The project is suitable for senior undergraduates or graduate students in civil engineering or related fields.

To foster curiosity and encourage innovative thinking, this group project asks students to collaborate, explore, and apply AI techniques in any engineering specialty that aligns with their individual interests. Each group has the freedom to select their own problem or area of focus within the built environment, decompose it into manageable components, and design an AI-driven solution that demonstrates creativity, innovation, and interdisciplinary thinking.

Although the specifics will become clearer as the students progress through the semester, it is important to emphasize that they must carefully select an appropriate AI algorithm based on their chosen problem or challenge.

Students are highly encouraged to identify a problem that has not been previously solved using AI. However, if the chosen problem has already been addressed with AI, they are required to solve it using at least two different algorithmic approaches and present a comparative analysis.

Prerequisites:

• Prior coursework in civil engineering fundamentals
• Some familiarity with a programming language such as Python or MATLAB
• Basic knowledge of AI/ML concepts

Project Materials:

• Detailed syllabus outlining project guidelines and timelines
• Repository of data sources relevant to civil engineering problems (e.g., sensor data, satellite imagery, historical records)
  
• Collection of literature and research papers on AI applications in civil engineering
• Examples of previous student projects and case studies
• Rubrics for assessing proposals, progress reports, presentations, and final reports
• In-class guided tutorials on AI and machine learning techniques applied to engineering related concepts
• Access to AI software and tools (e.g., Python, TensorFlow)
• Access to online tutorials and workshops on AI and machine learning techniques, such as [Coursera’s Machine Learning Specialization](https://www.coursera.org/specializations/machine-learning) or [Kaggle’s Intro to AI and Machine Learning](https://www.kaggle.com/learn/intro-to-ai-ml)

In CAE 5840, students embark on a project-based learning journey where they explore AI's potential in solving civil engineering challenges. This project is designed using several pedagogical practices that align with fostering an entrepreneurial mindset, particularly focusing on curiosity, and connections.

Students are divided into groups and tasked to select problems within their interest areas, decompose them, and develop AI-driven solutions. Each group will present their findings, showcasing the impact of AI compared to traditional approaches. By integrating AI into civil engineering education, this project not only enhances technical skills but also cultivates an entrepreneurial mindset, preparing students for the rapidly evolving industry landscape.

Week-by-Week Timeline for Term Project

1. Week 1-2: Introduction and Exploration  Introduce the course, project expectations, and the concept of the entrepreneurial mindset. Begin exploring AI applications in the built environment.
   • Activities:
     • Review case studies of AI in civil engineering.
     • Brainstorm potential project ideas and discuss them in groups.
2. Week 3-4: Problem Identification and Research  Identify a specific civil engineering problem to address using AI. Conduct initial research and literature review.
   • Activities:
     • Finalize problem selection.
     • Begin collecting relevant data sources and reviewing existing AI models.
     • Submit a brief problem statement and preliminary research findings.
3. Week 5-6: Problem Decomposition and Proposal Development  Break down the selected problem into manageable components. Develop a detailed project proposal.
   • Activities:
     • Work in groups to decompose the problem and outline the approach.
     • Draft the project proposal, detailing objectives, methodology, and timeline.
       
4. Week 7-8: AI Solution Design and Algorithm Selection  Design an AI-driven solution tailored to the identified problem. Select appropriate AI algorithms.
   • Activities:
     • Research different AI models and their suitability for the problem.
     • Finalize algorithm selection and outline the AI solution.
     • Begin drafting the methodology section of the final report.
     • Optional: Submit the project proposal for feedback (Week 8).
5. Week 9-10: Data Collection and Initial Model Development  Collect and preprocess data for the AI model. Start developing the initial AI model.
   • Activities:
     • Gather data from relevant sources (e.g., sensors, satellite imagery).
     • Clean and prepare the data for analysis.
     • Implement the first version of the AI model.
     • Optional: Submit a progress report for feedback (Week 10).
6. Week 11-12: Model Refinement and Testing  Refine the AI model and conduct testing. Evaluate model performance and make necessary adjustments.
   • Activities:
     • Test the AI model using appropriate metrics.
     • Optimize the model’s parameters for better accuracy and efficiency.
     • Document the steps taken and results obtained.
7. Week 13: Implementation and Integration  Implement the AI solution in a simulated or real-world environment. Integrate with relevant software or hardware as necessary.
   • Activities:
     • Deploy the AI model in a testing environment.
     • Integrate with other systems if applicable.
     • Prepare a draft of the final report, including all findings.
8. Week 14: Presentation and Peer Review  Present the project findings to the class. Receive feedback from peers and the instructor.
   • Activities:
     • Prepare and deliver a 20-minute presentation covering objectives, methodology, findings, and implications.
     • Engage in a Q&A session to discuss the project.
     • Collect feedback for final report refinement.
9. Week 15: Final Report Submission  Finalize and submit the project report. Reflect on the learning experience and the entrepreneurial mindset.
   • Activities:
     • Review and incorporate feedback from the presentation.
     • Ensure all sections of the report are complete and properly cited.
     • Submit the final report.

This week-by-week timeline helps guide students through the project, ensuring they stay on track and fully explore the potential of AI in civil engineering while continuously developing their entrepreneurial mindset.

Project Proposal (0%)

Encourage students to take advantage of this! (Most students will do it). This is an optional detailed proposal- outlines the selected problem or challenge, objectives, methodology, and timeline for the project. The report is due in week 8 of the semester and is not graded as part of the course grade. The intent of the proposal report is to allow students to get feedback on their work and ensure that they are on the right track.

The report should be a (1-2 pages) summary of the progress they have made to date in researching and preparing for their project. They must include the following:

1. The problem they are researching.
2. Any difficulties they have encountered or anticipate encountering in addressing the requirements defined for the project.

 Progress report (0%)

Encourage students to take advantage of this! (Some students will opt out here - as they have a clearer picture of what they are going to do). The progress report is due during week 10 and is also optional and (not graded as part of the course grade). The intent of the progress report is to allow students to get feedback on their work and ensure they are on the right track.

The report should be a (1-2 pages) summary of the progress they have made to date in researching and preparing for the project. They must include the following:

1. The problem they are researching.
2. The progress made to date in answering the questions in the bullet-pointed projects requirements list above.
3. Any difficulties they have encountered or anticipate encountering in addressing the requirements defined for the project. If needed, students are encouraged to schedule a follow-up meeting to discuss possible workarounds for any difficulties encountered in completing the project.

Class presentation (20%)

During Week 14, students will summarize and share their findings with the class. They are tasked to prepare an approximately 20-minute presentation for the class. The presentation will be graded based both on content and on the professionalness of the presentation.

Project report (30%)

During Week 15, students are tasked to complete the final report. The submission should clearly present the results of testing and performance evaluation of the AI solution, along with insights gained and recommendations for further improvements.

Pedagogical Practices

1. Project-Based Learning (PBL)
   • Why: PBL is used because it encourages active learning by placing students in the driver’s seat, allowing them to take ownership of their learning. In a rapidly changing field like AI in civil engineering, it’s crucial for students to develop problem-solving skills and the ability to apply theoretical knowledge to real-world scenarios.
   • How: Students choose a civil engineering problem, break it down into components, and apply AI techniques to develop a solution. They work in groups, fostering collaboration and encouraging the exchange of diverse ideas.
   • Benefits: PBL enhances critical thinking, encourages deep learning, and allows students to directly see the impact of AI on real-world problems. This approach also cultivates an entrepreneurial mindset by requiring students to explore uncharted problems and innovate solutions.
2. Group Project
   • Why: Group work is integral to fostering collaboration, a key component of the entrepreneurial mindset. In the professional world, engineers often work in teams, and this practice simulates that environment.
   • How: Students work in groups to identify problems, develop AI solutions, and present their findings. Each member contributes to the project, leveraging their strengths and learning from their peers.
   • Benefits: Working in groups enhances communication and teamwork skills. It also promotes interdisciplinary collaboration, as students with different specializations can combine their expertise to tackle complex problems.
3. Curiosity-Driven Exploration
   • Why: Curiosity is a cornerstone of innovation. By encouraging students to explore unsolved problems or approach known problems with novel AI techniques, the course fosters a mindset that constantly seeks new knowledge and solutions.
   • How: Throughout the project, students are tasked with investigating unique problems and questioning existing methods. They are assessed on their ability to explore new avenues and demonstrate a thorough understanding of AI applications in civil engineering.
   • Benefits: This approach leads to a deeper engagement with the subject matter and encourages students to push the boundaries of what is possible in their field.
4. Presentations and Peer Feedback
   • Why: Presenting findings and receiving feedback are essential for refining ideas and improving communication skills. These practices are critical for developing the ability to articulate and defend innovative ideas—an important entrepreneurial trait.
   • How: Students present their projects to the class and receive feedback from peers and the instructor. This process helps them refine their ideas and enhances their understanding of their project’s impact.
   • Benefits: Presentations help students build confidence in public speaking and the ability to convey complex ideas clearly. Feedback from peers provides new perspectives and fosters a collaborative learning environment.