In December 2019, a pandemic named COVID-19 broke out in Wuhan, China, and in a few weeks, it spread to more than 200 countries worldwide. Every country infected with the disease started taking necessary measures to stop the spread and provide the best possible medical facilities to infected patients and take precautionary measures to control the spread. As the infection spread was exponential, there arose a need to model infection spread patterns to estimate the patient volume computationally. Such patients' estimation is the key to the necessary actions that local governments may take to counter the spread, control hospital load, and resource allocations. This article has used long short-term memory (LSTM) to predict the volume of COVID-19 patients in Pakistan. LSTM is a particular type of recurrent neural network (RNN) used for classification, prediction, and regression tasks. We have trained the RNN model on Covid-19 data (March 2020 to May 2020) of Pakistan and predict the Covid-19 Percentage of Positive Patients for June 2020. Finally, we have calculated the mean absolute percentage error (MAPE) to find the model's prediction effectiveness on different LSTM units, batch size, and epochs. Predicted patients are also compared with a prediction model for the same duration, and results revealed that the predicted patients' count of the proposed model is much closer to the actual patient count.

In the digital era, the proliferation of online reviews through videos has been meteoric and driven by recent technological advancements. The sentiments expressed in these videos drive consumer reliance, decision-making and may shape perception building of general public. The sentiment classification of videos is emerging as a vital area of research in Natural Language Processing (NLP) and is challenging due to complexity of emotions and temporal aspects of modalities. These challenges become more complex for low-resourced languages such as Urdu. Addressing the need for a comprehensive study in this realm, we introduce a generic framework, Urdu Multimodal Sentiment Analysis (UMSA), for emotion detection and sentiment classification of videos. Our fusion-based approach highlights that incorporating additional modalities and cross-modal interactions significantly enhances the analysis. Our research culminates in the creation of the Urdu Sentiments Dataset (USD), a comprehensive collection of Urdu video reviews. In this study, we classify videos using a two-phase analysis approach that incorporates early fusion and ensembling. After fusion, we perform ensembling of two models for each modality: audio, text, and frames. We utilize Long Short-Term Memory (LSTM) networks and Random Forest Classifier for audio. Text-based analysis is conducted using Logistic Regression and the Bidirectional Encoder Representations from Transformers (BERT) model. For frames, we employ Random Forest and Convolutional Neural Networks (CNN). Afterwards, we implement model ensembling across the three modalities. This multimodal integration proves essential in providing a clearer and more comprehensive understanding of the sentiments conveyed and achieved more than 80% accuracy. The validation of this framework is reinforced through a comprehensive case study approach. This independent validation highlights the framework’s robustness and adaptability to real-world scenarios.

Generative AI e.g. Large Language Models (LLMs) can be used to generate new recipes. However, LLMs struggle with more complex aspects like recipe semantics and process comprehension. Furthermore, LLMs have limited ability to account for user preferences since they are based on statistical patterns. As a result, these recipes may be invalid. Evolutionary algorithms inspired by the process of natural selection are optimization algorithms that use stochastic operators to generate new solutions. These algorithms can generate large number of solutions from the set of possible solution space. Moreover, these algorithms have the capability to incorporate user preferences in fitness function to generate novel recipes that are more aligned with the fitness objective. In this paper, we propose the EvoRecipes framework to generate novel recipes. The EvoRecipes framework utilizes both Genetic Algorithm and generative AI in addition to RecipeOn ontology, and RecipeKG knowledge graph. Genetic Algorithm explore the large solution space of encoded recipe solutions and are capable of incorporating user preferences, while LLMs are used to generate recipe text from encoded recipe solutions. EvoRecipes uses a population of context-aware recipe solutions from the RecipeKG knowledge graph. RecipeKG encodes recipes in RDF format using classes and properties as defined in the RecipeOn ontology. Moreover, to evaluate the alignment of EvoRecipe generated recipes with multiple intended objectives, we propose a fitness function that incorporates novelty, simplicity, visual appeal, and feasibility. Additionally, to evaluate the quality of the EvoRecipe generated recipes while considering the subjective nature of recipes, we conducted a survey using multi-dimensional metrics (i.e. contextual, procedural, and novelty). Results show that EvoRecipes generated recipes are novel, valid and incorporate user preferences.