Augmented reality (AR) has gained enormous popularity and acceptance in the past few years. AR is indeed a combination of different immersive experiences and solutions that serve as integrated components to assemble and accelerate the augmented reality phenomena as a workable and marvelous adaptive solution for many realms. These solutions of AR include tracking as a means for keeping track of the point of reference to make virtual objects visible in a real scene. Similarly, display technologies combine the virtual and real world with the user’s eye. Authoring tools provide platforms to develop AR applications by providing access to low-level libraries. The libraries can thereafter interact with the hardware of tracking sensors, cameras, and other technologies. In addition to this, advances in distributed computing and collaborative augmented reality also need stable solutions. The various participants can collaborate in an AR setting. The authors of this research have explored many solutions in this regard and present a comprehensive review to aid in doing research and improving different business transformations. However, during the course of this study, we identified that there is a lack of security solutions in various areas of collaborative AR (CAR), specifically in the area of distributed trust management in CAR. This research study also proposed a trusted CAR architecture with a use-case of tourism that can be used as a model for researchers with an interest in making secure AR-based remote communication sessions.

Modern agriculture faces critical challenges, including climate change induced water shortage, inefficient resource utilization, and reducing soil health which reduce sustainability and reduce crop yields. Traditional farming methods, dependent on manual observation and generalized practices, often lack the precision needed to address these growing issues. To meet these demands, this study presents an artificial intelligence (AI) powered smart agriculture system that integrates deep learning (DL), Internet of Things (IoT), and explainable artificial intelligence (XAI) to enable intelligent, data-driven farming. This study addresses key challenges such as ineffective soil management, poor irrigation practices, and the absence of personalized crop and fertilizer recommendations. IoT-based sensors provide real-time soil analysis, measuring critical parameters such as nutrient levels, moisture, and temperature. Advanced DL models were employed for various tasks in the AI-Driven Smart Agriculture System. The Transformer-based Tabular Learning (TTL) model for irrigation advice gives an accuracy of 99.13%. For soil analysis, the TabNet regressor achieved a root mean square error (RMSE) of 1.51 and an R² score of 98.7%, while XAI techniques were used to explain and interpret its predictions. The Sparse Weighted Fusion Transformer (SwiFT) model for crop recommendation gives an accuracy of 98.75%. For fertilizer recommendation, the TabNet classifier achieved an accuracy of 99.3%, with XAI techniques applied to explain the reasoning behind its predictions. These results demonstrate that the system delivers precise and actionable insights. A weather Application Programming Interface (API) is integrated to support timely irrigation decisions through accurate forecasting. A chatbot interface is also added which enhances system usability, accessibility and user-friendliness for farmers. The proposed model improves crop productivity, optimizes resource use, and supports adaptation to environmental changes. By leveraging AI and IoT technologies, the proposed model gives a solution which helps in sustainable agriculture, environmental resilience, and global food security, thus benefiting stakeholders ranging from individual farmers to large-scale agricultural business. Future work will explore real-time adaptive control mechanisms and expand model generalization across diverse geographical region.

Over the last two decades, social media platforms have grown dramatically. Twitter and Facebook are the two most popular social media platforms, with millions of active users posting billions of messages daily. These platforms allow users to have freedom of expression. However, some users exploit this facility by disseminating hate speeches. Manual detection and censorship of such hate speeches are impractical; thus, an automatic detection mechanism is required to detect and counter hate speeches in a real-time environment. Most research in hate speech detection has been carried out in the English language. Still, minimal work has been explored in other languages, mainly Urdu written in Roman Urdu script. A few research have attempted machine learning, and deep learning models for Roman Urdu hate speech detection; however, due to a scarcity of Roman Urdu resources, and a large corpus with defined annotation rules, a robust hate speech detection model is still required. With this motivation, this study contributes in the following manner: we developed annotation guidelines for Roman Urdu Hate Speech. Second, we constructed a new Roman Urdu Hate Speech Dataset (RU-HSD-30K) that was annotated by a team of experts using the annotation rules. To the best of our knowledge, the Bi-LSTM model with an attention layer for Roman-Urdu Hate Speech Detection has not been explored. Therefore, we developed a context-aware Roman Urdu Hate Speech detection model based on Bi-LSTM with an attention layer and used custom word2vec for word embeddings. Finally, we examined the effect of lexical normalization of Roman Urdu words on the performance of the proposed model. Different traditional as well as deep learning models, including LSTM and CNN models, were used as baseline models. The performance of the models was assessed in terms of evaluation matrices like accuracy, precision, recall, and F1-score. The generalization of each model is also evaluated on a cross-domain dataset. Experimental results revealed that Bi-LSTM with attention outperformed the traditional machine learning models and other deep learning models with an accuracy score of 0.875 and an F-Score of 0.885. In addition, the results demonstrated that our suggested model (Bi-LSTM with Attention Layer) is more general than previous models when applied to unseen data. The results confirmed that lexical normalization of Roman Urdu words enhanced the performance of the suggested model.

Social media applications, such as Twitter and Facebook, allow users to communicate and share their thoughts, status updates, opinions, photographs, and videos around the globe. Unfortunately, some people utilize these platforms to disseminate hate speech and abusive language. The growth of hate speech may result in hate crimes, cyber violence, and substantial harm to cyberspace, physical security, and social safety. As a result, hate speech detection is a critical issue for both cyberspace and physical society, necessitating the development of a robust application capable of detecting and combating it in real-time. Hate speech detection is a context-dependent problem that requires context-aware mechanisms for resolution. In this study, we employed a transformer-based model for Roman Urdu hate speech classification due to its ability to capture the text context. In addition, we developed the first Roman Urdu pre-trained BERT model, which we named BERT-RU. For this purpose, we exploited the capabilities of BERT by training it from scratch on the largest Roman Urdu dataset consisting of 173,714 text messages. Traditional and deep learning models were used as baseline models, including LSTM, BiLSTM, BiLSTM + Attention Layer, and CNN. We also investigated the concept of transfer learning by using pre-trained BERT embeddings in conjunction with deep learning models. The performance of each model was evaluated in terms of accuracy, precision, recall, and F-measure. The generalization of each model was evaluated on a cross-domain dataset. The experimental results revealed that the transformer-based model, when directly applied to the classification task of the Roman Urdu hate speech, outperformed traditional machine learning, deep learning models, and pre-trained transformer-based models in terms of accuracy, precision, recall, and F-measure, with scores of 96.70%, 97.25%, 96.74%, and 97.89%, respectively. In addition, the transformer-based model exhibited superior generalization on a cross-domain dataset.

Various Artificial Intelligence (AI) techniques in water resource management highlight the current methodologies’ strengths and limitations in forecasting, optimization, and control. We identify a gap in integrating these diverse approaches for enhanced water prediction and management. We critically analyze the existing literature on artificial neural networks (ANNs), deep learning (DL), long short-term memory (LSTM) networks, machine learning (ML) models such as supervised learning (SL) and unsupervised learning (UL), and random forest (RF). In response, we propose a novel framework that synergizes these techniques into a unified, multi-layered model and incorporates a digital twin and a multi-modal transformer approach. This integration aims to leverage the collective advantages of each method while overcoming individual constraints, significantly enhancing prediction accuracy and operational efficiency. This paper sets the foundation for an innovative digital twin-integrated solution, focusing on reviewing past works as a precursor to a detailed exposition of our proposed model in a subsequent publication. This advanced approach promises to redefine accuracy in water demand forecasting and contribute significantly to global sustainability and efficiency in water use.