Statistička analiza podataka koji opisuju interakcije čovjeka i robota

master's thesis

• Title (english): Statistical analysis of data describing human-robot interactions
• Author: Anabela Tkalec
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2023-03-30, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Statistička analiza je vrlo važan alat koji služi za proučavanje trendova, obrazaca ponašanja te uzročnih veza korištenjem kvantitativnih podataka. U ovom se radu ona koristi na podacima prikupljenim tijekom interakcije afektivnog robota PLEA i ljudi s ciljem boljeg razumijevanja tog odnosa. Za donošenje bilo kakvih ispravnih zaključaka potrebno je pažljivo isplanirati tijek istraživanja, način prikupljanja uzoraka te njihovu količinu. Nakon toga, potrebno je prikupljene podatke organizirati i sažeti uz pomoć opisne statistike. Početne hipoteze i pretpostavke se testiraju za cijelu željenu populaciju. Na kraju, se ti zaključci interpretiraju i generaliziraju. U ovom se radu proučavaju emocije tijekom interakcije te ovisnost njenog trajanja o razvijenim emocijama. Cilj je proučiti vezu između dominantne emocije u cijeloj interakciji i duljine trajanje interakcije te odnos prvog dojma o robotu, tj. prve emocije koju ljudi osjete tijekom interakcije i duljine trajanja. Za obradu podataka korišteni su programski jezik Python i programski softver SPSS Statistics.

Abstract (english)

Statistical analysis is a very important tool used to study trends, patterns of behavior and causal relationships using quantitative data. In this paper, it is used on the data collected during interactions between the affective robot PLEA and humans with the aim of better understanding this relationship. In order to draw any correct conclusions, it is necessary to carefully plan the course of the research, the method of collecting samples and their quantity. After that, it is necessary to organize and summarize the collected data with the help of descriptive statistics. Initial hypotheses and assumptions are tested for the entire desired population. Finally, these conclusions are interpreted and generalized. In this paper, the emotions during the interaction and the dependence of the interaction's duration on the developed emotions are studied. The first goal is to study the relationship between the dominant emotions throughout the interaction and the duration of the interaction. The second one is to study the relationship between the first impression of the robot and the duration. Data processing is done using the python programming language and the SPSS Statistics software.

• Keywords: statistička analiza; PLEA; afektivna robotika; emocije; interakcija čovjeka i robota; python; SPSS Statistics
• Keywords (english): statistical analysis; PLEA; affective robotics; emotions; human-robot interactions; python; SPSS Statistics
• Language: croatian
• URN:NBN: urn:nbn:hr:235:779294
• Study programme: Title: Mechanical Engineering; specializations in: Design, Process and Energy Engineering, Production Engineering, Engineering Modelling and Computer Simulation, Marine Engineering, Industrial Engineering and Management, Materials Engineering, Mechatronics and Robotics, Autonomous Systems; Course: Mechatronics and Robotics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2023-03-23 08:45:13