Interactive Dashboard Development: Led the development of an interactive data dashboard utilizing Python, Plotly, and Dash to comprehensively analyze the impact of AI adoption trends across the United States. The dashboard enabled dynamic exploration of AI adoption metrics at both national and regional levels, empowering stakeholders with actionable insights for strategic decision-making.
Data Mining and Analysis: Applied advanced data mining techniques in conjunction with proprietary firm data to assess the adoption of AI technologies and its consequential impact on businesses. By meticulously analyzing diverse datasets, including industry-specific trends and adoption patterns, provided invaluable insights to stakeholders, enabling them to make informed decisions and optimize their business strategies accordingly.

Project Overview:

The SAE AutoDrive Challenge, organized by General Motors, is a prestigious competition challenging students to develop fully functional self-driving cars.

Role and Responsibilities:

• Lane Line Detection Package Update:
  • Played a key role in updating the Lane Line Detection package within the car, enhancing its functionality and performance.
• Testing and Fine-Tuning:
  • Conducted rigorous testing procedures to fine-tune the car’s performance at intersections, ensuring robust and reliable functionality.
• Unique Challenges Handling:
  • Designed and executed intricate testing protocols tailored to evaluate the car’s response to unique challenges posed by construction scenarios.
• Dataset Expansion:
  • Expanded the dataset by incorporating Type III barricades, a critical step in enhancing the car’s ability to recognize and navigate construction obstacles.

As a project for the Information Retrieval and Data Mining course at Kettering University, I developed a specialized text search engine. This search engine allows users to input a word or phrase, and it retrieves the specific location(s) where the word is present within a given text or document.

Development Process:

• Requirements Gathering:
  • Identified the need for a text search engine to efficiently locate specific words or phrases within documents.
• Algorithm Development:
  • Developed a custom search algorithm to efficiently scan and identify the location(s) of the input word(s) within the text.
• Â
• Backend Functionality:
  • Implemented the backend logic using Python to process user queries and search the text for matching occurrences.
• Search Result Presentation:
  • Designed the system to display the positions where the word(s) are found within the text.
• Testing and Refinement:
  • Conducted rigorous testing to ensure accurate and efficient search results.
  • Refinement of the algorithm and user interface based on testing feedback.

    • Key Features

    • Simple User Input: Users can input a single word or a phrase to search within the provided text.
    • Location Identification: The search engine returns the line numbers or positions within the text where the word(s) are found.
    • Fast and Efficient: The custom search algorithm ensures quick and accurate results, even with large text files.
    • Scalability: Designed to handle various text sizes and formats, making it versatile for different use cases.