This research proposes an automatic approach for classifying pigeon pox lesions using the DenseNet model, a deep learning architecture renowned for its dense connectivity patterns and efficient feature reuse. Pigeon pox, caused by the avipox virus, poses significant threats to avian populations and the poultry industry worldwide. Traditional diagnostic methods are laborious and time-consuming, prompting the exploration of machine learning techniques for automated disease diagnosis. The proposed approach leverages DenseNet for feature extraction from pigeon pox images, aiming to develop a robust and accurate classification system capable of distinguishing between healthy and infected birds based on visual features extracted from skin lesions. The study systematically evaluates the performance of the DenseNet model, demonstrating exceptional discriminatory power with an AUC of 0.99, accuracy of 0.98, and F1-score of 0.98. Comparative analysis with other deep learning models further validates DenseNet's superiority in pigeon pox classification. Overall, the proposed approach offers a promising solution for the early detection and control of pigeon pox, thereby improving bird health and welfare while mitigating economic losses in the poultry industry.

Accurate identification and classification of intestinal parasitic eggs are essential for effectively diagnosing and treating parasitic infections. Traditional manual microscopic diagnosis methods are time-consuming and prone to errors. Recent advancements in technology have shown potential in automating this process, yet more advanced and accurate methods are needed to overcome existing challenges. The proposed research aims to develop a robust and efficient approach for intestinal parasitic egg segmentation and classification using the Mask R-CNN algorithm. The research begins with an extensive review of existing literature on intestinal parasitic infections, their impact, and the limitations of current diagnostic methods. It further explores the principles of image processing, medical imaging techniques, and the fundamentals of the Mask R-CNN algorithm. The proposed work involves accessing a dataset comprising 10 thousand images of 10 different types of parasitic eggs from IEEE and preprocessing them to enhance their quality. The Mask R-CNN algorithm is then trained on this dataset, enabling it to accurately segment and classify intestinal parasitic eggs. Performance evaluation uses quantitative measures such as Precision, recall, and F1-score (shown in Table [1](#tbl-cap-0001)). The results demonstrate the effectiveness of the Mask R-CNN algorithm in segmenting and classifying intestinal parasitic eggs, achieving an overall accuracy of 95%. These findings contribute to intestinal parasitic egg analysis by providing an advanced and automated approach for SegmentationSegmentation and classification. Future research endeavors could expand the dataset, optimise computational efficiency, and integrate the developed algorithm into practical diagnostic tools.

5-methylcytosine (m 5C) is a widely known epigenetic moderation in RNA types. Methyltransferases catalyze the genesis of m5C. This site of RNA plays a crucial role in many biological activities. For many years in DNA, the synthetic process and biological role of m 5C sites have remained the concentrating domain for researchers. Recently, many characters of RNA m 5C sites have been discovered, but it is still considered in their infancy. The accurate and systematic detection and classification of m 5C remains a challenging task. The existence of m 5C sites shows a thriving role in numerous organic activities. Machine learning techniques are alternatives to laboratory experiments, which will ease the m 5C site’s identification in Homo sapiens. This article presents a novel computational model named m 5C-TNkmer to extract RNA sequences. The model is enriched with the k-mer feature extraction technique. Four subdatasets of the primary data set are created: DNC, TNC, tetra-NC, and penta-NC. The results highlighted that m 5C-TNKmers achieved 96.15% accuracy. The suggested technique is a talented one that will help scientists correctly identify RNA m 5C sites and their modification. It provides a clue to better understanding genetic function and controlling roles.

In today’s rapidly evolving digital landscape, social media platforms such as Twitter and Facebook are among the most popular microblogging applications, playing an important role in quickly disseminating up-to-date information to a large user base. In addition to being valuable sources of entertainment and platforms for business campaigns, social media apps significantly impact political activities in developing democracies. However, social media networks often become sources of rapid dissemination of fake news, viral videos, hate speech, and false articles, leading to political propaganda. Existing studies need to address how Pakistan’s three major political parties use social media platforms for this purpose. In this study, we used exploratory data analysis (EDA) to explore and analysed the initial content of social networks to understand, identify, and gain insights for further analysis. We developed a web scraper, a valuable tool used in data science, to extract unstructured content from the official Twitter and Facebook accounts, primarily used to spread political propaganda publicly. The web scraper automatically extracts various information from Facebook posts, including likes, shares, comments, and views. It extracts information such as likes, comments, and retweets from tweets. The collected data is then processed and analyzed using statistical methods to gain knowledge and insights from social media sites. One month of data analysis suggests that Pakistan Tehreek-e-Insaf (PTI) posted 79.37% more content on Facebook, while Pakistan Muslim League Nawaz (PML (N)) tweeted 89.30% more on Twitter compared to other parties. This activity is part of their political propaganda to build a narrative and shape public opinion among their followers and voters in Pakistan.