With the drastic drive in population and economy of Bangladesh, the urgency of higher education of the mass is also extending. Moreover, due to scarcity of resources, financial support and many other convoluted circumstances, for many of the university going youth, concentrating on study becomes arduous. Such phenomenon implies a repercussion on their academic result; which is absolutely not expected. In order to minimize such unwanted damage, we have carried out an investigation by surveying a number of undergraduate students of various universities of Bangladesh. Through our research we have tried to excavate the key features which mostly contribute to the aforementioned matter. Our research primarily focuses on the features that have been extracted by the feature selection process we have implemented. Firstly we have conducted classifier comparison on the original dataset which has provided us an insight about the distribution of the dataset. Furthermore, we have extracted out the most telling features with the help of feature importance ranking measure. Finally, we have once again carried out classifier comparison on the reduced dataset which has demonstrated better accuracy than that of the original dataset.
Conference Name: ICCA 2020 - International Conference on Computing Advancements.
Status: Published on March 21, 2020. (Acceptance Rate: 40.93%, Presenter: Majidur Rahman) [ACM DL Paper Link]
Tea grading is a very prominent factor of the tea industry. The standard, fragrance and sweetness of tea mostly relies on this grading system. This research is an step to introduce machine learning with the tea industry, where image classification and recognition is deployed to digitize the grading system by eradicating human intervention in it. Three models are used in this system in which two were pre-trained. They are as Faster RCNN (Inception-v2), and VGG16. The other one is manually trained, that is Sequential model or CNN. After a successful session of compulsory augmentation and scaling, we gathered 3000 raw images which were used to train and test the model spontaneously. Our productivity has rendered us tremendous satisfaction by supplying astonishing accuracy. So, it will be not wrong saying that this research has amalgamated machine learning technology with the grading system of tea very productively which can escort a great revolution to the tea industry.
Conference Name: ICCA 2020 - International Conference on Computing Advancements.
Status: Published on March 23, 2020. (Acceptance Rate: 40.93%, Presenter: Mahadi Hasan Kamrul) [ACM DL Paper Link]
Cancer has become one of the most life threatening disease over the past few decades. Especially on Bangladesh the number of people being affected by cancer is increasing in an agitating rate. Again cancer, diagnosed after a certain stage, inevitably leads towards death. To abate this vicious upheaval of cancer, awareness has no other alternative. Our research primarily focuses on detection of certain age group, according to the corresponding cancer diagnosis and relevant factors. In order to do so, we have implemented logistic regression, support vector machine and convolutional neural network on the original dataset. Afterwards, two feature selection methods (Feature Importance Ranking Method and Recursive Feature Elimination) have been applied on the dataset to extract out the most significant features. The three classifier comparison has been implied on both the feature selection methods. It is found that the classifier accuracy on the extracted features is significantly better in case of Recursive Feature Elimination rather than Feature Importance Ranking Method.
Conference Name: 22nd International Conference on Computer and Information Technology (ICCIT-2019).
Status: Published on March 19, 2020. (Acceptance Rate: 28.68%, Presenter: Majidur Rahman) [IEEEXplore Paper Link]
Bangladesh is a land of agriculture, where people consumes rice as the main meal for three times a day. Rice is undoubtedly the most cultivated crop in Bangladesh. Like every other crops, rice also gets affected by a lots of diseases. These diseases differ from region to region and season to season. Although a number of implementation of different technology in agricultural field is increasing at an enormous rate, the farmers of our country still depends on the ancient techniques of disease identification. By keeping this very thing in our mind, we have conducted this research where we have tried to develop a model which can recognize rice diseases by deploying machine learning. We have worked with six main disease that is commonly seen in the paddy fields of Bangladesh. Authentic dataset of these six diseases were collected very carefully so that our model can render us the highest accuracy rate. BRRI(Bangladesh Rice Research Institute) has assisted us a lot in this matter. Three vastly popular pre-trained models of CNN such as Inception-v3, MobileNet-v1 and Resnet50, have been used to carry out this research. Necessary augmentation and scaling was done in the dataset before employing them. The research yields gratifying outcome. Hence, it proves that how effectively machine learning can collide with the agriculture. This research will pave machine learning techniques a path to enter in the agricultural sector of our country as well as help the young generation immensely who will enter into the agriculture in the future.
Conference Name: 22nd International Conference on Computer and Information Technology (ICCIT-2019).
Status: Published on March 19, 2020. (Acceptance Rate: 28.68%, Presenter: Mahadi Hasan Kamrul) [IEEEXplore Paper Link]
Pregnancy termination is a trivial anomaly for third world countries like Bangladesh. The greater aspiration of this research is to downturn the rate of pregnancy termination. This research finds out the attributes that contribute to pregnancy termination and leads to propose a hybrid of supervised machine learning approach for predicting "Pregnancy Termination" in Bangladesh. Bivariate and multivariate analyses were carried out using the Bangladesh Demographic and Health Survey (BDHS), 2014 data which is reduced by analyzing attributes that exhibit information of interest to explore the current reasons of pregnancy termination. After extracting out the features of interest with the help of Weka provided feature ranking attribute evaluator, hybridization of supervised machine learning classifiers are done concerning the negatively biasedness of the dataset with respect to pregnancy termination. On this investigation, we've developed a hybrid approach with 67.2% accuracy considering the biasedness of the dataset which is relatively better than other classifiers in terms of performance metrics.
Conference Name: 2nd International Conference on Electrical, Computer and Communication Engineering (ECCE 2019).
Status: Published on April 04, 2019. (Acceptance Rate: 27.57%, Presenter: Md. Montasir Bin Shams) [IEEEXplore Paper Link]