PROJECT PROMPT

 Act as an expert in final-year project selection, AI/ML research, software engineering, and academic project evaluation.

I need you to help me identify and select the BEST final-year project idea for an undergraduate engineering/technology project.

Do not simply give me common or generic project ideas. Analyze the projects from the perspective of a project evaluator, researcher, software engineer, and academic guide.

Every project idea you suggest MUST satisfy the following conditions and constraints:

1. PROJECT RELEVANCE

   - The project should address a real-world problem.

   - It should be technically meaningful and suitable for a final-year project.

   - It should have clear practical applications.

   - Prefer projects involving AI, Machine Learning, Deep Learning, Generative AI, LLMs, Computer Vision, NLP, or intelligent software systems where appropriate.

2. PROJECTS

   - Suggest multiple strong and innovative project ideas first.

   - For every project, clearly explain the problem, proposed solution, technology used, expected outcome, and what makes it different from existing projects.

   - Avoid overused projects such as basic chatbots, simple attendance systems, basic CRUD applications, simple recommendation systems, or projects that are too easy.

3. TREND ALIGNMENT

   - Evaluate whether each project is aligned with current technology and research trends.

   - Prefer projects that are relevant to current AI/ML and software-development trends.

   - Explain why the project is currently relevant and how it could remain relevant in the next few years.

4. NOVELTY CHECK

   - Perform a novelty analysis for each project.

   - Identify what already exists and what can be improved or added.

   - The project should have a clear research gap, unique feature, novel methodology, or meaningful improvement over existing solutions.

   - Do not claim that a project is completely new unless there is strong evidence.

   - Suggest specific ways to increase its novelty.

5. 7-MONTH FEASIBILITY

   - The complete project must realistically be achievable within 7 months by undergraduate students.

   - Divide the project into a practical 7-month development/research roadmap.

   - Consider learning time, development, dataset collection, model training, testing, deployment, documentation, and final presentation.

   - Reject projects that are unrealistic for a 7-month timeline or require excessive hardware, huge datasets, expensive APIs, or advanced research infrastructure.

6. IEEE / SCOPUS PUBLICATION FEASIBILITY

   - Evaluate whether each project has potential for an IEEE or Scopus-indexed research paper.

   - Identify the possible research problem, methodology, experiments, evaluation metrics, and expected contribution.

   - Explain what kind of research contribution could potentially make the project publishable.

   - Do not guarantee publication; evaluate the realistic publication potential.

   - Prefer projects where meaningful experimental comparison, measurable results, and a research gap can be demonstrated.

7. AI / META-LEARNING / LLM MODEL ECOSYSTEM

   - Consider the practical use of modern AI models and platforms such as:

     • OpenAI models

     • Meta Llama models

     • NVIDIA AI technologies/platforms

   - Do not force these technologies into every project.

   - Use them only where they genuinely improve the project.

   - Explain which model/platform would be appropriate and why.

   - Consider both API-based and locally deployable/open-source approaches where applicable.

8. TECHNICAL FEASIBILITY

   - Prefer technologies that undergraduate students can realistically learn and implement.

   - Consider Python, Flask/FastAPI, MySQL/PostgreSQL, React or HTML/CSS/JavaScript, PyTorch/TensorFlow, Hugging Face, LLMs, computer vision, NLP, and relevant AI tools.

   - Clearly identify required hardware, software, datasets, APIs, and approximate cost.

   - Prefer projects that can be developed using free or low-cost resources.

9. EVALUATION

   For every project, provide scores out of 10 for:

   - Real-world impact

   - Innovation

   - Novelty

   - Trend alignment

   - Technical complexity

   - 7-month feasibility

   - IEEE/Scopus publication potential

   - Implementation feasibility

   - Career/placement value

10. FINAL SELECTION

   After analyzing all proposed projects, shortlist the TOP 5.

   Then compare the TOP 5 in a clear table.

   Finally, select ONE project as the BEST overall project.

   For the recommended project, provide:

   - Project title

   - Problem statement

   - Existing system

   - Proposed system

   - Research gap

   - Novel contribution

   - Objectives

   - Key features

   - System architecture

   - AI/ML methodology

   - Dataset requirements

   - Technologies and frameworks

   - Recommended AI models

   - Why OpenAI / Meta Llama / NVIDIA may or may not be used

   - 7-month development roadmap

   - Expected results

   - Evaluation metrics

   - IEEE/Scopus research potential

   - Possible research-paper title

   - Risks and limitations

   - Estimated cost

   - Future enhancements

   - How the project can be demonstrated during the final-year project presentation

IMPORTANT:

Do not select a project merely because it sounds impressive. Select it based on a balance of NOVELTY + REAL-WORLD IMPACT + TECHNICAL DEPTH + 7-MONTH FEASIBILITY + RESEARCH/PUBLICATION POTENTIAL + CAREER VALUE.

Think like an expert project-selection committee and critically reject weak ideas.

Before giving the final recommendation, compare the alternatives and explain WHY the selected project is better than the others.

If current technology trends, existing research, or publication feasibility need verification, use up-to-date web research rather than relying only on general knowledge.