Are you good at hiding your feelings?
No issues, your Wi-Fi router may soon be able to tell how you feel, even if you have a good poker face.
A team of researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a device that can measure human inner emotional states using wireless signals.
Dubbed EQ-Radio, the new device measures heartbeat, and breath to determine whether a person is happy, excited, sad, or angry.
Using EQ-Radio, which emits and captures reflected radio frequency (RF) waves, the team bounced waves off a person’s body to measure subtle changes in breathing patterns and heart rates.
This data was then run through a bunch of algorithms and a machine-learning process programmed to match a person's behaviour to how they acted previously, categorising the person's emotion as one of the four emotional states: Pleasure, Joy, Anger and Sadness.
The impressive part about the technique:
EQ-Radio doesn't require you to wear any sort of monitoring device or on-body sensor.
"The whole thing started by trying to understand how we can extract information about people’s emotions and health in general using something that’s completely passive—does not require people to wear anything on their body or have to express things themselves actively," says Prof. Dina Katabi, who conducted the research along with graduate students Mingmin Zhao and Fadel Adib.
In its test, the team says if their device is trained on each subject separately, it measures emotions with 87 percent accuracy and 72.3 percent accuracy when using a single classifier for all subjects.
EQ Radio uses the same carrier frequency as Wi-Fi, but with about 1,000 times less power, which means the system could be integrated into an existing Wi-Fi router or other devices that transmit and receives wireless signals.
According to the researchers, EQ-Radio, and similar systems may help in some practical situations, like:
movie makers and advertisers could use it to better evaluate people's reactions to their work in real time;
doctors could use it to diagnose mental health conditions like depression or bipolar disorder; and
it could also integrate into smart homes, adjust temperature, lighting, and music automatically to match the user's mood...
...all without the target's knowledge or consent. All it takes is some RF signals mixed with a set of algorithms and a dash of machine learning process.
No issues, your Wi-Fi router may soon be able to tell how you feel, even if you have a good poker face.
A team of researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a device that can measure human inner emotional states using wireless signals.
Dubbed EQ-Radio, the new device measures heartbeat, and breath to determine whether a person is happy, excited, sad, or angry.
Using EQ-Radio, which emits and captures reflected radio frequency (RF) waves, the team bounced waves off a person’s body to measure subtle changes in breathing patterns and heart rates.
This data was then run through a bunch of algorithms and a machine-learning process programmed to match a person's behaviour to how they acted previously, categorising the person's emotion as one of the four emotional states: Pleasure, Joy, Anger and Sadness.
The impressive part about the technique:
EQ-Radio doesn't require you to wear any sort of monitoring device or on-body sensor.
"The whole thing started by trying to understand how we can extract information about people’s emotions and health in general using something that’s completely passive—does not require people to wear anything on their body or have to express things themselves actively," says Prof. Dina Katabi, who conducted the research along with graduate students Mingmin Zhao and Fadel Adib.
In its test, the team says if their device is trained on each subject separately, it measures emotions with 87 percent accuracy and 72.3 percent accuracy when using a single classifier for all subjects.
EQ Radio uses the same carrier frequency as Wi-Fi, but with about 1,000 times less power, which means the system could be integrated into an existing Wi-Fi router or other devices that transmit and receives wireless signals.
According to the researchers, EQ-Radio, and similar systems may help in some practical situations, like:
movie makers and advertisers could use it to better evaluate people's reactions to their work in real time;
doctors could use it to diagnose mental health conditions like depression or bipolar disorder; and
it could also integrate into smart homes, adjust temperature, lighting, and music automatically to match the user's mood...
...all without the target's knowledge or consent. All it takes is some RF signals mixed with a set of algorithms and a dash of machine learning process.
