A PROJECT REPORT

ON .

“HUMAN DISEASE DETECTION SYSTEM”

SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR AWARD OF

DIPLOMA IN

COMPUTER TECHNOLOGY

SUBMITTED TO
MAHARASHTRA STATE BOARD OF TECHNICAL EDUCATION, MUMBAI

SUBMITTED BY

Sr.no Name Of Student Seat No Enrollment No.

1 Nahar Labhesh Mahavir 390759 2200790159
2 Rakhecha Aryan Ajay 390766 2200790168
3 Gandhi Tilak Sameer 390745 2200790142
4 Wavhal Akash Shailendra 390778 2200790183

GUIDED BY : MR.V.S.PATIL

SHRI HIRALAL HASTIMAL (JAIN

BROTHERS) POLYTECHNIC
CHANDWAD.
ACADEMIC YEAR
2024-2025

1
 SHRI HIRALAL HASTIMAL (JAIN BROTHERS) POLYTECHNIC CHANDWAD.
ACADEMIC YEAR
2024-2025

CERTIFICATE
This is to certify that the project report entitled “The Virtual Eye” Was successfully
completed by Student of Fifth semester Diploma in Computer Technology.

Sr.no Name Of Student Seat No Enrollment No.

1 Nahar Labhesh Mahavir 390759 2200790159
2 Rakhecha Aryan Ajay 390766 2200790168
3 Gandhi Tilak Sameer 390745 2200790142
4 Wavhal Akash Shailendra 390778 2200790183

in partial fulfillment of the requirements for the award of the Diploma in Computer
Technology and submitted to the Department of Computer Technology of
SNJB's Shri Hiralal Hastimal (Jain Brothers, Jalgaon) Polytechnic, Chandwad
work carried out during a period for the academic year 2024-25 as per curriculum.

Name of Guide: Mr.V.S.PATIL

Name of HOD: Mr. P. R. Sali

Coordinator: Ms. S. S. Shinde

Principal: Dr.V. A.Wankhede

2
SNJB's Shri Hiralal Hastimal (Jain Brothers, Jalgaon) Polytechnic,
Chandwad (All AICTE affiliated Programs NBA Accredited)
Department: Computer Technology
Academic Year: 2024-25
Criteria for marks for PA Capstone Project Planning

Title of the project: Facial Recognition Music Recommendation System

Group Details:

Sr.n Name of Student Exam Seat sign

o Number
1 Nahar Labhesh Mahavir 390759
2 Rakhecha Aryan Ajay 390766
3 Gandhi Tilak Sameer 390745
4 Wavhal Akash Shailendra 390778

Sign of Project Guide Sign of Project Coordinator HOD

MR V.S.PATIL ( Ms.S.S.Shinde ) (Mr.P.R.Sali)

3
 SNJB's Shri Hiralal Hastimal (Jain Brothers, Jalgaon)
Polytechnic, Chandwad ( All AICTE affiliated Programs Accredited )-
Department: Computer Technology
Academic Year: 2024-25
Criteria for marks for ESE Capstone Project Planning

Sr.no Name Of Student Seat No Sign

1 Nahar Labhesh Mahavir 390759

2 Rakhecha Aryan Ajay 390766
3 Gandhi Tilak Sameer 390745
4 Wavhal Akash Shailendra 390778

Sr. Marks obtained

Marks
No. Criteria S1 S2 S3 S4
2
1 Project Identification/Project Title

2 Industrial Survey/Literature Review 2

3 Project Proposal 3

4 Execution of Plan in fifth semester 2

5 Log Book 2

6 Portfolio for Self Learning and Reflection 4

7 Final Report writing including documentation 6

8 Presentation 2

9 Defense 2

Total 25

Sign of Project Guide Sign of Project Coordinator HOD

(Mr.V.S.PATIL) (Ms.S.S.Shinde) (Mr.P.R.Sali)

4
 ACKNOWLEDGMENT

We would like to take this opportunity to thank all the people who were a part
of this Preliminary Project in numerous ways, people who gave an un-ending support
right from the initial stage. In particular, we wish to thank our internal guide
Mr.V.S.PATIL who gave us co-operation timely and precious guidance without
which this project would not have been a success. We thank them for reviewing the
project with painstaking efforts and more of his unbanning ability to spot the
mistakes.
We would like to thank our HOD. Mr. P. R.Sali and project coordinator Ms.
S. S. Shinde for his continuous encouragement, support and guidance at each and
every stage of development of this project.
Last but not least we are very grateful for the staff members and people, who
helped us directly or indirectly for this project.

5
 INDEX

SR_NO. CONTENT PAGE NO.

7
1 Abstract
8
2 Introduction
10
3 Literature Survey
11
4 Methodology
12
5 Hardware and Software Requirement
Level-1 Flowchart 23
6
7 Use Case Diagram 24

8 DFD Diagram
Level-0 25
Level-1 26
9 System Architechture 27

29
Algorithm
10
11 Conclusion 31

12 References 32

6
1. ABSTRACT:

The Human Disease Detection System represents a cutting-edge solution tailored to

revolutionize healthcare by enabling accurate and early detection of diseases through advanced
technology. It includes AI-powered diagnostics that analyze medical data, such as symptoms and
imaging, to provide precise disease identification, while a user-friendly symptom checker offers
real-time insights and recommendations. The system features advanced imaging analysis capable
of processing X-rays, CT scans, and MRIs with exceptional accuracy, delivering detailed
diagnostic reports. Additionally, real-time health monitoring via wearable sensors tracks vital
signs, including heart rate and blood pressure, ensuring continuous health updates and proactive
care.With a GSM module for telemedicine and emergency alerts, along with cloud-based medical
records for secure data storage and sharing, patients and healthcare professionals can seamlessly
collaborate. Predictive analytics assess the risk of chronic diseases, while personalized health
insights deliver tailored recommendations for lifestyle improvements and medication adherence.
Together, these features empower individuals to take control of their health, enabling early
intervention, better treatment outcomes, and enhanced overall well-being.

7
 2. INTRODUCTION:

The Human Disease Detection System addresses critical healthcare challenges by leveraging advanced
technologies for accurate diagnosis and health management. It integrates features to detect diseases early
and provide personalized health solutions.

The system utilizes real-time data from wearable sensors and advanced imaging devices to monitor vital
signs and analyze symptoms. For instance, when a patient reports chest pain, the system can combine
heart rate data from a smartwatch with AI-based analysis of a chest X-ray to identify potential risks like
cardiac issues. Simultaneously, the cloud-based platform securely stores patient data, enabling healthcare
providers to access detailed medical histories instantly.

As the system processes data, it offers recommendations, such as visiting a specialist or performing
specific diagnostic tests. In chronic disease scenarios, such as diabetes management, the predictive
analytics feature tracks trends in glucose levels and offers warnings of potential complications before they
occur. The telemedicine feature connects users to physicians for virtual consultations, while the symptom
checker provides instant guidance based on real-time health data.

Key Features of the Human Disease Detection System:

Real-Time Health Monitoring

a. Wearable Sensors: Track vital signs like heart rate, blood pressure, and oxygen levels, ensuring
proactive health management.
b. Continuous Data Collection: Provides a 24/7 health profile for both preventive care and acute
interventions.

AI-Powered Diagnostics

a. Symptom Analysis: Uses AI to correlate symptoms with known conditions, offering probable
diagnoses.
b. Advanced Imaging Interpretation: Processes X-rays, MRIs, or CT scans to identify abnormalities
with high accuracy.

Cloud-Based Data Management

a. Secure Medical Records: Stores health data for easy access and analysis by healthcare professionals.
b. Data Sharing: Allows patients to share reports with specialists effortlessly.

Telemedicine Support
a. Remote Consultations: Facilitates video or audio calls with healthcare providers, reducing the need
for in-person visits.
b. Emergency Alerts: Notifies caregivers or physicians in case of health anomalies.

8
Predictive Analytics
a. Risk Assessment: Predicts the lik The Human Disease Detection System addresses critical healthcare
challenges by leveraging advanced technologies for accurate diagnosis and health management. It
integrates features to detect diseases early and provide personalized health solutions.

The system utilizes real-time data from wearable sensors and advanced imaging devices to monitor vital
signs and analyze symptoms. For instance, when a patient reports chest pain, the system can combine
heart rate data from a smartwatch with AI-based analysis of a chest X-ray to identify potential risks like
cardiac issues. Simultaneously, the cloud-based platform securely stores patient data, enabling healthcare
providers to access detailed medical histories instantly.

As the system processes data, it offers recommendations, such as visiting a specialist or performing
specific diagnostic tests. In chronic disease scenarios, such as diabetes management, the predictive
analytics feature tracks trends in glucose levels and offers warnings of potential complications before they
occur. The telemedicine feature connects users to physicians for virtual consultations, while the symptom
checker provides instant guidance based on real-time health data.

Key Features of the Human Disease Detection System:

1. Real-Time Health Monitoring

a. Wearable Sensors: Track vital signs like heart rate, blood pressure, and oxygen levels,
ensuring proactive health management.
b. Continuous Data Collection: Provides a 24/7 health profile for both preventive care and acute
interventions.

2. AI-Powered Diagnostics
a. Symptom Analysis: Uses AI to correlate symptoms with known conditions, offering probable
diagnoses.
b. Advanced Imaging Interpretation: Processes X-rays, MRIs, or CT scans to identify
abnormalities with high accuracy.

3. Cloud-Based Data Management

a. Secure Medical Records: Stores health data for easy access and analysis by healthcare
professionals.
b. Data Sharing: Allows patients to share reports with specialists effortlessly.

4. Telemedicine Support
a. Remote Consultations: Facilitates video or audio calls with healthcare providers, reducing the
need for in-person visits.
b. Emergency Alerts: Notifies caregivers or physicians in case of health anomalies.

9
 5. Predictive Analytics
a. Risk Assessment: Predicts the likelihood of diseases like hypertension or cancer based on
patient history and current trends.
b. Preventive Care Suggestions: Offers recommendations to minimize risks, such as lifestyle
changes or regular check-ups.

6. Personalized Feedback
a. Health Reports: Summarizes health trends and progress, assisting users in managing chronic
conditions.
b. Medication and Diet Plans: Tailored reminders and suggestions to improve treatment
adherence.

7. Battery Life & Device Integration

a. Power Optimization: Long-lasting battery for continuous monitoring devices.
b. Device Ecosystem: Seamlessly integrates with smartwatches, fitness bands, and mobile apps.

This comprehensive system empowers users and healthcare professionals to make informed decisions,
improving patient outcomes and enhancing the quality of life.

elihood of diseases like hypertension or cancer based on patient history and current trends.
b. Preventive Care Suggestions: Offers recommendations to minimize risks, such as lifestyle changes or
regular check-ups.

Personalized Feedback
a. Health Reports: Summarizes health trends and progress, assisting users in managing chronic
conditions.
b. Medication and Diet Plans: Tailored reminders and suggestions to improve treatment adherence.

Battery Life & Device Integration

a. Power Optimization: Long-lasting battery for continuous monitoring devices.
b. Device Ecosystem: Seamlessly integrates with smartwatches, fitness bands, and mobile apps.

This comprehensive system empowers users and healthcare professionals to make informed decisions,
improving patient outcomes and enhancing the quality of life.

10
3. LITERATURE SURVEY:

According to the review paper published by Shi Qiu ,Jun Hu,Ting Han ,Hirotaka Oswana and
MattiHias Rautherberg in 2020, there are many forms for designing The Virtual Eye . The design
of Virtual Eye systems for blind individuals has evolved over time, with earlier prototypes
consisting of bulky, standalone devices that required users to wear headgear or goggles.
These early designs were limited in terms of user comfort and functionality. Today, many modern
Virtual Eye systems are built by integrating existing technologies, such as wearable cameras,
sensors, and processors, into compact, adaptable units. Some are designed as "add-on" devices that
can be attached to clothing, glasses, or assistive devices, offering flexibility in how the system is
customized for individual users and their changing needs. The key objectives of Virtual Eye systems
are to enhance mobility, improve situational awareness, prevent collisions, and provide greater
autonomy for users. These systems help blind individuals navigate their environments more
effectively by detecting obstacles, providing sensory feedback (e.g., auditory or haptic cues), and
enabling tasks like reading, face recognition, and object identification. Virtual Eye systems can take
various forms, including wearable units (e.g., glasses with integrated cameras), add-on sensor units
for canes or other devices, and smartphone-based systems that use the built-in cameras and sensors
to provide real-time feedback. Regardless of the design, the systems prioritize user experience,
safety, adaptability, and ease of use, ensuring that the technology is intuitive, comfortable, and
reliable. With ongoing advancements in sensor technology and customization options, Virtual Eye
systems are increasingly improving the independence and quality of life for blind individuals.

11
 4. Methodology :
A Human Disease Detection System is designed to revolutionize healthcare by providing accurate, real-
time diagnostic capabilities using advanced technologies and algorithms. This system integrates a variety
of sensors, data processing techniques, and feedback mechanisms to detect and analyze potential health
issues efficiently and non-invasively.The system typically includes wearable devices equipped with
sensors to monitor vital signs such as heart rate, blood pressure, oxygen levels, and temperature. These
sensors transmit real-time data to a processing unit, such as a smartphone or a dedicated diagnostic
device, which uses AI and machine learning algorithms to analyze the data, detect abnormalities, and
predict potential diseases. Feedback to users is provided through visual displays, mobile apps, or auditory
alerts, detailing health insights and suggesting necessary actions. For example, the system may
recommend consulting a doctor if irregularities in heart rate or blood pressure are detected. Advanced
features like imaging analysis for X-rays or MRIs enable accurate identification of conditions such as
tumors or fractures.Customization is a critical feature, allowing users to personalize monitoring
preferences, alerts, and health goals. The system can also integrate seamlessly with cloud platforms to
store and analyze longitudinal health data, enabling healthcare professionals to track progress over time.
Additionally, the system employs predictive analytics to assess risks of chronic illnesses such as diabetes
or cardiovascular disease and suggests lifestyle adjustments to prevent these conditions. Integration with
telemedicine platforms allows for virtual consultations, providing convenience and reducing the need for
hospitalvisits.

12
5. HARDWARE AND SOFTWARE REQUIREMENT:

Hardware Requirements

1. Raspberry Pi 5
The Raspberry Pi 5 serves as the central processing unit in the human disease detection system
due to its robust computational capabilities and efficient integration with sensors and machine
learning models. This compact and cost-effective board processes real-time medical data,
facilitates machine learning inferences, and manages peripheral connections seamlessly.

Key Specifications and Features:

Specifications:

o Processor:
Quad-Core ARM Cortex-A76 for high-performance medical image analysis and data
processing.
o RAM:
8GB LPDDR4-3200 for smooth operation of memory-intensive ML tasks.
o Connectivity:
Bluetooth 5.0 and Wi-Fi for seamless integration with wearable medical devices and cloud
connectivity.
o Camera Interface:
Enhanced CSI for high-resolution medical imaging via compatible cameras.
o I/O Ports:
 USB 3.0 for connecting diagnostic tools and sensors.
 GPIO pins for interfacing biosensors like ECG, temperature, or SpO2 sensors.
o Power Supply:
USB-C power adapter ensures stability and reliable power delivery.

Features:

o High-speed data processing for analyzing medical datasets.

o Connectivity for real-time cloud updates and remote monitoring.
o Easy sensor integration for capturing patient vitals.
o Compact and energy-efficient design for portable diagnostic setups.

Fig 1: Raspberry Pi 5

2. GSM SIM900 Module

The GSM SIM900 enables the system to send notifications, alerts, and updates regarding patient
conditions or diagnostic results to caregivers or healthcare providers.

Features:

13
 o GSM connectivity for SMS or call-based communication of critical alerts.
o Dual-band operation for global compatibility.
o Supports data communication over GPRS for remote updates.

Applications:

o Sending emergency alerts for abnormalities detected in real-time.

o Remote consultation support with medical professionals.

Fig 2: GSM SIM900

3. GPS Module
The GPS module tracks the location of diagnostic devices for mobile healthcare setups, ensuring
accurate geolocation for ambulatory diagnostics or emergency services.

Features:

o Provides precise geolocation data for mobile or remote diagnostic systems.

o Useful for emergency cases requiring location-specific alerts to nearby medical centers.

Fig 3: GPS Module

4. Camera Module (e.g., Waveshare IMX378)

High-resolution cameras capture diagnostic images such as skin lesion photographs, X-rays, or
other medical scans for disease detection using ML.

Features:

o Wide Dynamic Range (WDR) for enhanced image quality in varying light conditions.
o Compatibility with Raspberry Pi for seamless integration.
o Compact size for handheld diagnostic devices.

Fig 4: Waveshare IMX378 Camera

5. Headphones (e.g., Bone Conduction Headphones)

Bone conduction headphones are used to provide auditory feedback for diagnostic results,
especially for visually impaired healthcare workers or patients.

Features:

o Direct sound transmission through bones for clear feedback.

o Allows simultaneous situational awareness during usage.

Fig 5: Bone Conduction Headphones

14
Software Requirements

Sr.
Parameter Description
No
1 Python Programming language for implementing ML models.
Framework for developing and deploying disease-detection ML
2 TensorFlow
models.
Library for image processing and feature extraction from diagnostic
3 OpenCV
images.
4 Flask/Django Web frameworks for creating interfaces for diagnostic reports.

1. Python
Python is the backbone of the disease detection system, providing a robust environment for
integrating ML models with peripheral devices. Libraries like TensorFlow and OpenCV are used
for training and inferencing disease detection algorithms.

2. TensorFlow
TensorFlow is pivotal in training machine learning models for classifying diseases, detecting
anomalies in X-rays, or analyzing other medical imaging data.

Applications:

o Classifying diseases like pneumonia or skin cancer from images.

o Building neural networks for time-series analysis of vital signs.

3. OpenCV
OpenCV processes medical images, extracts features, and prepares data for ML-based disease
detection. It enhances diagnostic accuracy by preprocessing medical images.

Applications:

o Image segmentation for identifying affected areas.

o Edge detection for analyzing X-rays or MRIs.

15
6. Flowchart

16
7. UseCase Diagram

17
 8. DFD Level 0 Diagram :

Fig 11: DFD Level 0 Diagram

9.DFD Level 1 Diagram :

18
9. PROJECT IMPLEMENTATION:

Fig 13: Project Implementation

19
10. ALGORITHM :

1. Input Data Acquisition

o Collect data from various sources such as wearable devices, medical imaging (X-rays, CT
scans), or electronic health records (EHR).
o Preprocess data to remove noise and ensure uniformity for analysis.
2. Data Preprocessing
o For image-based detection:
 Resize images to a standard size (e.g., 224x224 pixels for CNN models).
 Normalize pixel values and augment data for better training.
o For numerical or textual data:
 Clean and normalize data (e.g., scale numerical values, tokenize and encode text).
3. Feature Extraction
o For images:
 Use convolutional layers to extract spatial and hierarchical features from medical
images.
o For numerical/text data:
 Apply feature engineering techniques such as PCA (Principal Component
Analysis) or embeddings for dimensionality reduction.
4. Model Training
o Train machine learning or deep learning models:
 CNNs (Convolutional Neural Networks) for image-based disease detection.
 RNNs or Transformers for time-series or textual health data.
 Ensemble models for combined features from multiple sources.
o Use labeled datasets, such as scans annotated with disease presence or absence, for
supervised learning.
5. Prediction and Classification
o Input patient data (e.g., X-ray, vitals, or text) into the trained model.
o Model outputs probabilities for various diseases or conditions, along with a confidence
score for each prediction.
6. Post-Processing
o Apply thresholding to decide final classifications (e.g., disease present if probability >
0.5).
o Highlight critical regions in medical images using techniques like Grad-CAM to explain
predictions.
7. Result Communication
o Display or communicate the results via a user-friendly interface.
o Include recommendations for further tests or consultations based on detected conditions.

20
11.CONCLUSION :

Intelligent data processing is a social necessity for identifying, as soon as possible, of useful and robust
disease detections to provide patients with appropriate care within the shortest possible time. This
detection has been carried out in recent decades by detecting exciting patterns in databases. Smart data
processing is emerging as a requirement for effective and robust diseases to be found by society.
Detection of patients providing the necessary treatment as soon as possible within the shortest possible
period. This identification has been achieved in recent decades through the method of identifying exciting
patterns in databases. A comprehensive overview of intelligent data analysis tools in the medical sector is
given in this paper. Some examples of some algorithms used in these medical field areas are also
presented, examining potential patterns based on the target searched, the methodology used, and the
application field. Given the pace at which new works emerge in this emerging field, a systematic analysis
such as the one we have just presented may become obsolete in a short period. For this reason, we
consider that, after a careful quest for new scientific literature, Table 1 shoul Intelligent data processing is
a social necessity for identifying, as soon as possible, of useful and robust disease detections to provide
patients with appropriate care within the shortest possible time. This detection has been carried out in
recent decades by detecting exciting patterns in databases. Smart data processing is emerging as a
requirement for effective and robust diseases to be found by society. Detection of patients providing the
necessary treatment as soon as possible within the shortest possible period. This identification has been
achieved in recent decades through the method of identifying exciting patterns in databases. A
comprehensive overview of intelligent data analysis tools in the medical sector is given in this paper.
Some examples of some algorithms used in these medical field areas are also presented, examining
potential patterns based on the target searched, the methodology used, and the application field. Given the
pace at which new works emerge in this emerging field, a systematic analysis such as the one we have
just presented may become obsolete in a short period.

21
12.REFERENCES

[1] References Abdulqader, D. M., Abdulazeez, A. M., & Zeebaree, D. Q. (2020). Machine learning
supervised algorithms of gene selection: A review. Technology Reports of Kansai University,
62(3), 233–244.
[2] Acharya, U. R., Fujita, H., Oh, S. L., Hagiwara, Y., Tan, J. H., & Adam, M. (2017). Application
of deep convolutional neural network for automated detection of myocardial infarction using
ECG signals. Information Sciences, 415–416, 190–198.
[3] Ahmad, M. A., Teredesai, A., & Eckert, C. (2018). Interpretable machine learning in healthcare.
Proceedings - 2018 IEEE International Conference on Healthcare Informatics, ICHI 2018, 447.
https://doi.org/10.1109/ICHI.2018.00095

22