Paper Blogs 06

Reference Paper

Mimicking Expressiveness Of Movements By Autistic Children In Game Play

Daniel Tetteroo, Azadeh Shirzad, Mariana Serras Pereira, Matthijs Zwinderman, Duy Le, Emilia Barakova

(Digital Object Identifier 10.1109/SocialCom-PASSAT.2012.100)

Overview of the Paper

Mimicry is a very important social phenomenon which leads to emotional convergence in human interaction. Usually mimicry is viewed as the tendency of imitate the facial, vocal, postural and movement expressions of the people with whom he or she is interacting.

Children with Autism Spectrum Disorders (ASD) are thought to face difficulties when interacting with others. They have great difficulties in performing tasks that require imitate other in group settings. An experiment is designed in this paper to find out how the children with ASD behave in more natural conditions, like playing game.

In this paper, the authors designed a game setting where the children with ASD played a game against a confederate. The confederate showed different level of expressiveness in her movements. In the same setting, children who do not have ASD also played the game with the same confederate.

During the game, the motion was captured using Microsoft Kinect. After that, the expressiveness of movement for both children with ASD, and children without ASD, was measured by human observers and their modeled automated movement analysis system. Then they compare the result of these two methods.

 

Evaluation and Validity of the Paper

From the movement data, first the expressiveness of the participant player was measured by two human observers. For each five second slots, the observers rated the expressiveness. Then, from the video, their system rated the expressiveness. They use Laban Movement Analysis (LMA) for analyzing the movement. They only use the amplitude and acceleration of movements to analyze the expressiveness. For their game settings, they defined the expressiveness of movements as an area of movement per time period.

From the result obtained from human observers, there was no significant difference in expressiveness for both participant groups. But, they found some difference in result analyzed by their system.

 

Improvement Scopes

In their discussion, the authors mentioned about that there were some difference in the game settings for both groups of children. There may be a little chance for different result. Another, improvement scope might be, to consider other part of Laban Movement Analysis (LMA) to measure expressiveness by their system.

 

Further Reading

One of the interesting articles, which are cited by this paper, is “The Chameleon Effect: The Perception-Behavior Link and Social Interaction”, by Tanya L. Chartrand and John A. Bargh [2] (Digital Object Identifier: 10.1037/0022-3514.76.6.893). Chameleon effect is non-conscious mimicry.  In the cited article, the authors presented three studies to find out chameleon effect during conversations.

References

[1] D. Tetteroo, A. Shirzad, M. Serras Pereira, M. Zwinderman, D. Le, E. Barakova, “Mimicking Expressiveness Of Movements By Autistic Children In Game Play.” In: Proceedings 4th International Conference on Social Computing (SocialCom 2012), Workshop on Wide Spectrum Social Signal Processing, Amsterdam, Netherlands, 3-5 September, 2012

[2] T. Chartrand and J. Bargh, “The chameleon effect: The perception–behavior link and social interaction.” Journal of personality and social psychology, vol. 76, no. 6, p. 893, 1999.

3D Printing

3D printing technology is undoubtedly an exciting one of this time. The current additive technology is not perfect enough to manufacture everything, but it is not far in future when it will help the inventors to develop their prototype easily by 3D printer. 

The advantage of this additive technology has many folds. It will help to manufacture like daily goods to even fine electronics, which will reduce manufacturing cost, as well as human labor. Researchers can develop small prototypes with this technology. Also mass availability will help everyone to make their own product by themselves.

However, we need to think about the some negative impacts of this technology. What if someone wants to manufacture a gun? Will there be any protection mechanism embedded into the 3D printer to protect this sort of misuse. Or how the copyright laws or patent laws will be maintained? How about keeping track of manufactured products by companies? These issues need to be solved before mass marketing of 3D printer.

In my opinion, this technology will be a big lift in manufacturing industry in future. But the unsolved issues need to be addressed before make it available to the mass people. 

Paper Blogs 05

Reference Paper

Nonverbal Synchrony and Rapport: Analysis by the Cross-Lag Panel Technique

Marianne LaFrance

(Digital Object Identifier 10.2307/3033875)

Overview of the Paper

During the second half of the last century, many studies were performed by the psychology research community to investigate how a good rapport is established. This paper also investigated different aspects of developing a rapport. The hypothesis proposed by the author was that posture sharing may be influential in establishing a rapport.

Some studies were performed before, but those are less clear cut due to several factors. The author mentioned that those studies had the limitation of less iteration, very difficult explanations to replicate, not reliably measured rapport and tended to avoid inferential statistics.

In this paper, the authors propose and try to investigate the influence of posture sharing (PS) in establishing a rapport (R). To find out the degree to which PS and R are positively correlates, four scenarios are explained. First, a positive correlation between PS and R may be possible due to an unmeasured third factor. Second, PS and R may be causing each other by positive feedback. Third, PS may be influenced by R. Finally, PS may play the dominant role to establish R.

Data was collected from a college class taken during a six-week summer session. First during the initial week, the classes were videotaped; and during the last week classes were videotaped again. Posture sharing and rapport were evaluated among the students and the instructors.

 

Evaluation and Validity of the Paper

From the graded sheet by the students about the rapport generation and checked by a third coder later, the analysis of the study was performed. The author presented cross-lag analysis to show the experimental result. It showed that posture sharing and rapport were positively correlated. Although the cross-lag analysis differential result was not significant, the direction of the result supported the author’s hypothesis.

 

Improvement Scopes

In my opinion, the future work should include multi-modal data for this research. At the time of the experiment, only the video data was recorded. May be multi-modal data will help to establish the hypothesis with better confidence.  

 

Further Reading

One of the interesting articles, which are cited by this paper, is “Group rapport: Posture sharing as a non- verbal indicator”, by Marianne LaFrance and Maida Broadbent [2] (Digital Object Identifier: 10.1177/105960117600100307). In the cited article, the authors presented another study to investigate the relationship among the posture sharing and establishing a rapport in a group.

[1] M. LaFrance, “Nonverbal synchrony and rapport: Analysis by the cross-lag panel technique,” Social Psychology Quarterly, pp. 66–70, 1979.

[2] M. LaFrance and M. Broadbent, “Group rapport: Posture sharing as a nonverbal indicator,” Group & Organization Management, vol. 1, no. 3, pp. 328–333, 1976.

Motion Input in Windows 8

Not very long ago, the researchers used complex infrared cameras or stereo-vision technique to extract the depth information from the digital images. But these methods were computationally very expensive and also hard to calibrate. Microsoft came to rescue from this problem by presenting Kinect to the scientific community, which made 3D reconstruction lot easier and faster. Though the RGB camera of MS Kinect is not very good, but the depth sensor works reasonably well. 

Microsoft is now planning to use motion based inputs as a first order interface. Usually human motions are faster than traditional mouse clicks or keyboard hits. There are some researches in computer vision and also in psychology, which compares the traditional mouse with the cursor moved by eye-gaze. Results of these researches show that the eye-gaze cursor is faster. If Microsoft can detect the eye-gaze and use that information for mouse tracking, eye typing or selecting something, then it will be faster than the traditional methods. Again human gestures and postures are very important information in communication. If these features are detected correctly, then this information also can be used as inputs to the system, which will be more accurate input and faster.

Although, the current detection and tracking methods are not very accurate and fast, it will be nice to see how Windows can overcome these challenges. There may be some issues in the first release, but in my opinion, it will be a great step forward to the intelligent interface.

Paper Blogs 04

Reference Paper

Towards Real-Time Affect Detection Based on Sample Entropy Analysis of Expressive Gesture

Donald Glowinski and Maurizio Mancini

(Digital Object Identifier 10.1007/978-3-642-24600-5_56)

Overview of the Paper

During human-human communication, body movements play a vital role of affective information in nonverbal communication. Different affect detection systems have been developed based on movement direction and kinematics and arm extensions. In this paper, the authors propose a real-time affect detection system based on Sample Entropy (SampEn) method. 

Most of the methods developed to analyze behavior dynamics is fail to handle two main properties of human movements, they are non-linearity and non-stationarity. In this paper the authors try to handle these two properties of human movements. Their model is based on Camurri et al.’s [2] framework of expressive gesture analysis. According to Camurri et al. gesture analysis is performed in three steps,

      1. Low-level physical measures

      2. Overall gesture features

      3. High-level information

In this paper the authors try to focus on first two part of the above framework.

Microsoft Kinect is used here to capture the RGB image here. Three parts are considered here to form the bounding triangle; they are head, left hand and right hand. To extract the dynamic features of this triangle, two indices are used, smoothness index (SmI) and symmetry Index (SyI).

Smoothness index is computed using the curvature and velocity of the movements of left and right part. After computing the left and right smoothness index, the overall smoothness index is calculated by averaging these two values. Symmetry index is calculated from the horizontal and vertical symmetry value of the bounding triangle. The authors derive a dynamic updating formula for SyI and SmI. From these SyI and SmI value, the SampEn value is calculated. If the hand movements are symmetric and smooth for several frames, then the SmapEn value will be zero. On the other hand, if the movements are not symmetric or not smooth, then value of SampEn will be greater than zero. 

Evaluation and Validity of the Paper

One sample output is available for download here. In the following figure, as the movements are smooth in between t₁ and t­₂, so the SampEn(SmI) is zero. But, as there are some abrupt movement is between t₂ and t₃, SampEn(SmI) increases. Similarly, as the hands symmetry change in between t₄ and t₅, SampEn(SyI) increases. And, as the symmetry is not changes in t₅ and t₆, SampEn(SyI) value becomes zero.

 

Improvement Scopes

In my opinion, the future work should include incorporating these features to detect the high-level information in human-human communication. Also, next extension should include other 3D analysis like forward and backward movements, distance from the camera etc.

 

Further Reading

One of the interesting articles, which are cited by this paper, is “Communicating Expressiveness and Affect in Multimodal Interactive Systems”, by A. Camurri, G. Volpe, G. De Poli, M. Leman [2] (Digital Object Identifier: 10.1109/MMUL.2005.2). In the cited article, the authors preset the frame work for expressive gesture analysis.

[1] D. Glowinski and M. Mancini, “Towards real-time affect detection based on sample entropy analysis of expressive gesture,” Affective Computing and Intelligent Interaction, pp. 527–537, 2011. 

[2] A. Camurri, G. Volpe, G. De Poli, and M. Leman, “Communicating expressiveness and affect in multimodal interactive systems,” MultiMedia, IEEE, vol. 12, no. 1, pp. 43 – 53, 2005.