Emotion is well-recognized as a distinguished symbol of human beings. Psychologists believe that it plays a crucial role in delivering implicit messages in our daily communication. However, existing emotion sensing solutions exploring audiovisual clues or psychological sensors embody several inherent limitations such as the availability, reliability and privacy issues. To this end, we design EmoSense, a first-of-its-kind WiFi-based emotion sensing system, to offer a low-cost, robust and transparent service.
EmoSense needs to address two consecutive challenges: extracting physical expression from wireless channel data and recovering emotion from the corresponding physical expression. For the former, we present a Fresnel zone based theoretical model depicting the fingerprint on the channel data left by the physical expression. For the latter, we design an efficient data-driven mechanism to recognize emotion from the corresponding fingerprints. We prototyped EmoSense on the commodity WiFi infrastructure and compared it with the main-stream sensor-based approach in the real-world scenario, where its effectiveness has been confirmed. EmoSense only leverages the low-cost and prevalent WiFi infrastructures and thus constitutes a tempting solution for emotion sensing.
Publicantions:
*Yu Gu, Yantong Wang, Tao Liu, Yusheng Ji, Liu Zhi, Peng Li, Xiaoyan Wang, and Fuji Ren. EmoSense: Computational Intelligence Driven Emotion Sensing via Wireless Channel Data. IEEE Transactions on Emerging Topics in Computational Intelligence，Jan, 2019. pdf
*Yu Gu, Tao Liu, Jie Li, Fuji Ren, Zhi Liu, Xiaoyan Wang and Peng Li. EmoSense: Data-driven Emotion Sensing via Off-the-shelf WiFi Devices. IEEE ICC 2018, Kansas City, American, May 20-24, 2018.pdf
*Yu Gu, Yantong Wang, Tao Liu and Fuji Ren. Your WiFi Knows How You Feel: Leveraging Commodity WiFi Devices for Emotion Sensing, NLP-KE 2017, Chengdu, China, Dec 7-10, 2017. (Best Paper Award)pdf