New device tracks emotions with 87% more accuracy.
The use of photographic cues to detect human emotions was one of the breakthrough achievements of Microsoft’s Emotion API that analyzes faces to detect a range of feelings and personalize your app’s responses.
Now, a team of researchers from MIT’s Computers Science and Artificial Intelligence Lab has innovated the emotion recognition technology and achieved a new level of accuracy using wireless radio signals.
A newly developed device codenamed EQ-Radio is capable of tracking emotions including excitement, sadness, anger and happiness with 87% more accuracy than the previous technology used that to using wireless signals, claims the researchers at CSAIL.
The researchers also said that the new device doesn’t need anybody sensors to detect the emotions even though it is capable of getting data such as breathing patterns and heart rhythm. The researchers are of the opinion that the device will be a path breaker as it doesn’t require the anything to be worn by the user. Some call the new device a next generation lie detector as it can reveal the real emotion of people who tend to hide their feelings.
The research team also said that the new improved technology also avoids the accuracy pitfalls of camera-based facial recognition software, making it ideal for technology firms that embed emotional intelligence into their products.
“Just by generally knowing what human heartbeats look like in different emotional states we can look at a random person’s heartbeat and reliably detect their emotions,” Ph.D. student Mingmin Zhao and a team member was quoted by Engadget
Dina Katabi, the Andrew and Erna Viterbi Professor of Electrical Engineering and Computer Science at MIT and the director of the MIT Wireless Center who leads the development of the EQ-Radio was quoted by TechCrunch saying that the new device can be used in different spectrums ranging from entertainment, consumer advertising, and healthcare verticals.
The same can be also used in smart TV’s to analyses the viewer response to a particular ad or program, said Katabi. She also added that the same technology can be embedded into a smart home hub and trigger automated actions with connected devices like stereos and lighting, adjusting the mood of you home to counter or augment your emotions.
“By recovering measurements of the heart valves actually opening and closing at a millisecond time-scale, this system can literally detect if someone’s heart skips a beat,” FadelAdib, another team member explained. “This opens up the possibility of learning more about conditions like arrhythmia, and potentially exploring other medical applications that we haven’t even thought of yet.”
Katabi said that the technology, when used in the healthcare sector, can do wonders as it will aid in monitoring and diagnosing health conditions that are linked to emotion such as depression, stress, and anxiety. On a greater level, the device will help in understanding the emotional state of another person and give cues regarding how to behave and react to certain situations.
The new system analyzes and stores the emotions of an individual before attempting to predict. This is done in a set of five sessions that trigger emotions using music or video cues to level-set the recognition algorithm.