Applications of Artificial Intelligence (AI) has revolutionized the railway sector in recent years and are increasingly essential to the modernization of the railway industry. By making significant improvements in operational efficiency, safety, digital infrastructure, security, and passenger satisfaction, AI and its sub domains such as Machine Learning (ML), Deep Learning (DL) etc. have become integral to railway systems worldwide. This paper presents an in-depth analysis and review of AI applications across multiple domains of railways, including monitoring, predictive maintenance, traffic management, and passenger services etc. The role of AI extends beyond data prediction, maintenance, and management to the design and deployment of advanced controllers now used in rail vehicles. Furthermore, this paper highlights the contribution of AI algorithms to cybersecurity, particularly in preventing cyber-attacks on railway infrastructure. Several case studies are discussed to provide deeper insights into how AI algorithms are transforming modern railways into efficient, resilient, and passenger-centric systems. This paper provides a comprehensive review of AI applications with bibliometric analysis in almost all the domains of railway system with 360-degree coverage. It also discusses the strengths and limitations of present AI applications and highlights the gap analysis with expected future trends.
The segmentation of blood vessels through color fundus images is a difficult and time-consuming task that requires experienced clinicians. Recently, researchers have shown that blood vessel segmentation using methods based on deep neural networks has achieved highly satisfactory results. This motivates us to employ a fast and accurate deep learning-based method that can be used in blood vessel segmentation. Five improved deep learning-based networks (U-Net, DenseU-Net, LadderNet, R2U-Net, and ATTU-Net), along with an enhanced customized R2-ATT U-Net deep learning network, have been employed to segment the retinal blood vessel tree. Segmentation using patches extraction is executed, where we have used 10,000 patches per image, in total, 8000 for training and 2000 for testing public benchmark STARE dataset images. Initially, we performed the training, followed by testing for all six models using the patch extraction approach. All the aspects of the testing phase (test log, ROC curve, precision recall curves, and confusion matrix) and statistical performance measuring metrics (accuracy, sensitivity, specificity, F1 score, precision, and AUC values) are covered in this work and are also shown in the form of tables and graphs. An in-depth performance evaluation analysis of these six implemented improved nets has been performed to evaluate the segmentation process. We got the best result in the case of LadderNet, with an accuracy of 0.971, which is comparable to recent state-of-the-art studies. In terms of accuracy, the enhanced customized R2-ATT U-Net deep learning network is also highly satisfactory, being near the best model, LadderNet. The experiment results demonstrate that the proposed methodology achieves satisfactory performance in the retinal blood vessel extraction domain and can help ophthalmologists predict many eye-related diseases at a preliminary stage.
Globally, patients with diabetes, diabetic retinopathy, cancer, and heart disease are growing rapidly in developed and developing countries. As a result of these ailments, the rate of human mortality and vision loss has risen dramatically. The design and development of computer-based prediction systems may facilitate the appropriate treatment of these four illnesses by medical professionals. For the design of an efficient and fast prediction (or classification) system, it is necessary to use efficient feature selection techniques to reduce the complexity of the feature space. If there are n features, then there is a possibility that 2(n) subsets of features can be created, and testing all of these subsets of selected features would require a significant amount of time. The suggested technique is to investigate the application of ant-lion based optimization to choose a subset of features. The chosen characteristics are used to train and evaluate four classifiers (and their ensemble) based on machine learning. The study used over three public benchmark datasets and one privately composed dataset, each one was disease-specific. The performance of the recommended strategy was evaluated using five performance assessment measures. This adjustment significantly improves the outcome. The strategy may decrease the initial feature set by up to 50% without impacting performance (in terms of accuracy). We can get maximum accuracies of 84.44% for the heart disease dataset, 79.99% for the diabetes dataset, 98.52% for the diabetic retinopathy dataset, and 97.18% for the skin cancer dataset. This empirical research will help doctors and all people make better decisions by giving them a second opinion.
The fast development of cyber communications, multimedia distribution, remote working have promoted the demand to transmit sensitive information through secure means in both the public and the private networks. The advent of massive quantum computers is rendering traditional cryptographic algorithms like RSA and Elliptic Curve Cryptography (ECC) insecure because they can crack the classical public-key algorithms like the Shor and Grover algorithms. This brings an immediate need of hybrid cryptographic systems, which integrate classical, quantum, and post-quantum algorithms to provide confidentiality, integrity, authentication, and future security beyond the quantum threat horizon.The paper is a proposal of a Hybrid Quantum-Post-Quantum Cryptographic Framework of transmitting files safely. It starts by aggregating files, which is a process to compress several files, images, videos, and multimedia files that users have chosen into one file to minimize redundancy and ease encryption. The AES-256 encrypted file is in GCM mode and provides confidentiality and integrity of the compressed file.The dual-layer mechanism ensures key establishment security. To begin with, Quantum Key Distribution (QKD) based on the protocols of BB84/E91 allows the Sender and the Receiver to generate a Quantum Secret Key (QSK) by exchanging quantum bits in quantum channel. Constant monitoring of the error rate facilitates automatic eavesdropping detection, and guarantees the keys generation is made when the conditions are secure, as well as the safeguarding of interception and man-in-the-middle attacks.A post-quantum layer is provided to ensure long-term security against quantum cryptanalysis, which uses Kyber, a NIST-approved lattice-based Key Encapsulation Mechanism (KEM). The Receiver creates a key pair of Kyber and disseminates the public key to the Sender. By using encapsulation, the Sender gets a PQC ciphertext and a Shared Secret (SS), with decapsulation on the Receiver side giving ensure that only participants of good faith get the same secret value.The hybridization phase consists of combining the QSK of QKD and SS of Kyber with the help of HKDF-SHA256 to obtain a Final Wrap Key (FWK). AES-GCM encrypts the key of file encryption by wrapping it with FWK which allows a secure and authenticated transfer of the key. The Sender sends four messages: encrypted file, Kyber ciphertext, wrapped AES key and the initialisation vector. At Receiver end, FWK is calculated once again with the help of QSK and SS so that the original data can be decrypted with the help of AES key.The suggested framework provides a defense-in-depth solution based on the combination of quantum security, post-quantum resilience and authenticated symmetric encryption. It can be analyzed that there is a strong resistance to classical and quantum adversaries, scalability, and compatibility with the existing communication networks. This renders the model to be appropriate to secure government communication, military systems, data exchange in healthcare environments, cloud storage and financial infrastructures. Keywords— Quantum Key Distribution (QKD), Post-Quantum Cryptography (PQC), Kyber,Key Encapsulation Mechanism (KEM), HKDF-SHA256, Quantum Secret Key (QSK), GCM Mode.
Buckwheat ( Fagopyrum esculentum ) is a nutritionally rich pseudocereal recognized for its high-quality proteins, dietary fiber, essential minerals, and bioactive compounds. Due to its gluten-free nature and low glycemic index, buckwheat has gained considerable importance in functional foods and therapeutic diets. The present review and analytical study evaluates the nutritional composition, health benefits, spoilage characteristics, storage conditions, and safety parameters of buckwheat flour. Comparative nutritional analysis with wheat flour, rice flour, and commercial snack flour demonstrates that buckwheat flour contains higher protein (approximately 16.0%), fiber, ash content, and micronutrients such as magnesium, iron, zinc, manganese, and copper. Experimental observations indicate that improper storage conditions significantly influence flour quality through oxidation, fungal contamination, moisture absorption, and pH variation. Organoleptic analysis, microbiological testing, Fourier-transform infrared spectroscopy (FTIR), peroxide value analysis, and chromatographic methods were used to evaluate freshness and spoilage. Results confirm that buckwheat flour remains suitable for human consumption when stored under controlled temperature and low-humidity conditions. Refrigerated storage extended shelf life up to 3 months, whereas room-temperature exposure accelerated rancidity and microbial growth within 15–30 days. This manuscript highlights analytical techniques for quality assessment and provides safe consumption recommendations for consumers and food industries.
