# Title Team Members TA Documents Sponsor
67 Sound Controlled Smoke Detector
Meng Gao
Xinrui Zhu
Yihao Zhang
Luke Wendt
Almost all of us encounters false fire alarms at some point in our life. Although many modern fire alarms have the ability to mute temporarily with a push of button, the physical location of the smoke detector does not always make it easy to do so.
At the same time, voice controlled products are entering markets, and gaining popularity in recent days. These products, such as Android phones and Amazon Echo, can be activated by keyword such as “OK Google”, ”Alexa”, or “Amazon”.
Therefore, we propose a sound controlled fire alarm that allows you to easily turn the alarm off by shouting the keyword "cooking" when false alarm happens (in addition to a push button). The project will contain two parts: 1) a smoke alarm circuit with carbon monoxide sensor, microphone, mute button, and 2) a DSP core for the key word recognition.
The user will need to train the alarm once, where the DSP will find and store the Mel-Frequency Cepstral Coefficients (MFCCs) for the training word. Then once the alarm is triggered, interrupt will be served to the core through a interrupt pin or a GPIO, and the DSP will actively listen for any keywords, finding the MFCCs for what it hears, and comparing with the stored MFCCs. If the mean square error is below a threshold, the DSP will stop the alarm.
In additional, if we have time, we may also look into Dynamic Time Warping (DTW) to improve our accuracy.

Wireless IntraNetwork

Daniel Gardner, Jeeth Suresh

Wireless IntraNetwork

Featured Project

There is a drastic lack of networking infrastructure in unstable or remote areas, where businesses don’t think they can reliably recoup the large initial cost of construction. Our goal is to bring the internet to these areas. We will use a network of extremely affordable (<$20, made possible by IoT technology) solar-powered nodes that communicate via Wi-Fi with one another and personal devices, donated through organizations such as OLPC, creating an intranet. Each node covers an area approximately 600-800ft in every direction with 4MB/s access and 16GB of cached data, saving valuable bandwidth. Internal communication applications will be provided, minimizing expensive and slow global internet connections. Several solutions exist, but all have failed due to costs of over $200/node or the lack of networking capability.

To connect to the internet at large, a more powerful “server” may be added. This server hooks into the network like other nodes, but contains a cellular connection to connect to the global internet. Any device on the network will be able to access the web via the server’s connection, effectively spreading the cost of a single cellular data plan (which is too expensive for individuals in rural areas). The server also contains a continually-updated several-terabyte cache of educational data and programs, such as Wikipedia and Project Gutenberg. This data gives students and educators high-speed access to resources. Working in harmony, these two components foster economic growth and education, while significantly reducing the costs of adding future infrastructure.