-
-
App Icon
-
App screenshot
-
Database
Inspiration
We chose Smart DryBox because it was a project that matched our prior experience and allowed each team member to use their strengths. Mohammed was comfortable working with hardware and sensors, Ali focused on the app side, and Raj handled the AI and server logic. Hamza handled project integration and technical communication. We also noticed that storage damage often happens quietly, without warning, and we wanted to build something that could identify risks before damage occurs.
What It Does
Smart DryBox is a storage monitoring system that uses sensor data and artificial intelligence to warn users about incorrect storage conditions. It monitors ambient temperature in a storage area and analyzes the data using contextual factors such as region, season, and the type of items in storage. When unsafe conditions are detected, the system alerts the user and suggests possible solutions.
How We Built It
We used a temperature sensor to collect ambient temperature data from a storage environment and send it to a server. The server processes this data and evaluates it using contextual information provided by the user. Based on this analysis, the system determines whether the storage conditions are safe and notifies the user when risks are detected.
Challenges We Ran Into
One of the main challenges was finding the correct sensors required for our project. Many available sensors did not meet the accuracy or reliability we needed. Time constraints also limited how much testing and refinement we could do, which forced us to focus on core functionality and make careful design tradeoffs.
Accomplishments That We're Proud Of
Despite being separated due to campus closure on Sunday, our team stayed fully connected through Discord and Outlook to bring the project together. We are most proud of our team’s commitment, collaboration, and ability to deliver under constrained conditions.
What We Learned
Our next steps are to improve sensor coverage by adding dedicated humidity and additional air quality sensors, and to refine the AI analysis using more real-world data. We also plan to design and test a full user interface to improve clarity and usability, and explore deploying the system in real environments to validate accuracy, reliability, and scalability.
Log in or sign up for Devpost to join the conversation.