ABSTRACT
Language is a method by which individuals express their thoughts. Each language has its own alphabet and numbers. Oral and written communication are both effective means of human interaction. However, each language has a sign language equivalent. Hearing-impaired and/or nonverbal individuals communicate through sign language. BDSL is the abbreviation for the Bangla sign language. The dataset contains images of hand signs in Bangla. The collection comprises 49 individual sign language images of the Bengali alphabet. BDSL49 is a set of 29,490 images with 49 labels. During data collection, images of fourteen distinct adults, each with a unique appearance and context, were captured. During data preparation, numerous strategies have been utilized to reduce noise. This dataset is available for free to researchers. Using techniques such as machine learning, computer vision, and deep learning, they are able to develop automated systems. Moreover, two models were applied to this dataset. The first is for detection, and the second is for identification.
ABSTRACT
Misinformation such as on coronavirus disease 2019 (COVID-19) drugs, vaccination or presentation of its treatment from untrusted sources have shown dramatic consequences on public health. Authorities have deployed several surveillance tools to detect and slow down the rapid misinformation spread online. Large quantities of unverified information are available online and at present there is no real-time tool available to alert a user about false information during online health inquiries over a web search engine. To bridge this gap, we propose a web search engine misinformation notifier extension (SEMiNExt). Natural language processing (NLP) and machine learning algorithm have been successfully integrated into the extension. This enables SEMiNExt to read the user query from the search bar, classify the veracity of the query and notify the authenticity of the query to the user, all in real-time to prevent the spread of misinformation. Our results show that SEMiNExt under artificial neural network (ANN) works best with an accuracy of 93%, F1-score of 92%, precision of 92% and a recall of 93% when 80% of the data is trained. Moreover, ANN is able to predict with a very high accuracy even for a small training data size. This is very important for an early detection of new misinformation from a small data sample available online that can significantly reduce the spread of misinformation and maximize public health safety. The SEMiNExt approach has introduced the possibility to improve online health management system by showing misinformation notifications in real-time, enabling safer web-based searching on health-related issues.
