Please enable JavaScript.
Coggle requires JavaScript to display documents.
Plant Leaf Disease Detection and Classification System - Coggle Diagram
Plant Leaf Disease Detection and Classification System
Risk
Risk Analysis
Impact Assessment
project scope limitations
Timeline delays
Probability Estimation
Likelihood of data issues
Technical difficulties
Resource constraints
Risk Mitigation
Technical Support
Access to technical assistance like supervisor or community support
Regular backups
Use of reliable tools
Collaboration and Communication
Peer review and support
Use of project management tools like Trello
Maintain regular contact with supervisor
Data Validation
Use multiple sources for data
Cross-verify data quality
Regular dataset review
Risk Identification
Technical Risks
Software bugs or crashes
Inadequate computing resources
Model performance issue
Project Risks
Lack of collaboration
Delays in feedback from suprevisor
Academic Risks
Lack of sufficient data
Academic integrity issue
Failure to meet deadlines
Contingency Planning
Academic Support
Supervisor consultation
Crisis Management
Store all codes in Github
Immediate communication with supervisor
Alternative Resources
Additional software tools
Emergency access to funds
Backup datasets
Integration Management
Project Monitoring
Progress Tracking
Task status update (completed, in-progress, pending)
Record meeting minutes
Milestone completion (track against project timeline)
Quality checks
Quality metric evaluation (measure against set benchmarks)
Regular audits (check project progress and quality)
Conflict Management
Seek advice from supervisor if the conflict is unsolvable internally
Have open communication with team member
Resource
Human Resources
Supervisor
Provide guide on the topic
Review progress and give feedback
Team Members
Handle all the task as a team
Teaching Teams
Teach the concept of proper project management
Equipments
Compute Resource to run the model
Camera for high resolution images
Cost
Equipment Cost
Subcrive cloud compute services
Buy or rent camera
Material Cost
Pay subscription for digital content
Buy plant sample
Materials
Training and Testing Dataset
Code models related to the topic
Plant disease smaple
Research Paper
Stakeholders
End Users
Agricultural professionals
Farmers
Funding Bodies
Universities
Project Team
Teaching Staff
Final Year Project Team
Supervisor
Communication
Engagement with Teammates
Physical Meeting
Attending class togther
Working on collaborative task
Group Chat
Discussion on task
Online Meeting
Online meeting when physical meeting is not possible
Engagement with Supervisor
Performance review with supervisor
Setting goals with supervisor
Feedback from supervisor
Communicating concerns to supervisor
Receiving guidance from supervisor
Scope
Requirements
AI/ML models
Pre-trained models
Parameter Tuning
Customizable
User documentaion
Installation Guide
User Manual
Troubleshooting Section
Dataset of plant lead images
Diverse disease coverage
Proper annotation
High resolution images
Deliverables
Disease detection model
Training and testing dataset
AI/ML algorithm
Model performance report
User friendly interface
Mobile app / website / software design
User experience testing
Exclusions
Non lead based plant disease
Fruit disease
Stem disease
Root disease
Non agricultural plants
Wild plants
Forest plants
Ornamental plants
Project Objectives
Identify Plant Leaf Disease
Provide disease severity levels
Support multiple plant disease
Detect early signs of disease
Classify diseases accurately
High accuracy rate (>90%)
Real-time classification
Quality
Quality Assurance
Peer Feedback
Group discussions on challenges
Informal peer review sessions
Continuous Testing
Code testing and debugging
Data quality checks
Regular model evaluation
Supervisor Reviews
Progress checks
Draft reviews
Regular feedback sessions
Quality Control
Manual Testing
Review all data entries for accuracy
Ensure correct model outputs
Project Review
Check against assessment grading rubric
Quality Planning
Establish Testing Protocols
Model validation steps
Data integrity checks
Peer review
Set Performance Benchmarks
Accuracy targets (>90%)
Timeliness of project milestones
Quality of final deliverables
Define Academic Standards
Ethical considerations in data collection and usage
Clear research objectives
Continuous Improvement
Regular Updates
Iterative development based on testing results
Regular updates based on feedback
Feedback Incoporation
Regular communication with supervisors on progress
Keep project documentation up to date
Schedule
Timeline
Gann Chart
Task
Deploy application
Build deployment pipeline
Continuous integration setup
Annotate datasets
Manual annotation
Automated annotation tools
Quality control checks
Collect leaf images
Crowdsourcing new images
Research existing dataset
Train AI models
Parameter optimization/tuning
CPU/CPU utilization
Model Selection
Milestones
Data collection and preprocessing
Image acquisition
Data cleaning
Data source identification
Model deployment
Algorithm selection
Model training
Initial model evaluation
Project Kick-off
Get expectation from supervisor
Initial team member and supervisor meeting
Do project planning (Gann Chart)
Testing and validation
Model fine tuning
Performance benchmarking
Cross-validation
Dependencies
Tool Readiness
Software Installation
Codebase Setup
Team Collaboration
Regular Meetings
Communication Channels
Data Availability
Access to quality datasets
Financial
Cost Estimation
Hardware Resources
Borrowing or rent equipment
Utilize university computer lab if possible
Obtain equipment fby using school provided funds
Miscellaneous cost
Subscription for datasets
Software and Tools
Utilize student account for paid software
Prefer open source tools and software
Cost Control
Cost saving strategies
Apply for university grants
Use free resources
Financial risk management
Plan for unanticipated expenses
Seek supervisor's approval for major costs
Identify potential cost risks
Budget monitoring
Track expenses throughout the project
Regular updates with supervisor
Keep receipts and records
Budget Planning
Resource allocation
Allocate fund for essential resources
Plan for potential additional costs
Contingency Funds
Small reserve for unexpected costs
Emergency access to additional funds
Minimal Budgeting
Focus on free resource
Utilize university provided tools
Funding Sources
University Grants
Personal Funds