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.


The proposed gaze-assisted user intention prediction based on TIM.
© Copyright Policy
Related In: Results  -  Collection

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

f5-sensors-15-14679: The proposed gaze-assisted user intention prediction based on TIM.

Mentions: The proposed user intention prediction consists of a candidate selection module, a decision module and a preparation module based on the TIM, as shown in Figure 5. The candidate selection module selects prefetching target candidates based on the weighted proximity from the cursor to the target. The cursor position is chosen as an input for the candidate selection module considering the confidence level in user intention. Despite the fact that the gaze precedes the cursor, the saccadic eye movement causes too many target selections. The decision module computes the click possibility in the near future based on the cursor and gaze movement relationship and performs the actual prefetching when the click probability is sufficiently high. The high proximity target among the selected candidates starts to be preloaded firstly when prefetching is turned on by the decision module. The preparation module waits for the actual click action while preloading the filtered web video data as a buffer before the execution. When the user clicks the preloaded target properly, the execution module just plays that video.


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

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

The proposed gaze-assisted user intention prediction based on TIM.
© Copyright Policy
Related In: Results  -  Collection

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

f5-sensors-15-14679: The proposed gaze-assisted user intention prediction based on TIM.
Mentions: The proposed user intention prediction consists of a candidate selection module, a decision module and a preparation module based on the TIM, as shown in Figure 5. The candidate selection module selects prefetching target candidates based on the weighted proximity from the cursor to the target. The cursor position is chosen as an input for the candidate selection module considering the confidence level in user intention. Despite the fact that the gaze precedes the cursor, the saccadic eye movement causes too many target selections. The decision module computes the click possibility in the near future based on the cursor and gaze movement relationship and performs the actual prefetching when the click probability is sufficiently high. The high proximity target among the selected candidates starts to be preloaded firstly when prefetching is turned on by the decision module. The preparation module waits for the actual click action while preloading the filtered web video data as a buffer before the execution. When the user clicks the preloaded target properly, the execution module just plays that video.

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.