Lucami

Research Challenges

The following challenges are to be addressed on the way to the user-adapted solutions:

  • Human-machine communication is context dependent.
  • The natural user-to-machine communication is dependent on user’s personality, mood and emotions.
  • The user-to-machine communication is continuous. 
  • The communication system is autonomous in terms of information gathering and intelligent decision.

To make a step forward towards a solution of the above-listed challenges, our group is concentrating on the following fields:

  • User modelling and context-aware conversational recommender systems. 
  • User interface design. 
  • Multimedia signals and communication.
  • Social signals.
  • Internet of things (IoT) and big-data analysis for end-user context identification.
  • Special communication hardware solutions. 
  • Social network user-data acquisition.

Read more.


News and events

World Telecommunication and Information Society Day

May 17 2021 In November 2006, the ITU Plenipotentiary Conference in Antalya, Turkey, decided to celebrate both events on 17 May as World Telecommunication and Information Society Day. The updated Resolution 68 invites Member States and Sector Members to celebrate the day annually by organizing appropriate national programmes with a…

Living Lab automation: controlled lighting

Our Living lab got controlled lighting. Thanks to the company Entia, we have DALI controlled system allowing us to control lighting in the room in a simple and repeatable way.

Multimedia Exposure Measurement Experiment (MMEM)

In May of this year, we began an experiment to measure multimedia exposure. The study identifies the usefulness of psychophysiological signals for measuring multimedia exposure in terms of useful information for assessing multimedia exposure. As a true value of multimedia exposure, we will assess multimedia exposure using the MMES scale,…

The Communicator speaks Slovenian

The multi-year student project Communicator, which aims to create a socially intelligent communicator (a conversation system with an embodiment, aware of the user’s social signals), has reached a milestone – he speaks Slovenian. Technologies such as Amazon Alexa did not allow this, so we set up the architecture anew and…

Weak Ground Truth Determination of Continuous Human-Rated Data

A research paper (10.1109/ACCESS.2020.3046293) and web tool (https://www.lucami.org/en/WGT/) on Weak Ground Truth Determination of Continuous Human-Rated Data. The article presents a novel weak ground truth (WGT) determination and rater bias removal procedure on continuous human-rated data. The notion of WGT is essential in cases where there is no direct empirical…

Professor Andrej Košir will have a keynote speech at Slovenski oglaševalski festival

Title: Andrej Košir: Multimedia exposure meter using artificial social intelligence, Keynote at Slovenski oglaševalski festival (https://sof.si/govorci/) During the lecture, Andrej Košir will introduce the concept of measuring multimedia exposure with technology. It will open and highlight issues such as What is Multimedia Exposure? Is multimedia exposure objectively measurable? Is it…

Thesis defense: STRASNER KEVIN

Paper on student project building up student’s career prospects

Urban Burnik, Andrej Košir: Industrial product design project: building up engineering students’ career prospects The needs to bridge the academic skills of students involved in higher education and improve their readiness for employment in industry are being widely addressed. This paper presents results of a specific engineering project case supervised by…

Research

Multimedia Exposure Measurement Experiment (MMEM)

In May of this year, we began an experiment to measure multimedia exposure. The study identifies the usefulness of psychophysiological signals for measuring multimedia exposure in terms of useful information for assessing multimedia exposure. As a true value of multimedia exposure, we will assess multimedia exposure using the MMES scale,…

The Communicator speaks Slovenian

The multi-year student project Communicator, which aims to create a socially intelligent communicator (a conversation system with an embodiment, aware of the user’s social signals), has reached a milestone – he speaks Slovenian. Technologies such as Amazon Alexa did not allow this, so we set up the architecture anew and…

Weak Ground Truth Determination of Continuous Human-Rated Data

A research paper (10.1109/ACCESS.2020.3046293) and web tool (https://www.lucami.org/en/WGT/) on Weak Ground Truth Determination of Continuous Human-Rated Data. The article presents a novel weak ground truth (WGT) determination and rater bias removal procedure on continuous human-rated data. The notion of WGT is essential in cases where there is no direct empirical…

Clickstream based user persona recognition

Investor: Telekom Slovenije The team: principal investigator Andrej Košir, researchers Nejc Kozjek, Matevž Kunaver The project aimed at development, implementation and verification (feasibility study) of unsupervised user persona identification algorithm based on remote controller click-stream. We developed a novel user persona identification algorithm analyzing short sequences of user events. The…

User position and breathing rate measurement using pulse radar

Investor: Nielsen The team: principal investigator Andrej Košir, researcher Nejc Kozjek The study focused on evaluating accuracy of presence, distance and respiration rate of a person. Two different radars from the same manufacturer (Novelda) were used: XeThru X4M200 for respiration and XeThru X4M300 for distance measurement and presence. In order…

Human spoken commands recognition using Far-field voice processor

Investor: Nielsen The team: principal investigator Andrej Košir, researcher Nejc Kozjek The main goal of this study is to evaluate the potential of XMOS far-field sensor in terms of priory known human spoken commands and keywords recognition. The study includes analysis of basic connectivity and configurability of the sensor as…

Multimedia exposure meter

Published article in Eurasip

Contact
close slider

Contact

Head: Professor Andrej Košir

Address
User-adapted Communication and Ambient Intelligence Lab (LUCAMI)
Faculty of Electrical Engineering, University of Ljubljana
Tržaška 25, 1001 Ljubljana
Slovenia

Contact Info
Telephone: +386 1 4768 354 (Head)
Fax: +386 1 4768 855
E-mail: andrej.kosir@fe.uni-lj.si