180235(a2)
- 1. An assignment on Artificial Intelligence CSE-3201(A2) Computer Science & Engineering Discipline Khulna University,Khulna,Bangladesh Submitted To: Jabed Al Faysal Lecturer Computer science & Engineering Discipline. Khulna University, Khulna, Bangladesh. Submitted by : Md. Azizul Haque ID:180235 3rd year 2nd term Computer science & Engineering Discipline. Khulna University,Khulna Date of submission: 31 January,2021
- 2. Summary(P4): Machine learning based approaches for detecting COVID-19 using clinical text data The authors in this study weighed the machine learning based applications for detecting covid-19 through its decision making by experimenting the image and clinical data. COVID-19 has infected almost all countries in the world within a very short amount of time. Due to lacking the medical resources, insufficient number of testing kits, inadequate knowledge about this epidemic disease people’s life has become afflicted all over the world to its impacts in future. It is obligate to build a control system that will detect the coronavirus with the help of several AI tools which is cost effective than standard test for covid-19 and assured high accuracy. ML can be used to diagnose COVID-19 and predict the mortality risk of a infected person which needs a lot of research effort. The researchers categorized the textual clinical reports into four classes of viruses by dint of classical and ensemble machine learning algorithms. Feature engineering was performed using techniques like Term frequency/inverse document frequency (TF/IDF), Bag of words (BOW) and report length. The researchers propounded the methodology consist of 5 steps ((1) data collection (2) the refining of data (3) an overview of preprocessing (4) a mechanism for feature extraction (5) an overview of ensemble machine learning algorithms. After performing four classification the result was revealed that logistic regression and multinomial Naïve Bayesian classifier gives excellent results by having 94% precision, 96% recall, 95% f1 score and accuracy 96.2%. Various other machine learning algorithms that showed better results were random forest, stochastic gradient boosting, decision trees and boosting. In future recurrent neural network and more feature engineering can be used for better accuracy.
- 3. Summary(P5): Deep learning based detection and analysis of COVID-19 on chest X-ray images Coronavirus disease 2019 (COVID-19) is a contagious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that infects not only humans, but animals are also infected because of disease in globally. COVID-19 is an epidemic disease that threatens the human health, education, daily life of human beings and the economy of a country at a worldwide level and turned into a pandemic. A statistics of COVID-19 infected patients has shown that most of the patients are mostly infected from a lung infection after coming in close contact with another affected person. Medical imaging is also a method of analyzing and predicting the effects of covid-19 on the human body. Chest x-ray and chest CT(computed tomography) are a more effective medical imaging technique for diagnosing lunge related problems. And a substantial chest x-ray is a lower cost process than chest CT. Deep learning is the most successful technique of machine learning, which provides useful analysis to study a large amount of chest x-ray images that can critically impact on screening of Covid-19.The author collected uploaded data of X-ray images of healthy and covid-19 infected patients from different sources and applied deep learning-based CNN models (InceptionV3, Xception, and ResNeXt) and compared their performance.. To analyze the model performance, 6432 chest x-ray scans samples have been collected from the Kaggle repository, out of which 5467 were used for training and 965 for validation. The author concluded that the Xception model gives the highest accuracy (i.e., 97.97%) for detecting Chest X-rays images as compared to other models. The researcher focuses on possible methods of classifying covid-19 infected patients and advised to consult medical professionals for any practical use case of this project.
- 4. Summary(P6): COVID-19 Epidemic Analysis using Machine Learning and Deep Learning Algorithms Coronavirus disease 2019 (COVID-19) is an acute infection of the respiratory tract that emerged in late 2019 in China and then progressed to different countries around the world and caused considerable morbidity and mortality. The whole world is putting incredible efforts to fight against the spread of this deadly disease in terms of infrastructure, finance, data sources, protective gears, life-risk treatments and several other resources. To analyze the transmission growth at the earliest and forecast the forthcoming possibilities of the transmission, state-of-the-art mathematical models are adopted based on machine learning such as support vector regression (SVR) and polynomial regression (PR) and deep learning regression models such as a standard deep neural network (DNN) and recurrent neural networks (RNN) using long short-term memory (LSTM) cells. Machine learning and deep learning approaches are implemented to predict the total number of confirmed, recovered, and death cases worldwide. The AI researchers are focusing their expertise knowledge to develop mathematical models for analyzing this epidemic situation using nationwide shared data. To contribute towards the well-being of living society, this article proposes to utilize the machine learning and deep learning models with the aim for understanding its everyday exponential behaviour along with the prediction of future reachability of the COVID-2019 across the nations by utilizing the real-time information from the Johns Hopkins dashboard. The author show that polynomial regression (PR) yielded a minimum root mean square error (RMSE) score over other approaches in forecasting the COVID-19 transmission.