Browsing by Author "Dr. Shohana Rahman Deeba"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Open Access
    IoT BASED BATTERY HEALTH MONITORING SYSTEM BY USING ESP32
    (North South University, 2022-01) Ariful Islam; Abu Abrar Chowdhury; Dr. Shohana Rahman Deeba; 1512604042; 1811440043
    Now-a-days most of the electric devices are battery dependent. That’s why it is important to check battery health regularly. Battery health monitoring system using ESP32 is an easy way to monitor the battery voltage and percentage from anywhere in the world, and also measure current and temperature by IOT based. Therefore, this system is useful for monitoring battery charging/ discharging status remotely controlled. A Battery Health Monitoring System (BHMS) is a device that is used to monitor the state of a battery and track its performance over time. It is used to monitor the battery's voltage,temperature,humidity and battery health. The system can alert users when the battery's health is declining, and can provide recommendations for when the battery should be replaced. BHMS can be used for various types of batteries, including lead-acid batteries, lithium-ion batteries, and nickel-metal hydride batteries. The system can be used in a variety of applications, including electric vehicles, renewable energy systems, and backup power systems. IoT Based Battery Health Monitoring System" uses the ESP32 microcontroller and IoT technology to monitor the health of batteries. The system measures the voltage and temperature of the battery and sends the data to a cloud server for storage and analysis. The project provides real-time monitoring and alerts to help extend the life of the batteries and ensure reliable performance. Overall, the use of a battery health monitoring system can help to improve the reliability and performance of battery-powered systems, and can also help to reduce the environmental impact of these systems by extending the useful life of the batteries.The estimation of State-of-Charge, Stateof- Health, Discharge Rate, and Remaining Useful Life are then derived by utilizing the concept of correlation and regression from the yielded real-time parameters recorded to the SD card module. This study paves the way for the comprehensive and continuous progress of battery identification, monitoring, and diagnosis that is a thorough advancement in the E-Vehicle industry.
  • Thumbnail Image
    Item
    Open Access
    Mental Health Prediction Using Natural language Processing and Machine Learning Approach
    (North South University, 2022) Sadia Islam Shumona; Tashfiha Faruk; Dr. Shohana Rahman Deeba; 1821614042; 1911584642
    Due to the rise in mental health problems and the demand for efficient medical care, machine learning has been looked into as a potential solution for mental health disorders. This research presents analysis on how mental health disorders can be detected through Natural Language Processing (NLP).It deals with the capacity of computers to comprehend textual information in a manner similar to that of humans. The ability of NLP to process large amounts of unstructured data effectively and the way NLP analyzes text data more effectively than traditional methods, makes it well-suited for predicting mental health conditions. Digital text is subjected to sentiment analysis in an effort to extract human emotions. With the help of NLP sentiment analysis, we could analyze human emotions through the data provided on social networks and can come to conclusions that will help people who are suffering from mental illness and thus help in correct treatment. Currently our project aims to detect 5 types of mental illness such as Anxiety, Depression, PTSD, Social-anxiety and Suicidal thoughts. In this study we have used five machine learning techniques, one deep learning model and assessed their accuracy in identifying mental health issues using several accuracy criteria. The ml techniques are Random Forest, Linear SVC, Naive bayes, Logistic Regression, XGB and the Deep learning model is LSTM. We have compared these techniques and implemented them and also obtained the highest accuracy with Logistic regression technique which is 79.3%.