Results

A Method for Analysis of Patient Speech in Dialogue for Dementia Detection

Saturnino Luz, Sofia de la Fuente, Pierre Albert

We present an approach to automatic detection of Alzheimer's type dementia based on characteristics of spontaneous spoken language dialogue consisting of interviews recorded in natural settings.

Article, available at: https://arxiv.org/abs/1811.09919

Coaching Older Adults Persuasive and Multimodal Approaches to Coaching for Daily Living

Paraschivoiu2020a.pdf

An Active Feature Transformation Method for Attitude Recognition of Video Bloggers

Fasih Haider, Fahim A. Salim, Owen Conlan, Saturnino Luz

This study proposes a novel Active Feature Transformation (AFT) method for automatic recognition of attitudes (a form of non-verbal behaviour) in video blogs.

Article at:https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1222.pdf

Improving Response Time of Active Speaker Detection Using Visual Prosody Information Prior to Articulation

Fasih Haider, Saturnino Luz, Carl Vogel, Nick Campbell

In this paper, we propose a method for active speaker detection using visual prosody (lip and head movements) information before and after speech articulation to decrease the machine response time.

Article at: https://www.isca-speech.org/archive/Interspeech_2018/pdfs/2310.pdf

Decoupling approximation robustly reconstructs directed dynamical networks

Nikola Simidjievski, Jovan Tanevski, Bernard Zenko, Zoran Levnajic, Ljupco Todorovski, Saso Dzeroski

Relying on insights from equation discovery and machine learning, we here introduce decoupling approximation of dynamical networks and propose a new reconstruction method based on it.

Article available at: https://arxiv.org/abs/1712.03100

MetaBags: Bagged Meta-Decision Trees for Regression

Jihed Khiari, Luis Moreira-Matias, Ammar Shaker, Bernard Zenko, Saso Dzeroski

In this paper, we introduce MetaBags, a novel, practically useful stacking framework for regression. MetaBags is a meta-learning algorithm that learns a set of meta-decision trees designed to select one base model (i.e. expert) for each query, and focuses on inductive bias reduction.

Article available at: https://arxiv.org/abs/1804.06207

Social Activity Modelling and Multimodal Coaching for Active Aging

This paper presents a framework for development of a technological coaching solution that can safeguard or even boost the everyday social life of the elderly.

Full article available at: https://dl.acm.org/citation.cfm?id=3316782.3322761

Technology Use Among Older People After Lower Limb Amputation in Slovenia – Preliminary Results from SAAM Project

Mojca Debeljak, Zlatko Matjacic, Helena Burger

The aim of this study was to collect and analyze data of technology use among elderly after LLA to enable them active aging and in this way to stay at home as long as possible.

Article available at https://www2.cd-cc.si/Skripte/ISPO/Abstract_Book_ISPO2018.pdf

A System for Real-Time Privacy Preserving Data Collection for Ambient Assisted Living

Fasih Haider, Saturnino Luz

Interspeech 2019

We have developed a low-cost system which can extract audio features while protecting the actual spoken content upon detection of voice activity, and store audio features for further processing which offer privacy guarantees.

Article available at https://www.isca-speech.org/archive/Interspeech_2019/abstracts/8037.html

Attitude Recognition Using Multi-Resolution Cochleagram Features

Fasih Haider, Saturnino Luz

2019 IEEE International Conference on Acoustics, Speech and Signal Processing

This paper focuses on the task of categorizing speaker attitudes using speech features. Data extracted from video recordings are employed
in training and testing of predictive models consisting of different sets of speech features. A novel attitude recognition approach using Multi-Resolution Cochleagram (MRCG) features is proposed.

Downolad Article

Combining Measurements and Simulations for Evaluation of Tracking Algorithms

Klemen Bregar, Roman Novak, Mihael Mohorcic

2018 European Conference on Networks and Communications (EuCNC)

Wireless device position tracking has been already thoroughly studied in literature. Most of the studies rely on the presumption that location information is acquired based on range measurements that are performed in a very short period of time. However, in time-division-multiple-access (TDMA) two-way-ranging (TWR) ultra-wideband (UWB) wireless localization networks, those ranging measurements are always spread in time by significant time delays.

Article available at: .....

A qualitative research regarding technology use among older people with lower limb amputation

Mojca Debeljak, Agata Kriznar, Zlatko Matjacic, Helena Burger

15th Congress of the European Forum for Research in Rehabilitation (EFRR)

The world population is aging and there is a challenge to enable older people to live at home as independently and as long as possible. Current research shows that some technologies can improve the elderly’s quality of life. In our research we have focused on older people with lower limb amputation (LLA).

Article available at: ....

Emotion Recognition in Low-Resource Settings: An Evaluation of Automatic Feature Selection Methods

Fasih Haider, Senja Pollak, Pierre Albert, Saturnino Luz

This paper focuses on emotion recognition from speech data. In order to minimize the system's memory and computational needs, a minimum number of features should be extracted for use in machine learning models. A number of feature set reduction methods exist which seek to find minimal sets of relevant features.

Article available at: https://arxiv.org/abs/1908.10623

SAAMEAT: Active Feature Transformation and Selection Methods for the Recognition of User Eating Conditions

Fasih Haider, Senja Pollak, Eleni Zarogianni, Saturnino Luz

This paper presents Active Feature Transformation (AFT) and Active Feature Selection (AFS) methods, and applies them to all three tasks of the ICMI 2018 EAT Challenge for recognition of user eating conditions using audio and visual features.

Download Article.

Multi-criteria Modelling Approach for Ambient Assisted Coaching of Senior Adults

Passive Ultra-Wideband Coarse Localization and Activity Detection System for Assisted Living

An Assessment of Paralinguistic Acoustic Features for Detection of Alzheimer's Dementia in Spontaneous Speech

F. Haider, S. De La Fuente and S. Luz

Published in IEEE Journal of Selected Topics in Signal Processing. Doi: 10.1109/JSTSP.2019.2955022 

An Active Data Representation of Videos for Automatic Scoring of Oral Presentation Delivery Skills and Feedback Generation

Haider, Fasih, Maria Koutsombogera, Owen Conlan, Carl Vogel, Nick Campbell, and Saturnino Luz

Published in Frontiers in Computer Science 2 (2020)

Direct access link

Volleyball Action Modelling for Behavior Analysis and Interactive Multi-modal Feedback

Fahim A. Salim, Fasih Haider, Sena Busra Yengec Tasdemir, Vahid Naghashi, Izem Tengiz, Kubra Cengiz, Dees B.W. Postma, Robby van Delden, Dennis Reidsma, Saturnino Luz and Bert-Jan van Beijnum

Proceedings eNTERFACE’19, 15th International Summer Workshop on Multimodal Interfaces

Publisher: Computer Engineering Department, Bilkent University

Direct access link

Automatic Recognition of Low-Back Chronic Pain Level and Protective Movement Behaviour using Physical and Muscle Activity Infor

Fasih Haider, Pierre Albert and Saturnino Luz

15th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2020), Buenos Aires, Argentina, 18-22 May 2020

(accepted for publication)

Download paper

Emotion Recognition in Low-Resource Settings: An Evaluation of Automatic Feature Selection Methods

Haider, Fasih; Pollak, Senja; Albert, Pierre; Luz, Saturnino

Published in Computer Speech and Language, 11.06.2020

Download article

Cross-corpus Feature Learning between Spontaneous Monologue and Dialogue for Automatic Classification of Alzheimer's Dementia S

De La Fuente Garcia, Sofia; Haider, Fasih; Luz, Saturnino

Published as Conference proceeding - 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Institute of Electrical and Electronics Engineers (IEEE), 2020. (in Press)

Download article 

Automatic Transformation of a Video Using Multimodal Information for an Engaging Exploration Experience

Salim, Fahim A; Haider, Fasih; Luz, Saturnino; Conlan, Owen.

Contribution in Journal Applied Sciences, Vol. 10, No. 9, 27.04.2020

Download article.

Affective Speech for Alzheimer's Dementia Recognition

Haider, Fasih; De La Fuente Garcia, Sofia; Albert, Pierre; Luz, Saturnino.

LREC: Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments (RaPID). ed. / Dimitrios Kokkinakis; Kristina Lundholm Fors; Charalambos Themistocleous; Malin Antonsson; Marie Eckerström. European Language Resources Association (ELRA), 2020. p. 67-73.

Download article

Predicting Mini-Mental Status Examination Scores through Paralinguistic Acoustic Features of Spontaneous Speech

Fu, Ziyang; Haider, Fasih; Luz, Saturnino.

Conference contribution in 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Institute of Electrical and Electronics Engineers (IEEE), 2020.

Download article

Beyond Assistive: Four Tensions in the Design of AAL Based on the Capability Approach

Paraschivoiu, Irina; Winkler, Anna Carina; Meschtscherjakov, Alexander.

Adjunct Proceedings of the 2020 Conference on Designing Interactive Systems, ACM.

Download publication