Sperm morphological analysis (SMA) is an essential step in diagnosing male infertility. Using images of human sperm cells, this research proposes a unique sequential deep-learning method to detect abnormalities in semen samples. The proposed technique identifies and examines several components of human sperm. In order to conduct this study, we used the online Modified Human Sperm Morphology Analysis (MHSMA) dataset containing 1540 sperm images collected from 235 infertile individuals. For research purposes, this dataset is freely available online. To identify morphological abnormalities in different parts of human sperm, such as the head, vacuole, and acrosome, we proposed sequential deep neural network (SDNN) architecture. This technique is also particularly effective with low-resolution, unstained images. Sequential deep neural networks (SDNNs) demonstrate high accuracy in diagnosing morphological abnormalities based on the given dataset in our tests on the benchmark. Our proposed algorithm successfully detected abnormalities in the acrosome, head, and vacuole with an accuracy of 89%, 90%, and 92%, respectively. It is noteworthy that our system detects abnormalities of the acrosome and head with greater accuracy than current state-of-the-art approaches on the suggested benchmark. On a low-specification computer/laptop, our algorithm also requires less execution time. Additionally, it can classify photos in real time. Based on the results of our study, an embryologist can quickly decide whether to use the given sperm.

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.

Citrus family consists of a variety of eatable, consumable and usable items with varying nutritional contents. Naked eye citrus classification needs expert human effort, which provides poor decision reliability. The unreliable classification decision may be extremely hazardous when the citrus is being classified for exports or usage in pharmacy products and various food items. In this paper, citrus fruit has been classified on shape and texture features. Principal Component Analysis (PCA) was used as a methodology to explore statistical findings. The average accuracy of the system proposed is 84%. This system can be implemented on pharmacy stores, food production units, or industries, and citrus export centers for reliable citrus fruit classification.