| 1. |
- Agrawal, Vikas, et al.
(författare)
-
The AAAI-13 Conference Workshops
- 2013
-
Ingår i: The AI Magazine. - : Association for the Advancement of Artificial Intelligence. - 0738-4602 .- 2371-9621. ; 34:4, s. 108-115
-
Tidskriftsartikel (refereegranskat)abstract
- The AAAI-13 Workshop Program, a part of the 27th AAAI Conference on Artificial Intelligence, was held Sunday and Monday, July 14-15, 2013, at the Hyatt Regency Bellevue Hotel in Bellevue, Washington, USA. The program included 12 workshops covering a wide range of topics in artificial intelligence, including Activity Context-Aware System Architectures (WS-13-05); Artificial Intelligence and Robotics Methods in Computational Biology (WS-13-06); Combining Constraint Solving with Mining and Learning (WS-13-07); Computer Poker and Imperfect Information (WS-13-08); Expanding the Boundaries of Health Informatics Using Artificial Intelligence (WS-13-09); Intelligent Robotic Systems (WS-13-10); Intelligent Techniques for Web Personalization and Recommendation (WS-13-11); Learning Rich Representations from Low-Level Sensors (WS-13-12); Plan, Activity,, and Intent Recognition (WS-13-13); Space, Time, and Ambient Intelligence (WS-13-14); Trading Agent Design and Analysis (WS-13-15); and Statistical Relational Artificial Intelligence (WS-13-16)
|
|
| 2. |
|
|
| 3. |
- Barreiro, Anabela, et al.
(författare)
-
Multi3Generation : Multitask, Multilingual, Multimodal Language Generation
- 2022
-
Ingår i: Proceedings of the 23rd Annual Conference of the European Association for Machine Translation. - : European Association for Machine Translation. ; , s. 345-346
-
Konferensbidrag (refereegranskat)abstract
- This paper presents the Multitask, Multilingual, Multimodal Language Generation COST Action – Multi3Generatio(CA18231), an interdisciplinary networof research groups working on different aspects of language generation. This "meta-paper" will serve as reference for citationof the Action in future publications. It presents the objectives, challenges and a the links for the achieved outcomes.
|
|
| 4. |
- Bhatt, Mehul, Professor, 1980-, et al.
(författare)
-
A Causal Perspective to Qualitative Spatial Reasoning in the Situation Calculus
- 2006
-
Ingår i: Advances in Artificial Intelligence - IBERAMIA-SBIA 2006. - Berlin, Heidelberg : Springer. - 9783540454625 - 9783540454649 ; , s. 430-440
-
Konferensbidrag (refereegranskat)abstract
- We propose the utilisation of a general formalism to reason about action & change for reasoning about the dynamic purpose-directed aspects of spatial change. Such an approach is necessary toward the general integration of qualitative spatial reasoning with reasoning about the teleological aspects of spatial change. With this as the overall context, the main contribution of this paper is to illustrate first ideas relevant to providing a causal perspective to qualitative spatial reasoning using the situation calculus. With minimal notions about space & spatial dynamics, we perform a naive characterisation of objects based on their physical properties and investigate the key representational aspects of a topological theory of space, namely the region connection calculus, in the situation calculus. Further, ontological distinctions are made between various occurrents, i.e., actions and internal & external events, and a domain level characterisation of spatial occurrents in terms of their spatial pre-conditions & effects is performed so as to provide a causal perspective to spatial reasoning.
|
|
| 5. |
- Bhatt, Mehul, Professor, 1980-, et al.
(författare)
-
A distributed approach to sub-ontology extraction
- 2004
-
Ingår i: 18th International Conference on Advanced Information Networking and Applications (AINA 2004), 29-31 March 2004, Fukuoka, Japan. - Los Alamitos : IEEE Computer Society. - 0769520510 - 9780769520513 ; , s. 636-641
-
Konferensbidrag (refereegranskat)abstract
- The new era of semantic web has enabled users to extract semantically relevant data from the web. The backbone of the semantic web is a shared uniform structure which defines how web information is split up regardless of the implementation language or the syntax used to represent the data. This structure is known as an ontology.As information on the web increases significantly in size, Web ontologies also tend to grow bigger to such an extent that they become too large to be used in their entirety by any single application. This has stimulated our work in the area of sub-ontology extraction where each user may extract optimized sub-ontologies from an existing base ontology.Sub-ontologies are valid independent ontologies, known as materialized ontologies, that are specifically extracted to meet certain needs. Because of the size of the original ontology, the process of repeatedly iterating the millions of nodes and relationships to form an optimized sub-ontology can be very extensive. Therefore we have identified the need for a distributed approach to the extraction process. As ontologies are currently widely used, our proposed approach for distributed ontology extraction will play an important role in improving the efficiency of information retrieval.
|
|
| 6. |
- Bhatt, Mehul, Professor, 1980-, et al.
(författare)
-
A General Framework Based on Dynamic Constraints for the Enrichment of a Topological Theory of Spatial Simulation
- 2005
-
Ingår i: Knowledge-Based Intelligent Information and Engineering Systems. - Berlin, Heidelberg : Springer. - 9783540288978 - 9783540319979 ; , s. 366-373
-
Konferensbidrag (refereegranskat)abstract
- Qualitative spatial representation and reasoning has emerged as a major sub-field of AI in the past decade. An important research problem within the field is that of integrated reasoning about various spatial aspects such as distance, size, topology etc - an important application here being the qualitative simulation of physical processes. Approaches based on topology alone fail to provide an explicit account of other important aspects of spatial change thereby also not utilizing dynamically available information pertaining to them. Our work in this paper is based on the idea that a general theory of spatial simulation based on topological changes alone can be enriched by the inclusion of sub-theories relevant to other aspects of spatial change. We propose a general framework consisting of dynamic constraints for the enrichment of a topological theory of spatial changes. We propose the utilisation of such dynamic constraints for the incorporation of dynamically available information relevant to various aspects of space thereby making that aspect explicit in the theory. As an example of the proposed approach, we integrate dynamically available information pertaining to motion and size with the topological theory of RCC-8 using our framework of dynamic constraints.
|
|
| 7. |
- Bhatt, Mehul, Professor, 1980-, et al.
(författare)
-
A Qualitative Model of Dynamic Scene Analysis and Interpretation in Ambient Intelligence Systems
- 2009
-
Ingår i: International Journal of Robotics and Automation. - : ACTA Press. - 0826-8185 .- 1925-7090. ; 24:3, s. 235-244
-
Tidskriftsartikel (refereegranskat)abstract
- Ambient intelligence environments necessitate representing and reasoning about dynamic spatial scenes and configurations. The ability to perform predictive and explanatory analyses of spatial scenes is crucial towards serving a useful intelligent function within such environments. We present a formal qualitative model that combines existing qualitative theories about space with it formal logic-based calculus suited to modelling dynamic environments, or reasoning about action and change in general. With this approach, it is possible to represent and reason about arbitrary dynamic spatial environments within a unified framework. We clarify and elaborate on our ideas with examples grounded in a smart environment.
|
|
| 8. |
- Bhatt, Mehul, Professor, 1980-, et al.
(författare)
-
Architecture, computing, and design assistance
- 2013
-
Ingår i: Automation in Construction. - : Elsevier. - 0926-5805 .- 1872-7891. ; 32, s. 161-164
-
Tidskriftsartikel (refereegranskat)abstract
- Design is one of the most complex of human endeavors requiring an enormous number of often conflicting criteria to be contemplated when identifying optimal solutions. Design is constrained by guidelines, codes, and standards applicable to the specific cultural and locational context that the design will be sited. Furthermore, a design has to be created within a collaborative team consisting of many professionals focused on specific subsystems and expert preferences that provide unique functionality to the overall design. The increasing use and capability of software tools involved in the creation and processing of such spatial information has also led to elevated levels of complexity that spurred a need to structure, query and reason about multiple spatial representations of buildings and their components in new ways.
|
|
| 9. |
- Bhatt, Mehul, Professor, 1980-, et al.
(författare)
-
Artificial Intelligence for Predictive and Evidence Based Architecture Design
- 2016
-
Ingår i: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16). - : AAAI press. - 9781577357605 ; , s. 4349-4350
-
Konferensbidrag (refereegranskat)abstract
- The evidence-based analysis of people's navigation and wayfinding behaviour in large-scale built-up environments (e.g., hospitals, airports) encompasses the measurement and qualitative analysis of a range of aspects including people's visual perception in new and familiar surroundings, their decision-making procedures and intentions, the affordances of the environment itself, etc. In our research on large-scale evidence-based qualitative analysis of wayfinding behaviour, we construe visual perception and navigation in built-up environments as a dynamic narrative construction process of movement and exploration driven by situation-dependent goals, guided by visual aids such as signage and landmarks, and influenced by environmental (e.g., presence of other people, time of day, lighting) and personal (e.g., age, physical attributes) factors. We employ a range of sensors for measuring the embodied visuo-locomotive experience of building users: eye-tracking, egocentric gaze analysis, external camera based visual analysis to interpret fine-grained behaviour (e.g., stopping, looking around, interacting with other people), and also manual observations made by human experimenters. Observations are processed, analysed, and integrated in a holistic model of the visuo-locomotive narrative experience at the individual and group level. Our model also combines embodied visual perception analysis with analysis of the structure and layout of the environment (e.g., topology, routes, isovists) computed from available 3D models of the building. In this framework, abstract regions like the visibility space, regions of attention, eye movement clusters, are treated as first class visuo-spatial and iconic objects that can be used for interpreting the visual experience of subjects in a high-level qualitative manner. The final integrated analysis of the wayfinding experience is such that it can even be presented in a virtual reality environment thereby providing an immersive experience (e.g., using tools such as the Oculus Rift) of the qualitative analysis for single participants, as well as for a combined analysis of large group. This capability is especially important for experiments in post-occupancy analysis of building performance. Our construction of indoor wayfinding experience as a form of moving image analysis centralizes the role and influence of perceptual visuo-spatial characteristics and morphological features of the built environment into the discourse on wayfinding research. We will demonstrate the impact of this work with several case-studies, particularly focussing on a large-scale experiment conducted at the New Parkland Hospital in Dallas Texas, USA.
|
|
| 10. |
- Bhatt, Mehul, Professor, 1980-, et al.
(författare)
-
Artificial Visual Intelligence : Perceptual Commonsense for Human-Centred Cognitive Technologies
- 2023
-
Ingår i: Human-Centered Artificial Intelligence. - : Springer. - 9783031243486 - 9783031243493 ; , s. 216-242
-
Bokkapitel (refereegranskat)abstract
- We address computational cognitive vision and perception at the interface of language, logic, cognition, and artificial intelligence. The chapter presents general methods for the processing and semantic interpretation of dynamic visuospatial imagery with a particular emphasis on the ability to abstract, learn, and reason with cognitively rooted structured characterisations of commonsense knowledge pertaining to space and motion. The presented work constitutes a systematic model and methodology integrating diverse, multi-faceted AI methods pertaining Knowledge Representation and Reasoning, Computer Vision, and Machine Learning towards realising practical, human-centred artificial visual intelligence.
|
|
