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.


Test environment of the proposed gaze-assisted user intention prediction. (a) Framework of the implemented test system; (b) gaze trackers; (c) SmartEye Pro gaze tracking software.
© Copyright Policy
Related In: Results  -  Collection

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

f7-sensors-15-14679: Test environment of the proposed gaze-assisted user intention prediction. (a) Framework of the implemented test system; (b) gaze trackers; (c) SmartEye Pro gaze tracking software.

Mentions: Figure 7a shows the entire framework of the implemented test system, which includes a YouTube-like web video server, a data collecting server, a SmartEye Pro three-dimensional eye tracker (see Figure 7b) that has a 120-Hz sampling rate with real-time tracking software (see Figure 7c), a user desktop computer that is equipped with a 2.7-GHz processor, 8 GB of RAM and running Windows 8.1 64-bit and a 24-inch LCD monitor that has a resolution of 1920 × 1080 pixels. A Chrome browser extension for tracking the cursor movement by JavaScript and a medium software to transmit the gaze tracking data in real time though the UDP network from the desktop to the data collecting server were implemented. The data collecting server was based on Node.js and Redis to record all events, including the cursor and gaze coordinates, click event coordinates, page accesses, prefetching of candidates, prefetched video link ID, hit-ratio, preparation time, downlink bandwidth and initial delay along the timestamp.


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

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

Test environment of the proposed gaze-assisted user intention prediction. (a) Framework of the implemented test system; (b) gaze trackers; (c) SmartEye Pro gaze tracking software.
© Copyright Policy
Related In: Results  -  Collection

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

f7-sensors-15-14679: Test environment of the proposed gaze-assisted user intention prediction. (a) Framework of the implemented test system; (b) gaze trackers; (c) SmartEye Pro gaze tracking software.
Mentions: Figure 7a shows the entire framework of the implemented test system, which includes a YouTube-like web video server, a data collecting server, a SmartEye Pro three-dimensional eye tracker (see Figure 7b) that has a 120-Hz sampling rate with real-time tracking software (see Figure 7c), a user desktop computer that is equipped with a 2.7-GHz processor, 8 GB of RAM and running Windows 8.1 64-bit and a 24-inch LCD monitor that has a resolution of 1920 × 1080 pixels. A Chrome browser extension for tracking the cursor movement by JavaScript and a medium software to transmit the gaze tracking data in real time though the UDP network from the desktop to the data collecting server were implemented. The data collecting server was based on Node.js and Redis to record all events, including the cursor and gaze coordinates, click event coordinates, page accesses, prefetching of candidates, prefetched video link ID, hit-ratio, preparation time, downlink bandwidth and initial delay along the timestamp.

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.