Background The lack of knowledge about the intra- and interindividual attack frequency variabilit... more Background The lack of knowledge about the intra- and interindividual attack frequency variability in chronic cluster headache complicates power and sample size calculations for baseline periods of trials, and consensus on their most optimal duration. Methods We analyzed the 12-week baseline of the ICON trial (occipital nerve stimulation in medically intractable chronic cluster headache) for: (i) weekly vs. instantaneous recording of attack frequency; (ii) intra-individual and seasonal variability of attack frequency; and (iii) the smallest number of weeks to obtain a reliable estimate of baseline attack frequency. Results Weekly median (14.4 [8.2–24.0]) and instantaneous (14.2 [8.0–24.5]) attack frequency recordings were similar (p = 0.20; Bland-Altman plot). Median weekly attack frequency was 15.3 (range 4.2–140) and highest during spring (p = 0.001) compared to the other seasons. Relative attack frequency variability decreased with increasing attack frequency (p = 0.010). We tabu...
This deliverable presents the first version of a generic federated OOP architecture, supporting i... more This deliverable presents the first version of a generic federated OOP architecture, supporting interconnection and interoperability of national registries at the EU level. The architecture is in line with existing EU frameworks (EIRA, EIF), takes into account the e-SENS European Interoperability Reference Architecture and is based on the CEF DSIs and the Building Blocks consolidated by the e-SENS project. The first version focuses on interoperability at business and information level, to be extended iteratively in the future versions. The deliverable includes, among others, the requirements, the initial building blocks, and the interface specifications of the generic federated architecture. The overall logic of the deliverable emerges from the principle of reusing existing frameworks and building blocks provided by CEF, e-SENS, and other initiatives. As the first step, an initial inventory of existing e- Government Building Blocks is proposed. Then the principles of selection of bu...
This document presents the second official version of the generic federated OOP architecture. It ... more This document presents the second official version of the generic federated OOP architecture. It develops further and extends the deliverable "D2.1. Generic federated OOP architecture (1st version)" (D2.1). The architecture supports interconnection and interoperability of national registries at the EU level, is in line with existing EU frameworks (EIRA, EIF), takes into account the forthcoming regulation about the Single Digital Gateway (SDGR), and uses results of the e-SENS European Interoperability Reference Architecture. It provides support for future developers of OOP projects and is based on the Connecting Europe Facility (CEF) Digital Service Infrastructures (DSIs), the Building Blocks consolidated by the e-SENS project, and in justified cases, on the new building blocks. Compared to the first version D2.1, this deliverable develops the architecture further, aligns it with the provisions of the forthcoming regulation about the Single Digital Gateway, and focusses on ...
One of the challenges in the field of content-based image retrieval is to bridge the semantic gap... more One of the challenges in the field of content-based image retrieval is to bridge the semantic gap that exists between the information extracted from visual data using classifiers, and the interpretation of this data made by the end users. The semantic gap is a cascade of 1) the transformation of image pixels into labelled objects and 2) the semantic distance between the label used to name the classifier and that what it refers to for the end-user. In this paper, we focus on the second part and specifically on (semantically) scalable solutions that are independent from domain-specific vocabularies. To this end, we propose a generic semantic reasoning approach that applies semiotics in its query interpretation. Semiotics is about how humans interpret signs, and we use its text analysis structures to guide the query expansion that we apply. We evaluated our approach using a general-purpose image search engine. In our experiments, we compared several semiotic structures to determine to ...
The TOSO data is the (toy and office-supplies objects) dataset. It contains a set of 145 test ima... more The TOSO data is the (toy and office-supplies objects) dataset. It contains a set of 145 test images used for the GOOSE demonstrator as described in: "Interactive detection of incrementally learned concepts in images with ranking and semantic query interpretation", Klamer Schutte , Henri Bouma , John Schavemaker , Laura Daniele , Maya Sappelli, Gijs Koot , Pieter Eendebak , George Azzopardi , Martijn Spitters , Maaike de Boer , Maarten Kruithof , Paul Brandt To be published 13th International Workshop on Content-Based Multimedia Indexing (CBMI) June 10.-12. 2015, Prague, Czech Republic
Abstract. Patient observations in health care, subjective surveys in social research or dyke sens... more Abstract. Patient observations in health care, subjective surveys in social research or dyke sensor data in water management are all examples of measurements. Several ontologies already exist to express measurements, W3C's SSN ontology being a prominent example. However, these ontologies address quantities and properties as being equal, and ignore the foundation required to establish comparability between sensor data. Moreover, a measure of an observation in itself is almost always inconclusive without the context in which the measure was obtained. ContoExam addresses these aspects, providing for a unifying capability for context-aware expressions of observations about quantities and properties alike, by aligning them to ontological foundations, and by binding observations inextricably with their context.
Video fingerprinting is een bewezen en commercieel verkrijgbare techniek die ingezet kan worden o... more Video fingerprinting is een bewezen en commercieel verkrijgbare techniek die ingezet kan worden om kopieen van of videomateriaal op te sporen. Video fingerprinting vergelijkt digitale video’s met elkaar en moet typisch kunnen omgaan met zaken zoals verschillende video codecs, veranderde resolutie, het plaatsen van een logo, niet gelijke frame rates, etc. Ontwikkelingen in dit gebied zijn vooral gestimuleerd door de media wereld, die er belang bij heeft verspreiding van illegale kopieen van videomateriaal tegen te gaan. Er zijn echter meerdere toepassingen, ieder met eigen karakteristieken. In dit engelstalige rapport geven wij een overzicht van de bestaande video fingerprinting technieken. Naast video fingerprinting kijken wij ook naar een aantal gerelateerde technieken zoals audio fingerprinting en objectherkenning in video’s. Voor elke technologie beschrijven wij de state-of-the-art en inventariseren wij bestaande, commerciele oplossingen.
One of the challenges in the field of content-based image retrieval is to bridge the semantic gap... more One of the challenges in the field of content-based image retrieval is to bridge the semantic gap that exists between the information extracted from visual data using classifiers, and the interpretation of this data made by the end users. The semantic gap is a cascade of 1) the transformation of image pixels into labelled objects and 2) the semantic distance between the label used to name the classifier and that what it refers to for the end-user. In this paper, we focus on the second part and specifically on (semantically) scalable solutions that are independent from domain-specific vocabularies. To this end, we propose a generic semantic reasoning approach that applies semiotics in its query interpretation. Semiotics is about how humans interpret signs, and we use its text analysis structures to guide the query expansion that we apply. We evaluated our approach using a general-purpose image search engine. In our experiments, we compared several semiotic structures to determine to ...
The objective of our work was to improve healthcare services supported by eHealth applications in... more The objective of our work was to improve healthcare services supported by eHealth applications in sub-Saharan Africa (SSA) by proposing interoperability that is proportional, in terms of costs and benefits, to immediate demands and is capable to enable future scenarios of growth. (e)Health represents a very complex system with many stakeholders, services and technologies, varying objectives and forces that play out on separate hierarchical levels with inconsistent and sometimes even contradicting prerequisites as well as requirements. To provide individual patients with the integrated care they need and to meet the distinct however interrelated interests of the other primary stakeholders and society alike, interoperability guidance is required. To improve effectiveness and efficiency of eHealth in SSA, interoperability solutions that stimulate and consolidate cooperation on various levels (e.g., local, district, national, international) and in different dimensions (e.g., social and ...
We describe the TNO system and the evaluation results for TRECVID 2013 Multimedia Event Detection... more We describe the TNO system and the evaluation results for TRECVID 2013 Multimedia Event Detection (MED) and instance search (INS) tasks. The MED system consists of a bag-of-word (BOW) approach with spatial tiling that uses low-level static and dynamic visual features, an audio feature and high-level concepts. Automatic speech recognition (ASR) and optical character recognition (OCR) are not used in the system. In the MED case with 100 example training videos, support-vector machines (SVM) are trained and fused to detect an event in the test set. In the case with 0 example videos, positive and negative concepts are extracted as keywords from the textual event description and events are detected with the high-level concepts. The MED results show that the SIFT keypoint descriptor is the one which contributes best to the results, fusion of multiple low-level features helps to improve the performance, and the textual event-description chain currently performs poorly. The TNO INS system p...
Abstract—With the growth of open sensor networks, multiple applications in different domains make... more Abstract—With the growth of open sensor networks, multiple applications in different domains make use of a large amount of sensor data, resulting in an emerging need to search semantically over heterogeneous datasets. In semantic search, an important challenge consists of bridging the semantic gap between the high-level natural language query posed by the users and the low-level sensor data. In this paper, we show that state-of-the-art techniques in Semantic Modelling, Computer Vision and Human Media Interaction can be combined to apply semantic reasoning in the field of image retrieval. We propose a system, GOOSE, which is a general-purpose search engine that allows users to pose natural language queries to retrieve corresponding images. User queries are interpreted using the Stanford Parser, semantic rules and the Linked Open Data source ConceptNet. Interpreted queries are presented to the user as an intuitive and insightful graph in order to collect feedback that is used for furt...
2015 13th International Workshop on Content-Based Multimedia Indexing (CBMI), 2015
ABSTRACT The number of networked cameras is growing exponentially. Multiple applications in diffe... more ABSTRACT The number of networked cameras is growing exponentially. Multiple applications in different domains result in an increasing need to search semantically over video sensor data. In this paper, we present the GOOSE demonstrator, which is a real-time general-purpose search engine that allows users to pose natural language queries to retrieve corresponding images. Top-down, this demonstrator interprets queries, which are presented as an intuitive graph to collect user feedback. Bottom-up, the system automatically recognizes and localizes concepts in images and it can incrementally learn novel concepts. A smart ranking combines both and allows effective retrieval of relevant images.
Personal independence and active societal participation up to a high age call for a good open-sys... more Personal independence and active societal participation up to a high age call for a good open-system architecture and plugand-play applications preventing 'vendor lock in'. The supportive software which uses the ICT hardware infrastructure is the subject of this contribution. TCP/IP forms the standard for exchanging data, however, for turning data into information a number of (vendor-based) protocols are currently available. XML, the eXtensible Markup Language, as formulated in 1998, may become the de facto standard due to its popularity and its management by a number of standards development organizations. Like any ordinary language, XML has grammar and domain vocabularies. Established domain vocabularies used for delivering care services include HL7 (clinical data and practices) and CCR (care data in real-time). In addition, semantic web applications are expressed in XML and the architecture of a plugand-play environment has been formed in SOA (Service Oriented Architectures). Mass-individualized teleservices so urgently needed in our aging society, may be realized through extensive use of XML.
Patient observations in health care, subjective surveys in social research or dyke sensor data in... more Patient observations in health care, subjective surveys in social research or dyke sensor data in water management are all examples of measurements. Several ontologies already exist to express measurements, W3C's SSN ontology being a prominent example. However, these ontologies address quantities and properties as being equal, and ignore the foundation required to establish comparability between sensor data. Moreover, a measure of an observation in itself is almost always inconclusive without the context in which the measure was obtained. ContoExam addresses these aspects, providing for a unifying capability for context-aware expressions of observations about quantities and properties alike, by aligning them to ontological foundations, and by binding observations inextricably with their context.
Background The lack of knowledge about the intra- and interindividual attack frequency variabilit... more Background The lack of knowledge about the intra- and interindividual attack frequency variability in chronic cluster headache complicates power and sample size calculations for baseline periods of trials, and consensus on their most optimal duration. Methods We analyzed the 12-week baseline of the ICON trial (occipital nerve stimulation in medically intractable chronic cluster headache) for: (i) weekly vs. instantaneous recording of attack frequency; (ii) intra-individual and seasonal variability of attack frequency; and (iii) the smallest number of weeks to obtain a reliable estimate of baseline attack frequency. Results Weekly median (14.4 [8.2–24.0]) and instantaneous (14.2 [8.0–24.5]) attack frequency recordings were similar (p = 0.20; Bland-Altman plot). Median weekly attack frequency was 15.3 (range 4.2–140) and highest during spring (p = 0.001) compared to the other seasons. Relative attack frequency variability decreased with increasing attack frequency (p = 0.010). We tabu...
This deliverable presents the first version of a generic federated OOP architecture, supporting i... more This deliverable presents the first version of a generic federated OOP architecture, supporting interconnection and interoperability of national registries at the EU level. The architecture is in line with existing EU frameworks (EIRA, EIF), takes into account the e-SENS European Interoperability Reference Architecture and is based on the CEF DSIs and the Building Blocks consolidated by the e-SENS project. The first version focuses on interoperability at business and information level, to be extended iteratively in the future versions. The deliverable includes, among others, the requirements, the initial building blocks, and the interface specifications of the generic federated architecture. The overall logic of the deliverable emerges from the principle of reusing existing frameworks and building blocks provided by CEF, e-SENS, and other initiatives. As the first step, an initial inventory of existing e- Government Building Blocks is proposed. Then the principles of selection of bu...
This document presents the second official version of the generic federated OOP architecture. It ... more This document presents the second official version of the generic federated OOP architecture. It develops further and extends the deliverable "D2.1. Generic federated OOP architecture (1st version)" (D2.1). The architecture supports interconnection and interoperability of national registries at the EU level, is in line with existing EU frameworks (EIRA, EIF), takes into account the forthcoming regulation about the Single Digital Gateway (SDGR), and uses results of the e-SENS European Interoperability Reference Architecture. It provides support for future developers of OOP projects and is based on the Connecting Europe Facility (CEF) Digital Service Infrastructures (DSIs), the Building Blocks consolidated by the e-SENS project, and in justified cases, on the new building blocks. Compared to the first version D2.1, this deliverable develops the architecture further, aligns it with the provisions of the forthcoming regulation about the Single Digital Gateway, and focusses on ...
One of the challenges in the field of content-based image retrieval is to bridge the semantic gap... more One of the challenges in the field of content-based image retrieval is to bridge the semantic gap that exists between the information extracted from visual data using classifiers, and the interpretation of this data made by the end users. The semantic gap is a cascade of 1) the transformation of image pixels into labelled objects and 2) the semantic distance between the label used to name the classifier and that what it refers to for the end-user. In this paper, we focus on the second part and specifically on (semantically) scalable solutions that are independent from domain-specific vocabularies. To this end, we propose a generic semantic reasoning approach that applies semiotics in its query interpretation. Semiotics is about how humans interpret signs, and we use its text analysis structures to guide the query expansion that we apply. We evaluated our approach using a general-purpose image search engine. In our experiments, we compared several semiotic structures to determine to ...
The TOSO data is the (toy and office-supplies objects) dataset. It contains a set of 145 test ima... more The TOSO data is the (toy and office-supplies objects) dataset. It contains a set of 145 test images used for the GOOSE demonstrator as described in: "Interactive detection of incrementally learned concepts in images with ranking and semantic query interpretation", Klamer Schutte , Henri Bouma , John Schavemaker , Laura Daniele , Maya Sappelli, Gijs Koot , Pieter Eendebak , George Azzopardi , Martijn Spitters , Maaike de Boer , Maarten Kruithof , Paul Brandt To be published 13th International Workshop on Content-Based Multimedia Indexing (CBMI) June 10.-12. 2015, Prague, Czech Republic
Abstract. Patient observations in health care, subjective surveys in social research or dyke sens... more Abstract. Patient observations in health care, subjective surveys in social research or dyke sensor data in water management are all examples of measurements. Several ontologies already exist to express measurements, W3C's SSN ontology being a prominent example. However, these ontologies address quantities and properties as being equal, and ignore the foundation required to establish comparability between sensor data. Moreover, a measure of an observation in itself is almost always inconclusive without the context in which the measure was obtained. ContoExam addresses these aspects, providing for a unifying capability for context-aware expressions of observations about quantities and properties alike, by aligning them to ontological foundations, and by binding observations inextricably with their context.
Video fingerprinting is een bewezen en commercieel verkrijgbare techniek die ingezet kan worden o... more Video fingerprinting is een bewezen en commercieel verkrijgbare techniek die ingezet kan worden om kopieen van of videomateriaal op te sporen. Video fingerprinting vergelijkt digitale video’s met elkaar en moet typisch kunnen omgaan met zaken zoals verschillende video codecs, veranderde resolutie, het plaatsen van een logo, niet gelijke frame rates, etc. Ontwikkelingen in dit gebied zijn vooral gestimuleerd door de media wereld, die er belang bij heeft verspreiding van illegale kopieen van videomateriaal tegen te gaan. Er zijn echter meerdere toepassingen, ieder met eigen karakteristieken. In dit engelstalige rapport geven wij een overzicht van de bestaande video fingerprinting technieken. Naast video fingerprinting kijken wij ook naar een aantal gerelateerde technieken zoals audio fingerprinting en objectherkenning in video’s. Voor elke technologie beschrijven wij de state-of-the-art en inventariseren wij bestaande, commerciele oplossingen.
One of the challenges in the field of content-based image retrieval is to bridge the semantic gap... more One of the challenges in the field of content-based image retrieval is to bridge the semantic gap that exists between the information extracted from visual data using classifiers, and the interpretation of this data made by the end users. The semantic gap is a cascade of 1) the transformation of image pixels into labelled objects and 2) the semantic distance between the label used to name the classifier and that what it refers to for the end-user. In this paper, we focus on the second part and specifically on (semantically) scalable solutions that are independent from domain-specific vocabularies. To this end, we propose a generic semantic reasoning approach that applies semiotics in its query interpretation. Semiotics is about how humans interpret signs, and we use its text analysis structures to guide the query expansion that we apply. We evaluated our approach using a general-purpose image search engine. In our experiments, we compared several semiotic structures to determine to ...
The objective of our work was to improve healthcare services supported by eHealth applications in... more The objective of our work was to improve healthcare services supported by eHealth applications in sub-Saharan Africa (SSA) by proposing interoperability that is proportional, in terms of costs and benefits, to immediate demands and is capable to enable future scenarios of growth. (e)Health represents a very complex system with many stakeholders, services and technologies, varying objectives and forces that play out on separate hierarchical levels with inconsistent and sometimes even contradicting prerequisites as well as requirements. To provide individual patients with the integrated care they need and to meet the distinct however interrelated interests of the other primary stakeholders and society alike, interoperability guidance is required. To improve effectiveness and efficiency of eHealth in SSA, interoperability solutions that stimulate and consolidate cooperation on various levels (e.g., local, district, national, international) and in different dimensions (e.g., social and ...
We describe the TNO system and the evaluation results for TRECVID 2013 Multimedia Event Detection... more We describe the TNO system and the evaluation results for TRECVID 2013 Multimedia Event Detection (MED) and instance search (INS) tasks. The MED system consists of a bag-of-word (BOW) approach with spatial tiling that uses low-level static and dynamic visual features, an audio feature and high-level concepts. Automatic speech recognition (ASR) and optical character recognition (OCR) are not used in the system. In the MED case with 100 example training videos, support-vector machines (SVM) are trained and fused to detect an event in the test set. In the case with 0 example videos, positive and negative concepts are extracted as keywords from the textual event description and events are detected with the high-level concepts. The MED results show that the SIFT keypoint descriptor is the one which contributes best to the results, fusion of multiple low-level features helps to improve the performance, and the textual event-description chain currently performs poorly. The TNO INS system p...
Abstract—With the growth of open sensor networks, multiple applications in different domains make... more Abstract—With the growth of open sensor networks, multiple applications in different domains make use of a large amount of sensor data, resulting in an emerging need to search semantically over heterogeneous datasets. In semantic search, an important challenge consists of bridging the semantic gap between the high-level natural language query posed by the users and the low-level sensor data. In this paper, we show that state-of-the-art techniques in Semantic Modelling, Computer Vision and Human Media Interaction can be combined to apply semantic reasoning in the field of image retrieval. We propose a system, GOOSE, which is a general-purpose search engine that allows users to pose natural language queries to retrieve corresponding images. User queries are interpreted using the Stanford Parser, semantic rules and the Linked Open Data source ConceptNet. Interpreted queries are presented to the user as an intuitive and insightful graph in order to collect feedback that is used for furt...
2015 13th International Workshop on Content-Based Multimedia Indexing (CBMI), 2015
ABSTRACT The number of networked cameras is growing exponentially. Multiple applications in diffe... more ABSTRACT The number of networked cameras is growing exponentially. Multiple applications in different domains result in an increasing need to search semantically over video sensor data. In this paper, we present the GOOSE demonstrator, which is a real-time general-purpose search engine that allows users to pose natural language queries to retrieve corresponding images. Top-down, this demonstrator interprets queries, which are presented as an intuitive graph to collect user feedback. Bottom-up, the system automatically recognizes and localizes concepts in images and it can incrementally learn novel concepts. A smart ranking combines both and allows effective retrieval of relevant images.
Personal independence and active societal participation up to a high age call for a good open-sys... more Personal independence and active societal participation up to a high age call for a good open-system architecture and plugand-play applications preventing 'vendor lock in'. The supportive software which uses the ICT hardware infrastructure is the subject of this contribution. TCP/IP forms the standard for exchanging data, however, for turning data into information a number of (vendor-based) protocols are currently available. XML, the eXtensible Markup Language, as formulated in 1998, may become the de facto standard due to its popularity and its management by a number of standards development organizations. Like any ordinary language, XML has grammar and domain vocabularies. Established domain vocabularies used for delivering care services include HL7 (clinical data and practices) and CCR (care data in real-time). In addition, semantic web applications are expressed in XML and the architecture of a plugand-play environment has been formed in SOA (Service Oriented Architectures). Mass-individualized teleservices so urgently needed in our aging society, may be realized through extensive use of XML.
Patient observations in health care, subjective surveys in social research or dyke sensor data in... more Patient observations in health care, subjective surveys in social research or dyke sensor data in water management are all examples of measurements. Several ontologies already exist to express measurements, W3C's SSN ontology being a prominent example. However, these ontologies address quantities and properties as being equal, and ignore the foundation required to establish comparability between sensor data. Moreover, a measure of an observation in itself is almost always inconclusive without the context in which the measure was obtained. ContoExam addresses these aspects, providing for a unifying capability for context-aware expressions of observations about quantities and properties alike, by aligning them to ontological foundations, and by binding observations inextricably with their context.
Uploads
Papers by Paul Brandt