Computational Intelligence
Kaushal Kishore Rao Mangalore; Nikhitha Pradeep; Bhawesh Rajpal; Nitin Prasad; Ravi Shastri
Abstract
The move to standardize Indian Sign Language has created an opportunity for researchers to focus on solving local problems, to increase its reach. In this paper, a survey and assessment of the techniques applied to the recognition and conversion of Indian Sign Language are performed. An overview of the ...
Read More
The move to standardize Indian Sign Language has created an opportunity for researchers to focus on solving local problems, to increase its reach. In this paper, a survey and assessment of the techniques applied to the recognition and conversion of Indian Sign Language are performed. An overview of the techniques used in sign language recognition for Indian Sign Language is provided to understand the status of research in this field. Following this, a comparison of techniques aimed at rendering a more detailed picture of the research results is presented. The challenges faced by researchers, the limitations of current techniques, and the need for improved research in this area are highlighted. With the intent of spurring more in-depth research, key areas within the approaches and techniques in need of improvement are summarized.
Decision analysis and methods
Vahid Mottaghi; Mahdi Esmaeili; Ghasem Ali Bazaee; Mohammadali Afshar Kazemi
Abstract
With the increase of news on social networks, a way to identify fake news has become an essential matter. Classification is a fundamental task in natural language processing (NLP). Convolutional neural network (CNN), as a popular deep learning model, has shown remarkable success in the task of fake news ...
Read More
With the increase of news on social networks, a way to identify fake news has become an essential matter. Classification is a fundamental task in natural language processing (NLP). Convolutional neural network (CNN), as a popular deep learning model, has shown remarkable success in the task of fake news classification. In this paper, new baseline models were studied for fake news classification using CNN. In these models, documents are fed to the network as a 3-dimensional tensor representation to provide sentence-level analysis. Applying such a method enables the models to take advantage of the positional information of the sentences in the texts. Besides, analyzing adjacent sentences allows extracting additional features. The proposed models were compared with the state-of-the-art models using a collection of real and fake news extracted from Twitter about covid-19, and the fusion layer was used as the decision layer in selecting the best feature. The results showed that the proposed models had better performance, particularly in these documents, and the results were obtained with 97.33% accuracy for classification on Covid-19 after reviewing the evaluation criteria of the proposed decision system model.