Gaze-assisted user intention prediction for initial delay reduction in web video access

Seungyup Lee, Juwan Yoo, Gunhee Han

Research output: Contribution to journalArticle

8 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)14679-14700
Number of pages22
JournalSensors (Switzerland)
Volume15
Issue number6
DOIs
Publication statusPublished - 2015 Jun 19

Fingerprint

modules
predictions
commands
preparation
Websites
Cognition
cognition
Hardware
video data
Technology
proximity
resources
hardware
interactions

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

@article{e76e0bc02de94f598926f339879eb61c,
title = "Gaze-assisted user intention prediction for initial delay reduction in web video access",
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.",
author = "Seungyup Lee and Juwan Yoo and Gunhee Han",
year = "2015",
month = "6",
day = "19",
doi = "10.3390/s150614679",
language = "English",
volume = "15",
pages = "14679--14700",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "6",

}

Gaze-assisted user intention prediction for initial delay reduction in web video access. / Lee, Seungyup; Yoo, Juwan; Han, Gunhee.

In: Sensors (Switzerland), Vol. 15, No. 6, 19.06.2015, p. 14679-14700.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Gaze-assisted user intention prediction for initial delay reduction in web video access

AU - Lee, Seungyup

AU - Yoo, Juwan

AU - Han, Gunhee

PY - 2015/6/19

Y1 - 2015/6/19

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84933574616&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933574616&partnerID=8YFLogxK

U2 - 10.3390/s150614679

DO - 10.3390/s150614679

M3 - Article

VL - 15

SP - 14679

EP - 14700

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 6

ER -