Browsing by Author "Dr. Tanzilur Rahman"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Open Access
    A Smart Online Medicine Selling System Along With DIMS And BDMS
    (North South University, 2020-06) Muttakin Ahamed; Md. Golam Haider; Monjur A-Elahi Tanmoy; Dr. Tanzilur Rahman; 1610830042; 1620218042; 1620587042
    An Online Medicine Selling System is a platform where the user will be able to buy medicines online. There are some websites available in our country running online medicine selling systems. But the change we have made in ours is to sell not only New Medicines but also Unused Medicines by the user. Pharmaceuticals, generics, and indications will categorize each of the medicines. Pharmaceuticals will help users to know from which company this medicine has been produced, generics will allow users to know which type of drug it is, and indication will help to know for what disease or problem you need to take that medicine. Secondly, we made a Blood Donor Management System from where the user will find out blood donors available in our country for their needs. And finally, we made a Drug Information Management System, which will help users know about medicines in detail like pharmacology, indications, contraindications, side-effects, precautions, dosage & administrations, and so on. We planned to make a platform that will be a complete hospitality system related to the medical sector that will be a great help for the people of our country. From this thought, we collaborated on three important sectors of medical sectors under one single platform.
  • Thumbnail Image
    Item
    Open Access
    Automatic Sleep Stages Detection Using Supervised Machine Learning
    (North South University, 2020) Saidul Islam Tanveer; Tangim Hossain Akash; Rakibul Hoque Foysal; Dr. Tanzilur Rahman; 1611556043; 1530092042; 1431238043
    Sleep is a natural behavior and part and parcel of Human‟s life. Nowadays, sleeping disorder is common question for both man and women. So, sleep related research is accelerated by researcher and heath care community. Sleep research can achieve the better way for diagnosis and treatment of sleeping related complaint. Over the past few decades, sleep classification is introduced. Automatic sleep stages classification is preferable approach for sleep researchers. Manual sleep scoring also visible Sometimes, nowadays. There is lot of difficulty in manual scoring which is very time consuming and prone to Human error. Automatic sleep stages classification using Machine learning model can create a great solution for diagnosis purpose. Different kinds of machine learning algorithms are used by many researchers. Here, in this research we use multiple supervised machine learning model to classify the sleep stages. In this research using EEG patterns of healthy and mild difficulty subjects over 95% of accuracy is obtained by the classifier. Total 31 features (spectral and statistical features) is applied to dataset before that 10 features were taken. For finding the significance nature of features Kruskalwallis anova test is applied. After that using Knn, Decision tree and Bagged tree algorithms evaluated the model accuracy. Bagged tree algorithm take vital role in accuracy which is higher than two other algothoms.So, the model used in this thesis is effective for both healthy and mild difficulty subject.
  • Thumbnail Image
    Item
    Open Access
    Major Crops Yield Prediction For Bangladesh
    (North South University, 2020-09) Akhtaruzzaman Khan; Md. Muktadir Hossain; Nurun Naima Tuly; Dr. Tanzilur Rahman; 1611319042; 1610597042; 1620617042
    Bangladesh is predominantly an agricultural country where agriculture sector plays a vital role in accelerating the economic growth. Climate and other environmental changes has become a major threat in the agriculture field. In the present paper, we have considered Max-Temp, Min-Temp, Rainfall, Humidity, Wind Speed, Bright Sunshine, Cloud Coverage and Altitude from the weather dataset and Districts Name, Crop Name, Crop Category, Area, Production and Year from Crop dataset for 18 districts of Bangladesh and combined these two into one for 45 years from 1969 to 2013. Crop production environment consists of inherent sources of heterogeneity and their non-linear behavior. The proposed research work pursues to produce prediction model using machine learning algorithms on 6 types of crops ( Aman, Aus, Boro, Jute, Potato and Wheat ) based on weather data. For crop yield assessment and prediction 9 algorithms( Linear Regression, Lasso Regression, Ridge Regression, Bayesian Ridge, Random Forest, K-Nearest Neighbor, Decision Tree, SVR, Artificial Neural Network) these algorithms provided acceptable values and higher accuracy rate. Linear Regression gave highest score for Aman (R2= 0.79), Aus (R2= 0.88), Boro (R2= 0.95), Jute (R2= 0.96) and Wheat crop (R2= 0.93) and for Potato Random Forest(R2= 0.87). The main purpose of this research work for helping to the farmer to predict the yield of the crop before cultivating onto the agriculture field.The crop yield prediction model discussed in the present paper will further improve in future with the use of long period dataset. Similar model can be developed for different crops of other locations. Keywords: Crop yield, Aman, Aus, Boro, Jute, Potato, Wheat, Prediction, Linear Regression, Random Forest, K-Nearest Neighbor, Decision Tree, SVR, Artificial Neural Network