This paper introduces BioGPT, a generative transformer-based framework designed to advance personalized genomic medicine and rare disease diagnosis. Unlike conventional models that process either genomic sequences or clinical narratives in isolation, BioGPT employs a cross-modal architecture that effectively fuses both data streams, enabling precise classification and interpretable natural language generation. The model is pre-trained on large-scale genomic and electronic health record datasets and fine-tuned for rare disease tasks. Comprehensive experiments demonstrate BioGPT’s superiority over state-of-the-art biomedical models, including RarePT, BioBERT, and DNABERT, with improvements of up to 10% in F1-score and over 20 BLEU points in justification fluency. Ablation studies highlight the essential contribution of cross-attention mechanisms in enhancing multi-modal synergy. Furthermore, attention-based interpretability techniques show strong alignment with expert clinical markers, ensuring trust and transparency in diagnostic outputs. With sub-second inference times and compatibility with edge deployment strategies, BioGPT proves both effective and deployable in real-world clinical settings. This work establishes BioGPT as a robust, scalable, and explainable AI solution, setting a new benchmark for intelligent diagnostic systems in precision medicine.

In the modern era, new and innovative ways of securing data and communications are continuously developing. One such recent development is using the concept of DNA as a means of data encryption. In this work, we propose a new approach to encrypt data and communications on the MAVLink protocol for unmanned aerial vehicles (UAVs) using a lightweight GIFT algorithm and dynamic DNA coding (with binary bits). MAVLink is a communication protocol for UAVs, which is currently unencrypted and can easily be intercepted by anyone. As such, a secure MAVLink protocol has long been needed in the UAV industry. We describe a novel secure communication protocol for UAVs using dynamic DNA coding to encrypt MAVLink packets, which we call DMAV. Experimental results show that this novel means of securing the MAVLink protocol performs better than the traditional method (i.e., using public and private key cryptography). Therefore, the proposed approach could potentially change the way secure communications are conducted between UAVs in the future.

Human-Centric Artificial Intelligence (HCAI) is rapidly emerging as a transformative paradigm, shifting the focus of AI development from mere algorithmic optimization to ethical alignment, user trust, and societal integration most notably within the critical domain of healthcare. This review offers a comprehensive examination of the principles, architecture, challenges, and future directions underpinning HCAI, with an emphasis on its applications in health-related contexts. We begin by exploring the conceptual foundations of human-centricity, including core values such as transparency, fairness, autonomy, and privacy, all of which are essential in sensitive environments like clinical decision-making and patient data management. The paper then surveys key enabling technologies such as Explainable AI (XAI), Human-in-the-Loop learning, affective computing, and multi-agent collaboration demonstrating how these approaches operationalize human alignment in real-world systems, especially in personalized healthcare delivery and diagnostic support. Societal implications are critically evaluated, encompassing trust, data sovereignty, algorithmic bias, regulatory compliance, and cross-cultural adaptability, which are particularly pronounced in global health systems. We highlight the limitations of existing benchmarks and propose a multi-metric, user-centered evaluation framework capable of assessing both technical robustness and alignment with human values in healthcare and beyond. Finally, we identify open research challenges and outline a strategic agenda that integrates cognitive science, ethical theory, and participatory design. This review aims to serve as both a foundational reference and a forward-looking roadmap for researchers, developers, and policymakers striving to build AI systems that are not only intelligent, but also responsible, inclusive, and aligned with human dignity, particularly in life-critical domains like healthcare

This paper introduces a quantum-inspired ultra-lightweight encryption algorithm tailored for Internet of things devices with limited resources. The proposed algorithm excels in processing speed, memory usage, and energy efficiency, significantly outperforming existing lightweight cryptographic algorithms. With a processing speed of 12.4 ms, memory usage of 3.2 kilobytes, and energy consumption of 0.7 milli-Joules per kilobyte, the proposed algorithm stands out for its robust security and potential to enhance the security of Internet of things devices across various applications. This paper explores the methodology behind the proposed algorithm, comparing its performance metrics with conventional S-box generation approaches, and demonstrates its superiority in both theoretical and practical aspects.

The Deep Processing Optimization Network (DPON) is a novel deep learning framework designed to enhance image processing and classification tasks. By incorporating advanced techniques such as convolutional layers, residual connections, attention mechanisms, and global average pooling, DPON optimizes both performance and computational efficiency. The architecture is carefully structured to address key limitations in traditional convolutional neural networks (CNNs), particularly in terms of feature extraction and gradient flow, while maintaining a balance between accuracy and processing speed. Through comprehensive evaluations on benchmark datasets, including CIFAR-10, DPON demonstrates superior performance across multiple metrics, including accuracy, precision, recall, and F1-score, consistently outperforming established models such as ResNet-50, EfficientNet-B0, and DenseNet-121. The integration of attention mechanisms allows DPON to focus on the most relevant features of the input, improving classification precision while reducing misclassification rates. Additionally, the use of global average pooling significantly reduces the number of parameters, enhancing computational efficiency without sacrificing accuracy. DPON's robust design makes it highly adaptable for a wide range of applications, from image classification to real-time systems requiring fast inference times. This paper presents the architectural details of DPON, its mathematical foundation, and extensive performance evaluations, demonstrating its potential as a state-of-the-art solution for modern image processing challenges.