Browsing by Author "Sany, Saiful Islam"

Now showing 1 - 3 of 3

Comparison Study
(Proceedings of the 2019 8th International Conference on System Modeling and Advancement in Research Trends, IEEE, 2020-06-16) Arif, Md. Ariful Islam; Sany, Saiful Islam; Nahin, Faiza Islam; Rabby, AKM Shahariar Azad
The key to success in today's business is controlling the retails supply chain. Predicting customer demand is very essential for supply chain management. The perfect prediction has an effective impact on earning a profit., storage., lost profit., sales amount and consumer attraction. This article will produce a new method-using machine learning that will help for accurate prediction. This method collects the previous data of a store and analyze those data. Gathering the important information process those data and get prepared for using in method. Applying related algorithms towards the process data. We know K-Nearest Neighbor, Support Vector Machine, Gaussian Nave Bayes, Random Forest, Decision Tree Classifier and regressions have recently used an algorithm for prediction. We collect real-life data from the market. This paper made with the combination of shop position, month and occasion on that month and other related data. Our country's geographical area has an impact on prediction, which we discuss in our research. Our model produces a tentative demand for a particular product. This estimation helps retails and their businesses. After making a data set and apply appropriate algorithms, we will find different results and accuracy of different used algorithms. Compare them with others, we find out Gaussian Nave Bayes has the best accuracy. This helps to estimate the accurate product demand for a shop.
Drug Addiction Prediction Using Machine Learning
(Daffodil International University, 2020-07-19) Arif, Md. Ariful Islam; Sany, Saiful Islam; Nahin, Faiza Islam
Drugs and alcohol are dangerous to health and the body. Nowadays drug addiction has become a threat to Bangladeshi young people. Drugs and alcohol have a negative impact on our life. We have to keep an eye on the young people of our country not getting addicted to drugs quickly. We need to stay away from the drug before getting addicted to it. We will predict the risk of becoming addicted to drugs with machine learning. First, we study some related papers, journals, and online articles then we talk to doctors and drug addicts people; we find some common factors related to becoming addicted to drugs. Then we collect data based on those factors, such as age, gender, profession, health ability, mental pressure, trauma, family and friend’s history, incidents, etc. We collect data from both addicted and non-addicted people. We have two outcomes. One is ‘Yes’ means addicted and another is ‘No’ means not addicted. After data collection, we processed all the data and created a processed dataset. We applied machine-learning algorithms to our processed dataset. Since machine learning, artificial intelligence and deep learning used in various predictions and detection systems. We use k-nearest neighbor (kNN), logistic regression, support vector machine (SVM), naïve Bayes, random forest, adaptive boosting (ADA boosting), decision tree, multilayer perceptron (MLP) and gradient boosting classifier. In our work, out of nine algorithms, logistics regression gave the best performance based on accuracy and the accuracy of logistic regression was 97.91%.
Prediction of Addiction to Drugs and Alcohol Using Machine Learning
(International Journal of Electrical and Computer Engineering, 2021) Arif, Md. Ariful Islam; Sany, Saiful Islam; Sharmin, Farah; Rahman, Md. Sadekur; Habib, Md. Tarek
Nowadays addiction to drugs and alcohol has become a significant threat to the youth of the society as Bangladesh’s population. So, being a conscientious member of society, we must go ahead to prevent these young minds from life-threatening addiction. In this paper, we approach a machine learning-based way to forecast the risk of becoming addicted to drugs using machine-learning algorithms. First, we find some significant factors for addiction by talking to doctors, drug-addicted people, and read relevant articles and write-ups. Then we collect data from both addicted and no addicted people. After preprocessing the data set, we apply nine conspicuous machine learning algorithms, namely k-nearest neighbors, logistic regression, SVM, naïve Bayes, classification, and regression trees, random forest, multilayer perception, adaptive boosting, and gradient boosting machine on our processed data set and measure the performances of each of these classifiers in terms of some prominent performance metrics. Logistic regression is found outperforming all other classifiers in terms of all metrics used by attaining an accuracy approaching 97.91%. On the contrary, CART shows poor results of an accuracy approaching 59.37% after applying principal component analysis.