NuLocale

Hello every one. I am a big fan of numenta team and numenta technology. I am here to explain the basic plan of my project.

Imagine if we could somehow localize a person with in a room, observe his moves and make a prediction about his intention. If user turns-on the light immediately after entering a room and if we could capture the context of user entering the room and doesnt switch on the light. The detect such anamolies and should notify and ask if it should be switched on. Leaving the room without switching on the light should notify should equally work if above works. Idea is simple but technically image processing should suffice for such task with privacy, consumption and computation requirements as definite concerns). Basic IR range detection works too. But with increasing complexity in context basic thresholding logic is bad. Implememting fuzzy, ANN turns complex with complexity. On the other hand those approaches do not consider memory(history) sequences in such tasks. Nupic does that well. Nupic is good at observing coincidences too(From HTM micro circuits / Maths behind HTM paper by Hawkins and George). The current framework of NUPIC is enough for such application development if we could tap well its capabilities. But all this works given the assumption that we could somehow localize the person in a room and observe his cordinates.

There is a way to localize the person using wireless sensor networks in a cost efficient way. But with recent Bluetooth LE technology cost and energy efficiency is met with a radius of 30-60 meters connectivity range (could be Visibility rather connectivity not sure). Meaning that its best suited for Indoor localiztion. Indoor localization using wireless networks is a big challenge. Use signal strength alone and predict the location of person wearing an electronic device which supports some wireless protocol. The signal strength values are quite erratic in nature. Its not just random it depends on environments. If environment is dynamic too then the rssi values we get are not trust worthy. Predicting the rssi values helps us to filter outlier values. Since nupic is good at detecting the coincidences, the coincidence of this rssi value at this location is I chose light blue bean as the the ble. I detect four of these of device with in a room (while only three is enough, i prefer four for reliability and precision). I strongly feel we can tap that with we could have in memory hierarchy.

I used my surface pro 3 accelerometer and magnetometer sensors for additional context (accelerometer - to judge if i am walking, magn3d - for magnetic north compass direction context) more conincidences might lead to additional information and coincidences. My coordinates change only when i walk. My walk is judge based on accelerometer. The anomaly for the walk is when i dont walk is used instead (since thats equally a good negation context) . The magnetic compass plays two roles. The direction helps but more than that the our own physical body could affect rssi values (that could be great factor as far as i know)

I

Reference.... hypothesis..feedback...

SMS.....

Network....low level....opf....

Built With

• python
• ros