Browsing by Author "Islam, Rafiul"

Now showing 1 - 6 of 6

Diabetes Feature Extraction Through Machine Learning Approach
(Daffodil International University, 23-01-18) Islam, Rafiul; Nahid, MD Nabil Ahmed
There are a number of individuals who suffer from diabetes mellitus, definitely among the most popular severe diseases. Diabetic mellitus can be caused by a variety of factors, including age, obesity, inactivity, genetics, dietary habits, blood pressure, and others. An individual's risk of developing diabetes increases chance from growing several illnesses, affect the heart, renal disease, kidneys, nerves harm, eyesight damage and so on. The various tests that are widely utilized in hospitals to diagnose diabetes are used to determine appropriate treatment, according to that diagnosis. So, in this paper, we will discover what the essential components of diabetes causes are in this essay. In areas of application where datasets containing tens or thousands of elements are available, variable and feature choice have become the focus of significant study. Our determination of whether someone is likely to develop diabetes in the future will also focus on the most crucial characteristics. We used two ML algorithms on the dataset to predict diabetes. One is KNN where the other one is K-means algorithm. We found that the model KNN works well on diabetes prediction with the accuracy of 81%.
Impact of repeat customers in profitability of service industry: A study on Mental health service
(BRAC University, 2023-01) Islam, Rafiul; Lee, Dr. Sang H
This report focused on repeat customers contribution in profitability of service industry, particularly mental health service. It also discussed about Moshal Mental health services internal and external analysis and its financial aspects. It’s been found that repeat customers are more profitable than new customers considering cost-benefit analysis and secondary research. However, new customer acquisition is also important as new customers may become repeat customers at some point which is necessary for business scalability.
Impact on GDP and the Stock Market During Pandemics or Epidemics of 21st Century
(Journal of Interdisciplinary Mathematics, 2023-09-29) Hossen, Md. Arman; Rahman, Md. Merazur; Nahid, Md. Nabil Ahmed; Islam, Rafiul; Banshal, Sumit Kumar; Gupta, Vedika; Dass, Pranav
"In this article, we present the effect on GDP growth rate during key major pandemics in the twenty-first century. Ebola, cholera, and the most dangerous pandemic, Covid-19, are all fatal pandemics. It was said that Coronavirus started spreading from Wuhan, China. The virus then afflicted the entire human race worldwide. The major goal of this paper is to compare the most catastrophic pandemic to another pandemic in terms of its effect on GDP. This study also examined the impact of the pandemic on the stock market. We offer a descriptive examination of economic impact over the course of 19 years for different countries."
Solar battery charging station with automated switching system
(BRAC University, 8/28/2014) Islam, Rafiul; Hossain, Shakhwat; Showrav, Alaul Ashraf; Ayon, Asif Anjum; Azad, A.K.M Abdul Malek
In today’s environmentally conscious climate there is more and more interest being taken in alternative forms of power supply. Bangladesh is witnessing a significant increase in solar energy generation as a part of renewable energy generation as a safety net for the shortage of conventional power sources (coal, oil, gas etc.). Solar energy can be produced and converted to electrical energy via solar panels and then stored in batteries which can then be used for multiple household and commercial purposes. This project deals with the modified design of the pilot project, SBCS or Solar Battery Charging Station. This project is an attempt to assist the urban and rural areas with eco-friendly and cheap electricity supply, decreasing the load on the national grid in the process. The batteries charged in the process can also be used by electricity-driven rickshaws that will be helpful for those rickshaw pullers who are either old or physically handicapped. The implementation of the project includes charging 48-volts battery sets using two 200W solar panels providing discrete amount of power at different times of the day. In addition to that the project also includes an automated switching system by which the station will shift to backup power to charge the batteries if the solar irradiance is too low for the batteries to be charged in a given time constrain. This paper gives a full description of the charging process, both by the solar panels and by national grid.
Supervised Machine Learning Approaches to Identify the False and True News from Social Media Data
(IEEE, 2024-07-29) Sadik, Md Rezwane; Rana, Md Masum; Akter, Lima; Islam, Rafiul; Rahman, Md. Hasanur; Rahman, Md. Musfiqur
The increasing number of online communities and social platforms like Twitter and Facebook has facilitated a level of information sharing never before seen in human history Consumers are generating and sharing more data than ever before thanks to the proliferation of social media platforms, and some of it is deceptive and has no basis in reality. Automatically determining whether a text contains misleading data or misinformation is difficult. Before passing judgment on the accuracy of a piece, even a subject matter specialist needs to look into a number of different angles. Here, this research presents machine learning strategies for distinguishing between false and genuine news. In this study, we have collected data by web scraping and employed several different techniques to train a collection of machine learning algorithms and then compare how well they perform on our datasets. In this work five machine learning algorithms have been applied to find the best algorithms. After evaluating the model, the research found that the decision tree achieved the best 99.84% model accuracy from this study.
Supervised Machine Learning Approaches to Identify the False and True News from Social Media Data
(Scopus, 2024-07-29) Sadik, Md Rezwane; Rana, Md Masum; Akter, Lima; Islam, Rafiul; Rahman, Md. Hasanur; Rahman, Md. Musfiqur
The increasing number of online communities and social platforms like Twitter and Facebook has facilitated a level of information sharing never before seen in human history Consumers are generating and sharing more data than ever before thanks to the proliferation of social media platforms, and some of it is deceptive and has no basis in reality. Automatically determining whether a text contains misleading data or misinformation is difficult. Before passing judgment on the accuracy of a piece, even a subject matter specialist needs to look into a number of different angles. Here, this research presents machine learning strategies for distinguishing between false and genuine news. In this study, we have collected data by web scraping and employed several different techniques to train a collection of machine learning algorithms and then compare how well they perform on our datasets. In this work five machine learning algorithms have been applied to find the best algorithms. After evaluating the model, the research found that the decision tree achieved the best 99.84% model accuracy from this study.