Every time one of us flashes an Arduino’s internal memory, a nagging thought in the backs of our minds reminds us that, although everything in life is impermanent, nonvolatile re-writable memory is even more temporary. With a fixed number of writes until any EEPROM module fails, are we wasting writes every time we upload code with a mistake? The short answer is that most of us shouldn’t really be concerned with this unless we do what [AnotherMaker] has done and continually write data until the memory in an Arduino finally fails.
The software for this is fairly simple. He simply writes the first 256
ints with all zeros, reads them to make sure they are all there, and then repeats the process with ones. After iterating this for literally millions of times continuously over the course of about a month he was finally able to get his first read failure. Further writes past this point only accelerated the demise of the memory module. With this method he was able to get nearly three million writes before the device failed, which is far beyond the tens or hundreds of thousands typically estimated for a device of this type.
To prove this wasn’t an outlier, [AnotherMaker] repeated the test, and did a few others while writing to a much smaller amount of memory. With this he was able to push the number of cycles to over five million. Assuming the Arduino Nano clone isn’t using an amazingly high-quality EEPROM we can safely assume that most of us have nothing to worry about and our Arduinos will be functional for decades to come. Unless a bad Windows driver accidentally bricks your device.
Continue reading “Stress-Testing An Arduino’s EEPROM”
If you’ve never been a patient at a sleep laboratory, monitoring a person as they sleep is an involved process of wires, sensors, and discomfort. Seeking a better method, MIT researchers — led by [Dina Katabi] and in collaboration with Massachusetts General Hospital — have developed a device that can non-invasively identify the stages of sleep in a patient.
Approximately the size of a laptop and mounted on a wall near the patient, the device measures the minuscule changes in reflected low-power RF signals. The wireless signals are analyzed by a deep neural-network AI and predicts the various sleep stages — light, deep, and REM sleep — of the patient, negating the task of manually combing through the data. Despite the sensitivity of the device, it is able to filter out irrelevant motions and interference, focusing on the breathing and pulse of the patient.
What’s novel here isn’t so much the hardware as it is the processing methodology. The researchers use both convolutional and recurrent neural networks along with what they call an adversarial training regime:
Our training regime involves 3 players: the feature encoder (CNN-RNN), the sleep stage predictor, and the source discriminator. The encoder plays a cooperative game with the predictor to predict sleep stages, and a minimax game against the source discriminator. Our source discriminator deviates from the standard domain-adversarial discriminator in that it takes as input also the predicted distribution of sleep stages in addition to the encoded features. This dependence facilitates accounting for inherent correlations between stages and individuals, which cannot be removed without degrading the performance of the predictive task.
Anyone out there want to give this one a try at home? We’d love to see a HackRF and GNU Radio used to record RF data. The researchers compare the RF to WiFi so repurposing a 2.4 GHz radio to send out repeating uniformed transmissions is a good place to start. Dump it into TensorFlow and report back.
Continue reading “AI Watches You Sleep; Knows When You Dream”