Lightweight adaptation of classifiers to users and contexts: Trends of the emerging domain

Research output: Contribution to journalReview ArticleScientificpeer-review

2 Citations (Scopus)

Abstract

Intelligent computer applications need to adapt their behaviour to contexts and users, but conventional classifier adaptation methods require long data collection and/or training times. Therefore classifier adaptation is often performed as follows: at design time application developers define typical usage contexts and provide reasoning models for each of these contexts, and then at runtime an appropriate model is selected from available ones. Typically, definition of usage contexts and reasoning models heavily relies on domain knowledge. However, in practice many applications are used in so diverse situations that no developer can predict them all and collect for each situation adequate training and test databases. Such applications have to adapt to a new user or unknown context at runtime just from interaction with the user, preferably in fairly lightweight ways, that is, requiring limited user effort to collect training data and limited time of performing the adaptation. This paper analyses adaptation trends in several emerging domains and outlines promising ideas, proposed for making multimodal classifiers user-specific and context-specific without significant user efforts, detailed domain knowledge, and/or complete retraining of the classifiers. Based on this analysis, this paper identifies important application characteristics and presents guidelines to consider these characteristics in adaptation design.

Original languageEnglish
Article number434826
Number of pages29
JournalScientific World Journal
Volume2015
DOIs
Publication statusPublished - 1 Jan 2015
MoE publication typeA2 Review article in a scientific journal

Fingerprint

Classifiers
Computer applications
Databases
Guidelines
trend

Cite this

@article{628f65bc1eee4bfd830d2dc23486c9ec,
title = "Lightweight adaptation of classifiers to users and contexts: Trends of the emerging domain",
abstract = "Intelligent computer applications need to adapt their behaviour to contexts and users, but conventional classifier adaptation methods require long data collection and/or training times. Therefore classifier adaptation is often performed as follows: at design time application developers define typical usage contexts and provide reasoning models for each of these contexts, and then at runtime an appropriate model is selected from available ones. Typically, definition of usage contexts and reasoning models heavily relies on domain knowledge. However, in practice many applications are used in so diverse situations that no developer can predict them all and collect for each situation adequate training and test databases. Such applications have to adapt to a new user or unknown context at runtime just from interaction with the user, preferably in fairly lightweight ways, that is, requiring limited user effort to collect training data and limited time of performing the adaptation. This paper analyses adaptation trends in several emerging domains and outlines promising ideas, proposed for making multimodal classifiers user-specific and context-specific without significant user efforts, detailed domain knowledge, and/or complete retraining of the classifiers. Based on this analysis, this paper identifies important application characteristics and presents guidelines to consider these characteristics in adaptation design.",
author = "Elena Vildjiounaite and Georgy Gimel'Farb and Vesa Kyll{\"o}nen and Johannes Peltola",
year = "2015",
month = "1",
day = "1",
doi = "10.1155/2015/434826",
language = "English",
volume = "2015",
journal = "The Scientific World Journal",
issn = "2356-6140",
publisher = "Hindawi",

}

Lightweight adaptation of classifiers to users and contexts : Trends of the emerging domain. / Vildjiounaite, Elena; Gimel'Farb, Georgy; Kyllönen, Vesa; Peltola, Johannes.

In: Scientific World Journal, Vol. 2015, 434826, 01.01.2015.

Research output: Contribution to journalReview ArticleScientificpeer-review

TY - JOUR

T1 - Lightweight adaptation of classifiers to users and contexts

T2 - Trends of the emerging domain

AU - Vildjiounaite, Elena

AU - Gimel'Farb, Georgy

AU - Kyllönen, Vesa

AU - Peltola, Johannes

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Intelligent computer applications need to adapt their behaviour to contexts and users, but conventional classifier adaptation methods require long data collection and/or training times. Therefore classifier adaptation is often performed as follows: at design time application developers define typical usage contexts and provide reasoning models for each of these contexts, and then at runtime an appropriate model is selected from available ones. Typically, definition of usage contexts and reasoning models heavily relies on domain knowledge. However, in practice many applications are used in so diverse situations that no developer can predict them all and collect for each situation adequate training and test databases. Such applications have to adapt to a new user or unknown context at runtime just from interaction with the user, preferably in fairly lightweight ways, that is, requiring limited user effort to collect training data and limited time of performing the adaptation. This paper analyses adaptation trends in several emerging domains and outlines promising ideas, proposed for making multimodal classifiers user-specific and context-specific without significant user efforts, detailed domain knowledge, and/or complete retraining of the classifiers. Based on this analysis, this paper identifies important application characteristics and presents guidelines to consider these characteristics in adaptation design.

AB - Intelligent computer applications need to adapt their behaviour to contexts and users, but conventional classifier adaptation methods require long data collection and/or training times. Therefore classifier adaptation is often performed as follows: at design time application developers define typical usage contexts and provide reasoning models for each of these contexts, and then at runtime an appropriate model is selected from available ones. Typically, definition of usage contexts and reasoning models heavily relies on domain knowledge. However, in practice many applications are used in so diverse situations that no developer can predict them all and collect for each situation adequate training and test databases. Such applications have to adapt to a new user or unknown context at runtime just from interaction with the user, preferably in fairly lightweight ways, that is, requiring limited user effort to collect training data and limited time of performing the adaptation. This paper analyses adaptation trends in several emerging domains and outlines promising ideas, proposed for making multimodal classifiers user-specific and context-specific without significant user efforts, detailed domain knowledge, and/or complete retraining of the classifiers. Based on this analysis, this paper identifies important application characteristics and presents guidelines to consider these characteristics in adaptation design.

UR - http://www.scopus.com/inward/record.url?scp=84942274927&partnerID=8YFLogxK

U2 - 10.1155/2015/434826

DO - 10.1155/2015/434826

M3 - Review Article

AN - SCOPUS:84942274927

VL - 2015

JO - The Scientific World Journal

JF - The Scientific World Journal

SN - 2356-6140

M1 - 434826

ER -