A Synopsis on
" AyurGenixAI - An Ayurvedic Medication Advisor"
Submitted in partial fulfilment of the requirements of the degree
Bachelor of Engineering (Artificial Intelligence and Data Science)
Submitted by
1. Yadnesh Krishnakant Bhanushali
2. Kirti Anil Rane
3. Nikita Baban Yadav
Supervisor
Dr. (Mrs.) Preeti Jain
Department of Artificial Intelligence and Data Science
Airoli, Navi Mumbai
(Affiliated To University of Mumbai)
Academic Year 2024-2025
Certificate
This is to certify that, following students
1. Yadnesh Bhanushali
2. Kirti Rane
3. Nikita Yadav
Have satisfactorily completed the term work for project titled as " AyurGenixAI - An
Ayurvedic Medication Advisor", undertaken at "Datta Meghe College of Engineering, Airoli" in
partial fulfilment of the requirements of degree of "Bachelor of Engineering, (Artificial Intelligence
and Data Science)", (CBCGS Course), of "University of Mumbai", in semester VII during
academic year 2024-2025.
Dr. (Mrs.) Preeti Jain Dr. S. M. Patil Dr. P. A. Dode
Supervisor Head of Department Principal
Project Approval
This project, entitled as " AyurGenixAI - An Ayurvedic Medication Advisor", submitted by the
students,
1. Yadnesh Bhanushali
2. Kirti Rane
3. Nikita Yadav
Is approved for the term work in partial fulfilment of the requirements of degree of “Bachelor of
Engineering, (Artificial Intelligence and Data Science)", (CBCGS Course), of "University of
Mumbai", in semester VII during academic year 2024-2025.
1) Name and Signature of Internal Examiner:
2) Name and Signature of External Examiner:
Date:
Place: Airoli
Declaration
We declare that this written submission represents our idea in our own words and other ideas and
words which have been included are adequately cited and referenced from the original source. We
also declare that we have adhered to all principles of academic honesty and integrity and have not
misrepresented or fabricated or falsified an idea/data/fact/source in our submission. We understand
that our violation of above will cause disciplinary action by Institute and can also evoke penal
action for the sources which have thus not been properly cited or from whom proper permission has
not been taken when needed.
NAME SIGNATURE
1. Yadnesh Bhanushali
2. Kirti Rane
3. Nikita Yadav
Date:
Place: Airoli
Contents
Abstract vi
Acknowledgments vii
List of Abbreviations viii
List of Figures ix
List of Appendices x
1. Introduction 1
1.1 Introduction
1.2 Existing Systems and Their Limitations
1.3 Aims & Objectives
1.4 Organization of the Report
2. Literature Survey 4
2.1 Survey of Existing System
3. System Design 6
3.1 Architecture/ Framework
3.2 Algorithm and Process Design
3.4 Details of Hardware & Software Stack
4. Implementation and Result 12
4.1 Results
5. Conclusion and Future Scope 15
References xi
Abstract
By addressing the limitations of current healthcare advisory systems, which predominantly focus on
Western medicine, AyurGenixAI offers an alternative approach that prioritises natural remedies,
personalised health profiles, and user education. This project seeks to bridge the gap between
traditional Ayurvedic knowledge and modern healthcare practices, ensuring that common health
concerns can be addressed in a manner that is easy to comprehend, implement, and trust.
AyurGenixAI is an innovative web-based platform that integrates the principles of ayurveda with
modern AI technologies to provide personalised health solutions. Drawing from the ancient science of
ayurveda, the system offers natural remedies using common household ingredients such as ginger,
turmeric, and tulsi, making holistic healthcare accessible to all. The platform enables users to input
symptoms in everyday language, employs advanced machine learning models to identify potential
health conditions, and suggests personalised Ayurvedic treatments based on the diagnosis.
6
Acknowledgments
We would like to express our deepest gratitude to everyone who contributed to the partial completion
of this project report on AyurGenixAI. First and foremost, we extend our sincere thanks to our project
supervisor, Dr. (Mrs.) Preeti Jain, for her invaluable guidance, constant support, and expert feedback,
which were instrumental in shaping this project. We are deeply indebted to her for her constant
supervision and for providing essential information, which greatly facilitated the partial completion of
AyurGenixAI. We are also profoundly thankful to our Head of Department, Dr. S. M. Patil, for his
continued encouragement and leadership, as well as to all the professors and faculty members of the
Department of Artificial Intelligence and Data Science for their valuable insights and support
throughout the project. Finally, we would like to extend our heartfelt thanks to our Principal, Dr. P. A.
Dode, for his unwavering support and leadership, which provided the foundation for the successful
progress of this project.
Additionally, we are grateful to our families for their encouragement and cooperation, which played a
crucial role in helping us achieve our goals. We would also like to acknowledge the developers and
researchers in the fields of artificial intelligence and Ayurveda whose foundational work inspired and
informed our project.
7
List of Abbreviations
1. AI - Artificial Intelligence 1
2. ML - Machine Learning 4
3. KNN - K-Nearest Neighbors 4
4. LSTM - Long Short-Term Memory 4
5. NLG - Natural Language Generation 4
6. SVM - Support Vector Machine 5
7. OCR – Optical Character Recognition 6
8. NLP - Natural Language Processing 6
9. BERT - Bidirectional Encoder Representations from Transformers 9
10. XGBoost - Extreme Gradient Boosting 9
11. UI - User Interface 13
8
List of Figures
1. System Architecture 6
2. AyurGenixAI Process Flow 8
3. Disease Prediction UI with Encoded Data 13
4. Disease Prediction UI Prototype 14
9
List of Appendices
1. Appendix i. Synthetic Dataset 12
2. Appendix ii. Encoded Dataset 13
3. Appendix iii. Disease Prediction UI with Synthetic Data 14
10
Chapter 1
Introduction
1.1 Introduction
AyurGenixAI is a state-of-the-art ayurvedic medication advisor that merges the ancient wisdom of
ayurveda with cutting-edge AI technologies to offer personalised health solutions. ayurveda, meaning
"the science of life," has been practised for thousands of years and emphasises the use of natural
ingredients such as herbs[1], spices, and commonly available kitchen items to treat and prevent a
variety of ailments. This holistic approach not only addresses physical symptoms but also considers
the overall well-being of an individual by focusing on the balance of the mind, body, and spirit.
In today’s fast-paced society, many individuals are unaware of how to effectively use ayurvedic
remedies for minor health concerns, often resorting to modern medicine for quick relief. AyurGenixAI
acts as a bridge between ancient ayurvedic practices and modern digital technologies by providing an
easy-to-use platform where users can enter their symptoms and receive personalised recommendations
for ayurvedic treatments. This approach not only advocates for a natural and holistic form of
healthcare but also makes it accessible to a wide audience, including those with no prior understanding
of ayurveda[3].
1.2 Existing Systems and Their Limitations
Several digital healthcare platforms currently offer advice and treatments based on user-input
symptoms. However, these platforms predominantly focus on modern allopathic medicine and fail to
provide comprehensive guidance on Ayurvedic treatments. Common issues with existing systems
include:
● Most current platforms and healthcare apps focus on diagnosing illnesses using Western medicine,
typically recommending pharmaceutical solutions without considering natural alternatives that
may be more appropriate for minor ailments.
● Ayurveda places significant emphasis on individual differences, such as Prakriti [4] (body
constitution) and Dosha [5] (Vata, Pitta, Kapha). Existing systems often lack the capability to
personalise recommendations based on these factors, frequently offering generic, one-size-fits-all
solutions.
● The medical advice provided by these platforms is often laden with complex terminology and
jargon, making it difficult for users without a medical background to fully understand and apply
11
the recommendations.
● Many healthcare apps overlook the preferences of users who favour natural, home-based
treatments that utilise easily available household ingredients like ginger, turmeric, and tulsi.
● Even when ayurveda is included, it is often treated as a secondary option, with limited remedy
databases and minimal understanding of the core principles behind Ayurvedic treatments.
These limitations underscore the need for a platform that is specifically centred on Ayurveda, user-
friendly, and capable of offering accurate and personalised treatment recommendations.
1.3 Aim & Objectives
AyurGenixAI aims to fill the gap in current healthcare advisory systems by offering a platform that
integrates traditional Ayurvedic practices with modern AI technology. The following are the aim and
objectives of this project:
Problem Statement: The lack of accessible platforms for personalised Ayurvedic treatment forces
many people to rely on scattered information or conventional healthcare. AyurGenixAI solves this by
providing tailored Ayurvedic treatment recommendations through an easy-to-use digital platform,
offering a convenient and natural health solution.
Aim: To develop a web-based platform that delivers accurate and personalised Ayurvedic treatment
recommendations based on user-input symptoms, making Ayurvedic healthcare easily accessible to the
general public.
Objectives:
1. Leverage advanced machine learning models to identify potential illnesses based on user-provided
symptoms. This will involve training the models on a diverse dataset of symptoms and associated
illnesses to ensure accurate predictions.
2. Provide customised Ayurvedic treatment recommendations tailored to the diagnosed illness,
considering the user's specific symptoms and preferences. These suggestions will include common
home remedies and the use of ingredients like ginger, turmeric, tulsi, and other medicinal herbs.
3. Create a simple, intuitive platform where users can input symptoms in everyday language. The
system should be capable of understanding and interpreting common expressions of discomfort or
illness, ensuring accessibility even to those without medical expertise.
12
4. Evaluate whether the diagnosed illness can be managed with home remedies or if expert
consultation is required. The platform will clearly indicate when users should seek professional
medical advice.
5. Educate users on Ayurvedic principles, remedies, and the benefits of using natural ingredients for
health and wellness. The platform will function as both a diagnostic and educational tool, raising
awareness of Ayurvedic practices.
This holistic approach ensures that AyurGenixAI not only provides accurate treatment
recommendations but also educates users on the advantages of ayurveda, promoting a more
comprehensive approach to health management.
1.4 Organization of the report
This report is structured to provide a comprehensive overview of the AyurGenixAI project, from its
conceptual framework to implementation. Each chapter is organised as follows:
Chapter 1: Introduction This chapter provides an overview of AyurGenixAI, detailing its objectives,
the relevance of ayurveda in contemporary health practices, and the limitations of existing healthcare
systems that highlight the need for an AI-driven solution.
Chapter 2: Literature Survey This chapter conducts a comprehensive review of existing digital
healthcare platforms that integrate artificial intelligence, assessing their limitations in addressing
Ayurvedic healthcare and emphasising the distinctive features of AyurGenixAI.
Chapter 3: System Design This section presents the architectural framework of AyurGenixAI,
outlining the technologies employed, including machine learning algorithms, database structures, and
the overall system workflow.
Chapter 4: Implementation and Results This chapter elaborate on the implementation of the
AyurGenixAI platform, detailing the processes involved in coding, testing, and deployment, as well as
presenting the performance metrics achieved.
Chapter 5: Conclusion and Future Scope The final chapter synthesises the key findings of the project,
emphasising the advantages of integrating ayurveda with AI, and outlines potential future
developments aimed at enhancing the platform’s functionality and global reach.
13
Chapter 2
Literature Survey
The integration of machine learning (ML) algorithms with traditional Ayurvedic practices has
significantly advanced healthcare solutions, particularly in managing chronic conditions such as
arthritis. One notable system, AyuAIra: Intelligent Ayurvedic Medicine System for Arthritis[12],
employs various ML techniques, including KNN[7] for X-ray analysis, LSTM[8] for blood report
monitoring, decision trees for Ayurvedic treatment recommendations, and XGBoost[9] for continuous
patient monitoring. These algorithms enable personalised treatment plans using individual patient data,
ensuring tailored care. Additionally, real-time feedback and continuous monitoring enhance the
timeliness of interventions, potentially improving treatment outcomes. However, further
improvements, including clinical validation and user interface enhancements, are necessary to increase
the system's reliability and accessibility for diverse user groups, especially older patients and non-
English speakers.
Similarly, the Ayurvedacharya App[13] offers straightforward and cost-effective Ayurvedic
remedies for common ailments, complemented by an exercise module featuring yoga videos and
images. Developed using Android Studio and SQLite, this app features a user-friendly interface that
makes it accessible to a broad audience. While the app promotes overall well-being, its functionality
could be improved by incorporating stronger security measures to protect user data, offering more
detailed medical advice, and integrating direct consultation options with Ayurvedic practitioners.
Expanding the range of remedies available would further enhance its utility.
Another innovative solution, [Link][15], employs classification techniques in machine learning to
predict Ayurvedic herbs for specific diseases, creating a comprehensive healthcare approach that
combines Ayurvedic, allopathic, and home remedies. Utilising Natural Language Processing (NLP)
and Natural Language Generation (NLG), the chatbot facilitates user interactions in multiple
languages, enhancing accessibility for a diverse user base. However, to maximise its effectiveness,
improvements in dataset quality, broader disease coverage, and stronger privacy protections are
recommended. Furthermore, clinical validation of the chatbot’s predictions is essential to ensure
reliability and trustworthiness.
14
Lastly, the integration of machine learning classification techniques in predicting Ayurvedic herbs for
specific diseases marks a significant advancement in modernising traditional healthcare practices. By
employing decision trees, random forests, and support vector machines (SVM), these systems provide
personalised herb recommendations tailored to specific disease profiles. However, there is a pressing
need to expand datasets to include a wider variety of diseases and herbs, refine classification
algorithms for more complex cases, and validate these systems with real-world data to enhance their
accuracy and reliability. Incorporating these systems into clinical decision-making tools could further
promote their adoption in healthcare settings.
15
Chapter 3
System Design
3.1 Architecture
System design outlines an architecture that integrates modern AI with Ayurvedic principles for disease
prediction and treatment recommendations. The process begins with web scraping and OCR to collect
raw data from various online sources, such as medical texts and reports. This data is then pre-
processed to remove irrelevant information, structured, and stored in a database for future use. When a
user inputs their symptoms through the UI, the system utilises Ayurgenix AI to analyse these
symptoms, referencing the stored data. The AI processes the input and outputs a predicted disease
using a disease prediction model trained on medical data.
Once the disease is predicted, the system evaluates whether the condition can be treated at home. If
not, the user is advised to seek professional medical care. If yes, the system proceeds to the Ayurvedic
Medicine Recommender, which provides treatments based on Ayurvedic practices. The NLP processor
then translates these technical results into user-friendly language, offering a list of home remedies
tailored to the predicted disease. The system presents these findings through a UI, allowing users to
easily interact with the application and receive actionable, holistic health advice.
Fig 1. System Architecture
16
1. Web Scraping and OCR:
○ Collects raw data from various online sources (e.g., Ayurvedic texts, medical journals)
using web scraping techniques.
○ Converts images (if present) into text for further processing.
2. Pre-Processing and Warehousing:
○ Cleans and standardises the collected data to remove noise, inconsistencies, and
irrelevant information.
○ Stores the preprocessed data in a database for efficient access and analysis.
3. User Input (Symptoms):
○ Allows users to input their symptoms through a user-friendly interface.
4. Ayurgenix AI:
○ Orchestrates the entire system and coordinates the interactions between different
components.
○ Utilises machine learning algorithms to predict diseases based on the user's inputted
symptoms.
○ Suggests appropriate Ayurvedic remedies based on the predicted disease.
5. NLP Processor:
○ Processes the user's input (symptoms) using natural language processing techniques to
extract relevant information.
6. Decision Point:
○ Determines whether the predicted disease is treatable at home or requires professional
medical attention.
7. UI (User Interface):
○ Displays the predicted disease and recommended Ayurvedic remedies to the user.
Key Interactions:
● Raw data is collected through web scraping and OCR, preprocessed, and stored in the database.
● The user enters their symptoms through the UI.
● The Ayurgenix AI processes the symptoms and predicts the disease using the machine learning
model.
● The Ayurvedic medicine recommender suggests appropriate remedies based on the predicted
disease.
● The NLP processor extracts relevant information from the user's input.
● The system determines whether the disease is treatable at home.
17
● The UI presents the predicted disease and recommendations to the user.
This architecture seamlessly combines modern AI-driven disease prediction with traditional Ayurvedic
treatment recommendations, providing users with home remedies when applicable, while also guiding
them to seek professional care if needed.
3.2 Algorithm and Process Design
Fig 2. AyurGenixAI Process Flow
18
3.2.1. Algorithm Design
Step 1: Natural Language Processing (NLP) [14] for Symptom analysis
● Input: User provides symptoms via text input.
● Goal: Identify relevant Ayurvedic formulations and treatment suggestions.
● Algorithm: Pre-trained NLP [14] models such as BERT [17] or GPT-based models fine-tuned
for medical symptom classification.
o Symptom Matching: Use symptom keywords or contextual embedding (through BERT)
to match symptoms to the most relevant diseases and treatments.
o Custom Tokenization: Add specific ayurvedic terms, herbs, and formulations to the
tokenizer.
● Output: Symptoms classified into diseases.
Step 2: Disease Prediction
● Input: Symptoms extracted from the previous step.
● Goal: Predict the most likely disease or condition.
● Algorithm: XGBoost model trained specifically for disease prediction based on ayurvedic
principles.
o Feature Set: Include features such as disease, doshas (Vata, Pitta, Kapha) [4], and user-
specific health data (Prakriti, age, gender).
● Output: Predicted disease on the input symptoms.
Step 3: Recommendation System for ayurvedic Treatment
● Input: Disease prediction.
● Goal: Recommend the appropriate ayurvedic formulations, herbs, and treatment strategies.
● Algorithm: Content-based filtering or knowledge-graph based recommendation.
o Features: Herbal ingredients, dosage, administration guidelines, user preferences (like
vegan or allergen-free), dosha-balancing effects.
o Side Effect Prediction: Evaluate if the recommended herbs or formulations conflict
with the user's constitution (Prakriti) or existing conditions.
● Output: Personalised Ayurvedic medication or regimen.
3.2.2. Process Design
Data Flow
1. User Input: Symptoms (e.g., "headache, nausea, dry throat").
19
2. NLP Preprocessing: Clean and process the input using BERT or GPT for contextual symptom
understanding.
3. Symptom Classification: The model classifies the symptoms into potential diseases or
conditions.
4. Disease Prediction: BERT [17] model predicts the most relevant disease(s) based on symptom
input.
5. Formulation Matching: Based on the predicted disease, map the relevant ayurvedic
formulations (herbs, diet, lifestyle changes).
6. Dosha and Prakriti Check: Cross-check user’s dosha and prakriti[4] (constitution) for
compatibility with the treatment recommendations.
7. Final Recommendation: Present the ayurvedic formulation with:
o Herb/medicine name
o Dosage
o Administration guidelines
o Dosha balance effects
o Potential side effects
o Lifestyle and dietary suggestions
3.2.3. Challenges and Solutions
● One of the major challenges encountered was the lack of a ready-made dataset from online
sources. A dataset had to be created from scratch by gathering information from various
sources, such as government Ayurvedic websites, Ayurvedic textbooks, and synthesising data
where necessary. This process involved extensive manual data collection, validation from
authoritative Ayurvedic sources, and the generation of synthetic data based on typical disease-
symptom relationships.
● Another challenge was accurately mapping the collected data to specific diseases and
subsequently linking these diseases to the appropriate Ayurvedic ingredients. This task was
intricate due to the holistic nature of Ayurvedic treatments, which often address multiple
factors simultaneously. The problem was addressed by implementing a thorough data
validation step, consulting with Ayurvedic practitioners, and utilising expert knowledge to
ensure accurate mappings between symptoms, diseases, and ingredients.
● Choosing the correct model for disease identification presented a critical hurdle. Several
models were tested, including SVM, XGBoost, and Naive Bayes, with their performance
20
evaluated based on accuracy and other metrics. The solution involved selecting models that not
only provided the highest accuracy but also offered the potential for fine-tuning to handle more
complex cases. This iterative process allowed for the identification of models optimised for
future applications.
● Symptoms such as "fatigue" or "headache" often overlap across multiple diseases, leading to
potential misclassification. To address this, a weighted symptom approach was implemented,
assigning lower predictive weight to common symptoms and allowing the model to focus on
more distinctive symptoms for disease identification.
● Ayurvedic treatment is highly individualised, considering the patient's prakriti (body
constitution). The challenge was to ensure that the system dynamically adjusted treatment
recommendations based on the user’s prakriti, avoiding the aggravation of any dosha. This was
resolved by integrating a prakriti-based adjustment mechanism into the recommendation
algorithm.
● Ayurvedic treatments often rely on specific herbs that may not always be available. To address
this, an alternative herb suggestion system was built into the model, offering replacements for
unavailable ingredients while maintaining the treatment’s efficacy.
3.2.4. Tools and Technologies
● Core Model: XGBoost, Random Forest, Ensemble Learning.
● NLP Model: BERT.
● Backend: Flask/Django [18], MongoDB.[19]
● Frontend: React for user-friendly interaction.
● Database: MongoDB [19] for storing Ayurvedic formulations, symptoms, and disease
mappings.
3.3 Software Stack
● Frontend: Gradio
● Database: MongoDB (PostgreSQL optional).
● Machine Learning: BERT, XGBoost, Ensemble Learning, PyTorch/TensorFlow.
● VCS: GitHub.
21
Chapter 4
Implementation and Results
4.1 Results
Appendix i. Synthetic Dataset
22
Appendix ii. Encoded Dataset
Fig 3. Disease Prediction UI with Encoded Data
23
Fig 4. Disease Prediction UI Prototype
Appendix iii. Disease Prediction UI with Synthetic Data
24
Chapter 5
Conclusion and Future Scope
Conclusion
In conclusion this project provides an overview of dataset creation techniques and model selection
processes in the context of Ayurvedic disease prediction. It covers various stages of data preparation,
including scraping government websites, consulting Ayurvedic textbooks, and generating synthetic
data to fill gaps. This comprehensive dataset not only maps symptoms to diseases but also includes
detailed information about medicinal herbs, such as the part of the plant used, dosage, and therapeutic
properties. The project involved extensive data gathering and preparation from diverse sources such as
scraping relevant websites, extracting information from Ayurvedic textbooks, and creating synthetic
datasets to fill any gaps. Multiple machine learning models were explored, and after careful
evaluation, XGBoost and Decision Tree models were chosen for their superior performance in disease
classification tasks. These models were further fine-tuned to achieve optimal results, ensuring accurate
disease predictions.
In addition, a comprehensive dataset was created containing detailed information about medicinal
herbs, including plant parts used, dosage guidelines, therapeutic uses, and administration instructions.
This dataset serves as a key resource for linking symptoms to Ayurvedic treatments, allowing for
personalised and effective recommendations. Overall, this project highlights the significance of
building customised datasets in healthcare and emphasises the importance of selecting appropriate
machine learning models. The insights gained through the experiments illustrate the potential of data-
driven approaches in Ayurvedic medicine and contribute to a more informed decision-making process
for future applications in disease prediction and treatment recommendation systems.
Future Scope
The future scope of AyurGenixAI includes several key developments aimed at enhancing its
functionality and accessibility. Firstly, integrating advanced Natural Language Processing (NLP)
algorithms can improve symptom understanding and context recognition, leading to more accurate
predictions. Additionally, incorporating data from wearable technology, such as heart rate monitors
and activity trackers, would provide users with comprehensive health insights. The system could also
evolve to include personalised health tracking, enabling continuous monitoring of symptoms and
responses to ayurvedic treatments. Ongoing research into ayurvedic herbs and treatments will further
enhance the recommendation engine with evidence-based suggestions. Building a community
platform for users to share experiences could enrich the dataset, while incorporating telemedicine
25
features would facilitate
direct consultations with ayurvedic practitioners, offering professional guidance and personalised
care. Lastly, expanding the system’s capabilities to support multiple languages and cultural contexts
would enhance its global accessibility and applicability, promoting health awareness and the adoption
of ayurvedic practices worldwide.
By continuing to innovate and integrate new technologies, AyurGenixAI has the potential to
revolutionise personal health management, making Ayurvedic practices relevant and beneficial for
modern health challenges
26
References
[1] Pandey MM, Rastogi S, Rawat AK. Indian traditional ayurvedic system of medicine and
nutritional supplementation. Evid Based Complement Alternat Med. 2013;2013:376327.
doi:10.1155/2013/376327
[2] [Link]
w-can-they-boost-engagement-and-conversion/
[3] Jayasundar, Rama. “Ayurveda: A Distinctive Approach to Health and Disease.” Current Science,
vol. 98, no. 7, 2010, pp. 908–14. JSTOR, [Link] Accessed 16 Oct.
2024.
[4] Ahmad Wani, *Bilal, Kumar Mandal, S., & Godatwar, P. (2017). PRAKRITI ANALYSIS AND
ITS CLINICAL SIGNIFICANCE. International Journal of Ayurveda and Pharma Research, 5(9).
Retrieved from [Link]
[5] Kalpana S. Joshi, Tanuja M. Nesari, Amrish P. Dedge, Vikram R. Dhumal, Sushant A. Shengule,
Maithili S. Gadgil, Sundeep Salvi, Marthanda Varma Sankaran Valiathan,Dosha phenotype specific
Ayurveda intervention ameliorates asthma symptoms through cytokine modulations: Results of whole
system clinical trial,Journal of Ethnopharmacology,Volume 197,2017,Pages 110-117,ISSN 0378-
8741,[Link]
[6]Vivek Kaul, Sarah Enslin, Seth A. Gross,History of artificial intelligence in
medicine,Gastrointestinal Endoscopy,Volume 92, Issue 4,2020,Pages 807-812,ISSN 0016-
5107,[Link]
[7] Guo, Gongde & Wang, Hui & Bell, David & Bi, Yaxin. (2004). KNN Model-Based Approach in
Classification.
[8] A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN,
LSTM, GRU FARHAD MORTEZAPOUR SHIRI1 , University Putra Malaysia (UPM), Malaysia
THINAGARAN PERUMAL , University Putra Malaysia (UPM), Malaysia NORWATI
MUSTAPHA, University Putra Malaysia (UPM), Malaysia RAIHANI MOHAMED, University Putra
Malaysia (UPM), Malaysia.
[9] [Link]
[10] Lakmi Hewapathirana, Shehan Mallawaarachchi, Wasundara Samaranayaka,
Chathurani Jayangika, N.H.P. Ravi Supunya Swarnakantha, P.K. Suriyaa Kumari,
“AyuAIra: Intelligent Ayurvedic Medicine System for Arthritis” Published in International
Research Journal of Innovations in Engineering and Technology - IRJIET, Volume 7, Issue
6, pp 77-83, June 2023.
[11] International Journal for Research in Applied Science & Engineering Technology
27
(IJRASET) ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538 Volume 10 Issue V
May 2022
[12] [Link]
[13] [Link]
[14][Link]
or_Specific_Diseases_by_Classification_Techniques_in_Machine_Learning
[15] [Link]
[16] [Link]
[17] [Link]
[18] [Link]
[19][Link]
g_machine_learning_techniques
[20] Bodduru Keerthana, J Vamsinath, Ch Sita Kumari, Setti Vidya Sagar Appaji, P Pratima
Rani and Satyanarayana Chilukuri (2024). Machine Learning Techniques for Medicinal Leaf
Prediction and Disease Identification. International Journal of Experimental Research and Review, 42,
320-327.
28