Povećanja brzine unosa teksta na zaslonu osjetljivom na dodir prediktivnim vizualnim isticanjem

undergraduate thesis

• Title (english): Increasing Text Input Rate on Touchscreens by Predictive Highlighting
• Author: Mihael Marović
• Mentor: Vlado Glavinić (mentor)
• Committee member: Vlado Glavinić (predsjednik povjerenstva)
• Committee member: Nikolina Frid (član povjerenstva)
• Committee member: Ivan Krešo (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Tema ovog rada je povećanje brzine unosa teksta na zaslonu osjetljivom na dodir prediktivnim vizualnim isticanjem.
Da bismo pristupili tome problemu odlučili smo na korisnicima početnicima usporediti dva mehanizma predikcije.
Jedan je standardan mehanizam predikcije (kakvoga koriste neke komercijalne tipkovnice ili su već instalirane pri kupnji uređaja određene marke), a drugi je alternativan temeljen na radu Isokoskog. Iako smo u konačnici za standardnu tipkovnicu uzeli komercijalnu SwiftKey tipkovnicu, u sklopu ovog rada proučeno je i kako samo samostalno implementirati standardni mehanizam predikcije. Za alternativnu tipkovnicu napravljena je autorska implementacija naziva RadialKey. Zatim, kroz razrađenu metodologiju, izvršeno je eksperimentalno vrednovanje ovih dviju tipkovnica na zaslonima različitih veličina (tabletima i mobitelu). Napravljena je statistička obrada rezultata i analizirani su rezultati ankete. Anketirani korisnici dali su kvalitetno mišljenje o vrednovanim mehanizmima predikcije i neke nove ideje za poboljšanje alternativnog mehanizma predikcije.

Abstract (english)

The subject of this work is increasing text input rate on touchscreens by predictive highlighting. To tackle that problem, we decided to test two prediction mechanism on beginner users. One of them is standard prediction mechanism (such mechanism is used on some commercial keyboards or it comes along with the electronic device itself), and the other one is alternative based Isokoski's work. Even though, we eventually took commercial SwiftKey keyboard as our standard keyboard, in the scope of this work, we tried to make the custom implementation of standard prediction mechanism. The alternative keyboard (bases on Isokoski's work) was made and named RadialKey. Then, through an elaborate methodology, we made an experimental evaluation of these two keyboards on different sizes of touch screen. The statistical analysis of results was made. Results of survey were analysed. Through survey, we got quality opinion about evaluated prediction mechanisms, and some new ideas to improve alternative prediction mechanism.

• Keywords: tipkovnica; predikcija; isticanje; vrednovanje; grupiranje; implementacija; eksperiment; histogram; T9 algoritam; sufiks; latinski kvadrat; operacijski sustav Android; riječ; radijalno; ANOVA
• Keywords (english): keyboard; prediction; highlighting; evaluation; grouping; implementation; experiment; histogram; T9 algorithm; suffix; Latin square; the operating system Android; word; radial; ANOVA
• Language: croatian
• URN:NBN: urn:nbn:hr:168:712586
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 10:29:19