Browsing by Author "Intisar Tahmid Naheen"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Open Access
    Human Activity Recognition Using Multiple Learning & XAI Techniques with Wearable Sensor Data
    (North South University, 2023) Monirul Islam Mahmud; Md Shihab Reza; Hafeza Akter; Intisar Tahmid Naheen; 2011839042; 1931229042; 1922175042
    Human Activity Recognition (HAR) is an important area of research in artificial intelligence, machine learning, and ubiquitous computing. It involves identifying or predicting human actions based on sensor data. This paper investigates Human Activity Recognition (HAR), a crucial area in artificial intelligence and multiple learning. It focuses on identifying human actions using sensor data. We analyze various machine learning techniques, including Random Forest, Gradient Boosting, AdaBoost, K-Nearest Neighbors (KNN), and the Voting Classifier, as well as deep learning models like CNN, ANN, CNN ANN Hybrid, and LSTM with our collected 72,095 collected sensor data. We also employ XAI (SHAP) techniques to understand feature importance. Results indicate that, Random Forest leads with an 85% accuracy rate. Among deep learning models, ANN achieves the highest accuracy at 82%. LGB, CatBoost, and XGBoost perform well, each reaching an 84% accuracy rate. In Federated Learning, 72% accuracy is achieved by global model with ANN. We propose an app for activity detection and data collection. These findings emphasize the potential of machine learning in enhancing HAR systems, with implications for applications from healthcare to wearable technology.
  • Thumbnail Image
    Item
    Open Access
    Smart Phone Control Robotic Arm
    (North South University, 2024) Sarah Al Aiz; Md Ibnul Hasan Abir; Intisar Tahmid Naheen; 1831254045; 1821604643
    In the recent years with increasing development of robotic arm and the wireless communications, the demand for a system that could easily connect devices for transfer of data over a long distance - without cables, grew stronger. This project is presenting the development of a smartphone control robot arm. A mobile robot that functional to do pick and place operation and be controlled by using Bluetooth H05 controller. It can move forward, reverse, turn right and left for a specific distance according to the controller specification. The development of this robot is based on Arduino UNO platform that will be interfaced with the smartphone application controller to the robotic arm. Analysis such as speed, distance, load that can be lifted of the robot has been done in order to know its performance. Finally, this prototype of the robot is expected to overcome the problem such as placing or picking object that far away from the user, pick and place hazardous object in the fastest and easiest way. This project will inspire the future generation for using the robotic arm and also informed the advantage of using this robot.