| 1. |
- Björkelund, Anders, et al.
(författare)
-
On the Integration of Skilled Robot Motions for Productivity in Manufacturing
- 2011
-
Ingår i: IEEE International Symposium on Assembly and Manufacturing (ISAM), 2011. - 9781612843438 - 9781612843421 ; , s. 1-9
-
Konferensbidrag (refereegranskat)abstract
- Robots used in manufacturing today are tailored to their tasks by system integration based on expert knowledge concerning both production and machine control. For upcoming new generations of even more flexible robot solutions, in applications such as dexterous assembly, the robot setup and programming gets even more challenging. Reuse of solutions in terms of parameters, controls, process tuning, and of software modules in general then gets increasingly important. There has been valuable progress within reuse of automation solutions when machines comply with standards and behave according to nominal models. However, more flexible robots with sensor-based manipulation skills and congnitive functions for human inteaction are far too complex to manage, and solutions are rarely reusable since knowledge is either implicit in imperative software or not captured in machine readable form. We propose techniques that build on existing knowledge by converting structured data into an RDF-based knowledge base. By enhancements of industrial control systems and available engineering tools, such knowledge can be gradually extended as part of the interaction during the definition of the robot task.
|
|
| 2. |
- Björkelund, Anders, et al.
(författare)
-
A high-performance syntactic and semantic dependency parser
- 2010
-
Ingår i: [Host publication title missing]. ; , s. 33-36
-
Konferensbidrag (refereegranskat)abstract
- This demonstration presents a highperformance syntactic and semantic dependency parser. The system consists of a pipeline of modules that carry out the tokenization, lemmatization, part-of-speech tagging, dependency parsing, and semantic role labeling of a sentence. The system’s two main components draw on improved versions of a state-of-the-art dependency parser (Bohnet, 2009) and semantic role labeler (Björkelund et al., 2009) developed independently by the authors. The system takes a sentence as input and produces a syntactic and semantic annotation using the CoNLL 2009 format. The processing time needed for a sentence typically ranges from 10 to 1000 milliseconds. The predicate–argument structures in the final output are visualized in the form of segments, which are more intuitive for a user.
|
|
| 3. |
- Björkelund, Anders, et al.
(författare)
-
Exploring Lexicalized Features for Coreference Resolution
- 2011
-
Ingår i: CoNLL 2011 - 15th Conference on Computational Natural Language Learning: Shared Task, Proceedings. - 9781937284084 ; , s. 45-50
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we describe a coreference solver based on the extensive use of lexical features and features extracted from dependency graphs of the sentences. The solver uses Soon et al. (2001)'s classical resolution algorithm based on a pairwise classification of the mentions. We applied this solver to the closed track of the CoNLL 2011 shared task (Pradhan et al., 2011). We carried out a systematic optimization of the feature set using cross-validation that led us to retain 24 features. Using this set, we reached a MUC score of 58.61 on the test set of the shared task. We analyzed the impact of the features on the development set and we show the importance of lexicalization as well as of properties related to dependency links in coreference resolution.
|
|
| 4. |
- Björkelund, Anders, et al.
(författare)
-
Knowledge and Skill Representations for Robotized Production
- 2011
-
Ingår i: Proceedings of the 18th IFAC World Congress, 2011. - 1474-6670. - 9783902661937 ; , s. 8999-9004
-
Konferensbidrag (refereegranskat)abstract
- Model-based systems in control are a means to utilize efficiently human knowledge and achieve high performance. While models consisting of formalized knowledge are used during the engineering step, running systems usually do not contain a high-level, symbolic representation of the control and most of its properties, typically named numerical parameters. On a system level and beyond the plant data, there is also a need to represent the meaning of the data such that deployment and fault analysis could be augmented with partly automated inference based on the semantics of the data. To that end, we extended the formalized knowledge traditionally used in control to include the control purpose, engineering assumption, quality, involved state machines, and so on. We then represented the control semantics in a format that allows an easier extraction of information using querying and reasoning. It aims at making knowledge in control engineering reusable so that it can be shipped together with the control systems. We implemented prototypes that include automatic conversion of plant data from AutomationML into RDF triples, as well as the automated extraction of control properties, the conversion of parameters, and their storage in the same triple store. Although these techniques are standard within the semantic web community, we believe that our robotic prototypes for semantic control represent a novel approach.
|
|
| 5. |
- Björkelund, Anders, et al.
(författare)
-
Knowledge for Intelligent Industrial Robots
- 2012
-
Ingår i: AAAI Technical Report SS-12-02, Designing Intelligent Robots: Reintegrating AI. - 9781577355519 ; SS-12-02
-
Konferensbidrag (refereegranskat)abstract
- This paper describes an attempt to provide more intelligence to industrial robotics and automation systems. We develop an architecture to integrate disparate knowledge representations used in different places in robotics and automation. This knowledge integration framework, a possibly distributed entity, abstracts the components used in design or production as data sources, and provides a uniform access to them via standard interfaces. Representation is based on the ontology formalizing the process, product and resource triangle, where skills are considered the common element of the three. Production knowledge is being collected now and a preliminary version of KIF undergoes verification.
|
|
| 6. |
|
|
| 7. |
- Hellgren, Margareta, 1955, et al.
(författare)
-
Feasibility of the FINDRISC questionnaire to identify individuals with impaired glucose tolerance in Swedish primary care. A cross-sectional population-based study.
- 2012
-
Ingår i: Diabetic Medicine. - : Wiley. - 1464-5491 .- 0742-3071. ; 29:12, s. 1501-1505
-
Tidskriftsartikel (refereegranskat)abstract
- Aim: To evaluate the performance of the FINDRISC questionnaire as a tool to recruit individuals with impaired glucose tolerance for lifestyle intervention programmes. Methods: A cross-sectional population-based study in primary Health Care Centres in a middle-sized Swedish town. All 9734 individuals, aged 35–75 years, living within a defined area, were invited by mail to fill in and return the FINDRISC questionnaire. Participants with a risk score ≥ 15 (n = 525) were invited to perform an oral glucose tolerance test while those with known diabetes were excluded. Results: In total, 5452 questionnaires (58%) were returned and revealed a mean risk-score of 8.5 ± 4.5 (mean ± SD). We found that 525 participants had a risk-score ≥ 15 and 302 (58%) were further examined with an oral glucose tolerance testing (OGTT). Among them we detected 11% with previously undiagnosed Type 2 diabetes, 16% with impaired glucose tolerance and 29% with impaired fasting glucose. A FINDRISC score ≥ 15 was associated with a positive predictive value of 55% for impaired glucose metabolism (impaired fasting glucose + impaired glucose tolerance + Type 2 diabetes) and of 16% for impaired glucose tolerance, respectively. The positive predictive value for impaired glucose tolerance did not increase to more than 17% when choosing the cut-point 17, while there was a significant increase in the positive predictive value for impaired glucose metabolism (70%). Conclusions: The FINDRISC questionnaire is a useful instrument for identification of individuals with impaired glucose metabolism but seems less effective for detection of individuals with impaired glucose tolerance. Strategies to find individuals with impaired glucose tolerance for implementation of lifestyle changes in primary care should therefore be developed further.
|
|
| 8. |
|
|
| 9. |
- Persson, Jacob, et al.
(författare)
-
A knowledge integration framework for robotics
- 2010
-
Ingår i: ISR/ROBOTIK 2010 : Proceedings for the joint conference of ISR 2010 (41st International Symposium on Robotics) and ROBOTIK 2010 (6th German Conference on Robotics). - 9783800732739
-
Konferensbidrag (refereegranskat)abstract
- This paper describes a knowledge integration framework for robotics, whose goal is to represent, store, adapt, and distribute knowledge across engineering platforms. The architecture abstracts the components as data sources, where data are available in the AutomationML data exchange format. AutomationML is an on-going standard initiative that aims at unifying data representation and APIs used by engineering tools. A triplification procedure converts native formats used by data sources into RDF triples and then exposes them via a SPARQL endpoint. The triplification step has been implemented for the CAEX top level and logic data parts of AutomationML, where the conversion uses XSLT rules.
|
|
| 10. |
|
|
