Limits...
Gaze-Assisted User Intention Prediction for Initial Delay Reduction in Web Video Access.

Lee S, Yoo J, Han G - Sensors (Basel) (2015)

Bottom Line: The introduction of the sequential and concurrent flow of resources in human cognition and behavior can significantly improve the accuracy and preparation time for intention prediction.This paper introduces a threaded interaction model and applies it to user intention prediction for initial delay reduction in web video access.Experimental results show a 92% hit-ratio, 0.5-s initial delay on average and 1.5-s worst initial delay, which is much less than a user's tolerable limit in web video access, demonstrating significant improvement of accuracy and advance time in intention prediction by introducing the proposed threaded interaction model.

View Article: PubMed Central - PubMed

Affiliation: School of Integrated Technology, Yonsei University, Incheon 406-840, Korea. youb007@yonsei.ac.kr.

ABSTRACT
Despite the remarkable improvement of hardware and network technology, the inevitable delay from a user's command action to a system response is still one of the most crucial influence factors in user experiences (UXs). Especially for a web video service, an initial delay from click action to video start has significant influences on the quality of experience (QoE). The initial delay of a system can be minimized by preparing execution based on predicted user's intention prior to actual command action. The introduction of the sequential and concurrent flow of resources in human cognition and behavior can significantly improve the accuracy and preparation time for intention prediction. This paper introduces a threaded interaction model and applies it to user intention prediction for initial delay reduction in web video access. The proposed technique consists of a candidate selection module, a decision module and a preparation module that prefetches and preloads the web video data before a user's click action. The candidate selection module selects candidates in the web page using proximity calculation around a cursor. Meanwhile, the decision module computes the possibility of actual click action based on the cursor-gaze relationship. The preparation activates the prefetching for the selected candidates when the click possibility exceeds a certain limit in the decision module. Experimental results show a 92% hit-ratio, 0.5-s initial delay on average and 1.5-s worst initial delay, which is much less than a user's tolerable limit in web video access, demonstrating significant improvement of accuracy and advance time in intention prediction by introducing the proposed threaded interaction model.

No MeSH data available.


(a) A video website layout; (b) mouse event pattern of the video website used; (c) gaze event pattern of the video website used.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4507624&req=5

f3-sensors-15-14679: (a) A video website layout; (b) mouse event pattern of the video website used; (c) gaze event pattern of the video website used.

Mentions: The TIM can be applied to develop the user intention prediction scheme suitable for web video access. First of all, as the visual (gaze actions) and manual (mouse actions) constructs are the most typical cognitive resources for web access in the desktop environment, the threads in these constructs should be carefully examined based on the TIM. The gaze and cursor movement pattern was obtained from 10 participants, who used a typical video website (see Figure 3a), accessing any video of their own interests. Unlike the common web page, the video website typically has two main graphical user interface (GUI) components, the video player region and the video list region, as shown in Figure 3a. Figure 3b and Figure 3c show that distinct user behavior was observed in this web page layout. Table 1 summarizes the horizontal distribution of cursor, gaze and click events in each area. The cursor hovered over the blank area around the video thumbnail image region for most of time, because the cursor was in a static state while watching the video and placed so as not to block the thumbnail images. Meanwhile, the gaze dwelled almost on the video player region. Saccadic gaze movements occasionally occurred when the users wanted to search other videos. The cursor transited to the dynamic state for click action when the user wanted to watch other videos.


Gaze-Assisted User Intention Prediction for Initial Delay Reduction in Web Video Access.

Lee S, Yoo J, Han G - Sensors (Basel) (2015)

(a) A video website layout; (b) mouse event pattern of the video website used; (c) gaze event pattern of the video website used.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4507624&req=5

f3-sensors-15-14679: (a) A video website layout; (b) mouse event pattern of the video website used; (c) gaze event pattern of the video website used.
Mentions: The TIM can be applied to develop the user intention prediction scheme suitable for web video access. First of all, as the visual (gaze actions) and manual (mouse actions) constructs are the most typical cognitive resources for web access in the desktop environment, the threads in these constructs should be carefully examined based on the TIM. The gaze and cursor movement pattern was obtained from 10 participants, who used a typical video website (see Figure 3a), accessing any video of their own interests. Unlike the common web page, the video website typically has two main graphical user interface (GUI) components, the video player region and the video list region, as shown in Figure 3a. Figure 3b and Figure 3c show that distinct user behavior was observed in this web page layout. Table 1 summarizes the horizontal distribution of cursor, gaze and click events in each area. The cursor hovered over the blank area around the video thumbnail image region for most of time, because the cursor was in a static state while watching the video and placed so as not to block the thumbnail images. Meanwhile, the gaze dwelled almost on the video player region. Saccadic gaze movements occasionally occurred when the users wanted to search other videos. The cursor transited to the dynamic state for click action when the user wanted to watch other videos.

Bottom Line: The introduction of the sequential and concurrent flow of resources in human cognition and behavior can significantly improve the accuracy and preparation time for intention prediction.This paper introduces a threaded interaction model and applies it to user intention prediction for initial delay reduction in web video access.Experimental results show a 92% hit-ratio, 0.5-s initial delay on average and 1.5-s worst initial delay, which is much less than a user's tolerable limit in web video access, demonstrating significant improvement of accuracy and advance time in intention prediction by introducing the proposed threaded interaction model.

View Article: PubMed Central - PubMed

Affiliation: School of Integrated Technology, Yonsei University, Incheon 406-840, Korea. youb007@yonsei.ac.kr.

ABSTRACT
Despite the remarkable improvement of hardware and network technology, the inevitable delay from a user's command action to a system response is still one of the most crucial influence factors in user experiences (UXs). Especially for a web video service, an initial delay from click action to video start has significant influences on the quality of experience (QoE). The initial delay of a system can be minimized by preparing execution based on predicted user's intention prior to actual command action. The introduction of the sequential and concurrent flow of resources in human cognition and behavior can significantly improve the accuracy and preparation time for intention prediction. This paper introduces a threaded interaction model and applies it to user intention prediction for initial delay reduction in web video access. The proposed technique consists of a candidate selection module, a decision module and a preparation module that prefetches and preloads the web video data before a user's click action. The candidate selection module selects candidates in the web page using proximity calculation around a cursor. Meanwhile, the decision module computes the possibility of actual click action based on the cursor-gaze relationship. The preparation activates the prefetching for the selected candidates when the click possibility exceeds a certain limit in the decision module. Experimental results show a 92% hit-ratio, 0.5-s initial delay on average and 1.5-s worst initial delay, which is much less than a user's tolerable limit in web video access, demonstrating significant improvement of accuracy and advance time in intention prediction by introducing the proposed threaded interaction model.

No MeSH data available.