Scribd
Upload
44 views2 pages

Project Synopsis

Uploaded by

spruhaloff
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
44 views2 pages

Project Synopsis

Uploaded by

spruhaloff
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Main - Project 1 Page Synopsis (back-to-back)

Project Batch No. : BE/ECE/Sem-7/Batch Group No – P33


Academic Year : Aug 23 - Dec 23, ODD Semester, 2023-24 Batch
Course Name & Code : Project work phase I/19EC7ICPR1
Title of the final year BE
: SwiftEdge: Smart Elderly Assistance at the Network Edge.
project work (VII/VIII Sem)
Project Guide : Dr. Druva Kumar S Sign:
Section in-charge (Mentor) : Prof. Bindu H M Sign:
Project Coordinator : Dr. Abhishekh M B Sign:
HOD : Dr. T C Manjunath Sign:
Field / area of project : IoT, Edge Computing, Machine Learning

Name: Spruhal Prem Name: Suhas B Name: Tarun Ganesh K Name: Tushar M Gunari
USN: 1DS20EC201 USN: 1DS20EC209 USN: 1DS20EC218 USN: 1DS20EC222
7022422210
Phone no./email-id student-1 : P Sign:
Name: Spruhal Prem E [email protected]
Phone no./email-id student-2 P 8747043392
: Sign:
Name: Suhas B E [email protected]
Phone no./email-id student-3 P 9448100675
: Sign:
Name: Tarun Ganesh K E [email protected]
Phone no./email-id student-4 P 8088250211
: Sign:
Name: Tushar M Gunari E [email protected]

Abstract:
"SwiftEdge: Smart Elderly Assistance at Network Edge" pioneers a paradigm shift in elderly care by
integrating edge computing on a Raspberry Pi wearable. As the aging population grows, the need for
personalized, real-time assistance becomes paramount. SwiftEdge addresses this challenge through multi-
faceted features, including precise fall detection using gyroscopes, accelerometers, and machine learning.
Real-time location tracking and geo-fencing enhance safety, while a manual assistance request system ensures
immediate distress communication. Motion-based activity monitoring provides a comprehensive
understanding of daily routines. The project concludes with a user-friendly web interface for family members,
offering continuous updates and alerts. Embracing edge computing ensures low-latency responses and
addresses privacy concerns through local data processing. SwiftEdge represents a holistic approach to elderly
care, showcasing the potential of edge computing to elevate the quality of life for the aging population by
prioritizing security, real-time assistance, and privacy.

Introduction - "SwiftEdge: Smart Elderly Care at Network Edge" leverages edge computing on a
Raspberry Pi wearable for transformative advancements in elderly care. This project introduces
precision in fall detection, geo-fencing for adaptive safety, and a manual assistance request system.
SwiftEdge's holistic approach includes motion-based activity monitoring, medication management, and
calendar synchronization, marking a notable stride from conventional solutions. A user-friendly web
interface facilitates real-time updates for family members. Pioneering a transformative shift in elderly
care, SwiftEdge emphasizes responsiveness, accuracy, and data security through cutting-edge edge
computing technologies.

Dept. of ECE, DSCE, Bangalore


Main - Project 1 Page Synopsis (back-to-back)

Block Diagram -

Aim - The aim of "SwiftEdge" is to implement a sophisticated elderly care system on a Raspberry Pi
wearable, utilizing edge computing. It aims to achieve real-time monitoring with precision through
gyroscopes, accelerometers, and machine learning for fall detection, geo-fencing for adaptive safety, and
seamless integration of motion-based activity monitoring, medication management, and calendar
synchronization. The technical focus lies in optimizing processing at the network edge for reduced latency
and increased responsiveness, ensuring a holistic and advanced solution for elderly care.

Objectives -The project aims to achieve the following:


- Develop an efficient data collection mechanism for location and movement data.
- Implement machine learning algorithms for real-time data analysis.
- Utilize edge computing for processing data locally, ensuring low latency and quick response.
- Generate timely alerts, reminders, etc. based on the analyzed data.

Proposed methodology -
- Data Collection: Utilize sensors and IoT devices to collect real-time data on vital parameters like gyroscope data, location, etc.
- Data Preprocessing: Clean and preprocess the collected data to remove noise and inconsistencies, ensuring high-quality input for
machine learning algorithms.
- Machine Learning Model: Implement machine learning algorithms to analyze the preprocessed data and detect patterns indicative
of potential health issues.
- Edge Computing: Deploy learned models to edge device. Process data locally on edge devices to reduce latency and ensure quick
response times.
- Alert Generation: Generate timely alerts, reminders, etc. based on the analyzed data for family members and
emergency responders.

Working of the main project module - The system continuously collects data from sensors and IoT devices,
preprocesses the data, and applies machine learning algorithms for real-time analysis. Edge computing processes the
data locally, and if any abnormal patterns are detected, alerts are generated instantly. These alerts are sent to family
members and emergency responders, enabling them to intervene promptly and provide necessary medical attention.

Tools used - Raspberry Pi (or similar edge computing devices), various sensors (gyroscope, accelerometer, GPS
module, etc.), IoT devices. Python for programming machine learning algorithms, TensorFlow or scikit-learn for
implementing machine learning models, MQTT or other communication protocols for data transmission, and
appropriate IDEs for coding and debugging.

Applications - "SwiftEdge" enhances elderly care by seamlessly integrating edge computing on a Raspberry Pi
wearable, ensuring real-time monitoring, precise fall detection, adaptive safety measures, and comprehensive well-
being management.

Flowline -
Jul-Aug: Case study, topic search, finalization, approval from guide.
Sep-Oct: Starting of project work, study, and implementation of OCR.
Nov-Dec: Translation into other languages, test run.
Jan-Feb: Final implementation and project demo with main-project exhibition, SEE.

Dept. of ECE, DSCE, Bangalore

You might also like