Striking It Rich In The App Store: For Developers, It's More Casino Than Gold Mine

To develop a mobile application for App Store, now-a-days the developers only need a laptop and some development experience. This is why there is an outburst of applications in the App Store. Monitory development cost of these applications varies from few dollars to even hundred thousand. But, the question is, does the success of an application depend only on the quality, invest, or it is just a luck game? In his article, the author Chris Stevens brings this topic in front. His opinion is that it is more like a casino than a goldmine. I mostly agree with his view.

When developing an application, except the monitory investment, there are some other related investments too. The most important one is the intellectual investment. The application does not always need to be a new one, but to be attracted by the user; something new should be in it. Here comes the intellectual investment. The developer needs to be up to date with real world trend, as well as needs to be creative. 

However, even if an application comes with a completely new idea, it is impossible to tell certainly that the application will be a business success. It follows no pattern. Due to the uncertainty of human psychology, it is not always the case that, when investment on an application is high, it will be a business success. However, the odds of being successful by a badly polished and poorly invested application is also not very high.   

In my opinion, App Store is more or less like a casino. Even when you are uploading a well-furnished, well-developed application, it is not certain that it will be a jackpot winner. Rather it is like, you are betting in a casino, and your betting amount is proportional to your invest. If you invest more on the application, the chance of winning the jackpot will be high.  

Paper Blogs 10

Reference Paper

Modeling Eye Gaze Patterns in Clinician-Patient Interaction With Lag Sequential Analysis

Enid Montague, Jie Xu, Ping-yu Chen, Onur Asan, Bruce P. Barrett, and Betty Chewning

(Digital Object Identifier: 10.1177/0018720811405986)

Overview of the Paper

Non-verbal communication is very important in Clinician-Patient interaction. It is a very important aspect which may affect patient outcomes. In this paper the authors tried to examine whether lag sequential analysis could be used to describe the eye gaze orientation of the clinician and patient in a medical settings. This study topic is especially important, because new technologies are implemented in multiuser settings where trust is a very critical point. And, nonverbal cues are very critical to achieve the trust. So, this study method can be used in future technologies.

Study showed that, during health care encounters, if there was a moderate level of mutual gaze between the clinician and the patient, then patient perceived it as empathy, clinician’s interest in patient and warmth. Also, positive interactions and communication of the patient were correlated with the measure of satisfaction of the patients. In this study, the authors try to find out the answers of two research questions:

      1.      How was the clinician’s gaze related to the patient’s gaze?

a.       Did the patient follow where the clinician gazed?

b.      If so, what was the timing of this behavior relative to the clinician’s behavior?

      2.      How was the patient’s gaze related to the clinician’s gaze?

a.       Did the clinician follow where the patient gazed?

b.      If so, what was the timing of this behavior relative to the patient’s behavior?

  

Evaluation and Validity of the Paper

In this study, the eye gaze behavior of clinicians and patients were recorded. They recorded 110 videos in medical encounters. Then they analyzed the eye gaze behavior by lag sequential analysis method to find out significant behavior. They performed both event-based and time-based lag sequential analysis in there study. They performed the event-based lag sequential analysis to check whether there was any event lag between their behaviors. And, the time-based lag sequential analysis was to find out the time lag between the events, if there was any.

From there event-based lag analysis, the authors found that the patient’s gaze followed gaze of clinicians. But, the clinician’s gaze did not follow patient’s gaze. And, the time-based lag analyses showed that, the patient’s behavior usually followed clinician’s behavior within 2s of the initial behavior.

Improvement Scopes

One extension of this paper will be to implement an automated gaze detection method in their system. In their experiment, the authors used human coders to code the gaze of clinicians and also patients. From the videos it is sometimes very hard for the human coders to detect the gaze perfectly, which may lead to some erroneous result.   

 

 

Further Reading

One of the interesting articles, which are cited by this paper, is “Meaning of five patterns of gaze”, by Michael Argyle, Luc Lefebvre, and Mark Cook [2] (Digital Object Identifier: 10.1002/ejsp.2420040202). In this paper, the authors used a conversation-setting where the participants were talked with different trained confederates, who displayed five patterns of gaze with different subjects. The gaze patters were: zero, looking while talking, looking while listening, normal and continuous. Then, after the conversation the participants rated the confederates. The authors wanted to see how the scores of the confederate depended on the gaze patterns.

References

 

[1] E. Montague, J. Xu, P. Chen, O. Asan, B. Barrett, and B. Chewning, “Modeling eye gaze patterns in clinician–patient interaction with lag sequential analysis,” Human Factors: The Journal of the Human Factors and Ergonomics Society, vol. 53, no. 5, pp. 502–516, 2011.

[2] M. Argyle, L. Lefebvre, and M. Cook, “The meaning of five patterns of gaze,” European journal of social psychology, vol. 4, no. 2, pp. 125–136, 1974.

Paper Blogs 09

Full body expressivity analysis in 3D Natural Interaction: a comparative study

George Caridakis and Kostas Karpouzis

Overview of the Paper

Non-verbal behavior and communication are very important research topic in the field of psychology and cognitive science. Measuring expressive characteristics of body motion, posture, gestures qualitatively are primarily focused on human-human communication. These methods also can be extended to human-computer interaction. In order to model expressivity properly, many researchers studied human movement closely and categorized them mainly in five binary categories. They are slow/fast, restricted/wide, weak/strong, small/big, unpleasant/pleasant. These expressivity dimensions are selected as the most complete approach to body expressivity modeling. This paper presents preliminary research work on defining and extracting full body expressivity features.

    In this paper, the authors consider five parameters for modeling behavioral expressivity. They are,

      1. Overall activation 

      2. Spatial extent 

      3. Temporal expressivity 

      4. Fluidity 

      5. Power

To formulate the full body expressivity feature, the authors define the body pose P as

P = [l, r, S, D, F, J]

Where, l and r are the 3D coordinates of left and right hand respectively,

                S is binary silhouette image,

                D is the depth image,

                F is the face information, and

                J is skeleton joint of left and right arm.

Using this information, three different methods for formulating expressivity are presented in this paper. They methods are named as silhouette method, limbs method and joints method. From these methods, the expressiveness parameters are modeled.

 

Evaluation and Validity of the Paper

In this paper, the authors only present the initial work. But, they try to formalize the framework of expressivity measure. Some initial phase result is shown here. Initial dataset was generated by capturing the video of four users by Microsoft Kinect. Sample images are shown in figure 1.

They S (silhouette) and D (depth) image result are shown in figure 2.

From the S and D image, the Joint (J) are calculated and shown in figure 3. 

 

Improvement Scopes

One extension of this paper will be to implement all the methods describes in this framework to see how it works. Then it needs to be validated against some other proposed approaches. Also it needs to be validated by experience movement analyst for considering it as a valid framework.

 

Further Reading

One of the interesting articles, which are cited by this paper, is “How to Distinguish Posed from Spontaneous Smiles using Geometric Features”, by Michel F. Valstar, Hatice Gunes, and Maja Pantic [2] (Digital Object Identifier: 10.1145/1322192.1322202). In this paper, the authors used geometric approach for automatic detection of posed and spontaneous expression. They fused head, shoulder and face modalities to distinguish between two smiles.

[1] G. Caridakis and K. Karpouzis, “Full body expressivity analysis in 3D natural interaction: a comparative study,” in Affective Interaction in Natural Environments workshop, ICMI 2011 International Conference on Multimodal Interaction. 14-18th November 2011, Alicante, Spain, 2011.

[2] M. Valstar, H. Gunes, and M. Pantic, “How to distinguish posed from spontaneous smiles using geometric features,” in Proceedings of the 9^th international conference on Multimodal interfaces. ACM, 2007, pp 38–45.

Research Without Walls

Recently, the ‘Research without walls’ pledge attracts attention of the scientific community. Those who are signing in this pledge are promising not to peer review for a venue that does not open their publications for free. According to their website (http://www.researchwithoutwalls.org/), the institutions with most signatures include Google, Microsoft and UC Berkeley. I think this is a very good initiative.

In my opinion, everyone should have access to the new knowledge. My undergraduate institution did not have any contract with most of the famous journals. And, the student account was too costly for us. So, we were facing really hard time to have a pdf of particular paper if there is no free copy available online. Sometimes, we need to mail our friends abroad, who had access in those journals to download the pdf for us. I guess there are many institutions in third world country still facing this problem. In my opinion, ‘Research without walls’ pledge is a very good initiative, which will eventually make the publishers to publish their publications for free.

However, I know there are many technical and business issues associated with it. Conference and journals need money to keep everything working. They need money for their workers, for printing, storing etc. But, most of the time, the money they demand to give access to their servers, are not very feasible for the students from the poor counties. If those, who are signing to the pledge, will agree to volunteer peer review for the free publishing journals then open access conferences and journals will be a very good alternative. 

Lastly, I hope, this initiative will be successful. 

Paper Blogs 08

Reference Paper (From Maryam's blog post)

HEFES: An Hybrid Engine for Facial Expressions Synthesis to control human-like androids and avatars

Daniele Mazzei, Nicole Lazzeri, David Hanson and Danilo De Rossi 

(Digital Object Identifier: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6290687&tag=1)

Overview of the Paper

Facial expression analysis is very important in the field of affective computing. Affective computing is the section of computer science which deals with detecting and expressing human emotions and different affective states. The Facial Action Coding System (FACS) is a guide to study the facial expressions of human. This method is based of anatomical properties of human face. This model is used to synthesize human expression in avatar or robotic faces. FACS works with different action units. Action units refer to a single or combination of muscles. The authors tested their proposed method on both physical humanoid robot and also in 3-D virtual avatar.

Evaluation and Validity of the Paper

Human-like robots are used widely now-a-days in health sectors. One of the examples of human-like robot usage is in an alternative therapy for children with autism disorder (ASD). ASD children are facing difficulties to communicate with human. There are some experiments in health section is to see who well they communicate with virtual agents or human-like avatars. There are several algorithms like HEFES which is used to synthesis human emotions in virtual agents face based on FACS.

In this paper, the authors designed an experiment with two groups of children to test the capability of HEFES algorithm in conveying emotion to the robot. One group of children is normal children, and the other group of children is children with ASD. Both groups of children are interacting with robots both individually and under the supervision of a therapist. The result of this study shows that happiness, anger, and sadness are recognized by both groups of children. This is because body movements and verbal cues play a great role in conveying these emotions.

Improvement Scopes

One extension of this paper may be considering other non-verbal features like eye-gaze and head movements. These two non-verbal behavior plays very important role in emotion detection, and emotion synthesis. 

Further Reading

One of the interesting articles, which are cited by this paper, is “Exploring the Aesthetic Range for Humanoid Robots”, by David Hanson [2]. In this paper, the author performed experiment on human reaction to near realistic androids.

References

[1] D.Mazzei, N.Lazzeri, D.Hanson, and D. De Rossi, HEFES: an Hybrid Engine for Facial Expressions Synthesis to control, in proceeding BIOROB 2012 proceedings, 2012.

[2] D. Hanson, “Exploring the aesthetic range for humanoid robots,” in Proceedings of the ICCS CogSci 2006 Symposium Toward Social Mechanisms of Android Science. Citeseer, 2006, p. 1620.