Browsing by Author "Akhter, Sonia"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    An LSTM-Based Word Prediction in Bengali
    (Springer, 2022-11-14) Hasan, Mustahid; Sakib, Nazmus; Hridoy, Rashidul Hasan; Ananto, Nazmul Hossain; Akhter, Sonia; Habib, Md. Tarek
    "In this paper, Bengali text information has been utilized for predicting the next word contingent based on the previous one. To do that, one should consider two key aspects such as the natural language processing (NLP) stage and the word predicting stage. When both work together, the system gets a new predicted word that is relevant to the previous word. For achieving such correct predicted words, long short-term memory (LSTM) has been used which is best known for its memory management. LSTM embeds the input words and fits them into the model, then after successful training of the model, it can predict the next word from a given sentence. The user can also initialize the number of predicted words. This paper gives an overview of word prediction for the Bengali language based on LSTM and describes the database integration and proposed approach obtained 97.60% accuracy."
  • Thumbnail Image
    Item
    Sars-covid 19 Prediction
    (Daffodil International University, 2021-12-04) Ananto, Nazmul Hossain; Mahfuja, Ishrat Binte; Akhter, Sonia; Howlader, Md. Rony
    COVID-19 infections have become prevalent, prompting worldwide efforts to control and treat the virus. Unfortunately, even after the invention of the vaccine so far, no vaccine invention organization has claimed that their vaccine can completely prevent Coronavirus and therefore the virus isn't going to be completely prevented. Since this life-threatening virus has no specific and special treatment and it spreads very easily and very quickly in human habitation. So, in an overpopulated and developing country like Bangladesh in south Asia, it's very difficult to identify every infected person and give them proper treatment for government and health workers. In recent years, artificial intelligence and machine learning have achieved appeal as a part of enhancing healthcare and research in general, especially in the field of the medical sector. To predict "COVID-19", a wide range of machine learning approaches, applications, and algorithms are developed. A machine-learning model is developed through which a potentially infected individual can know how susceptible he/she is to become infected with COVID-19 and their conditions. It may be very helpful for people to detect their problem and get primary treatment from home until they reach the stage of going to the hospital. This may make it possible to reduce the burden of health workers and the government. To acquire the best potential result in this system, more advanced and dynamic algorithms are required, such as K-nearest Neighbor, Decision Tree, Random Forest, AdaBoost, XGBoost, Stochastic Gradient Descent, Linear SVC, Perceptron, Naive Bayes, Support Vector Machines, Logistic Regression, Discriminant Analysis, and other.