Graph Neural Networks (GNNs) have become increasingly prominent in Natural Language Processing (NLP) due to their ability to model intricate relationships and contextual connections between texts. Unlike traditional NLP methods, which typically process text linearly, GNNs utilize graph structures to represent the complex relationships between texts more effectively. This capability has led to significant advancements in various NLP applications, such as social media interaction analysis, sentiment analysis, text classification, and information extraction. Notably, GNNs excel in scenarios with limited labeled data, often outperforming traditional approaches by providing deeper, context-aware... More >

The rapid advancement of AI-based language models has transformed the field of Natural Language Processing (NLP) into a powerful tool for text generation. This study evaluates the performance of models in different categories such as factual accuracy, creative writing, open-ended writing, and technical explanation. We have considered three popular and advanced large language models (LLMs) for this analysis. To quantify their performance, we have applied a combination of statistical and linguistic metrics. We have used Dale-Chall to analyze the readability score of the responses. For lexical diversity, we have used the type-token ratio technique. In addition, a cosine similarity with TF-IDF i... More >

This paper advances a decision-aligned post-processing layer for government bond yield forecasts, turning competent sequence predictions into curve-consistent and economically calibrated outputs with minimal engineering burden. Starting from capacity-fair baselines in the LSTM, GRU and compact transformer families, used only to generate initial point forecasts for five, ten and thirty year maturities at short horizons, we add two model-agnostic stages. A curve consistency projection enforces monotone ordering across maturities and, when warranted, mild convexity while preserving local signal. An asymmetric economic calibration then learns a monotone mapping that down-weights the costlier sid... More >

Yield optimization in advanced manufacturing rarely proceeds as a tidy pipeline; it arises from the gradual convergence of evidence across spatial wafer patterns, multivariate metrology, and asynchronous process and equipment events that interact in ways that are only partially observable. Prior studies often separate these modalities, assigning convolutional encoders to wafer maps, sequence models to metrology, and template based encoders to logs, an arrangement that can perform well locally yet struggles to sustain cross-modal alignment or to reason over the hierarchy that links defects to steps and equipment. Building on these observations, we introduce a manufacturing semantics oriented... More >

The rapid global deployment of solar photovoltaic (PV) technology presents a significant and often overlooked challenge: the effective management of end-of-life (EoL) solar panels. This issue is particularly acute in developing and emerging economies, where established reverse logistics infrastructure is often lacking. A critical limitation in current academic literature is the oversimplified forecasting of EoL waste streams, which fails to account for the dynamic interplay of socio-economic, policy, and environmental variables. To bridge this gap, we propose a novel decision support system (DSS) for the design of a sustainable reverse logistics network. Our system uniquely integrates a hybr... More >

The growing presence of malicious bot accounts on social media poses a threat to the authenticity of online communities, as they amplify misinformation, spread spam, and manipulate engagement. Reliable detection of these accounts is therefore essential to protect the integrity of platforms such as Instagram. This study introduces a deep learning–based detection framework built on the CrossGatedTabular (CGT) architecture, designed to learn complex patterns in user activity. To strengthen evaluation, two publicly available datasets of Instagram accounts were merged into a comprehensive benchmark representing diverse user behaviors. Natural language processing (NLP) was applied to refine text... More >

This paper presents a novel hybrid copy–move forgery detection method that combines the efficiency of FAST-BRIEF (for rapid keypoint detection and binary descriptors) with the robustness of SIFT (for scale- and rotation-invariant feature matching). The proposed framework employs g2NN matching for accurate feature correspondence, followed by morphological processing and LSC-SSIM superpixel segmentation for precise localization of tampered regions. The method is evaluated on 30 diverse test images from benchmark datasets comprising over 700 images, achieving a 95% F-measure with an average CPU time of 6.02 seconds. It demonstrates strong resilience to geometric transformations (rotation, sca... More >

The growing demand for secondary use of electronic health records (EHRs) in clinical research has amplified the importance of effective de-identification of protected health information (PHI) to comply with privacy regulations such as HIPAA. Manual annotation remains error-prone, time-consuming, and inconsistent across healthcare institutions, while existing automated systems often face trade-offs between accuracy, interpretability, and computational cost. This study proposes a novel hybrid de-identification framework that integrates neural, statistical, and rule-based approaches to achieve high recall, operational efficiency, and deployment feasibility in real-world healthcare settings. More >