Scribd Logo
Upload

Welcome to Scribd!

  • 60 views

    Detection of Employee Stress Using Machine Learning

    Uploaded by

    D.Naresh Babu
    This document proposes a system to detect employee stress levels using machine learning techniques. It discusses shortcomings of existing systems that use algorithms like Naive Bayes and SVM with less data and efficiency. The proposed system uses SVM and Random Forest algorithms on employee Twitter data to predict stress levels with better accuracy. It outlines functional requirements like data collection, preprocessing, feature selection, model development and evaluation, real-time monitoring, alert generation, and maintenance. Non-functional needs around scalability, availability and maintainability are also covered. Finally, it lists the software and hardware requirements to implement the system.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd

    Detection of Employee Stress Using Machine Learning

    Uploaded by

    D.Naresh Babu
    60 views14 pages
    This document proposes a system to detect employee stress levels using machine learning techniques. It discusses shortcomings of existing systems that use algorithms like Naive Bayes and SVM with less data and efficiency. The proposed system uses SVM and Random Forest algorithms on employee Twitter data to predict stress levels with better accuracy. It outlines functional requirements like data collection, preprocessing, feature selection, model development and evaluation, real-time monitoring, alert generation, and maintenance. Non-functional needs around scalability, availability and maintainability are also covered. Finally, it lists the software and hardware requirements to implement the system.

    Original Description:

    Detection-of-Employee-Stress-Using-Machine-Learning by using the system

    Original Title

    Detection-of-Employee-Stress-Using-Machine-Learning

    Copyright

    © © All Rights Reserved

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document proposes a system to detect employee stress levels using machine learning techniques. It discusses shortcomings of existing systems that use algorithms like Naive Bayes and SVM with less data and efficiency. The proposed system uses SVM and Random Forest algorithms on employee Twitter data to predict stress levels with better accuracy. It outlines functional requirements like data collection, preprocessing, feature selection, model development and evaluation, real-time monitoring, alert generation, and maintenance. Non-functional needs around scalability, availability and maintainability are also covered. Finally, it lists the software and hardware requirements to implement the system.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    60 views14 pages

    Detection of Employee Stress Using Machine Learning

    Uploaded by

    D.Naresh Babu
    This document proposes a system to detect employee stress levels using machine learning techniques. It discusses shortcomings of existing systems that use algorithms like Naive Bayes and SVM with less data and efficiency. The proposed system uses SVM and Random Forest algorithms on employee Twitter data to predict stress levels with better accuracy. It outlines functional requirements like data collection, preprocessing, feature selection, model development and evaluation, real-time monitoring, alert generation, and maintenance. Non-functional needs around scalability, availability and maintainability are also covered. Finally, it lists the software and hardware requirements to implement the system.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    of 14

    Project Title -

    Detection of Employee

    Stress By Using Machine

    Learning Technique
    Abstract
    Abstract:
    Disorders of stress are very casual thing
    among the employees who are working in
    corporate sectors.
    As with changing work of people and their
    living lifestyle, we can see the increment of
    stress in the working employees.
     Many corporate sectors are providing variety
    of schemes related to mental health and trying
    to reduce the disorders of stress in the working
    environment.
    In our paper, we are going to make use of
    two techniques of machines to determine the
    amount of stress the employee is having who is
    working in corporate sectors and try to narrow
    down the issues that identify the stress levels.
    We are going to apply two techniques of
    machine learning (i.e. SVM and Random Forest)
    when the data preprocessing and the cleaning
    of data is once finished.
    EXISTING SYSTEM
    EXISTING SYSTEM:
     This system was uses Naive Baye's
    algorithms, Support vector Machine,
    Gaussian Classifiers etc.

     They need lot of Data for training


    which apparently takes more execution
    time and also yields less efficient
    outputs.
    PROPOSED SYSTEM
    PROPOSED SYSTEM:
     We propose an efficient system which
    is uses Machine learning algorithms
    SVM and Random Forest it give the best
    accuracy compare to Existing system.

    In this system we use the Employee


    Twitter data for predicting the employee
    is stress are not.
    FUNCTIONAL
    REQUIREMENTS
    FUNCTIONAL REQUIREMENTS:
     Data Collection:- Collect a diverse dataset
    that includes relevant features, such as employee
    demographics, communication patterns, work-
    related information, ect..,

     Data Preprocessing:- Clean & preprocess


    the collected data by handling missing values for
    improving the quality of the input.

    Feature Selection:- Identify and select the


    most relevant features from preprocess dataset, for
    using techniques like statistical analysis and
    correlation analysis.

    Model Development:- Choose the decision


    trees, random forests, support vector machines
    (SVM) or neural networks.

    Model Evaluation:- Assess the performance


    of trained model using suitable evaluation metrics,
    Such as accuracy, precision, recall and FQ-score.
    Real-Time Monitoring:- Implement a system
    to continuously monitor employee stress levels
    using trained model. That takes in real-time data &
    provides stress predictions.

    Alert Generations:- Setup the Alerts to notify


    relevant parties(Manager or HR) when an
    employee’s Stress level exceeds a certain threshold.
    This allows for support & intervention.

    Model Updates & Maintenance:- Regularly


    update & maintain the model as new data becomes
    available. It helps model worked accurate &
    effective over time.

    User Interface(UI):- Develop the user friendly


    interface to interact with the system, allowing the
    authorized users to access Stress related data, view
    alerts & generate the reports if needed.

    Security and Privacy:- Implement the


    security measures for protect data, And ensure with
    privacy regulations such as GDPR or HIPAA.
    NON-FUNCTIONAL
    REQUIREMENTS
    NON-FUNCTIONAL REQUIREMENTS:

    Scalability :- The system must be able


    to scale up or down as needed.

    Availability :- The System must be


    available when needed.

    Maintenace:- The System must be easy


    to maintain and update.

    Portability:- The system must be able


    to run different Platforms with minimal
    Changes.
    SYSTEM
    REQUIREMENTS
    SOFTWARE REQUIREMENTS:

     Python idel 3.7 version (or)


     Anaconda 3.7 ( or)
     Jupiter (or)
     Google colab

    HARDWARE REQUIREMENTS:

     Processor : Minimum intel i3


     Ram: Minimum 4 gb
     Harddisk : Minimum 250gb

     Operating system: Windows, Linux

    You might also like