Supply chain resilience and efficiency are vital in industries characterized by volatile demand and uncertain supply, such as textiles and personal protective equipment (PPE). Traditional forecasting and optimization approaches often operate in isolation, limiting their real-world effectiveness. This paper proposes a Hybrid AI Framework for Demand–Supply Forecasting and Optimization (HAF-DS), which integrates a Long Short-Term Memory (LSTM)–based demand forecasting module with a mixed-integer linear programming (MILP) optimization layer. The LSTM captures temporal and contextual demand dependencies, while the optimization layer prescribes cost-efficient replenishment and allocation decisions. The framework jointly minimizes forecasting error and operational cost through embedding-based feature representation and recurrent neural architectures. Experiments on textile sales and supply chain datasets show significant performance gains over statistical and deep learning baselines. On the combined dataset, HAF-DS reduced Mean Absolute Error (MAE) from 15.04 to 12.83 (14.7%), Root Mean Squared Error (RMSE) from 19.53 to 17.11 (12.4%), and Mean Absolute Percentage Error (MAPE) from 9.5% to 8.1%. Inventory cost decreased by 5.4%, stockouts by 27.5%, and service level rose from 95.5% to 97.8%.

The problem of fake news detection (FND) is becoming increasingly important in the field of natural language processing (NLP) because of the rapid dissemination of misleading information on the web. Large language models (LLMs) such as GPT-4. Zero excels in natural language understanding tasks but can still struggle to distinguish between fact and fiction, particularly when applied in the wild. However, a key challenge of existing FND methods is that they only consider unimodal data (e.g., images), while more detailed multimodal data (e.g., user behaviour, temporal dynamics) is neglected, and the latter is crucial for full-context understanding. To overcome these limitations, we introduce M3-FND (Multimodal Misinformation Mitigation for False News Detection), a novel methodological framework that integrates LLMs with multimodal data sources to perform context-aware veracity assessments. Our method proposes a hybrid system that combines image-text alignment, user credibility profiling, and temporal pattern recognition, which is also strengthened through a natural feedback loop that provides real-time feedback for correcting downstream errors. We use contextual reinforcement learning to schedule prompt updating and update the classifier threshold based on the latest multimodal input, which enables the model to better adapt to changing misinformation attack strategies. M3-FND is tested on three diverse datasets, FakeNewsNet, Twitter15, and Weibo, which contain both text and visual social media content. Experiments show that M3-FND significantly outperforms conventional and LLM-based baselines in terms of accuracy, F1-score, and AUC on all benchmarks. Our results indicate the importance of employing multimodal cues and adaptive learning for effective and timely detection of fake news.

Generative Artificial Intelligence (AI) is reshaping digital marketing by creating automated content, personalizing campaigns, and offering new ways to engage consumers. This systematic review examines research on generative AI, highlighting both its technological progress and the ethical, technical, and organizational hurdles that could limit its use. We used a PRISMA-based method to search major databases (ACM Digital Library, IEEE Xplore, and Scopus) for peer-reviewed studies published from 2018 to 2025. Our findings reveal major gains in text creation, image generation, and multimodal campaigns, which can lower costs and spark creative thinking. Still, data privacy, bias in models, and laws around compliance show the need for clear and responsible adoption. By bringing in ideas from Innovation Diffusion Theory and the Technology Acceptance Model, this review shows how organizational culture and perceived value interact with ethical frameworks to shape how generative AI tools take hold. We provide insights for marketers who want to apply generative AI in a responsible way and set a path for future research aimed at protecting consumer trust.

This study offers an in-depth exploration of traveling wave solutions to the simplified modified Camassa-Holm (SMCH) equation through the application of the modified S-expansion method. Utilizing a traveling wave transformation, the SMCH equation is converted into a nonlinear ordinary differential equation, from which a wide range of exact solutions is systematically obtained. The modified S-expansion method, implemented using the Maple software, proves to be a robust and efficient analytical tool, yielding a variety of soliton solutions such as kink, bright, and dark solitons. To capture the intricate behavior of these solutions, MATLAB is employed to produce detailed 2D, 3D, and contour visualizations that reveal their structural features and propagation dynamics. A comparative assessment with the modified simple equation method and the exp(-ϕ(η))-expansion method highlights the modified S-expansion method's superior accuracy, simplicity, and adaptability to solve nonlinear partial differential equations. Significantly, the method also extends to fractional-order equations, showcasing its broad applicability in nonlinear system analysis. Key solutions are graphically represented under constrained parameter values to emphasize the core propagation features. Overall, this work enhances the current analytical methods to solve both classical and fractional-order nonlinear partial differential equations (PDEs) and offers a valuable foundation for future research into closed-form traveling wave solutions across various disciplines.