Change search
Link to record
Permanent link

Direct link
BETA
Gustafsson, Lennart
Publications (10 of 42) Show all publications
Gustafsson, L. (2019). A Case of Near-Optimal Sensory Integration Based on Kohonen Self-Organizing Maps. Neural Computation, 31(7), 1419-1429
Open this publication in new window or tab >>A Case of Near-Optimal Sensory Integration Based on Kohonen Self-Organizing Maps
2019 (English)In: Neural Computation, ISSN 0899-7667, E-ISSN 1530-888X, Vol. 31, no 7, p. 1419-1429Article in journal (Refereed) Published
Abstract [en]

This letter shows by digital simulation that a simple rule applied to one-dimensional self-organized maps for integrating sensory perceptions from two identical sources yielding position information as integers, corrupted by independent noise sources, yields almost statistically optimal results for position estimation as determined by maximum likelihood estimation. There is no learning of the corrupting noise sources nor is any information about the statistics of the noise sources available to the integrating process. The simple rule employed yields a measure of the quality of the estimated position of the source. The letter also shows that if the Bayesian estimates, which are rational numbers, are rounded in order to comply with the stipulation that integers be identified, the Bayesian estimation will have a larger variance than the proposed integration.

Place, publisher, year, edition, pages
MIT Press, 2019
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electronic systems
Identifiers
urn:nbn:se:ltu:diva-74532 (URN)10.1162/neco_a_01200 (DOI)000471704300006 ()31113302 (PubMedID)2-s2.0-85067341006 (Scopus ID)
Note

Validerad;2019;Nivå 2;2019-07-04 (johcin)

Available from: 2019-06-14 Created: 2019-06-14 Last updated: 2019-07-10Bibliographically approved
Gustafsson, L., Jantvik, T. & Paplinski, A. (2014). A Self-organized artificial neural network architecture that generates the McGurk effect (ed.). In: (Ed.), (Ed.), The 2014 International Joint Conference on Neural Networks (IJCNN 2014): Bejing, China 7-11 July 2014. Paper presented at International Joint Conference on Neural Networks : 06/07/2014 - 11/07/2014 (pp. 3974-3980). Piscataway, NJ: IEEE Communications Society
Open this publication in new window or tab >>A Self-organized artificial neural network architecture that generates the McGurk effect
2014 (English)In: The 2014 International Joint Conference on Neural Networks (IJCNN 2014): Bejing, China 7-11 July 2014, Piscataway, NJ: IEEE Communications Society, 2014, p. 3974-3980Conference paper, Published paper (Refereed)
Abstract [en]

A neural network architecture, subjected to incon-gruent stimuli in the form of lip reading of spoken syllables and listening to different spoken syllables, is shown to generate the well-known McGurk effect, e.g. visual /ga/ and auditory /ba/ is perceived as /da/ by the network. The neural network is based on an architecture which has previously been successfully applied to sensory integration of congruent stimuli and is here extended to take into account that lip reading groups consonants into equivalence classes, bilabial, dento-labial and nonlabial consonants, rather than distinguishing between individual consonants.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Communications Society, 2014
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-39563 (URN)10.1109/IJCNN.2014.6889411 (DOI)2-s2.0-84908472294 (Scopus ID)e60ec4fc-a7ab-47b5-a9f4-127326fd779e (Local ID)978-1-4799-6627-1 (ISBN)e60ec4fc-a7ab-47b5-a9f4-127326fd779e (Archive number)e60ec4fc-a7ab-47b5-a9f4-127326fd779e (OAI)
Conference
International Joint Conference on Neural Networks : 06/07/2014 - 11/07/2014
Note
Godkänd; 2014; 20140924 (andbra)Available from: 2016-10-03 Created: 2016-10-03 Last updated: 2018-07-10Bibliographically approved
Sandin, F. & Gustafsson, L. (2014). Intelligent Industrial Processes & Enabling ICT – A Machine Learning and Intelligence Perspective (ed.). Paper presented at . : Luleå tekniska universitet
Open this publication in new window or tab >>Intelligent Industrial Processes & Enabling ICT – A Machine Learning and Intelligence Perspective
2014 (English)Report (Other academic)
Abstract [en]

Intelligent Industrial Processes (IIP) and Enabling Information and Communication Technology (Enabling ICT) are two out of the nine areas of excellence in research and innovation at the Luleå University of Technology (LTU), which are formed to foster interdisciplinary research and innovation in strategically important areas. This report presents a perspective on the role of machine learning and intelligence in these two areas, focusing in particular on future ICT for industrial process automation (ProcessIT) up to the year 2030. The study that is presented here complements similar studies made in other fields, with the common goal to create the first inputs for a broader discussion and formulation of strategic objectives in the form of a roadmap.This report presents my interpretation of the concept of Intelligent Industrial Processes and the role of ICT in that context, including novel information processing methods and devices that are inspired by biological circuits and systems. This report also includes brief introductions and definitions of important concepts; a summary of seven documents presenting international strategic agendas and objectives; a summary of identified strengths, weaknesses, opportunities and threats; a description of selected research trends with references to interesting results; a tentative outline of interesting research problems and first steps towards 2030; and a list of research groups with complementary competences that may merit future partnership. It is concluded that the Open Research and Innovation Platform that is outlined in a parallel study would be a valuable resource for machine-learning research, development and education because transparent access to data is a key enabling factor. In terms of machine-learning research it is concluded that we need to take the step from studies of isolated learning algorithms and applications to closed-loop learning architectures for large-scale sensor-actuator systems, possibly including human- machine interaction, decision support systems and models of complex systems such as maintenance systems and markets.The aim to develop intelligent industrial processes using a new generation of ICT is an ambitious interdisciplinary initiative, which is likely to force us thinking beyond conventional methods and to educate a new generation of engineers that understand the necessary concepts.

Place, publisher, year, edition, pages
Luleå tekniska universitet, 2014. p. 44
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-23813 (URN)885a48e7-fe7a-4577-be7b-aa5f72b3fa8a (Local ID)885a48e7-fe7a-4577-be7b-aa5f72b3fa8a (Archive number)885a48e7-fe7a-4577-be7b-aa5f72b3fa8a (OAI)
Note
Godkänd; 2014; 20141125 (fresan)Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-05-04Bibliographically approved
Paplinski, A., Gustafsson, L. & Mount, W. M. (2011). A recurrent multimodal network for binding written words and sensory-based semantics into concepts (ed.). In: (Ed.), Bao-Liang Lu; Liqing Zhang; James Kwok (Ed.), Neural Information Processing: 18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings. Paper presented at International Conference on Neural Information Processing : 13/11/2011 - 17/11/2011 (pp. 413-422). Berlin: Springer Science+Business Media B.V., 1
Open this publication in new window or tab >>A recurrent multimodal network for binding written words and sensory-based semantics into concepts
2011 (English)In: Neural Information Processing: 18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings / [ed] Bao-Liang Lu; Liqing Zhang; James Kwok, Berlin: Springer Science+Business Media B.V., 2011, Vol. 1, p. 413-422Conference paper, Published paper (Refereed)
Abstract [en]

We present a recurrent multimodal model of binding written words to mental objects and investigate the capability of the network in reading misspelt but categorically related words. Our model consists of three mutually interconnected association modules which store mental objects, represent their written names and bind these together to form mental concepts. A feedback gain controlling top-down influence is incorporated into the model architecture and it is shown that correct settings for this during map formation and simulated reading experiments is necessary for correct interpretation and semantic binding of the written words.

Place, publisher, year, edition, pages
Berlin: Springer Science+Business Media B.V., 2011
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 7062
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-33177 (URN)10.1007/978-3-642-24955-6_50 (DOI)81855226561 (Scopus ID)7f9bd680-9a12-4053-9e84-ef1a0cd9d4d9 (Local ID)7f9bd680-9a12-4053-9e84-ef1a0cd9d4d9 (Archive number)7f9bd680-9a12-4053-9e84-ef1a0cd9d4d9 (OAI)
Conference
International Conference on Neural Information Processing : 13/11/2011 - 17/11/2011
Note
Validerad; 2011; 20111116 (ysko)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
Jantvik, T., Gustafsson, L. & Paplinski, A. (2011). A self-organized artificial neural network architecture for sensory integration with applications to letter-phoneme integration (ed.). Paper presented at . Neural Computation, 23(8), 2101-2139
Open this publication in new window or tab >>A self-organized artificial neural network architecture for sensory integration with applications to letter-phoneme integration
2011 (English)In: Neural Computation, ISSN 0899-7667, E-ISSN 1530-888X, Vol. 23, no 8, p. 2101-2139Article in journal (Refereed) Published
Abstract [en]

The multimodal self-organizing network (MMSON), an artificial neural network architecture carrying out sensory integration, is presented here. The architecture is designed using neurophysiological findings and imaging studies that pertain to sensory integration and consists of interconnected lattices of artificial neurons. In this artificial neural architecture, the degree of recognition of stimuli, that is, the perceived reliability of stimuli in the various subnetworks, is included in the computation. The MMSON's behavior is compared to aspects of brain function that deal with sensory integration. According to human behavioral studies, integration of signals from sensory receptors of different modalities enhances perception of objects and events and also reduces time to detection. In neocortex, integration takes place in bimodal and multimodal association areas and result, not only in feedback-mediated enhanced unimodal perception and shortened reaction time, but also in robust bimodal or multimodal percepts. Simulation data from the presented artificial neural network architecture show that it replicates these important psychological and neuroscientific characteristics of sensory integration.

National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-15007 (URN)10.1162/NECO_a_00149 (DOI)21521039 (PubMedID)2-s2.0-79959644938 (Scopus ID)e76f2112-d1ae-448f-bcb3-bf30233e9e76 (Local ID)e76f2112-d1ae-448f-bcb3-bf30233e9e76 (Archive number)e76f2112-d1ae-448f-bcb3-bf30233e9e76 (OAI)
Note
Validerad; 2011; 20110427 (tamjan)Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-07-10Bibliographically approved
Paplinski, A., Gustafsson, L. & Mount, W. (2010). A model of binding concepts to spoken names (ed.). Paper presented at . Australian Journal of Intelligent Information Processing Systems, 11(2), 1-5
Open this publication in new window or tab >>A model of binding concepts to spoken names
2010 (English)In: Australian Journal of Intelligent Information Processing Systems, ISSN 1321-2133, Vol. 11, no 2, p. 1-5Article in journal (Refereed) Published
Abstract [en]

Towards hardware implementation of real-time visual image processing, we propose a region-based coupled Markov Random Field (MRF) model with phases as hidden variables for coarse image region segmentation tasks. In general, two types of coupled MRF models, boundary-based and region-based, are known according to their hidden variables that play a crucial role for detecting discontinuities in intensity, color, depth and motion in image scenes. A region-based coupled MRF model with phases as hidden variables has been proposed for image restoration task. For coarse region image segmentation tasks, we customize the previous model in view of effient hardware implementation. Our model has an advantage over the resistive-fuse network, which is a boundary-based coupled MRF model, in dealing with the hidden variables explicitly. Consequently, our model can extract closed regions from given images by phases as labels at di®erent timing and act as a spatial-temporal nonlinear filter.

Keywords
Technology - Information technology, Teknikvetenskap - Informationsteknik
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-7986 (URN)66dd2e10-07f8-11e0-b767-000ea68e967b (Local ID)66dd2e10-07f8-11e0-b767-000ea68e967b (Archive number)66dd2e10-07f8-11e0-b767-000ea68e967b (OAI)
Note
Godkänd; 2010; 20101215 (lgus)Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2017-11-24Bibliographically approved
Gustafsson, L., Jantvik, T. & Paplinski, A. (2007). A multimodal self-organizing network for sensory integration of letters and phonemes (ed.). In: (Ed.), Angel Pascqal del Pobil (Ed.), Proceedings of the 11th IASTED International Conference Artificial Intelligence and Soft Computing: August 29 - 31, 2007, Palma de Mallorca, Spain. Paper presented at IASTED International Conference on Artificial Intelligence and Soft Computing : 29/08/2007 - 31/08/2007 (pp. 25-31). Anaheim, CA: ACTA Press
Open this publication in new window or tab >>A multimodal self-organizing network for sensory integration of letters and phonemes
2007 (English)In: Proceedings of the 11th IASTED International Conference Artificial Intelligence and Soft Computing: August 29 - 31, 2007, Palma de Mallorca, Spain / [ed] Angel Pascqal del Pobil, Anaheim, CA: ACTA Press, 2007, p. 25-31Conference paper, Published paper (Refereed)
Abstract [en]

Integration of signals from sensory receptors of different modalities is known to enhance perception. Integration takes place in bimodal and multimodal association areas of neocortex and results in robust bimodal or multimodal percepts as well as in feedback mediated enhanced unimodal perception. A Multimodal Self-Organizing Network, Mu-SON, is presented as a tool for simulating sensory integration. The latest version of this MuSON, that is described in the current paper, also takes the degree of recognition of stimuli in the various maps of the network into account. Simulation results show the same characteristics as corresponding results from psychology and neuroscience.

Place, publisher, year, edition, pages
Anaheim, CA: ACTA Press, 2007
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-32208 (URN)6a146820-e139-11dc-9e29-000ea68e967b (Local ID)978-0-88986-693-5 (ISBN)6a146820-e139-11dc-9e29-000ea68e967b (Archive number)6a146820-e139-11dc-9e29-000ea68e967b (OAI)
Conference
IASTED International Conference on Artificial Intelligence and Soft Computing : 29/08/2007 - 31/08/2007
Note
Validerad; 2007; 20080222 (ysko)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
Chou, S., Papliński, A. & Gustafsson, L. (2007). Speaker-dependent bimodal integration of Chinese phonemes and letters using multimodal self-organizing networks (ed.). In: (Ed.), (Ed.), The 2007 IEEE International Joint Conference on Neural Networks: [IJCNN 2007] ; Orlando, FL, 12 - 17 August 2007. Paper presented at IEEE International Joint Conference on Neural Networks : 12/08/2007 - 17/08/2007 (pp. 248-253). Piscataway, NJ: IEEE Communications Society
Open this publication in new window or tab >>Speaker-dependent bimodal integration of Chinese phonemes and letters using multimodal self-organizing networks
2007 (English)In: The 2007 IEEE International Joint Conference on Neural Networks: [IJCNN 2007] ; Orlando, FL, 12 - 17 August 2007, Piscataway, NJ: IEEE Communications Society, 2007, p. 248-253Conference paper, Published paper (Refereed)
Abstract [en]

We present a model of integration of auditory and visual information as in the human cortex. More specifically, we demonstrate a possible way in which the phonetic symbols and associated Mandarin Chinese phonemes pronounced by different speakers are mapped onto the model of cortical areas. Our model has been strongly influenced by recent fMRI studies on integration of letters and speech sounds in the human brain. The model is based on multimodal self-organizing networks (MuSoNs) which were introduced in our previous works and proved to be a convenient tool to describe and study mapping and integration of sensory information as in the cortex. The model also shows how phonemes pronounced by different speakers are mapped onto overlapping cortical areas

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Communications Society, 2007
Series
International Conference on Neural Networks. Proceedings, ISSN 1098-7576
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-39053 (URN)10.1109/IJCNN.2007.4370963 (DOI)000254291100043 ()2-s2.0-51749108658 (Scopus ID)da43fa50-ca40-11df-a707-000ea68e967b (Local ID)978-1-424-41379-9 (ISBN)da43fa50-ca40-11df-a707-000ea68e967b (Archive number)da43fa50-ca40-11df-a707-000ea68e967b (OAI)
Conference
IEEE International Joint Conference on Neural Networks : 12/08/2007 - 17/08/2007
Note
Validerad; 2007; 20100927 (andbra)Available from: 2016-10-03 Created: 2016-10-03 Last updated: 2018-07-10Bibliographically approved
Gustafsson, L. & Paplinski, A. (2006). Bimodal integration of phonemes and letters: an application of multimodal self-organizing networks (ed.). In: (Ed.), (Ed.), International Joint Conference on Neural Networks: IJCNN '06. Paper presented at IEEE World Congress on Computational Intelligence : 16/07/2006 - 21/07/2006 (pp. 312-318). Piscataway, NJ: IEEE Communications Society
Open this publication in new window or tab >>Bimodal integration of phonemes and letters: an application of multimodal self-organizing networks
2006 (English)In: International Joint Conference on Neural Networks: IJCNN '06, Piscataway, NJ: IEEE Communications Society, 2006, p. 312-318Conference paper, Published paper (Refereed)
Abstract [en]

Multimodal integration of sensory information has clear advantages for survival: events that can be sensed in more than one modality are detected more quickly and accurately, and if the sensory information is corrupted by noise the classification of the event is more robust in multimodal percepts than in the unisensory information. It is shown that using a Multimodal Self-Organizing Network (MuSON), consisting of several interconnected Kohonen Self-Organizing Maps (SOM), bimodal integration of phonemes, auditory elements of language, and letters, visual elements of language, can be simulated. Robustness of the bimodal percepts against noise in both the auditory and visual modalities is clearly demonstrated.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Communications Society, 2006
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-34134 (URN)10.1109/IJCNN.2006.246697 (DOI)84039b50-965f-11db-8975-000ea68e967b (Local ID)0-7803-9490-9 (ISBN)84039b50-965f-11db-8975-000ea68e967b (Archive number)84039b50-965f-11db-8975-000ea68e967b (OAI)
Conference
IEEE World Congress on Computational Intelligence : 16/07/2006 - 21/07/2006
Note
Godkänd; 2006; 20061228 (ysko)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
Gustafsson, L. & Paplinski, A. (2006). Feedback in multimodal self-organizing networks enhances perception of corrupted stimuli (ed.). In: (Ed.), Abdul Sattar; Byeong-Ho Kang (Ed.), AI 2006: Advances in Artificial Intelligence. 19th Australian Joint Conference on Artificial Intelligence, Hobart, Australia, December 4-8, 2006. Proceedings. Paper presented at Australian Joint Conference on Artificial Intelligence : 04/12/2006 - 08/12/2006 (pp. 19-28). : Encyclopedia of Global Archaeology/Springer Verlag
Open this publication in new window or tab >>Feedback in multimodal self-organizing networks enhances perception of corrupted stimuli
2006 (English)In: AI 2006: Advances in Artificial Intelligence. 19th Australian Joint Conference on Artificial Intelligence, Hobart, Australia, December 4-8, 2006. Proceedings / [ed] Abdul Sattar; Byeong-Ho Kang, Encyclopedia of Global Archaeology/Springer Verlag, 2006, p. 19-28Conference paper, Published paper (Refereed)
Abstract [en]

It is known from psychology and neuroscience that multimodal integration of sensory information enhances the perception of stimuli that are corrupted in one or more modalities. A prominent example of this is that auditory perception of speech is enhanced when speech is bimodal, i.e. when it also has a visual modality. The function of the cortical network processing speech in auditory and visual cortices and in multimodal association areas, is modeled with a Multimodal Self-Organizing Network (MuSON), consisting of several Kohonen Self-Organizing Maps (SOM) with both feedforward and feedback connections. Simulations with heavily corrupted phonemes and uncorrupted letters as inputs to the MuSON demonstrate a strongly enhanced auditory perception. This is explained by feedback from the bimodal area into the auditory stream, as in cortical processing.

Place, publisher, year, edition, pages
Encyclopedia of Global Archaeology/Springer Verlag, 2006
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 4304
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-31745 (URN)10.1007/11941439_6 (DOI)601f6b00-960b-11db-8975-000ea68e967b (Local ID)3-540-49787-0 (ISBN)601f6b00-960b-11db-8975-000ea68e967b (Archive number)601f6b00-960b-11db-8975-000ea68e967b (OAI)
Conference
Australian Joint Conference on Artificial Intelligence : 04/12/2006 - 08/12/2006
Note
Validerad; 2006; Bibliografisk uppgift: Lecture Notes in Artificial Intelligence; 20061228 (ysko)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
Organisations

Search in DiVA

Show all publications