Report 1 AI
Report 1 AI
Report 1 AI
SHASHANK S(1JB20IS059)
SANDEEP D K(1JB20IS055)
SRINIVAS P C(1JB20IS067)
UJWAL KUMAR R(1JB20IS081)
Mr. Vishruth B G
Assistant Professor
Dept. of ISE, SJBIT
CERTIFICATE
Certified that the project work entitled “AI HEALTH ASSISTANT” carried out by Mr. Shashank S
bearing USN 1JB20IS059, Mr. Sandeep DK bearing USN 1JB20IS055 , Mr. Srinivas Prasad C
bearing USN 1JB20IS067 , Mr. Ujwal Kumar R bearing USN 1JB20IS034, are bonafide students of
SJB Institute of Technology in partial fulfillment for the award of BACHELOR OF ENGINEERING in
Belagavi during the Academic Year 2023-24. It is certified that all corrections/suggestions indicated for
Internal Assessment have been incorporated in the report deposited in the departmental library. The project
report (Phase -1) has been approved as it satisfies the academic requirements in respect of Project work
We would like to express our profound grateful to His Divine Soul Padmabhushan Sri Sri Sri Dr.
Balagangadharanatha Maha Swamiji and His Holiness Jagadguru Sri Sri Sri Dr.
Nirmalanandanatha Maha Swamiji for providing us an opportunity to complete our academics in
this esteemed institution.
We would also like to express our profound thanks to Revered Sri Sri Dr. Prakashnath Swamiji,
Managing Director, SJB Institute of Technology, for his continuous support in providing amenities
to carry out this project in this admired institution.
We express our gratitude to Dr. K V Mahendra Prashanth, Principal, SJB Institute of Technology,
for providing us an excellent facilities and academic ambience; which have helped us in satisfactory
completion of project work.
We extend our sincere thanks to Dr. Shashidhara H R, Professor & Head, Department of
Information Science and Engineering; for providing us an invaluable support throughout the period
of our project work.
We wish to express our heartfelt gratitude to our guide, Mr. Vishruth B G, Assistant Professor,
Department of Information Science and Engineering and the project coordinator Mr. Ranjith J,
Assistant Professor , Department of Information Science & Engineering , for their valuable
guidance, suggestions and cheerful encouragement during the entire period of our project work.
Finally, we take this opportunity to extend our earnest gratitude and respect to our parents, teaching
& non-teaching staff of the department, and all our friends, who have directly or indirectly supported
us during the period of our phase -1 project work.
Regards,
Shashank S(1JB20IS059)
Sandeep DK(1JB20IS055)
Srinivas Prasad C(1JB20IS067)
Ujwal Kumar R(1JB20IS081)
ABSTRACT
In an era of rapidly advancing technology, the AI Health Assistant emerges as a revolutionary solution
for individuals seeking personalized healthcare guidance. This intelligent health companion combines
cutting-edge artificial intelligence with extensive medical knowledge to provide comprehensive support
for your health needs. MediAdvisor goes beyond mere symptom analysis; it is designed to assist users
in making informed decisions about their health. Whether you upload a photo of a disease or describe an
injury or ailment in text, MediAdvisor offers expert guidance on suitable medicines and treatments,
helping you take control of your well-being.But that's not all – MediAdvisoris your gateway to the healthcare
ecosystem. It can also locate nearby hospitals and clinics based on your current location, offering the names and
contact numbers of trusted medical facilities. This feature ensures quick access to quality healthcare when you
need it most. With its user-friendly interface and round-the-clock availability, MediAdvisor becomes your
reliable health ally, empowering you to make informed healthcare choices and connect with medical facilities in
your vicinity effortlessly. Embrace the future of healthcare with AI Health Assistant , and let MediAdvisor guide
you on your path to a healthier, happier life.
iv
TABLE OF CONTENTS
Acknowledgement iii
Abstract iv
Table of Contents v
List of Figures vi
4 System Design 19 - 13
4.1 Design Overview 9
4.2 System Architecture 10
5 System Implementation 14 - 17
5.1 Modules 14
6 Snapshots 18 – 20
6.1 Image Collection 18
6.2 User Interface 20
7 Conclusion 21
8 References 22
v
LIST OF FIGURES
6.3 Results 18
vi
CHAPTER 1
INTRODUCTION
AI HEALTH ASSISTANT:
In an era characterized by technological innovation and a growing emphasis on personalized
healthcare, the convergence of Artificial Intelligence (AI) and medical expertise has emerged as a
transformative force in shaping the future of medicine. Against this backdrop, we introduce
MediAdvisor, an AI Health Assistant poised to revolutionize the way individuals access and
manage their healthcare needs.
In this report, we delve into the motivations behind the development of MediAdvisor,
exploring its potential to address healthcare disparities, enhance accessibility, and deliver
personalized healthcare guidance. We examine the features and functionalities that distinguish
MediAdvisor as a pioneering solution in the healthcare landscape, as well as its broader
implications for the future of medicine.
Through a combination of in-depth analysis and real-world examples, we aim to shed light
on the transformative impact of MediAdvisor in shaping a healthier, happier future for individuals
worldwide. Join us as we embark on a journey to explore the capabilities, challenges, and
opportunities presented by this groundbreaking AI Health Assistant.
1
HYBRID APPROACH LEAF DISEASE DETECTION
AND DISEASE MANAGEMENT USING CNN Introduction
Motivation:
In a world where healthcare accessibility and personalized guidance are paramount, the
introduction of MediAdvisor marks a significant step forward. By integrating advanced AI and
medical knowledge, this innovative platform offers tailored assistance on symptoms, medications,
and treatments. With its user-friendly interface and round-the-clock availability, MediAdvisor
aims to democratize healthcare, providing individuals with reliable guidance and facilitating
seamless access to quality medical services. In essence, MediAdvisor represents a transformative
force in shaping the future of healthcare, promising a healthier, happier life for all
Challenges:
Absolutely, points highlight some of the critical challenges associated with AI Health
Assistant . Let's delve a bit deeper into each of these challenges:
• Data Security and Privacy Problem : Ensuring user data security and privacy compliance
presents challenges in implementing robust encryption, access controls, and data
anonymization techniques.
• Preformatted Data: Integrating diverse medical data formats into MediAdvisor requires
addressing interoperability issues and collaborating with healthcare providers for seamless
integration.
Objectives:
LITERATURE SURVEY
The objective of carrying out literature survey before implementing any project is to get an idea
of how the project can be implemented and to understand various technologies used to build a
project. So it is of utmost necessary to find the most recent and promising research papers related to
our project topic“ Hybrid approach for leaf disease detection and disease management using CNN”.
4
HYBRID APPROACH LEAF DISEASE DETECTION
AND DISEASE MANAGEMENT USING CNN Literature Survey
ML, Deep Learning (DL), this area of research appears to have a lot of promise in terms of improved
accuracy. The proposed method uses a convolutional neural network and a Deep Neural Network to
identify and recognise crop disease symptoms effectively and accurately. Furthermore, multiple
efficiencymetrics are used to assess these strategies. This article offers a thorough description of the DL
models thatare used to visualise crop diseases. Furthermore, several research gaps are identified from
which greater transparency for detecting diseases in plants can be obtained, even before symptoms
occur. The proposed methodology aims to develop a convolution neural network-based strategy for
detecting plant leaf disease.
Title: A novel deep learning method for detection and classification of plant diseases
Author: Waleed Albattah· Marriam Nawaz · Ali Javed· Momina Masood · Saleh Albahli1
Publication: 28 September 2021
Abstract: The agricultural production rate plays a pivotal role in the economic development of a
country. However, plant diseases are the most significant impediment to the production and quality of
food. The identification of plant diseases at an early stage is crucial for global health and wellbeing. The
traditional diagnosis process involves visual assessment of an individual plant by a pathologist through
on-site visits. However, manual examination for crop diseases is restricted because of less accuracy and
the small accessibility of human resources. To tackle such issues, there is a demand to design automated
approaches capable of efficiently detecting and categorizing numerous plant diseases.
Abstract: Deep learning is a branch of artificial intelligence. In recent years, with the advantages of
automatic learning and feature extraction, it has been widely concerned by academic and industrial circles.
It has been widely used in image and video processing, voice processing, and natural language processing.
At the same time, it has also become a research hotspot in the field of agricultural plant protection, such
as plant disease recognition and pest range assessment, etc. The application of deep learning in plant
disease recognition can avoid the disadvantages caused by artificial selection of disease spot features,
make plant disease feature extraction more objective, and improve the research efficiency and techcrop
leaf disease identification in recent years.
Title: Plant Leaf Disease Detection Using Computer Vision Techniques and
Machine Learning
Author: Kalpesh Joshi1 , Rohan Awale2, Sara Ahmad3, Sanmit Patil4, and Vipul Pisal
Publication: 2022
Existing System
The current system's simplicity, driven by the absence of image upload, ensures a user-friendly
experience. This streamlined approach not only makes navigation more straightforward but also
contributes to improved resource efficiency, requiring fewer computational resources. Additionally,
users benefit from faster response times, as the system isn't burdened with the processing demands
associated with handling image data..
Proposed System
Data Acquisition:
In the data acquisition phase, our focus will be on gathering diverse health-related data. This
will include behavioral data collected from wearable devices and surveys, as well as medical
images submitted securely by users. Throughout this process, we will prioritize data security
and patient privacy, ensuring compliance with relevant regulations and protocols.
Additionally, we will explore opportunities for augmenting our datasets through partnerships
with healthcare institutions, leveraging their resources and expertise to enrich our data source,
Feature Engineering: Following data acquisition, our attention will turn to feature
engineering. Here, we will extract relevant features from the collected data using advanced
techniques. This will involve employing methods such as natural language processing (NLP)
to derive insights from electronic health records, as well as utilizing Convolutional Neural
Networks (CNNs) for image feature extraction. Our goal in this phase will be to identify key
patterns and insights that can inform the algorithms powering the AI Health Assistant,
enabling it to provide accurate and personalized recommendations.
Module Design and Development : With the extracted features in hand, we will proceed to
the module design and development phase. Here, we will define the requirements and
functionalities for each module of the AI Health Assistant. Clean, maintainable code will be
developed following industry best practices and coding standards, ensuring scalability and
flexibility for future enhancements. Additionally, we will prioritize user-centric design
principles, aiming to create an intuitive and seamless user experience that caters to the diverse
needs and preferences of our user base.
Testing ang Integration : rigorous testing and integration will be conducted to validate the
functionality and reliability of the AI Health Assistant. This will involve thorough testing at
multiple levels, including unit testing to validate individual module functionalities and
integration testing to ensure seamless interaction between modules. By identifying and
addressing any issues or bugs early in the development process, we will ensure that the AI
Health Assistant delivers on its promise of providing accurate, reliable, and user-friendly
healthcare guidance.
System requirements specification establishes the basis for an agreement between customers
and contractors or suppliers on how the software product should function. SRS is a rigorous
assessment of requirements before the more specific system design stages, and its goal is to reduce
later redesign. It should also provide a realistic basis for estimating product costs, risks, and schedules.
Used appropriately, software requirements specifications can help prevent software project failure.
Hardware Requirements
Processor : >i3
Ram :4GB.
Hard Disk : 500GB.
Input device : Standard Keyboard and Mouse.
Compact Disk : 650Mb.
Output device : High Resolution Monitor
Software Requirements
Programming Languages: Java, JavaScript/Node.Js.
Development Frameworks: React, Angular.
Database Management : SQL,MongoDB.
Development Environment: Visual Studio Code, or Jupyter Notebook for efficient coding.
Map and Location APIs: integrating map and location APIs such as Google Maps APIMachine
Learning Tool Box
8
CHAPTER 4
SYSTEM DESIGN
System design is the process of defining the architecture, components, modules, interfaces, and
data for a system to satisfy specified requirements. System design is one of the important phases of
software development process. The purpose of the design is to plan the solution of a problem specified
by the requirement documentation. In other words, the first step in the solution to the problem is the
design of the project. The design concepts provide the software designer with a foundation from which
more sophisticated methods can be applied. Software design is a process of problem-solving and
planning for a software solution.
After the purpose and specifications of software are determined, software developers will design
or employ designers to develop a plan for a solution. It includes low-level components and algorithm
implementation issues as well as the architectural view. Object-oriented analysis and design methods are
becoming the most widely used methods for computer system design. It is widely used for modelling
software systems and is increasingly used for high designing non-software systems and organization.
System design is the process of defining the architecture, components, modules, interface and data fora
system to satisfy specified requirements. System design could see it has the application of systems theory
to product development.
Design Overview
The increasing importance of software running on generic platforms has enhanced the discipline
of software engineering. Object-oriented analysis and design methods are becoming the most widely
used methods for computer systems design. The UML has become the standard language in object-
oriented analysis and design. It is widely used for modelling software systems and is increasingly used
for high designing non-software systems and organizations.
System design is one of the most important phases of software development process. The purpose
of the design is to plan the solution of a problem specified by the requirement documentation. In other
words, the first step in the solution to the problem is the design of the project.
The design will contain the specification of all those modules their interaction with the other
modules and desired output from each module. The output of design process is a description of software
architecture.
9
HYBRID APPROACH LEAF DISEASE DETECTION
AND DISEASE MANAGEMENT USING CNN System Design
System Architecture
The system architecture of the AI Health Assistant orchestrates a seamless flow of processes,
starting with data acquisition from diverse sources like wearable devices and electronic health records.
Through preprocessing and feature extraction, raw data is refined into actionable insights, enabling
accurate diagnosis and personalized treatment recommendations. Leveraging machine learning
algorithms and intuitive user interfaces, the architecture ensures efficient analysis of symptoms and
delivers tailored healthcare guidance. Robust backend services manage data storage and security,
guaranteeing confidentiality and compliance with regulatory standards. Overall, the architecture fosters
a scalable and adaptable framework, empowering users to make informed decisions and achieve
optimal health outcomes.
A Data Flow Diagram (DFD) is a graphical representation of the "flow" of data through an
information system, modelling its process aspects. A DFD is often used as a preliminary step to create
an overview of the system without going into great detail, which can later be elaborated. DFDs can also
be used for the visualization of data processing (structured design).
A DFD shows what kind of information will be input to and output from the system, how the data
will advance through the system, and where the data will be stored. It does not show information about
process timing or whether processes will operate in sequence or in parallel, unlike a traditional structured
flowchart which focuses on control flow, or a UML activity workflow diagram, which presents both
control and data, flows as a unified model.
A dataflow outline is a tool for referring to knowledge progression from one module to the next module
as shown in Fig 4.3 This graph gives the data of each module's info and yield. The map has no power flow
and there are no circles at the same time.
VGG, or the Visual Geometry Group, is a renowned research group at the University of Oxford
focusing on computer vision. VGG16 and VGG19 are well-known convolutional neural network
(CNN) architectures developed by this group. They're popular for their simplicity and effectiveness in
image classification tasks. These architectures have been widely used as benchmarks in computer
vision research and have contributed to advancements in image recognition and object detection.
SYSTEM IMPLEMENTATION
System implementation marks the critical juncture where conceptual plans materialize into
functional software. Its successful execution is paramount, as it determines whether the developed
solution aligns with predefined objectives, meets user needs, and adheres to industry standards. This
phase not only brings the project to fruition but also lays the groundwork for scalability,
maintainability, and adaptability. A well-executed implementation ensures the system's ability to
address healthcare challenges effectively, leading to improved patient outcomes and enhanced
healthcare delivery. Thus, system implementation stands as a pivotal step in realizing the
transformative potential of the AI Health Assistant, driving positive change in the healthcare
landscape.
Modules
The numbers of modules implemented in this project are six and are listed below as follow:
Module 3: Segmentation
Module 5: Prescription
The Data Acquisition module is responsible for gathering diverse health-related data from various
sources such as wearable devices, mobile apps, and electronic health records (EHRs). This includes
behavioral data, medical images, and patient-reported information, ensuring a comprehensive dataset
for analysis and decision-making.
Code Snippet:
import os
import pandas as pd
13
def data_dict():
# Define paths for training and testing images
path_train = "/gdrive/My Drive/Skin_disease_data_1/train/"
path_test = "/gdrive/My Drive/Skin_disease_data_1/test/"
14
Module 2: Image Preprocessing:
In the Preprocessing module, collected data undergoes cleaning, normalization, and transformation to
prepare it for analysis. This involves handling missing values, removing outliers, and standardizing
data formats to ensure consistency and reliability in subsequent processing steps.
Code Snippet:
images = []
label = []
for i in train['image_path']:
img = cv2.imread(i)
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
img = cv2.resize(img,(180,180))
images.append(img)
plt.show()
Module 3: Segmentation
The Segmentation module focuses on separating relevant regions or components from complex
datasets. In the context of medical imaging, segmentation techniques are applied to isolate specific
structures or anomalies from background noise, facilitating accurate analysis and diagnosis.
Module 4: Identification
In the Identification module, extracted features and segmented data are analyzed to identify patterns,
trends, and anomalies indicative of potential health conditions or risks. Machine learning algorithms
and statistical methods are employed to classify and diagnose patients based on their health data.
15
Module 5: Prescription
The Prescription module generates personalized treatment recommendations based on the identified
health conditions and patient characteristics. This may include medication prescriptions, lifestyle
modifications, or referrals to healthcare providers, aiming to optimize patient outcomes and improve
overall well-being.
16
CHAPTER 6
SNAPSHOTS
This chapter shows some of the working snapshots of our project “AI HEALTH ASSISTANT ”.
Image Collection
User Interface
1. Login Page
17
HYBRID APPROACH LEAF DISEASE DETECTION
AND DISEASE MANAGEMENT USING CNN Snapshots
2. Result
19 0
REFERENCES
[1] Tanwar S. & Goyal R. (2020). Automatic plant leaf disease detection and classification using convolutional
neural network. In 2020 11th International Conference on Computing, Communication network and
[2] Umar, S., Prasad, K., Srilekha, A., Suman, T., Rao, B. P., & Vamshi Krishna, J. N. (2020). Leaf Disease
Detection and Classification based on Machine Learning. In 2020 International Conference on Smart
[3] Singh A., & Gupta A. (2019). Designed disease detection and diagnosis on the leaves using image
[4] S. K. Sood & Singh, A. (2018). Image based Recognition of Plant Leaf Diseases using MATLAB. In 2018
[5] Muthukaruppan, S., & Muthuramalingam, R. (2018). Plant Leaf Diseases Detection and Classification
Using Image Processing and Deep Learning Techniques. In 2018 International Conference on Advances
[6] M. N. Patel, R. K. V. G. Rao, and S. M. Patel, "Identification of Leaf Diseases using Image Processing
Techniques: A Review," Journal of Emerging Trends in Computing and Information Sciences, 2011.
[7] M. Rahaman, M. A. Hossain, and M. S. Kaiser, "Plant Leaf Disease Detection and Classification using
Convolutional Neural Network," Journal of King Saud University - Computer and Information Sciences,
2019.
[8] A. Ghosal, S. Blystone, S. Singh, and S. Ganapathysubramanian, "Detection of Plant Diseases by Image-
[9] A. Ferentinos, "Identification of Plant Leaf Diseases Using a Smartphone“, Neural Computing and
Applications, 2018.
20
REFERENCES
[10] K. K. Khandakar, S. K. Gedeon, and A. B. Kamruzzaman, "A Review on Automatic Plant Disease
Identification using Mobile Image Processing“, Computers and Electronics in Agriculture, 2019.
[11]S.Raj Kumar , S.Sowrirajan,” Automatic Leaf Disease Detection and Classification using Hybrid Features
and Supervised Classifier”, International Journal of Advanced Research in Electrical, Electronics and
[12] Tatem, D. J. Rogers, and S. I. Hay, “Global transport networks and infectious disease spread,” Advances in
Parasitology, vol. 62, pp. 293–343, 2006. View at Publisher · View at Google Scholar · View at Scopus.
[13] J. R. Rohr, T. R. Raffel, J. M. Romansic, H. McCallum, and P. J. Hudson, “Evaluating the links between
climate, disease spread, and amphibian declines,” Proceedings of the National Academy of Sciences of the
United States of America, vol. 105, no. 45, pp. 17436–17441, 2008.
[14] Mrunalini R. et al., An application of K-means clustering and artificial intelligence in pattern recognition for crop
diseases ,2011.
[15] T. Van der Zwet, “Present worldwide distribution of fire blight,” in Proceedings of the 9th International Workshop
21