Browsing by Author "Islam, Md. Sadequl"

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Mangrove Tree Recognition Using Deep Learning
    (Daffodil International University, 2019-04) Islam, Md. Sadequl; Masum, Md. Osman Gani Khan
    This thesis titled “Mangrove Tree Recognition using Deep Learning” is a very important topic in not only Computer Science and Engineering but also Botany. Recognition of different mangrove trees with high accuracy provides a lot of knowledge to people. However, because of the complex background of mangrove tree, the similarity between the different species of mangrove tree, and the differences among the same species of mangrove tree, there are some challenges in the recognition of mangrove tree images. This mangrove tree recognition is mainly based on the three features: leaf, root and fruit, which requires people to select features for recognition, and the accuracy is not very high. In this project, based on Inception-v3 model of TensorFlow platform, we use the transfer learning technology to retrain the mangrove tree category datasets, which can greatly improve the accuracy of mangrove tree recognition. We have used Google’s Inception-v3 model trained on 3000 images covering 5 different categories. We retrained the Inception model to classify the mangrove tree images, using the Tensorflow Library and achieved an overall accuracy of 99% on the images.
  • Thumbnail Image
    Item
    Mangrove Tree Recognition using Deep Learning
    (Daffodil International University, 2019-04-07) Islam, Md. Sadequl; Masum, Md Osman Gani Khan
    This thesis titled “Mangrove Tree Recognition using Deep Learning” is a very important topic in not only Computer Science and Engineering but also Botany. Recognition of different mangrove trees with high accuracy provides a lot of knowledge to people. However, because of the complex background of mangrove tree, the similarity between the different species of mangrove tree, and the differences among the same species of mangrove tree, there are some challenges in the recognition of mangrove tree images. This mangrove tree recognition is mainly based on the three features: leaf, root and fruit, which requires people to select features for recognition, and the accuracy is not very high. In this project, based on Inception-v3 model of TensorFlow platform, we use the transfer learning technology to retrain the mangrove tree category datasets, which can greatly improve the accuracy of mangrove tree recognition. We have used Google’s Inception-v3 model trained on 3000 images covering 5 different categories. We retrained the Inception model to classify the mangrove tree images, using the Tensorflow Library and achieved an overall accuracy of 99% on the images.
  • Thumbnail Image
    Item
    The Role of Mass Educational Programme in Political Development: A Study of Selected Two Villages of Paba Thana Under Rajshahi District
    (University of Rajshahi, 2011) Khanam, Mst. Murshida; Islam, Md. Sadequl; Karim, Md. Rezaul
    An attempt has been made in the study to inquire into the role of mass education in political development. The study was conducted among the 100 participants and 200 non­participants in mass education-in two selected villages of Paba Upazila of Rajshahi district in Bangladesh. The researcher followed the techniques of survey and observation methods to collect primary & field data for this study. The data were collected on different dimensions such as demographic and socio-economic political background of participant and non-participant in mass education in the study area and political awareness, values, and political participation of respondents. To investigate the role of mass education in political development, the researcher examined the participation of the respondents about political right, political participation, awareness about female members, citizenship duties as voters, knowledge of cross voting and opinion about the bad impact of strike, opinion about of voting in election and other activities of political development. The study revealed that the respondents are lower in soci-economic status, in terms of occupation, land ownership, income and so on. The study explored that participants in mass education have better political knowledge and awareness than non participant respondents. An analysis of non participant's political background revealed that they were not politically active and conscious. Though majority of the non participants of respondents who did not come in touch of mass education have given their vote in favour of their party's nominated candidate. Candidate's quality or party's programme was less important to them. On the other hand, those who come in touch of the mass education programme before performing their voting power, have considered party's programme and quality of candidates. The study has clearly depicted that most of non-participants of the respondents at the grass root level were not aware of and active about politics, political rights and participation in political activities. However, it was found that participants in mass education were comparatively more aware than the non-participants regarding these issues. The study also explored that there is a significant relationship between mass education of participant's and their occupations, political involvement of family members and political awareness of respondents. Finally, the study identified some issues which need serious attention to develop the role of mass education in political development.