Search results for "categorization"
showing 10 items of 199 documents
Bagging and Boosting with Dynamic Integration of Classifiers
2000
One approach in classification tasks is to use machine learning techniques to derive classifiers using learning instances. The co-operation of several base classifiers as a decision committee has succeeded to reduce classification error. The main current decision committee learning approaches boosting and bagging use resampling with the training set and they can be used with different machine learning techniques which derive base classifiers. Boosting uses a kind of weighted voting and bagging uses equal weight voting as a combining method. Both do not take into account the local aspects that the base classifiers may have inside the problem space. We have proposed a dynamic integration tech…
Fuzzy gender categories: How emotional expression influences typicality *The authors would like to thank Fieke Harinck for her help in conducting Stu…
2001
Social categories are conceived of as broad classes in which some instances are better exemplars than others, and non-necessary features are assumed to modulate typicality. This research investigated how various emotional expressions impact on gender categorization. Two concurrent measures - response latencies and prototypicality judgments - were collected and compared in three experiments. The results showed that emotional expressions of any kind are highly relevant in modulating females' category membership, while they are of less relevance in making a male more or less prototypical. These findings provide new insights into the relation between gender and emotional expressions.
El capital psíquico. Aportes de la Psicología Positiva.
2006
The article presents a brief analysis of the central proposals of contemporary Positive Psychology. The notion of Psychologiocal Capital is presented and a proposal for categorization of its principal components in terms of cognitive, affective and psychosocial processes is explained.
The role of semantic distance in learning and generalization of novel names in typically developing and atypically developing children
2019
International audience; Children often learn the extension of novel words with a limited number of exemplars. There is evidence that the opportunity to compare stimuli is beneficial for learning and generalizing novel names in typically developing (TD) children. This is important since they are in need of well-devised learning situations. We manipulated the role of semantic distance within training stimuli and between training and test stimuli and their influence on taxonomically-based generalization. We hypothesized more difficulties for ID children especially in “larger” semantic distance cases. Our results revealed that ID children were better than the matched TD children, suggesting fun…
Rapid categorization of sound objects in anesthetized rats as indexed by the electrophysiological mismatch response
2014
It is not known whether animals can, similarly to humans, categorize auditory objects based on an abstract rule in combining their physical features. We recorded local-field potentials from the dura above the primary auditory cortex in urethane-anesthetized rats presented with sound series occasionally violating a rule (e.g., "the higher the frequency, the weaker the intensity"). In a separate control condition, the same frequency and intensity levels were applied in the sound objects, but they obeyed no rule. Responses found selectively to the violations of the rule suggest that an abstract rule was represented in the rat brain, enabling auditory categorization.
Do categorical representations modulate early perceptual or later cognitive visual processing? An ERP study.
2021
Abstract Encoding of perceptual categorical information has been observed in later cognitive processing like memory encoding and maintenance, starting around 300 ms after stimulus onset (P300). However, it remains open whether categorical information is also encoded in early perceptual processing steps (reflected in the mismatch negativity component; vMMN). The main goal of this study was to assess the influence of categorical information on both early perceptual (i.e., vMMN component) and later cognitive (i.e., P300 component) processing within one paradigm. Hence, we combined an oddball paradigm with a delayed memory task. We used five-dot patterns belonging to different categories even t…
Iteratively Learning a Liver Segmentation Using Probabilistic Atlases: Preliminary Results
2016
This works deals with the concept of liver segmentation by using a priori information based on probabilistic atlases and segmentation learning based of previous steps. A probabilistic atlas is here understood as a probability or membership map that tells how likely is that a point belongs to a shape drawn from the shape distribution at hand. We devise a procedure to segment Perfusion Magnetic Resonance liver images that combines both: a probabilistic atlas of the liver and a segmentation algorithm based on global information of previous simpler segmentation steps, local information from close segmented slices and finally a mathematical morphology procedure, namely viscous reconstruction, to…
A new image segmentation approach using community detection algorithms
2015
Image segmentation has an important role in many image processing applications. Several methods exist for segmenting an image. However, this technique is still a relatively open topic for which various research works are regularly presented. With the recent developments on complex networks theory, image segmentation techniques based on graphs has considerably improved. In this paper, we present a new perspective of image segmentation, by applying three of the most efficient community detection algorithms, Louvain, infomap and stability optimization based on the louvain algorithm, and we extract communities in which the highest modularity feature is achieved. After we show that this measure …
Efficient Multi-scale Patch-Based Segmentation
2015
The objective of this paper is to devise an efficient and accurate patch-based method for image segmentation. The method presented in this paper builds on the work of Wu et al. [14] with the introduction of a compact multi-scale feature representation and heuristics to speed up the process. A smaller patch representation along with hierarchical pruning allowed the inclusion of more prior knowledge, resulting in a more accurate segmentation. We also propose an intuitive way of optimizing the search strategy to find similar voxel, making the method computationally efficient. An additional approach at improving the speed was explored with the integration of our method with Optimised PatchMatch…
Smart city. Four approaches to the concept of understanding
2020
The paper analyzes the rhetoric of the smart city (SC) concept in order to recognize, categorize, and describe different perspectives of understanding the notion. Four approaches to the SC concept were isolated: three affirmative, and one rejecting. The approaches present a different understanding of the SC and indicate different elements creating urban ‘smartness.’ Despite differences, there is one common goal in every affirmative approach: to improve the quality of urban life. It is achieved through activities covering five dimensions distinguished within affirmative approaches. Together they can serve, i.e.,as a framework for SC case study analyses.