Browsing by Author "Md. Shahriar Karim"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Open Access
    Early Detection of Mental Health over Social Media Using Machine Learning
    (North South University, 2020) Sabbir Hasan; Md. Tashfiq H. Choudhury; Md. Shahriar Karim; 1411107042; 1611508042
    In this project, we have worked on the use of machine learning algorithms that may indicate the mental state or sentiment of the users of social media. The current linguistic research on tweets or statuses shows distinct language patterns talks much about the sentiments of the users. As such, we are encouraged to use the available social media dataset repository for performance analysis of the supervised learning models generally applied in the case of large datasets. We have captured the texts and preprocessed the text data using Python tools for feature selection that provides clues to sentiment and subsequently, the subjective sentences are classified as positive or negative. We built machine learning (ML) models out of the classified text features for random forest and LSTM algorithms. The accuracy of the classification in both cases is encouraging, particularly the LSTM algorithm. The whole work is carried out using rich libraries of Python machine language modules. A prototype web application is developed with a front end (input and output) and back end (ML models and classification) using a rapid prototype web application framework for testing the algorithms that enable us to check the mental status of a social media user to determine if they may require medical or emotional support. Social media emerges as the most critical source of information, reflecting people's expressions and communication through textual content. This work contributes to the application of machine learning to further enhance the early detection of the mental health of users.
  • Thumbnail Image
    Item
    Open Access
    SAVIOUR, THE SURVEILLANCE BOT
    (North South University, 2019) MD. Shaiful Alam Turza; Sharmina Islam Surmi; Meraj Jannat; Md. Shahriar Karim; 1420652042; 1420116042; 1420052042
    This report represents a survivor robot model motivated by the physique of a spider which may be used for search and rescue operations. Various types of walking algorithm took place to make this survivor robot and have been tested on the robot too. Control of this robot is done by the use of RC remote AT 9s. This spider robot is based on six leg system and this is expected to be well suited for navigation in rough terrains. To move the robot into rough fields we have put some functional algorithm on to it. Moreover, these algorithms provide varieties of speed parameters to the robot which is based on the structure of the robot leg system. Each leg is joined by three servo motors that are controlling the limbs from every joint. In addition, we have developed a prototype for the experimental purpose.
  • Thumbnail Image
    Item
    Open Access
    Virtual Responsive Learning Assistance- A Learning Aid for Primary Level Education
    (North South University, 2019) Shimanto Haque; Devasish Ghosh; Mohammad Khurshed Alam; Md. Shahriar Karim; 1331333042; 1431154642; 1420799042
    This paper deals with recognizing characters written on thin air. The aim of this project was to enhance the learning method of primary school education in learning alphabets and numbers and counting. Children of primary level can draw characters in thin air, and see three dimensional or two dimensional images of the characters they write on the screen as a means of Augmented Reality, and also see examples associated with the characters and numbers. This is done by identifying a certain gesture of the hand as a pointer and then tracking that pointer as a means of drawing a character. The detection of the pointer is done with one single-lens web camera and without the usage of any motion sensors or any other external devices. Google’s Tensorflow module was used for training the pointer, and the entire project is done with simple python libraries such as OpenCV, numpy and others. The system requires the minimum manual involvement, and operates within three keystrokes.