KGiSL Institute of Technology (KiTE) is a private engineering college started in 2008 by G. Bakthavathsalam, Founder-Chairman of KG Hospital. It is located at Saravanampatti in Coimbatore, Tamil Nadu, India. The college is affiliated to Anna University. It offers various undergraduate and postgraduate courses leading to the Degree of Bachelor of Engineering (B.E)..
Face detection remains a core challenge in computer vision, particularly for biometric and surveillance systems operating under limited computational resources. While the Viola–Jones (V–J) framework enabled early real-time detection, its robustness is insufficient for modern, unconstrained environments. This paper presents a hybrid, task-oriented extension of the V–J pipeline that integrates hierarchical CNN verification and an explicit Quality Assessment Module (QAM) to enforce biometric readiness. The proposed system combines multi-scale detection, quality-gated filtering, and multiplicative fusion of detection confidence and visual quality, while preserving the reject-fast philosophy of classical methods. Evaluation on WIDER FACE, FDDB, and AFW demonstrates a Conditional Detection Rate of 97.2
Hydrogen generation is a promising solution for achieving clean, sustainable, and renewable energy, playing a vital role in reducing dependence on fossil fuels and mitigating environmental pollution. MXene-metal-organic framework (MOF) hybrid composites have recently attracted considerable interest owing to their outstanding catalytic performance and unique structural benefits. MXenes, with their unique two-dimensional (2D) layered structure, high electrical conductivity, and abundant active sites, facilitate rapid charge transfer and enhance catalytic activity. At the same time, MOFs offer high surface areas, adjustable porosity, and a variety of metal centers, which enhance mass transport, increase adsorption capacity, and improve access to active sites. The integration of MXenes with MOFs generates a synergistic effect, leading to improved hydrogen evolution reaction (HER) performance, increased stability, and an extended operational lifespan. This review critically explores the synthesis strategies, structural characteristics, and catalytic performance of MXenes-MOF hybrids for hydrogen generation. It also highlights the challenges, limitations, and future directions for the large-scale application of these hybrid materials in sustainable hydrogen production.
Hydrogen storage remains a key challenge in achieving a sustainable hydrogen economy. Metal-organic frameworks (MOFs) and metal hydrides have emerged as promising candidates due to their high storage density and tuneable sorption behaviour. This review provides a comprehensive analysis of MOF-metal hydride composites, emphasizing their synergistic effects on hydrogen adsorption, desorption kinetics, and thermodynamic stability. The cooperative mechanisms of nanoconfinement, catalytic activation, and interfacial charge redistribution are highlighted as crucial parameters governing reversible hydrogen release. Comparative evaluation of MgH2-, NaAlH4-, and LiBH4-based systems demonstrates how framework composition and pore geometry influence the hydrogenation-dehydrogenation balance. The integration of multifunctional materials such as MXenes, perovskites, and carbon derivatives further enhances hydrogen transport and structural integrity. Computational modelling and emerging AI-guided design strategies offer additional insight into optimizing interfacial thermodynamics and diffusion pathways. Finally, the review outlines current limitations and future perspectives, providing a roadmap for scalable, durable, and high-capacity MOF-hydride composites tailored for practical solid-state hydrogen storage applications.
An intrusion detection system (IDS) with powerful capabilities that the existing conventional systems are unable to sufficiently supply is required from a security perspective, according to studies of compromised ultra-densified ubiquitous wireless networks that resulted from 6G wireless communications. IDSs are still not strong enough to fend against persistent, unexpected attacks against networks used for wireless communication, particularly on the more recent, extremely susceptible networks. As a result, their accuracy and detection rates are low, and their false-positive and false-negative cases. In this paper, an anomaly detection system (ADS) empowered by a bidirectional 3D quasi-recurrent neural network for securing 5G networks is proposed (5G-ADS-Bi-3DQRNN). The proposed framework's various stages are intended to locate anomalies. At first, the CIC_IDS2017 dataset is utilized to assemble the information network. After that, preprocessing is performed on the network-sourced input data. The preprocessing stage comprises three primary stages: transformation, filtration and standardization using min-max normalization (MMN). The best arrangement of features is chosen utilizing the suggested A-CEWT strategy. In this manner, the picked features go through the utilization of a modern enhancement strategy, similar to the improved red panda optimization algorithm (IRPOA), which changes the weight boundary of A-CEWT to work with a compelling element streamlining technique. In conclusion, the framework utilizes updated features to utilize the Bi-3DQRNN to recognize attack types such as DDoS, savage power, XSS, SQL infusion, penetration, port sweep, botnet attack and normal. The recommended approach is done in Python, and basic assessment measurements like F-measure, MSE, accuracy, sensitivity, specificity and precision are utilized to assess the strategy's exhibition completely. The proposed method attains 21.83%, 26.46% and 30.84% securing superior accuracy over current methods by boosting security controls and making use of cutting-edge 5G and future networks, utilizing an innovative deep reinforcement learning technique (5G-ADS-DRL), deep learning (DL) and machine learning (ML) techniques to create a system for identifying dropping threats on 5G networks (5G-ADS-KNN), and elaborates the next-generation networks using an IDS with dimensionality reduction (5G-ADS-DNN), respectively.
The highly competitive nature of the online food delivery (OFD) market faces a serious retention problem, with acquiring new users typically being much more expensive than retaining existing users. Traditional prediction methods that rely primarily upon static transactional metrics such as recency and frequency are often unable to capture the psychological 'disconfirmation' which occurs prior to churn. To fill this gap, this study proposes a framework based on Expectation-Confirmation Theory (ECT). Unsupervised K-Means clustering was employed to classify a simulated and filtered dataset with 1500 customer records containing behaviour, geography, etc. This framework also couples sentiment analysis from BERT, allowing it to identify psychological "silent" attrition. Heterogeneous cohorts, which exhibit different psychological antecedents (utilitarian versus hedonic), were identified. The empirical results of our analyses demonstrated that Random Forest Classifiers with segment-specific features outperform baseline transactional models (F1 = 0.76) with an F1 Score of 0.89. The visual analytic interface developed provides a holistic view of the consumption process than traditional prediction models, including prescriptive, automated segment-based mitigation strategies. Our findings contradict the assumption that the "frequency-loyalty" model applies to all users. High-frequency discretionary users are found to be elastic in terms of retention and will experience significant churn. By utilising the automated action log, managers can plan targeted, highly efficient retention strategies rather than blanket discounting approaches.
