3 Search Results for "Zhu, Rui"


Document
Automatically Discovering Conceptual Neighborhoods Using Machine Learning Methods

Authors: Ling Cai, Krzysztof Janowicz, and Rui Zhu

Published in: LIPIcs, Volume 240, 15th International Conference on Spatial Information Theory (COSIT 2022)


Abstract
Qualitative spatio-temporal reasoning (QSTR) plays a key role in spatial cognition and artificial intelligence (AI) research. In the past, research and applications of QSTR have often taken place in the context of declarative forms of knowledge representation. For instance, conceptual neighborhoods (CN) and composition tables (CT) of relations are introduced explicitly and utilized for spatial/temporal reasoning. Orthogonal to this line of study, we focus on bottom-up machine learning (ML) approaches to investigate QSTR. More specifically, we are interested in questions of whether similarities between qualitative relations can be learned from data purely based on ML models, and, if so, how these models differ from the ones studied by traditional approaches. To achieve this, we propose a graph-based approach to examine the similarity of relations by analyzing trained ML models. Using various experiments on synthetic data, we demonstrate that the relationships discovered by ML models are well-aligned with CN structures introduced in the (theoretical) literature, for both spatial and temporal reasoning. Noticeably, even with significantly limited qualitative information for training, ML models are still able to automatically construct neighborhood structures. Moreover, patterns of asymmetric similarities between relations are disclosed using such a data-driven approach. To the best of our knowledge, our work is the first to automatically discover CNs without any domain knowledge. Our results can be applied to discovering CNs of any set of jointly exhaustive and pairwise disjoint (JEPD) relations.

Cite as

Ling Cai, Krzysztof Janowicz, and Rui Zhu. Automatically Discovering Conceptual Neighborhoods Using Machine Learning Methods. In 15th International Conference on Spatial Information Theory (COSIT 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 240, pp. 3:1-3:14, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2022)


Copy BibTex To Clipboard

@InProceedings{cai_et_al:LIPIcs.COSIT.2022.3,
  author =	{Cai, Ling and Janowicz, Krzysztof and Zhu, Rui},
  title =	{{Automatically Discovering Conceptual Neighborhoods Using Machine Learning Methods}},
  booktitle =	{15th International Conference on Spatial Information Theory (COSIT 2022)},
  pages =	{3:1--3:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-257-0},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{240},
  editor =	{Ishikawa, Toru and Fabrikant, Sara Irina and Winter, Stephan},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.COSIT.2022.3},
  URN =		{urn:nbn:de:0030-drops-168884},
  doi =		{10.4230/LIPIcs.COSIT.2022.3},
  annote =	{Keywords: Qualitative Spatial Reasoning, Qualitative Temporal Reasoning, Conceptual Neighborhood, Machine Learning, Knowledge Discovery}
}
Document
xNet+SC: Classifying Places Based on Images by Incorporating Spatial Contexts

Authors: Bo Yan, Krzysztof Janowicz, Gengchen Mai, and Rui Zhu

Published in: LIPIcs, Volume 114, 10th International Conference on Geographic Information Science (GIScience 2018)


Abstract
With recent advancements in deep convolutional neural networks, researchers in geographic information science gained access to powerful models to address challenging problems such as extracting objects from satellite imagery. However, as the underlying techniques are essentially borrowed from other research fields, e.g., computer vision or machine translation, they are often not spatially explicit. In this paper, we demonstrate how utilizing the rich information embedded in spatial contexts (SC) can substantially improve the classification of place types from images of their facades and interiors. By experimenting with different types of spatial contexts, namely spatial relatedness, spatial co-location, and spatial sequence pattern, we improve the accuracy of state-of-the-art models such as ResNet - which are known to outperform humans on the ImageNet dataset - by over 40%. Our study raises awareness for leveraging spatial contexts and domain knowledge in general in advancing deep learning models, thereby also demonstrating that theory-driven and data-driven approaches are mutually beneficial.

Cite as

Bo Yan, Krzysztof Janowicz, Gengchen Mai, and Rui Zhu. xNet+SC: Classifying Places Based on Images by Incorporating Spatial Contexts. In 10th International Conference on Geographic Information Science (GIScience 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 114, pp. 17:1-17:15, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@InProceedings{yan_et_al:LIPIcs.GISCIENCE.2018.17,
  author =	{Yan, Bo and Janowicz, Krzysztof and Mai, Gengchen and Zhu, Rui},
  title =	{{xNet+SC: Classifying Places Based on Images by Incorporating Spatial Contexts}},
  booktitle =	{10th International Conference on Geographic Information Science (GIScience 2018)},
  pages =	{17:1--17:15},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-083-5},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{114},
  editor =	{Winter, Stephan and Griffin, Amy and Sester, Monika},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GISCIENCE.2018.17},
  URN =		{urn:nbn:de:0030-drops-93450},
  doi =		{10.4230/LIPIcs.GISCIENCE.2018.17},
  annote =	{Keywords: Spatial context, Image classification, Place types, Convolutional neural network, Recurrent neural network}
}
Document
Order-Preserving Pattern Matching Indeterminate Strings

Authors: Rui Henriques, Alexandre P. Francisco, Luís M. S. Russo, and Hideo Bannai

Published in: LIPIcs, Volume 105, 29th Annual Symposium on Combinatorial Pattern Matching (CPM 2018)


Abstract
Given an indeterminate string pattern p and an indeterminate string text t, the problem of order-preserving pattern matching with character uncertainties (muOPPM) is to find all substrings of t that satisfy one of the possible orderings defined by p. When the text and pattern are determinate strings, we are in the presence of the well-studied exact order-preserving pattern matching (OPPM) problem with diverse applications on time series analysis. Despite its relevance, the exact OPPM problem suffers from two major drawbacks: 1) the inability to deal with indetermination in the text, thus preventing the analysis of noisy time series; and 2) the inability to deal with indetermination in the pattern, thus imposing the strict satisfaction of the orders among all pattern positions. In this paper, we provide the first polynomial algorithms to answer the muOPPM problem when: 1) indetermination is observed on the pattern or text; and 2) indetermination is observed on both the pattern and the text and given by uncertainties between pairs of characters. First, given two strings with the same length m and O(r) uncertain characters per string position, we show that the muOPPM problem can be solved in O(mr lg r) time when one string is indeterminate and r in N^+ and in O(m^2) time when both strings are indeterminate and r=2. Second, given an indeterminate text string of length n, we show that muOPPM can be efficiently solved in polynomial time and linear space.

Cite as

Rui Henriques, Alexandre P. Francisco, Luís M. S. Russo, and Hideo Bannai. Order-Preserving Pattern Matching Indeterminate Strings. In 29th Annual Symposium on Combinatorial Pattern Matching (CPM 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 105, pp. 2:1-2:15, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@InProceedings{henriques_et_al:LIPIcs.CPM.2018.2,
  author =	{Henriques, Rui and Francisco, Alexandre P. and Russo, Lu{\'\i}s M. S. and Bannai, Hideo},
  title =	{{Order-Preserving Pattern Matching Indeterminate Strings}},
  booktitle =	{29th Annual Symposium on Combinatorial Pattern Matching (CPM 2018)},
  pages =	{2:1--2:15},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-074-3},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{105},
  editor =	{Navarro, Gonzalo and Sankoff, David and Zhu, Binhai},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CPM.2018.2},
  URN =		{urn:nbn:de:0030-drops-87087},
  doi =		{10.4230/LIPIcs.CPM.2018.2},
  annote =	{Keywords: Order-preserving pattern matching, Indeterminate string analysis, Generic pattern matching, Satisfiability}
}
  • Refine by Author
  • 2 Janowicz, Krzysztof
  • 2 Zhu, Rui
  • 1 Bannai, Hideo
  • 1 Cai, Ling
  • 1 Francisco, Alexandre P.
  • Show More...

  • Refine by Classification
  • 1 Computing methodologies → Computer vision tasks
  • 1 Computing methodologies → Knowledge representation and reasoning
  • 1 Computing methodologies → Machine learning
  • 1 Computing methodologies → Neural networks
  • 1 Computing methodologies → Spatial and physical reasoning
  • Show More...

  • Refine by Keyword
  • 1 Conceptual Neighborhood
  • 1 Convolutional neural network
  • 1 Generic pattern matching
  • 1 Image classification
  • 1 Indeterminate string analysis
  • Show More...

  • Refine by Type
  • 3 document

  • Refine by Publication Year
  • 2 2018
  • 1 2022

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail