Scribd
Upload
5 views16 pages

Major Project

Uploaded by

abhitelasang2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
5 views16 pages

Major Project

Uploaded by

abhitelasang2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

K.L.

E College of Engineering and Technology


Chikodi 591201

Department of Computer Science and


Engineering Major project on
“Machine Learning Series Demonstrator For
Android Application”

Presented By,
Anusha Bisti [2KD21CS014]
Abhi Telasang [2KD21CS001] Under the Guidance of,
Prof. Sunita Karabasannavar
Anjum Shaikh [2KD21CS011]
Namrata Katageri [2KD21CS046]

1
CONTENT

 INTRODUCTION
 LITERATURE SURVEY
 PROBLEM STATEMENT
 OBJECTIVES
 OVERVIEW OF PROPOSED SYSTEM
 FUNCTIONAL FLOW DIAGRAM
 METHEDOLOGY
 SYSTEM REQUIREMENTS
 PROJECT SNAPSHOTS
 CONCLUSION
 REFERENCES
Machine Learning Series Demonstrator For Android Application 1
INTRODUCTION
 In the machine learning, the fusion of cutting-edge technologies like
image recognition, audio analysis, and pattern detection has
revolutionized various domains

 This task endeavors to harness the competencies of device learning


algorithms to tackle a diverse range of tasks, including plant disease
detection, vitamin deficiency identification, object detection, bird
sound identification on Android devices

Machine Learning Series Demonstrator For Android Application 2


LITERATURE SURVEY

Machine Learning Series Demonstrator For Android Application 3


PROBLEM STATEMENT

The manual approach to detecting plant diseases, vitamin deficiencies, object identification,
and bird species classification is inefficient, often inaccessible, and prone to human error.
Reliance on expert consultations and visual observation can lead to delays and
inconsistencies, especially for those in remote or underserved areas. This lack of immediate
diagnostic tools hampers timely decision-making in agriculture, health, and conservation
efforts. There is a pressing need for an automated, accurate, and user-friendly mobile
application that addresses these limitations. This project seeks to bridge this gap by offering
an accessible, multi-functional detection system powered by machine learning.

Machine Learning Series Demonstrator For Android Application 4


OBJECTIVES
 Plant Disease Detection: identifying diseases in plants using various
techniques, Early and accurate detection helps prevent crop loss and
improve agricultural productivity.

 Vitamin Deficiency Identification: detects low levels of essential


vitamins in the body, often through symptoms or blood tests.

 Object Detection: Detecting and locating objects within images can


have applications in security, autonomous vehicles, and augmented
reality.

 Bird Sound Identification: Identifying bird species through their


unique sounds.

Machine Learning Series Demonstrator For Android Application 5


OVERVIEW OF PROPOSED SYSTEM
The Machine Learning Series Demonstrator focuses on creating an
Android application that utilizes machine learning for real-time plant
disease detection, vitamin deficiency detection, object detection, and bird
sound identification. This project aims to provide participants with
practical experience in implementing machine learning algorithms on
mobile platforms.

Machine Learning Series Demonstrator For Android Application 6


FUNCTIONAL FLOW DIAGRAM

Fig 1 : Functional Flow Diagram of Machine Learning Series Demonstrator For Android Application

Machine Learning Series Demonstrator For Android Application 7


METHODOLOGY
 Machine Learning Model Selection: Pre-trained models with TensorFlow are chosen
for each use case. TensorFlow Lite is used for on-device inference.

 Android Studio Integration: The ML models are integrated within Android Studio using
libraries like TensorFlow Lite.

 User Interaction: Each application is designed to be user-friendly and efficient, running


machine learning tasks seamlessly on mobile devices without requiring cloud
processing.

 Model Optimization: The models are optimized to run efficiently on mobile devices,
ensuring fast inference times and minimal impact on device performance.

Machine Learning Series Demonstrator For Android Application 8


REQUIREMENTS
Hardware Requirements
 Processor - I3/Intel Processor
 RAM - 8 GB
 Hard Disk - 1TB (Optional)

Software Requirements
 Operating System - Windows 10
 JDK - Java
 Plugin - Kotlin
 SDK - Android
 IDE - Android studio

Machine Learning Series Demonstrator For Android Application 9


PROJECT SNAPSHOTS

Fig 2 : Dashboard
Machine Learning Series Demonstrator For Android Application 11
Fig 3 : Plant Disease Detection
Machine Learning Series Demonstrator For Android Application 12
Fig 4 : Vitamin Deficiency Detection
Machine Learning Series Demonstrator For Android Application 13
CONCLUSION
• This Android application effectively merges advanced machine learning
techniques with user-friendly design to address critical challenges in agriculture
and health. By facilitating timely plant disease detection, identifying vitamin
deficiencies, recognizing objects, and classifying bird species
• The app not only enhances agricultural productivity and personal health but also
fosters environmental awareness and conservation efforts.

Machine Learning Series Demonstrator For Android Application 10


REFERENCES
 Agbaje, M., & Kalu, I. (2023). "Mobile Application for Plant Disease Detection
Using Machine Learning." International Journal of Computer Applications,
182(20), 1-6.
 Sharma, A., & Kumar, R. (2022). "Development of a Mobile Application for
Detecting Vitamin Deficiency." Journal of Health Informatics in Developing
Countries, 14(1), 15-22.
 Kaur, M., & Singh, R. (2022). "AI-Powered Mobile Application for Object
Recognition in Agricultural Fields." Journal of Agricultural Science and
Technology, 24(2), 267-278.
 Zhao, J., & Liu, Y. (2021). "Bird Species Identification Using Audio
Classification in Mobile Applications." Ecological Informatics, 62, 101252.

Machine Learning Series Demonstrator For Android Application 11


THANK YOU

Machine Learning Series Demonstrator For Android Application 12

You might also like