Browsing by Author "Akter, Sima"

Now showing 1 - 4 of 4

Lychee Tree Disease Classification and Prediction Using Deep Learning
(Daffodil International University, 22-08-14) Akter, Sima; Ali, Md. Almas
Bangladesh is a predominantly agricultural nation. The majority of people depend on agriculture. But it is a sad fact that the quality and quantity of our fruits are declining due to numerous diseases. People in our nation are discovering numerous new unusual diseases in our native fruits, but we are failing to diagnose these diseases, and the severity of this issue is growing daily. So, to combat this issue, suitable treatment or recuperation is required. Since we live in a technological age, it goes without saying that technology may be quite helpful in identifying these ailments. As the health of a plant depends on its leaves, it is crucial to first identify any tree diseases. As a result, we can prevent illness from spreading to the tree and fruit. We are trying to identify tree and leaf diseases through our research. Research into lychee tree disease is something we are highly interested in. Therefore, by preventing sickness in our lychee fruit, we can contribute to the Bangladeshi economy. We use cutting-edge image processing methods that are very beneficial to us to guarantee the freshness of the leaves. By simply looking at the leaves, it is quite difficult to identify any disease. Our system uses a cutting-edge method called image processing. For this, we use the method CNN (Convolutional Neural Network) based transfer learning classification algorithm. In this, we use the VGG16, InceptionV3, and Xception algorithm and as a result, the Inception-V3 model beat the other two models with a maximum accuracy of 92.67%, which indicate the successful outcome of this study.
Performance Evaluation of Traditional Classifiers on Prediction of Credit Recovery
(Scopus, 2020) Pradhan, Mohammad Rajib; Akter, Sima; Marouf, Ahmed Al
In the era of Big Data, machine learning is an emerging technique to analyze the large volume of data and is used to make critical business decisions. It is broadly used in different area such as medical, telecom, social media, banking data analysis and so on to learn the data and perform predictive analysis as well as building recommendation system. With the progression of technology, data availability and computing power, most of the banks and financial institutions are adapting their business model with technological development. Credit risk analysis is a cardinal field for banking and financial institutions, and there are numerous credit risk technique exists to predict the creditworthiness of the customer and loan default probability. In this study, we explore credit defaulter dataset of Bangladeshi bank and conduct several traditional machine learning classifier to predict the delinquent clients who possessed the highest probability of short-term credit recovery. Furthermore, we perform feature engineering to identify the important features for credit recovery prediction. We then apply our final features on different machine learning classifier and compare the predictive accuracy with the other classifier. We observe that random forest classifier gives 90% accuracy in credit recovery prediction. Finally, we propose a noble strategy to identify the potential customer for recovering the credit amount by using supervised machine learning techniques.
“PSD to HTML & CSS Conversion
(Daffodil International University, 2019-04-07) Akter, Sima
This internship report is for completion of my B.Sc at Daffodil International University. For this I had an internship over “ PSD to HTML & CSS Conversion” at a Networking & Website design company named Sumtech IT Institute. There I had many responsibilities like installing and configuration XAMPP server, website design and report to the manager of a project. In this internship report I basically tried to show that how I managed those things and how efficient I was there in the time of internship. Moreover I tried to present whether my internship was a successful or not. Solving real life problems was another key issue. This report takes me through all the details of every knowledge and experience gathered during this internship period.
Study on credit risk modeling system using Machine learning techniques
(Daffodil International University, 2018-09-08) Akter, Sima
Every lender’s organization such as banks and credit card companies use credit score system to determining the creditworthiness of their clients. Currently, they are using numerical scoring system in where the score determined by the compering new customer vs. existing customer profile. This does not capture the exact behavior of certain individual entities or more optimal ways to segment scoring models for which few loan trends to classify in a result organization are deprive of profit and lead to the loss. Now it analyzed that the problem can be optimized using Machine Learning technique and possible to forecast the behavior of the customer. In this study, we applied various machine learning technique to predict the classified loans, minimize credit risk and maximize the profit of the lender’s organization. Hence, this study intended to find the best modeling with best performance and accuracy by the comparing their results.