fog computing layer, cloud storage layer, and blockchain layer. The edge layer collects and sends periodic medical information from the patient to the higher layer. The multimedia data from the edge layer is securely preserved in blockchain-assisted cloud storage through fog nodes using lightweight cryptography. Medical users then safely search such data for medical treatment or monitoring. Lightweight cryptographic procedures are proposed by employing Elliptic Curve Cryptography (ECC) with Elliptic Curve Diffie-Hellman (ECDH) and Elliptic Curve Digital Signature (ECDS) algorithm to secure biomedical image processing while maintaining privacy (ECDSA). The proposed technique is experimented with using publically available chest X-ray and CT images. The experimental results revealed that the proposed model shows higher computational efficiency (encryption and decryption time), Peak to Signal Noise Ratio (PSNR), and Meas Square Error (MSE).
Scene Text Recognition (STR) involves deciphering textual content embedded within complex, natural scene images, often following detection stages or integrated into end-to-end pipelines. Addressing the challenge of STR in noisy target domains, characterized by inter-domain and intra-domain noise, cluttered backgrounds, and irregular text shapes, this study proposes a robust and understandable framework titled Fusion-Based Adaptation for Scene Text Recognition (FASTR). The framework integrates a primary classifier with an epistemically aware auxiliary classifier to model uncertainty, supported by a novel Adaptive Scale Feature Module (ASFM) that enhances localisation through pixel-level mask prediction and multi-scale fusion. A Triple-Level Confidence (TLC) strategy—categorized into high, medium, and low consistency thresholds—is introduced to enforce consistency loss and improve generalisation across domains. Additionally, a pseudo-labelling scheme refines the adaptation process through self-training under structured domain noise. FASTR is trained and evaluated on both synthetic (SynthText, MJSynth) and real-world (ICDAR 2013, SVT, and IIIT5K) datasets. It achieves a word recognition accuracy of 92.4
Over the past few years, global use of Online Social Networks (OSNs) has increased. The rising use of OSN makes protecting users’ privacy from OSN attacks difficult. Finally, it affects the basic commitment to protect OSN users from such invasions. The lack of a distributed, dynamic, and artificial intelligence (AI)-based privacy-preserving strategy for performance trade-offs is a research challenge. We propose the Distributed Privacy Preservation (DPP) for OSN using Artificial Intelligence (DPP-OSN-AI) to reduce Information Loss (IL) and improve privacy preservation from different OSN threats. DPP-OSN-AI uses AI to design privacy notions in distributed OSNs. DPP-OSN-AI consists of AI-based clustering, l-diversity, and t-closeness phases to achieve the DPP for OSN. The AI-based clustering is proposed for dynamic and optimal clustering of OSN users to ensure personalized k-anonymization to protect from AI-based threats. First, the optimal number of clusters is discovered dynamically with simple computations, and then the Whale Optimization Algorithm is designed to optimally place the OSN users across the clusters such that it helps to protect them from AI-based threats. Because k-anonymized OSN clusters are insufficient to handle all privacy concerns in a distributed OSN environment, we systematically applied the l-diversity privacy idea followed by the t-closeness to it, resulting in higher DPP and lower IL. The DPP-OSN-AI model is assessed for IL Efficiency (ILE), Degree of Anonymization (DoA,) and computational complexity using publically accessible OSN datasets. Compared to state-of-the-art, DPP-OSN-AI model DoA is 15.57% higher, ILE is 17.85% higher, and computational complexity is 3.61% lower.
Wireless Sensor Networks (WSNs) are crucial in the burgeoning Internet of Things (IoT) landscape, serving as a backbone technology that enables myriad applications across various industries. Originating as a simple methodology, WSNs have evolved significantly, propelled by rapid advancements in sensor technology and hardware capabilities. These networks play a pivotal role in collecting and transmitting data, which is essential for the infrastructure of most IoT systems. WSNs operate by deploying sensor nodes across diverse locations to gather environmental data. This scalability and adaptability of WSNs were demonstrated in studies where network coverage was expanded to include 100 and 200 nodes. Notably, the implementation of the innovative FLECH (Fuzzy Logic Energy-efficient Clustering Hierarchy) protocol significantly enhanced energy efficiency, reducing consumption by 12.69
Based on this research, the authors think that quantum technologies could be used to make small-world networks work better so that AI transactions can be trusted. The goal is to build small-world networks powered by quantum mechanics to reduce the risks that come from bad actors and people who don't have permission to join them. This will make it possible for AI agents to converse and do business safely. The ability of AI agents to carry out deals that can be trusted and checked is looked into in terms of the new features of quantum-enhanced small-world networks. The authors also look into how scalable quantum-enhanced small-world networks can be so that AI communities stay safe and reliable. They also look at possible uses for the proposed framework, such as in autonomous systems, healthcare, and the financial sector—all of which rely on AI agents being able to interact reliably and safely with each other. Finally, the authors talk about some of the problems and possible future research directions that come up with creating quantum-enhanced small-world networks that allow global trusted AI transactions.
