| 1. |
- Lu, Zhihan, et al.
(författare)
-
Multimodal Hand and Foot Gesture Interaction for Handheld Devices
- 2014
-
Ingår i: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP). - : Association for Computing Machinery (ACM). - 1551-6857 .- 1551-6865. ; 11:1
-
Tidskriftsartikel (refereegranskat)abstract
- We present a hand-and-foot-based multimodal interaction approach for handheld devices. Our method combines input modalities (i.e., hand and foot) and provides a coordinated output to both modalities along with audio and video. Human foot gesture is detected and tracked using contour-based template detection (CTD) and Tracking-Learning-Detection (TLD) algorithm. 3D foot pose is estimated from passive homography matrix of the camera. 3D stereoscopic and vibrotactile are used to enhance the immersive feeling. We developed a multimodal football game based on the multimodal approach as a proof-of-concept. We confirm our systems user satisfaction through a user study.
|
|
| 2. |
- Isaksson, Martin, et al.
(författare)
-
Adaptive Expert Models for Federated Learning
- 2023
-
Ingår i: <em>Lecture Notes in Computer Science </em>Volume 13448 Pages 1 - 16 2023. - Cham : Springer Science and Business Media Deutschland GmbH. - 9783031289958 ; 13448 LNAI, s. 1-16
-
Konferensbidrag (refereegranskat)abstract
- Federated Learning (FL) is a promising framework for distributed learning when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous and non-IID. We propose a practical and robust approach to personalization in FL that adjusts to heterogeneous and non-IID data by balancing exploration and exploitation of several global models. To achieve our aim of personalization, we use a Mixture of Experts (MoE) that learns to group clients that are similar to each other, while using the global models more efficiently. We show that our approach achieves an accuracy up to 29.78% better than the state-of-the-art and up to 4.38% better compared to a local model in a pathological non-IID setting, even though we tune our approach in the IID setting. © 2023, The Author(s)
|
|
| 3. |
- Lindén, Joakim, et al.
(författare)
-
Evaluating the Robustness of ML Models to Out-of-Distribution Data Through Similarity Analysis
- 2023
-
Ingår i: Commun. Comput. Info. Sci.. - : Springer Science and Business Media Deutschland GmbH. - 9783031429408 ; , s. 348-359, s. 348-359
-
Konferensbidrag (refereegranskat)abstract
- In Machine Learning systems, several factors impact the performance of a trained model. The most important ones include model architecture, the amount of training time, the dataset size and diversity. We present a method for analyzing datasets from a use-case scenario perspective, detecting and quantifying out-of-distribution (OOD) data on dataset level. Our main contribution is the novel use of similarity metrics for the evaluation of the robustness of a model by introducing relative Fréchet Inception Distance (FID) and relative Kernel Inception Distance (KID) measures. These relative measures are relative to a baseline in-distribution dataset and are used to estimate how the model will perform on OOD data (i.e. estimate the model accuracy drop). We find a correlation between our proposed relative FID/relative KID measure and the drop in Average Precision (AP) accuracy on unseen data.
|
|
| 4. |
- Frid, Emma, et al.
(författare)
-
Perception of Mechanical Sounds Inherent to Expressive Gestures of a NAO Robot - Implications for Movement Sonification of Humanoids
- 2018
-
Ingår i: Proceedings of the 15th Sound and Music Computing Conference. - Limassol, Cyprus. - 9789963697304
-
Konferensbidrag (refereegranskat)abstract
- In this paper we present a pilot study carried out within the project SONAO. The SONAO project aims to compen- sate for limitations in robot communicative channels with an increased clarity of Non-Verbal Communication (NVC) through expressive gestures and non-verbal sounds. More specifically, the purpose of the project is to use move- ment sonification of expressive robot gestures to improve Human-Robot Interaction (HRI). The pilot study described in this paper focuses on mechanical robot sounds, i.e. sounds that have not been specifically designed for HRI but are inherent to robot movement. Results indicated a low correspondence between perceptual ratings of mechanical robot sounds and emotions communicated through ges- tures. In general, the mechanical sounds themselves ap- peared not to carry much emotional information compared to video stimuli of expressive gestures. However, some mechanical sounds did communicate certain emotions, e.g. frustration. In general, the sounds appeared to commu- nicate arousal more effectively than valence. We discuss potential issues and possibilities for the sonification of ex- pressive robot gestures and the role of mechanical sounds in such a context. Emphasis is put on the need to mask or alter sounds inherent to robot movement, using for exam- ple blended sonification.
|
|
| 5. |
- Frid, Emma, 1988-, et al.
(författare)
-
Perceptual Evaluation of Blended Sonification of Mechanical Robot Sounds Produced by Emotionally Expressive Gestures : Augmenting Consequential Sounds to Improve Non-verbal Robot Communication
- 2021
-
Ingår i: International Journal of Social Robotics. - : Springer Nature. - 1875-4791 .- 1875-4805.
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents two experiments focusing on perception of mechanical sounds produced by expressive robot movement and blended sonifications thereof. In the first experiment, 31 participants evaluated emotions conveyed by robot sounds through free-form text descriptions. The sounds were inherently produced by the movements of a NAO robot and were not specifically designed for communicative purposes. Results suggested no strong coupling between the emotional expression of gestures and how sounds inherent to these movements were perceived by listeners; joyful gestures did not necessarily result in joyful sounds. A word that reoccurred in text descriptions of all sounds, regardless of the nature of the expressive gesture, was “stress”. In the second experiment, blended sonification was used to enhance and further clarify the emotional expression of the robot sounds evaluated in the first experiment. Analysis of quantitative ratings of 30 participants revealed that the blended sonification successfully contributed to enhancement of the emotional message for sound models designed to convey frustration and joy. Our findings suggest that blended sonification guided by perceptual research on emotion in speech and music can successfully improve communication of emotions through robot sounds in auditory-only conditions.
|
|
| 6. |
- Latupeirissa, Adrian Benigno, et al.
(författare)
-
Exploring emotion perception in sonic HRI
- 2020
-
Ingår i: 17th Sound and Music Computing Conference. - Torino : Zenodo. ; , s. 434-441
-
Konferensbidrag (refereegranskat)abstract
- Despite the fact that sounds produced by robots can affect the interaction with humans, sound design is often an overlooked aspect in Human-Robot Interaction (HRI). This paper explores how different sets of sounds designed for expressive robot gestures of a humanoid Pepper robot can influence the perception of emotional intentions. In the pilot study presented in this paper, it has been asked to rate different stimuli in terms of perceived affective states. The stimuli were audio, audio-video and video only and contained either Pepper’s original servomotors noises, sawtooth, or more complex designed sounds. The preliminary results show a preference for the use of more complex sounds, thus confirming the necessity of further exploration in sonic HRI.
|
|
| 7. |
- Amundin, Mats, et al.
(författare)
-
A proposal to use distributional models to analyse dolphin vocalisation
- 2017
-
Ingår i: Proceedings of the 1st International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots, VIHAR 2017. - 9782956202905 ; , s. 31-32
-
Konferensbidrag (refereegranskat)abstract
- This paper gives a brief introduction to the starting points of an experimental project to study dolphin communicative behaviour using distributional semantics, with methods implemented for the large scale study of human language.
|
|
| 8. |
- Frezza, S., et al.
(författare)
-
Modelling competencies for computing education beyond 2020 : A research based approach to defining competencies in the computing disciplines
- 2018
-
Ingår i: Annual Conference on Innovation and Technology in Computer Science Education, ITiCSE. - New York, NY, USA : Association for Computing Machinery. - 9781450362238 ; , s. 148-174, s. 148-174
-
Konferensbidrag (refereegranskat)abstract
- How might the content and outcomes of tertiary education programmes be described and analysed in order to understand how they are structured and function? To address this question we develop a framework for modelling graduate competencies linked to tertiary degree programmes in the computing disciplines. While the focus of our work is computing the framework is applicable to education more broadly. The work presented here draws upon the pioneering curricular document for information technology (IT2017), curricular competency frameworks, other related documents such as the software engineering competency model (SWECOM), the Skills Framework for the Information Age (SFIA), current research in competency models, and elicitation workshop results from recent computing conferences. The aim is to inform the ongoing Computing Curricula (CC2020) project, an endeavour supported by the Association for Computing Machinery (ACM) and the IEEE Computer Society. We develop the Competency Learning Framework (CoLeaF), providing an internationally relevant tool for describing competencies. We argue that this competency based approach is well suited for constructing learning environments and assists degree programme architects in dealing with the challenge of developing, describing and including competencies relevant to computer and IT professionals. In this paper we demonstrate how the CoLeaF competency framework can be applied in practice, and though a series of case studies demonstrate its effectiveness and analytical power as a tool for describing and comparing degree programmes in the international higher education landscape.
|
|
| 9. |
- Frid, Emma, et al.
(författare)
-
An Exploratory Study On The Effect Of Auditory Feedback On Gaze Behavior In a Virtual Throwing Task With and Without Haptic Feedback
- 2017
-
Ingår i: Proceedings of the 14th Sound and Music Computing Conference. - Espoo, Finland : Aalto University. - 9789526037295 ; , s. 242-249
-
Konferensbidrag (refereegranskat)abstract
- This paper presents findings from an exploratory study on the effect of auditory feedback on gaze behavior. A total of 20 participants took part in an experiment where the task was to throw a virtual ball into a goal in different conditions: visual only, audiovisual, visuohaptic and audio- visuohaptic. Two different sound models were compared in the audio conditions. Analysis of eye tracking metrics indicated large inter-subject variability; difference between subjects was greater than difference between feedback conditions. No significant effect of condition could be observed, but clusters of similar behaviors were identified. Some of the participants’ gaze behaviors appeared to have been affected by the presence of auditory feedback, but the effect of sound model was not consistent across subjects. We discuss individual behaviors and illustrate gaze behavior through sonification of gaze trajectories. Findings from this study raise intriguing questions that motivate future large-scale studies on the effect of auditory feedback on gaze behavior.
|
|
| 10. |
- Elowsson, Anders
(författare)
-
Deep Layered Learning in MIR
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Deep learning has boosted the performance of many music information retrieval (MIR) systems in recent years. Yet, the complex hierarchical arrangement of music makes end-to-end learning hard for some MIR tasks – a very deep and structurally flexible processing chain is necessary to extract high-level features from a spectrogram representation. Mid-level representations such as tones, pitched onsets, chords, and beats are fundamental building blocks of music. This paper discusses how these can be used as intermediate representations in MIR to facilitate deep processing that generalizes well: each music concept is predicted individually in learning modules that are connected through latent representations in a directed acyclic graph. It is suggested that this strategy for inference, defined as deep layered learning (DLL), can help generalization by (1) – enforcing the validity of intermediate representations during processing, and by (2) – letting the inferred representations establish disentangled structures that support high-level invariant processing. A background to DLL and modular music processing is provided, and relevant concepts such as pruning, skip connections, and layered performance supervision are reviewed.
|
|
