Search results for "artificial intelligence"
showing 10 items of 6122 documents
Autonomic behaviors in an Ambient Intelligence system
2014
Ambient Intelligence (AmI) systems are constantly evolving and becoming ever more complex, so it is increasingly difficult to design and develop them successfully. Moreover, because of the complexity of an AmI system as a whole, it is not always easy for developers to predict its behavior in the event of unforeseen circumstances. A possible solution to this problem might lie in delegating certain decisions to the machines themselves, making them more autonomous and able to self-configure and self-manage, in line with the paradigm of Autonomic Computing. In this regard, many researchers have emphasized the importance of adaptability in building agents that are suitable to operate in real-wor…
Physical simulation for real-time image/video retargeting
2012
Retargeting methods present content on arbitrary aspect ratio me- dia displays limiting distortions in relevant objects. This is done by means of applying non-homogeneous resizing operators across the whole media, constraining it to fit into the required size. Several succesful systems have been proposed to achieve image retargeting, while video retargeting is still challenging due to time consistency and computational complexity requirements. Two important con- tributes were proposed: non-homogeneous retargeting [Wolf et al. 2007] and improved seam-carving [Rubinstein et al. 2008]. The first one claims to achieve real-time performance but considers spa- tial coordinates separately. The lat…
Dialog Structure Automatic Modeling
2010
This paper presents the approach implemented as part of a conversational bot named WIH (Word Intelligent Handler). It has a complex architecture with several components. Some of them are the ER-memory, EP-memory and other minor modules that provide the prototype of good modeling of Spanish sentences. They constitute the knowledge-representation mechanism that is used by WIH to build automatic answers during dialogs with humans. In this paper a small description of these components and some of its interaction is given, along with test cases and a statistical analysis of the results obtained. It is shown here that WIH prototype can adapt its behavior and learning rate of its internal working …
Preventing Overlaps in Agglomerative Hierarchical Conceptual Clustering
2020
Hierarchical Clustering is an unsupervised learning task, whi-ch seeks to build a set of clusters ordered by the inclusion relation. It is usually assumed that the result is a tree-like structure with no overlapping clusters, i.e., where clusters are either disjoint or nested. In Hierarchical Conceptual Clustering (HCC), each cluster is provided with a conceptual description which belongs to a predefined set called the pattern language. Depending on the application domain, the elements in the pattern language can be of different nature: logical formulas, graphs, tests on the attributes, etc. In this paper, we tackle the issue of overlapping concepts in the agglomerative approach of HCC. We …
Special interpretation of formal measurement scales for the case of multiple heterogeneous properties
2001
A formal model of measurement is constructed and its components are outlined in this paper. An integrated hierarchical formal four-level structure which allows description of the multiple heterogeneous properties of a complex object under measurement is developed in order to have a uniform tool for the selection of specific scales for the measurement of these properties. A special treatment of a measurement scale defined on the space of the object states is offered, and corresponding structures of basic types of scales are explained permitting to take into consideration distances between relations on these states. Our approach can serve as the uniform formalised basis for development of mea…
An In-Depth Experimental Comparison of RNTNs and CNNs for Sentence Modeling
2017
The goal of modeling sentences is to accurately represent their meaning for different tasks. A variety of deep learning architectures have been proposed to model sentences, however, little is known about their comparative performance on a common ground, across a variety of datasets, and on the same level of optimization. In this paper, we provide such a novel comparison for two popular architectures, Recursive Neural Tensor Networks (RNTNs) and Convolutional Neural Networks (CNNs). Although RNTNs have been shown to work well in many cases, they require intensive manual labeling due to the vanishing gradient problem. To enable an extensive comparison of the two architectures, this paper empl…
More Than (Single) Text Comprehension? – On University Students’ Understanding of Multiple Documents
2020
The digital revolution has made a multitude of text documents from highly diverse perspectives on almost any topic easily available. Accordingly, the ability to integrate and evaluate information from different sources, known as multiple document comprehension, has become increasingly important. Because multiple document comprehension requires the integration of content and source information across texts, it is assumed to exceed the demands of single text comprehension due to the inclusion of two additional mental representations: the integrated situation model and the intertext model. To date, there is little empirical evidence on commonalities and differences between single text and mult…
Analyzing the Effects of Lexical Cognates on Translation Properties: A Multivariate Product and Process Based Approach
2021
The translation of cognates has received renewed interest in Translation Process Research (Oster (2017) Empir Model Transl Interpret 7:23; Hansen-Schirra et al. (2017) Predicting cognate translation. In: Hansen-Schirra S, Czulo O, Hofmann S (eds) Empirical modelling of translation and interpreting. Language Science Press, Berlin, pp 3–22) but tends to be relatively time-consuming due to the manual identification of cognates and their translations. On the basis of work by Heilmann (Profiling effects of syntactic complexity in translation: a multi-method approach. PhD thesis, 2021) and the structure of the TPR-DB, we devised a relatively simple way to determine the cognate status of ST words …
An Analysis of the Internal Organization of Facebook Groups
2019
With the rapid development and growth of online social networks (OSNs), researchers have been pushed forward to improve the knowledge of these complex networks by analyzing several aspects, such as the types of social media, the structural properties of the network, or the interaction patterns among users. In particular, a relevant effort has been devoted to the study and identification of cohesive groups of users in OSNs (also referred as communities) because they are the basic building block of each OSN. While several research works on groups in OSNs have mainly focused on identifying the types of groups and the contents created by their members, the analysis of internal organizations of …
Logic for accumulation of design science research theory
2014
The paper introduces a structured logic for iterative and incremental accumulation of a design theory during a research project and across research programs. The logic is proposed to help researchers understand the links between parallel search spaces related to a particular design and linking to theoretical knowledge bases produced by previous search processes. The proposition rests on the notion that representing the structure and logic of design science research (DSR) theory using CIMO enables the elements of the knowledge base to be more easily evaluated, combined, and transferred between related search spaces. We view DSR theory development as an iterative and incremental social proces…