Scribd Logo
Upload

Welcome to Scribd!

  • 205 views

    Human Activity Recognition

    Uploaded by

    Sita Putra Teja
    This document discusses human activity recognition using machine learning. It presents the motivation as analyzing fitness data to understand a person's acceleration which is difficult for humans but possible through machine learning. The dataset used contains smartphone accelerometer data of various activities like walking, jogging, sitting. Models like CNNs and Naive Bayes are implemented on the data to classify activities. The relevance is developing a mobile fitness tracker app through this activity recognition model that can help users monitor their performance and fitness levels.

    Copyright:

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

    Human Activity Recognition

    Uploaded by

    Sita Putra Teja
    205 views10 pages
    This document discusses human activity recognition using machine learning. It presents the motivation as analyzing fitness data to understand a person's acceleration which is difficult for humans but possible through machine learning. The dataset used contains smartphone accelerometer data of various activities like walking, jogging, sitting. Models like CNNs and Naive Bayes are implemented on the data to classify activities. The relevance is developing a mobile fitness tracker app through this activity recognition model that can help users monitor their performance and fitness levels.

    Original Title

    Human Activity Recognition (1)

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses human activity recognition using machine learning. It presents the motivation as analyzing fitness data to understand a person's acceleration which is difficult for humans but possible through machine learning. The dataset used contains smartphone accelerometer data of various activities like walking, jogging, sitting. Models like CNNs and Naive Bayes are implemented on the data to classify activities. The relevance is developing a mobile fitness tracker app through this activity recognition model that can help users monitor their performance and fitness levels.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    205 views10 pages

    Human Activity Recognition

    Uploaded by

    Sita Putra Teja
    This document discusses human activity recognition using machine learning. It presents the motivation as analyzing fitness data to understand a person's acceleration which is difficult for humans but possible through machine learning. The dataset used contains smartphone accelerometer data of various activities like walking, jogging, sitting. Models like CNNs and Naive Bayes are implemented on the data to classify activities. The relevance is developing a mobile fitness tracker app through this activity recognition model that can help users monitor their performance and fitness levels.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 10

    HUMAN ACTIVITY RECOGNITION

    PROBLEM STATMENT
    UMAN ACTIVITY RECOGNITION

    DOMAIN OF THE PROJECT


    MACHINE LEARNING IN
    HEALTH CARE MANAGMENT
    Human activity recognition is an important
    area of machine learning research.

    Activity recognition is considered as an important


    task in many applications, particularly in
    healthcare services.

    Providing accurate and opportune


    information on people’s activities and
    behaviors is one of the most important
    INTRODUCTION tasks in pervasive computing.

    Among these applications include medical


    diagnostics, monitoring of users' daily
    routine and detection of abnormal cases.
    MOTIVATION
    The main motivation is that we are trying to analyze
    the fitness data of a person, how the acceleration of
    a person is changing, but it is very hard for a human
    to analyze the data and give conclusions, in that case
    we are using machine learning to provide us with the
    information about the acceleration of the person.
    Despite human activity recognition (HAR) being an
    active field for more than a decade, there are still key
    aspects that, if addressed, would constitute a
    significant turn in the way people interact with
    mobile devices.
    we will be using a standard HAR dataset which is publicly available from the

    DATASET WISDM group. Android smart phone-based application was used to collect
    data. Each user was asked to take the smart phone in a front leg pocket and
    performed five different activities in supervised condition which were
    walking, jogging, walking upstairs, walking downstairs, sitting, and standing.

    While performing these


    activities, the sampling rate for
    accelerometer sensor was kept
    of 20Hz. This dataset contains
    data collected through
    controlled , laboratory
    conditions.This data has been
    released by the Wireless Sensor
    Data Mining
    STATSTICS
    •Raw Time Series Data
    •Number of examples: 1,098,207
    •Number of attributes: 6
    •Missing attribute values: None
    •Class Distribution
    •Walking: 424,400 (38.6%)
    •Jogging: 342,177 (31.2%)
    •Upstairs: 122,869 (11.2%)
    •Downstairs: 100,427 (9.1%)
    •Sitting: 59,939 (5.5%)
    •Standing: 48,395 (4.4%)
    Implementing deep neural networks and 2D
    convolutional neural networks and getting train and test
    accuracy.

    2D CNN method
    Naïve Bayes
    Decision Tree
    K Nearest Neighbors
    SELECTION OF ALGORTHIMS
    The main idea is to create a
    model which informs us the
    INDUSTRY/ acceleration of the user
    SOCIETY RELAVANCE The model can then be upgraded by
    adding features like calories, heart
    rate monitor, steps count etc. and
    convert into a fitness tracker
    The fitness tracker model can later
    be converted into an application for
    mobile phones which enables our
    user to keep a check on their
    performance and maintaining their
    fitness.
    This Photo by
    Unknown Author is
    licensed under
    CC BY-SA
    REFERENCES
    Dataset
    https://www.cis.fordham.edu/wisdm/dataset.php
     
    Research paper
    Jennifer R. Kwapisz, Gary M. Weiss and Samuel A. Moore (2010). Activity Recognition using Cell Phone
    Accelerometers, Proceedings of the Fourth International Workshop on Knowledge Discovery from Sensor
    Data (at KDD-10), Washington DC.
    https://www.academia.edu/40912303/Daily_Human_Activity_Recognition_using_Adaboost_Classifiers_on_Wisdm
    _Dataset
    (Human activity recognition from accelerometer data)
     
    YouTube reference
    https://www.youtube.com/watch?v=lUI6VMj43PE
    TEAM
    MEMBERS

    Siddhartha das
    Kolla teja Rishit mohan
    gupta

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy