Scribd Logo
Upload

Welcome to Scribd!

  • 124 views

    Project - PPT - Design - Phase (2) (1) Final

    Uploaded by

    Raghavendra Kusoor
    The document proposes developing an AI-driven system to predict air quality in Karnataka's smart cities. It involves collecting a region-specific dataset, creating an early warning system, and designing a machine learning model for air quality prediction trained on the customized dataset.

    Copyright:

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

    Project - PPT - Design - Phase (2) (1) Final

    Uploaded by

    Raghavendra Kusoor
    124 views15 pages
    The document proposes developing an AI-driven system to predict air quality in Karnataka's smart cities. It involves collecting a region-specific dataset, creating an early warning system, and designing a machine learning model for air quality prediction trained on the customized dataset.

    Original Description:

    good

    Original Title

    Project_PPT_Design_Phase[2][1] final

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document proposes developing an AI-driven system to predict air quality in Karnataka's smart cities. It involves collecting a region-specific dataset, creating an early warning system, and designing a machine learning model for air quality prediction trained on the customized dataset.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    124 views15 pages

    Project - PPT - Design - Phase (2) (1) Final

    Uploaded by

    Raghavendra Kusoor
    The document proposes developing an AI-driven system to predict air quality in Karnataka's smart cities. It involves collecting a region-specific dataset, creating an early warning system, and designing a machine learning model for air quality prediction trained on the customized dataset.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 15

    SURESH ANGADI EDUCATION FOUNDATION’S

    ANGADI INSTITUTE OF TECHNOLOGY AND MANAGEMENT


    Savagaon Road, BELAGAVI – 590 009.
    (Approved by AICTE, New Delhi &Affiliated to Visvesvaraya Technological University, Belagavi, Accredited by NAAC & NBA)

    AIR QUALITY PREDICTION IN


    SMART CITIES USING MACHINE
    LEARNING
     SUBMITTED BY- PROJECT GUIDE-
     Mr. SHIVANAND LAMANI (2AG20CS066)
    PROF. MANJUNATH PATIL
     Mr. RAGHAVENDRA KUSOOR (2AG20CS050)

     Mr. SUHAS PAWAR (2AG20CS075)

     Mr. VIVEK BORGALLE (2AG20CS093)


    INTRODUCTION :
    • Introduction of AI-driven solution for air quality prediction in Karnataka's smart cities, addressing
    the pressing issue of deteriorating air quality due to rapid urbanization and industrialization.

    • Recognition of Karnataka's diverse urban landscape and unique environmental challenges,


    necessitating tailored solutions for effective pollution management.

    • Emphasis on the significance of proactive measures to mitigate the adverse effects of air pollution
    on public health and the environment in Karnataka's urban centers.

    • Collaboration with local authorities, environmental agencies, and technology experts to implement
    and refine the AI-driven air quality prediction system for sustainable urban development in
    Karnataka.
    PROBLEM STATEMENT :

    • Monitoring and preserving air quality has become one of the most essential
    activities in many industrial and urban areas today.

    • The quality of air is adversely affected due to various forms of pollution caused by
    transportation, industries etc.
    OBJECTIVES :
    • Develop a Region-Specific Dataset: Collect and curate a comprehensive dataset specific to the
    environmental characteristics of cities in Karnataka, incorporating factors such as local
    meteorological conditions, industrial emissions, and traffic density.

    • Early Warning System: Create an early warning system to alert residents and authorities to potential
    air pollution events.

    • Implement AI-Driven Air Quality Prediction Model: Design and develop a robust machine learning
    model for air quality prediction, leveraging classification algorithms. Ensure the model is trained on
    the region-specific dataset to enhance accuracy and relevance.
    SYSTEM
    REQUIREMENTS:
    Hardware Requirements:
    ❖ CPU: Quad-core processor (or higher)
    ❖ RAM: 16 GB (or higher)
    ❖ Storage: 500 GB SSD (or higher)
    ❖ Network: Gigabit Ethernet

    Software Requirements:
    ❖ Programming Language : Python (version 3.8)
    ❖ Machine learning frameworks for model development and prediction.
    ❖Web application development for data visualization and notification systems.
    YEAR Author Title Journal DESCRIPTION

    2021 Rajesh K. Gupta, Integration of IEEE Integration of IoT devices in air quality
    Priya S. Sharma IoT and Machine monitoring provides real-time data on
    Learning for Air pollutant levels, weather conditions, and
    Quality geographical factors, enriching the dataset for
    Monitoring in machine learning algorithms.
    Smart Cities

    2020 Emily Y. Chen, Predicting Air IEEE The application of deep learning techniques
    Michael J. Wang Quality in Urban in air quality prediction leverages advanced
    Environments neural networks, enhancing the model's
    with Deep ability to capture intricate patterns and
    Learning relationships within complex datasets.
    Techniques .
    YEAR Author Title Journal DESCRIPTION

    2019 Ayesha N. Ali, Predictive IEEE Applied for air pollution predictive modeling,
    Farhan A. Khan Modeling of Air it examines historical data to understand
    Pollution Using temporal pollutant dynamics.
    Time Series
    Analysis Provides valuable insights into future air
    pollution trends using time series analysis.

    2018 Nisha A. Mathew, A Survey on IEEE A survey assesses challenges hindering smart
    Abhinav K. Singh Smart City city initiatives' implementation.
    Initiatives:
    Challenges and The survey also explores opportunities within
    Opportunities the realm of smart city initiatives,
    contributing to informed decision-making.
    ARCHITECTURE DIAGRAM:
    TRAINED AIR
    USER MODEL CLASSIFICATION
    REGISTRATION/
    LOGIN
    DATABASE

    GENERATED REPORT
    AIR
    CLASSIFICATION
    SYSTEM

    FEATURE AIR QUALITY


    AIR CASSES OUTPUT
    EXTRACTION DETECTION

    Fig :1 Architecture Diagram


    USE CASE DIAGRAM:
    REGISTER VALIDATE

    LOGIN

    AIR QUALITY
    CLASSIFICATION

    UPDATE PROFILE

    VIEW PROFILE
    USER

    VIEW REPORT

    Fig:2. Use Case Diagram


    BLOCK DIAGRAM:
    INPUT DATA EXTRACTION OF
    ACQUISTION PROCESSING FEATURES

    COMPARING WITH
    CLASSIFYING INPUTS
    TRAINED MODEL

    Fig:3.Block Diagram of Process


    ACTIVITY DIAGRAM:
    LOGIN

    Invalid
    AUTHENTIC
    ATION
    Valid

    UPLOAD GENERATE UPDATE VIEW


    CLASSIFICATION REPORT
    DATA PROFILE REPORT

    MODIFY MODIFY
    UPLOADED DETAILS

    LOGOUT

    Fig:4 Activity Diagram of Admin


    DATAFLOW DIAGRAM:
    USERS

    Login Response

    AIR QUALITY REPORT


    DETECTION

    Fig:5. DataFlow Diagram Level 0


    USER PREPROCESSING SEGMENTATION CLASSIFICATION PREDICTION DASHBOARD

    Value captured
    Log In

    Log Out
    Input pre-processing

    Analyzing Data

    Feature Extraction
    Classified output

    Fig:6.Sequence diagram
    CONCLUSION :
    The study offers a comprehensive comparative analysis of different regression models for predicting
    air quality in smart cities and recommends exploring diverse machine-learning approaches, along
    with investigating the effect of meteorological data, such as temperature, pressure, humidity, and
    wind speed, to further enhance AQI and air pollution prediction accuracy.
    Thank You

    You might also like