sort by:  author date

Link between Sentiment and Human Activity Represented by Footsteps ? Experiment Exploiting IoT Devices and Social Networks

SALAMON, J., MOUČEK, R. Link between Sentiment and Human Activity Represented by Footsteps ? Experiment Exploiting IoT Devices and Social Networks. In Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2016) - Volume 5: HEALTHINF. Setúbal: SciTePress, 2016. s. 450-457. ISBN: 978-989-758-170-0
Abstract PDF BibTeX

The Internet of Things world brings to our lives many opportunities to monitor our daily activities by collecting data from various devices. Complementary to it, the data expressing opinions, suggestions, interpretations, contradictions, and uncertainties are more accessible within variety of online resources. This paper deals with collection and analysis of hard data representing the number of steps and soft data representing the sentiment of participants who underwent a pilot experiment. The paper defines outlines of the problem and presents possible sources of reliable data, sentiment evaluation, sentiment extraction using machine learning methods, and links between the data collected from IoT devices and sentiment expressed by the participant in a textual form. Then the results provided by using inferential statistics are presented. The paper is concluded by discussion and summarization of results and future work proposals.

On data and metadata formats for electrophysiological experiments

VANĚK, J., MOUČEK, R. On data and metadata formats for electrophysiological experiments. In 2015 IEEE 13th International Scientific Conference on Informatics - INFORMATICS 2015. Piscataway: IEEE, 2015. s. 290-295. ISBN: 978-1-4673-9867-1
Abstract PDF BibTeX

Despite standardization efforts there is still no widely used standard format for storing electrophysiological data. This standard is necessary for effective collaboration between scientists. This work deals with adjustments of existing general data/metadata model for electrophysiological experiments and proposal/implementation of HDF data format for their storage.

odML templates generator from relational database

JEŽEK, P., KRAUZ, J. odML templates generator from relational database. 2014.
Abstract PDF BibTeX

Data management systems typically include database and user interface, which allows access to stored data. Common shortcoming of these user interfaces is their strong dependence on the structure of the database. User interfaces are designed for specific system and can not be easily reused for another. This tool is able to generate platform-independent odML template for any relational database. These templates describing database structure can be used for creation of the graphical interface of the client application.

Ontology Developmnet in EEG/ERP Domain

JEŽEK, P. Ontology Developmnet in EEG/ERP Domain. 1. vyd. Plzeň : 2012, 127 s.
Abstract PDF BibTeX

Because of difficulties with neuroinformatics data/metadata storage, a new research field dealing with the development of neuroinformatics databases is gradually formed. The data within these databases are supposed to be recognizable by interested researchers. To support the development of these databases the description of specific neuroscience fields is needed. Therefore, the scientific community is intensively working on description of individual neuroscience fields by domain ontology. This ontology is expressed by Semantic Web languages. Since the current neuroinformatics software tools are usually based on object-oriented languages and relational databases a need for suitable mapping is emerging. Due to differences in semantic expressivity of common modeling techniques and Semantic Web languages it is necessary to fill these semantic gaps. This work is focused on developing ontology for EEG/ERP domain that expresses EEG/ERP experiments. The developed ontology is practically implemented together with the EEG/ERP Portal. The goal of the EEG/ERP Portal is to serve as a system for storing, managing and interchanging EEG/ERP experiments. The work particularly solves semantic gaps between object-oriented code and Semantic Web languages by adding a missing semantics into the object-oriented code. The developed mapping is implemented within the presented Semantic Framework. The integration of the Semantic Framework within the EEG/ERP Portal ensures transformation of stored experiments into the ontology representation. The registration of the EEG/ERP Portal within the Neuroscience Information Framework practically validates the presented approach.

Text, Speech and Dialogue

MATOUŠEK, V., MAUTNER, P. Text, Speech and Dialogue. 1.. vyd. Berlin : Springer, 2003, 426 s. ISBN: 3-540-20024-X
Abstract PDF BibTeX

Proceedings of the 6th international conference on text and speech processing and dialogue system implementation.

Our partners