Filters








53,458 Hits in 4.7 sec

Inferring Position Knowledge from Location Predicates [chapter]

Jörg Roth
Location- and Context-Awareness  
Often, position data is thus merged from a set of systems, each contributing a piece of position knowledge.  ...  Many context-and location-aware applications request high accuracy and availability of positioning systems.  ...  Conclusion and Future Work In this paper we presented the new MAP 3 approach that infers knowledge about the current position from sets of location predicates.  ... 
doi:10.1007/978-3-540-75160-1_15 dblp:conf/loca/Roth07 fatcat:utt66vwrnnc63fchdx5ebcltru

Using context with statistical relational models

Chen Wu, Hamid Aghajan
2009 Proceedings of the Workshop on Use of Context in Vision Processing - UCVP '09  
The user's activity is analyzed from images of cameras installed in the home. Relationship between user activity and objects is defined in a knowledge base with MLN.  ...  Experiments show that objects in the home can be recognized irrespective of their position, size and appearance in the image.  ...  Model prior knowledge of object functions in Markov logic network. 3. Infer location and identity of objects from observations of user activity.  ... 
doi:10.1145/1722156.1722161 fatcat:q2lbkghi3vha3e33o2enjfder4

Inferring User Preferences by Probabilistic Logical Reasoning over Social Networks [article]

Jiwei Li, Alan Ritter, Dan Jurafsky
2014 arXiv   pre-print
The algorithm uses distant supervision, semi-supervised data harvesting and vector space models to extract user attributes (e.g. spouse, education, location) and preferences (likes and dislikes) from text  ...  by building a probabilistic model that reasons over user attributes (the user's location or gender) and the social network (the user's friends and spouse), via inferences like homophily (I am more likely  ...  User Attributes: Location The goal of location inference is to identify the US state the user tweets from, out of the 50 states.  ... 
arXiv:1411.2679v1 fatcat:kxeh577o25ghvhbouh3binrs74

Grounded spatial symbols for task planning based on experience

Kai Welke, Peter Kaiser, Alexey Kozlov, Nils Adermann, Tamim Asfour, Mike Lewis, Mark Steedman
2013 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)  
We demonstrate how spatial knowledge can be extracted from these two sources of experience.  ...  This representation is grounded on the sensorimotor level by means of exploration and on the language level by making use of common sense knowledge.  ...  ACKNOWLEDGMENT The research leading to these results has received funding from the European Union Seventh Framework Programme FP7/2007-2013 under grant agreement N o 270273 (Xperience).  ... 
doi:10.1109/humanoids.2013.7030018 dblp:conf/humanoids/WelkeKKAALS13 fatcat:a6avmppfbfhy7nt4say2ltgdsq

Parameterizing actions to have the appropriate effects

Lorenz Mosenlechner, Michael Beetz
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
A badly chosen put-down location can "block" trajectories for grasping other objects that were valid before and can even prevent the robot from reaching these objects.  ...  We demonstrate how we implement predicates that make use of OpenGL, the Bullet physics engine and inverse kinematics calculation.  ...  To infer the predicates from a scene, we first need to generate a scene from a symbolic representation of the world.  ... 
doi:10.1109/iros.2011.6094883 dblp:conf/iros/MosenlechnerB11 fatcat:vowrw7dpqngidbhkbzmh6g6u2a

Inference and Plausible Reasoning in a Natural Language Understanding System Based on Object-Oriented Semantics [article]

Yuriy Ostapov
2012 arXiv   pre-print
Such inference is necessary for logical questions when the direct comparison of objects from a question and database can not give a result.  ...  As a knowledge domain under consideration is social behavior of persons, plausible reasoning is based on laws of social psychology.  ...  An inference is inserted into these algorithms when the direct comparison of predicates from a question and database is insufficient to form an answer.  ... 
arXiv:1202.0116v1 fatcat:64qclk4qufeohdbno56ifc2uii

Model Checking for Sentient Computing: An Axiomatic Approach

Eleftheria Katsiri, Alan Mycroft
2005 International Conference on Mobile Data Management  
The authors' previous work [11, 12] proposes a model for inferring high-level, abstract knowledge from low-level, concrete knowledge, that is directly derived from sensors by means of frequent updates  ...  SCAFOS enables uses to infer high-level knowledge from low-level sensor-driven concrete knowledge. The work described in this paper is part of SCAFOS.  ... 
dblp:conf/mdm/KatsiriM05 fatcat:zmojiy6wefh33ewuotf7uukvci

Using situation lattices in sensor analysis

Juan Ye, Lorcan Coyle, Simon Dobson, Paddy Nixon
2009 2009 IEEE International Conference on Pervasive Computing and Communications  
parallel challenges: how to design a sensor suite that can efficiently and cost-effectively support the needs of given services; and to extract the semantically relevant interpretations, or "situations", from  ...  The domain knowledge can be the knowledge about an environment such as a location map, which defines the spatial containment, connectedness, and disjointness relationships between locations [22] .  ...  For example, the situation "dishwashing" should be identifiable if the positioning sensor can accurately locate the male subject's location (i.e., in the kitchen), and the faucet in the kitchen can recognise  ... 
doi:10.1109/percom.2009.4912762 dblp:conf/percom/YeCDN09 fatcat:tfs2wxxvujb4ni2gfbpbvtavly

Multi-agent event recognition in structured scenarios

Vlad I. Morariu, Larry S. Davis
2011 CVPR 2011  
logical inference to determine the most consistent sequence of events.  ...  Knowledge about spatiotemporal structure is encoded using first-order logic using an approach based on Allen's Interval Logic, and robustness to low-level observation uncertainty is provided by Markov  ...  As expected, most false positive hypotheses were removed (from 2302 to 279), but recall was reduced since some true positive hypotheses became false negatives after being labeled false by the MLN inference  ... 
doi:10.1109/cvpr.2011.5995386 dblp:conf/cvpr/MorariuD11 fatcat:kyq3ogkmbzcibdudcesqgl2ima

A knowledge-based system approach for a context-aware system

Nayat Sánchez-Pi, Javier Carbó, José Manuel Molina
2012 Knowledge-Based Systems  
The knowledge is usually derived from expertise in specific areas and has to be validated according to a different methodology than is used in conventional systems because the knowledge is symbolic.  ...  We also evaluate the context-aware information system from the user's point of view using a U2E system and also validate it through a simulated example in a realistic environment: an airport domain, which  ...  Inference knowledge configuration in Appear As explained abstractly, there are concepts in Appear, like predicates, context predicates and conditions (Fig. 14) , that are com-bined to create rules which  ... 
doi:10.1016/j.knosys.2011.08.017 fatcat:frsd22byvjbvtm2a2n3vybfnfq

Reasoning by Analogy Using Past Experiences

Fabio Leuzzi, Stefano Ferilli
2013 Italian Conference on Computational Logic  
∀t /t ∈ θ t , t is a term of l ∈ L in position w, t is a term of l ∈ L in position w, θ t and θ t are t-compatible, then θ t ← θ t ∪ θ t . Moreover, if exists a predicate mapping θ p s.t.  ...  For the predicates use/2, located/2, couldnotuse/2 and partof/2 there is no novelty.  ...  He positioned the low-intensity rays at multiple locations around the patient's body. The low intensity rays simultaneously converged on the tumor. In this way the rays destroyed the tumor."  ... 
dblp:conf/cilc/LeuzziF13 fatcat:rtbxskjyjzd7jmaewsqlv3rjoq

Learning Task Knowledge from Dialog and Web Access

Vittorio Perera, Robin Soetens, Thomas Kollar, Mehdi Samadi, Yichao Sun, Daniele Nardi, René van de Molengraft, Manuela Veloso
2015 Robotics  
OpenEval for object location inference; (c) Learned knowledge base with "7602" being the room number of location "kitchen".  ...  The instances that serve as positive examples of one predicate are negative examples of the others [48] .  ... 
doi:10.3390/robotics4020223 fatcat:4yzwwl2sfndazkurawikmly2v4

Extending effect annotation with lexical decomposition

Josef Ruppenhofer, Jasper Brandes
2015 Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis  
We extend the theory and present an extensive scheme that combines both approaches and thus extends the set of inference-relevant predicates.  ...  In this contribution, we report on an effort to annotate German data with information relevant to opinion inference.  ...  Pragmatic inference vs. lexical sentiment It is desirable to keep the positive/negative state characterization of a predicate separate from any additional sentiment that the predicate may carry.  ... 
doi:10.18653/v1/w15-2910 dblp:conf/wassa/RuppenhoferB15 fatcat:5r2uh763afaaxi325fvg37lkl4

Inductive Learning of the Surgical Workflow Model through Video Annotations

Hirenkumar Nakawala, Elena de Momi, Laura Erica Pescatori, Anna Morelli, Giancarlo Ferrigno
2017 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS)  
With the expansion of new technologies, large video archive can be created and annotated exploiting and storing the expert's knowledge.  ...  Predicates are either true or false. Annotations were used to specify target predicates, e.g. relation between phase and anatomical location, for surgical workflow description.  ...  a set of examples, which produces, by induction, the new knowledge or construct a set of constraints inference rules that participate to build the workflow of the surgery.  ... 
doi:10.1109/cbms.2017.91 dblp:conf/cbms/NakawalaMPMF17 fatcat:a2gro3r3mffdvkn2piuheqvgz4

Verifying the robustness of opinion inference

Josef Ruppenhofer, Jasper Brandes
2016 Conference on Natural Language Processing  
There is increasing interest in recognizing opinion inferences in addition to expressions of explicit sentiment.  ...  representing inferential mechanisms are being developed and lexical resources are being built alongside, we here address the need for deeper investigation of the robustness of various aspects of opinion inference  ...  Location This functor covers predicates entailing a state of location, e.g. in/out of ; at/away from and enter/exit. We will use the Similarity functor in our crowdsourcing experiments.  ... 
dblp:conf/konvens/RuppenhoferB16 fatcat:ciggmc7olfchxpuxbay5wp2ym4
« Previous Showing results 1 — 15 out of 53,458 results