Anjalee Ramwani@Anjalee

In this project, we confront the linguistic barriers faced by Yoruba speakers due to limited language resources. Image generation models primarily excel with English prompts, posing a challenge for non-English speakers. To address this, we embarked on a dual-track approach: data collection and model development. Firstly, recognizing the scarcity of Yoruba datasets, particularly in image generation prompts, we meticulously curated our own dataset. English sentences were carefully selected to serve as image generation prompts and then translated into Yoruba using a dictionary-based approach. Next, we developed a custom translator model trained specifically to translate Yoruba into English. This intermediary step ensures seamless integration with image generation models, allowing for smoother operation and accurate results. Through rigorous testing, we achieved an impressive 85% accuracy on the test set, affirming the efficacy of our approach. The core strength of our project lies in its ability to empower users to generate images in their native language without encountering language barriers. By collecting our own data and training custom models, we circumvent the limitations imposed by the scarcity of Yoruba resources. Leveraging the SDXL API for image generation further enhances the user experience, ensuring high-quality outputs. Looking ahead, we envision extending our efforts to include additional languages such as Fon and Dendi, expanding our dataset and catering to a broader audience. Furthermore, our ultimate goal is to develop a model capable of directly generating images from Yoruba, Fon, and Dendi without the need for translation into English. In summary, our project not only addresses a pressing need within the Yoruba-speaking community but also lays the groundwork for future advancements in multi-lingual image generation. Through our innovative approach, we pave the way for inclusive, barrier-free communication and creative expression.

1. Optimised Prompt based on User's reuirement with simplicity and precision. User are asked to fill the answer based on the default questions like goals , interest and challenges faced, based on the mentioned criteria. Solution: It will be a prompt that gets generated along with the solution that is provided based on the tailored prompt. 2. In built AI application for Brainstorming - The AI will directly interact based on the prompt, it will be more refined and video link is also added. 3. Providing additional features like youtube links that are related to the topic of discussion - For every prompt answered, there will be a youtube link. Why you ask? We understood the Customer pain point where we felt that for certain propts for example: cooking having a video along with the videos would really help the customers to work on this with ease and confidence. 4. How does this bring value as a product and business: a) As a product - To provide an assistance for any kind of AI tools: as AI is available, but the instructions required to prompt the AI is not available. This is where Volund comes in. Avoiding reprtition prompts and instructions saving time and effort with additional links always helps in providing a good experience. b) As a business - We are able to include a large number of potential users that have not been included and building AI.With a growing market in AI, the dependency on right prompt with becomes very important to understand the intention of the user who is looking for solutions.

Chorus is an AI voice partner designed to empower vocally impaired individuals, enabling them to communicate with confidence. The problem we’re focused on solving is democratizing access to a speech pathologist healing emotional trauma from a vocal injury receiving feedback without paying large amounts of money. GPT4o allows vocal comprehension in tandem with Whisper and TTS. I built Chorus to help vocally impaired people progress and speak confidently through AI-assisted voice rehab. This is a personal problem for me, as I've had surgery to remove benign tumors from my vocal cords when I was 13, and had to teach myself how to speak again from scratch. NGL the experience was emotionally painful and I think younger me would've loved a guide to speak to 1 on 1.

The Lokahi Precision Care Portal unifies patient care, monitoring, and billing by leveraging synthetic data, wearables, and agentic technology. This innovative solution delivers personalized insights and remote care management, with a specific focus on the breast cancer use case. The initiative aims to modernize medical insurance programs and provide seamless, patient-centered solutions by ensuring new technologies are fully integrated rather than treated as add-ons. Using Power B I we analyzed the Lokahi insurance database to facilitate this seamless integration, laying the foundation for a holistic approach to precision care. The project emphasizes addressing challenges unique to breast cancer patients, such as cognitive conditions like "Chemo Brain." It incorporates several data streams—Wearable Data, Breast Cancer Data, and a comprehensive Treatment Model—to deliver tailored insights. These tools work in harmony with the Patient Talk feature, which enhances engagement by providing real-time, personalized guidance, fostering trust, and enabling timely interventions through an agentic Clinical Decision Support System (CDSS). Together, these elements improve patient outcomes and optimize healthcare delivery. By combining cutting-edge technology and accessibility, the Lokahi Precision Care Portal redefines healthcare with an integrated solution that unifies care and billing while alleviating the strain on Hawaii's medical system. Special thanks to the team: Ahmad, Bilal, Amanullah, Reema, and Anjalee.

LexAI is a cutting-edge legal assistant platform designed to simplify the legal experience for users, from individuals to law firms. By harnessing advanced AI technology, LexAI offers a comprehensive suite of features that streamline legal processes and provide valuable insights. Key Features Legal Chatbot Assistant: The AI-driven chatbot offers instant responses to legal inquiries, making legal information accessible without extensive knowledge. Document Analysis: Users can upload legal documents for analysis, where LexAI extracts key information, highlights potential issues, and summarizes important clauses. Case Precedent Finder: This feature helps users locate relevant case law based on specific legal queries, enhancing their research capabilities. Legal Cost Estimator: LexAI provides estimates based on case type and complexity, helping users anticipate legal costs and budget effectively. Automated Legal Brief Generation: The platform streamlines the creation of legal briefs by automatically generating structured documents based on user input. Case Trend Visualizer: Users can visualize trends in legal cases, gaining insights into patterns that may affect their legal strategies. Comprehensive Document Analysis: LexAI performs in-depth analyses of uploaded documents, providing summaries and identifying potential issues. Web and Wikipedia Search Integration: The platform enhances responses by sourcing information from the web and Wikipedia, ensuring users access the most relevant legal information. Find lawyers in your area : Get a list of all the best lawyers in you area User-Friendly Interface: Designed for ease of use, LexAI allows users to navigate various functionalities effortlessly, making it beneficial even for those without legal training and many more features. LexAI is a comprehensive legal assistant that combines multiple functionalities into a single platform. By addressing common challenges faced by individuals and legal professionals.

GreenGuardian is an advanced AI-powered plant care assistant that combines cutting-edge technologies to help both novice gardeners and experienced horticulturists maintain healthy, thriving plants. At its core, GreenGuardian utilizes the Llama 3 language model, known for its deep understanding and generation capabilities, to provide highly personalized and accurate plant care advice. This intelligent system offers tailored care plans for a wide variety of plant species, taking into account factors such as plant type, growth stage, local climate, and specific user needs. By analyzing user-uploaded images through state-of-the-art computer vision algorithms, GreenGuardian can assess plant health, identify potential issues, and suggest appropriate interventions. Key features of GreenGuardian include: 1. Customized care schedules 2. Watering and fertilization recommendations 3. Pest and disease identification 4. Growth tracking and progress reports 5. Seasonal care adjustments Whether you're nurturing a small indoor herb garden or managing a large outdoor landscape, GreenGuardian acts as your personal plant expert, available 24/7 to answer questions and provide guidance. Its intuitive interface and continuous learning capabilities ensure that users receive up-to-date, relevant advice to help their plants flourish.​​​​​​​​​​​​​​​​