SomnoScope

Thumbnail

💭 Inspiration SomnoScope was inspired by the idea of bridging the gap between science and self-discovery through the analysis of dreams. We wanted to explore how technology, specifically NLP and brain mapping, can provide users with insights into their subconscious. The addition of AI-generated dream imagery enhances this self-discovery process, creating a more immersive and personal experience for the user.

💻 What it does SomnoScope analyzes dreams submitted by users, extracting key themes, emotions, and sentiments through NLP techniques. It then correlates those themes with different regions of the brain, visualizing this data on an interactive brain map. The optional AI image generation feature creates visual representations of the dream based on the analysis, offering a creative interpretation of the user's subconscious thoughts.

🔧 How we built it We used Django as the back-end framework to manage user data, views, and interactions. On the front-end, we utilized Python, HTML, and CSS to build a clean and intuitive interface for users to interact with the system. We also integrated brain mapping Public API to visualize how different emotions and themes are linked to brain regions. Using Databases, we stored the data of past users into the Database to show the summation of everyone's dreams and our analysis of their dreams. Finally, we incorporated AI-generated prompts and images using Groq, Hugging Face and Python Regular Expression Model to further enhance our application of SomnoScope.

⚙️ Challenges we ran into One of the biggest challenges was integrating the different components, especially aligning the dream analysis with the brain mapping visualization. There were also technical challenges in ensuring the front-end was responsive and interactive while still handling complex data from the back-end. Additionally, ensuring the AI-generated imagery was relevant to the dreams was tricky, as it required careful text prompting.

⭐️ Accomplishments that we're proud of We're proud of how the dream analysis pipeline came together, with the NLP components accurately identifying keywords and emotions from the text. The interactive brain map visualization exceeded our expectations, providing users with a visually appealing and insightful way to explore their dreams. We're also proud of successfully integrating the AI-generated images into the user experience, adding a creative layer to the dream interpretation process. We are most proud of the SomnoScope project, as we feel it is a unique, creative and innovative project in contribution to Deerhacks.

🧠 What we learned We learned a great deal about integrating multiple technologies, especially how NLP can be used to extract and interpret complex psychological data. We also gained experience working with Django's flexible back-end and learned the nuances of creating responsive, interactive front-end visualizations. Finally, the project gave us the skills to integrate with AI while using python, leading to a overall excellent composition of data.

❤️ What's next for SomnoScope In the future, we'd like to refine the dream analysis pipeline, adding more sophisticated machine learning models for deeper insights. We're also interested in expanding the brain map visualization to be more interactive and detailed, potentially incorporating 3D elements. Additionally, adding features like user accounts for tracking dream history, as well as expanding the AI imagery to more personalized dream visuals, could be exciting directions to explore.