Taku Hachisu | Baptiste BOURREAU

ウェアラブルデバイスを用いたワークショップにおける対面行動の評価 | Evaluation of Face-to-Face Behavior in Workshops Using Wearable Devices

The objective of this study is to observe the relationship between a frequency of face-to-face behavior and an evaluation of an idea presented in a discussion. Therefore, we conducted workshop experiments and analyzed the frequency of face-to-face behavior, the pulse rate, the evaluation value of ideas, and the order of explaining the ideas. As a result, we observed a positive correlation between the frequency of face-to-face behavior and the evaluation value. In addition, the ideas described in the second half showed that the face-to-face behavior decreased somewhat as the "description order" was earlier.

tomohiro-nishida

• Jun 27, 2019 • 1 min read

EnhancedTouchX: Smart Bracelets for Augmenting Interpersonal Touch Interactions

EnhancedTouchX, a bracelet-type interpersonal body area network device, not only detects but also quantifies interpersonal hand-to-hand touch interactions. Without any wired connection, it can identify the direction and gestures of a touch. The developed device can connect to an external device via Bluetooth Low Energy for monitoring and logging where, when, how long, who, and how the touch interactions occurred. These daily augmented touch interactions provided by such contextual information would offer a variety of applications to facilitate social interactions. Our experiment, conducted with several pairs of participants, demonstrates that the devices can identify the direction of a touch (from one initiating the touch (active touch) to the one being touched (passive touch)) with 95% accuracy. In addition, the devices are also capable of identifying four types of touch gestures with 85% accuracy using a simple threshold classifier.

taku-hachisu

• May 2, 2019 • 1 min read

FaceLooks: A Smart Headband for Signaling Face-to-Face Behavior

Eye-to-eye contact and facial expressions are key communicators, yet there has been little done to evaluate the basic properties of face-to-face; mutual head orientation behaviors. This may be because there is no practical device available to measure the behavior. This paper presents a novel headband-type wearable device called FaceLooks, used for measuring the time of the face-to-face state with identity of the partner, using an infrared emitter and receiver. It can also be used for behavioral healthcare applications, such as for children with developmental disorders who exhibit difficulties with the behavior, by providing awareness through the visual feedback from the partner's device. Two laboratory experiments showed the device's detection range and response time, tested with a pair of dummy heads. Another laboratory experiment was done with human participants with gaze trackers and showed the device's substantial agreement with a human observer. We then conducted two field studies involving children with intellectual disabilities and/or autism spectrum disorders. The first study showed that the devices could be used in the school setting, observing the children did not remove the devices. The second study showed that the durations of children's face-to-face behavior could be increased under a visual feedback condition. The device shows its potential to be used in therapy and experimental fields because of its wearability and its ability to quantify and shape face-to-face behavior.

taku-hachisu

• Jun 28, 2018 • 1 min read

Best Paper Award

複数人による双方向の対面行動を計量する頭部装着型デバイス | A Head-Mounted Device for Measuring Mutual Facing Behavior among Individuals

In this paper, we describe the development of a head-mounted device that weighs and realizes in real time the interactive face-to-face behavior of multiple people. First, we define face-to-face interaction as a state in which two people's faces are positioned within ±20 degrees of each other's head direction, and describe the implementation of a head-mounted device that weighs face-to-face behavior based on the relative head directions of multiple people. This device uses an infrared communication module whose optical axis is aligned with the head direction to measure face-to-face behavior based on the state of established communication with other devices. It is also capable of showing the weighing results in real time by emitting light, and recording the start time, duration, and partner of the face-to-face state by interfacing with an Android terminal. Next, we analyze the subject's eye and head movements while looking at the other person's face to verify the validity of the defined face-to-face behavior. Then, we evaluate the performance of the developed device through laboratory experiments. From the experimental results, we confirmed that the device has a face-to-face detection threshold of approximately ±20 degrees and a response time of approximately 330 milliseconds. The face-to-face action measurements by the device and the video observer were compared, and the results showed statistically high agreement.

taku-hachisu

• Feb 1, 2018 • 1 min read

Function of eye contact and face-to-face during dyadic conversation

Previous studies have reported that the results of experiments on social attention differ in physical face-to-face and mediated face-to-face (e.g., real people vs. images of people). These results do not indicate only the difference between laboratory setting and daily life, but suggests that the control variables of social attention difficult to control in the laboratory might have a great influence on social attention in the daily living environment. In this paper, we outline the previous studies related to eye contact and face-to-face during dyadic conversation and introduces the experimental plan using wearable eye-tracker and device that measures face-to-face.

soichiro-matsuda

• Dec 15, 2017 • 1 min read

Wearable Device for Measuring Face-to-Face Behavior via Infrared Communication

We present a novel head-mounted device for measuring face-to-face behavior. The device has unique capabilities: measuring timing and duration of face-to-face behavior as well as an identity of the partner, being used by multiparty, and automatically logging the behavior by connecting with Android device. We employ infrared communication technique for measuring the behavior. A pilot experiment with two dummy heads shows that the developed devices can detect the face-to-face behavior with a certain angle. We also conducted an experiment with human participants. The events recorded by the developed device show moderate agreement with those coded from video by human observers.

taku-hachisu

• Jan 1, 2017 • 1 min read