| 1. |
- Antanas, Laura, et al.
(författare)
-
There are plenty of places like home : Using relational representations in hierarchies for distance-based image understanding
- 2014
-
Ingår i: Neurocomputing. - : Elsevier. - 0925-2312 .- 1872-8286. ; 123, s. 75-85
-
Tidskriftsartikel (refereegranskat)abstract
- Understanding images in terms of logical and hierarchical structures is crucial for many semantic tasks, including image retrieval, scene understanding and robotic vision. This paper combines robust feature extraction, qualitative spatial relations, relational instance-based learning and compositional hierarchies in one framework. For each layer in the hierarchy, qualitative spatial structures in images are detected, classified and then employed one layer up the hierarchy to obtain higher-level semantic structures. We apply a four-layer hierarchy to street view images and subsequently detect corners, windows, doors, and individual houses.
|
|
| 2. |
- Crone, Sven F., et al.
(författare)
-
Feature selection for time series prediction : A combined filter and wrapper approach for neural networks
- 2010
-
Ingår i: Neurocomputing. - : Elsevier. - 0925-2312 .- 1872-8286. ; 73:10-12, s. 1923-1936
-
Tidskriftsartikel (refereegranskat)abstract
- Modelling artificial neural networks for accurate time series prediction poses multiple challenges, in particular specifying the network architecture in accordance with the underlying structure of the time series. The data generating processes may exhibit a variety of stochastic or deterministic time series patterns of single or multiple seasonality, trends and cycles, overlaid with pulses, level shifts and structural breaks, all depending on the discrete time frequency in which it is observed. For heterogeneous datasets of time series, such as the 2008 ESTSP competition, a universal methodology is required for automatic network specification across varying data patterns and time frequencies. We propose a fully data driven forecasting methodology that combines filter and wrapper approaches for feature selection, including automatic feature evaluation, construction and transformation. The methodology identifies time series patterns, creates and transforms explanatory variables and specifies multilayer perceptrons for heterogeneous sets of time series without expert intervention. Examples of the valid and reliable performance in comparison to established benchmark methods are shown for a set of synthetic time series and for the ESTSP'08 competition dataset, where the proposed methodology obtained second place.
|
|
| 3. |
- Qu, Hong, et al.
(författare)
-
An improved genetic algorithm with co-evolutionary strategy for global path planning of multiple mobile robots
- 2013
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 120, s. 509-517
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a Co-evolutionary Improved Genetic Algorithm (CIGA) for global path planning of multiple mobile robots, which employs a co-evolution mechanism together with an improved genetic algorithm (GA). This improved GA presents an effective and accurate fitness function, improves genetic operators of conventional genetic algorithms and proposes a new genetic modification operator. Moreover, the improved GA, compared with conventional GAs, is better at avoiding the problem of local optimum and has an accelerated convergence rate. The use of a co-evolution mechanism takes into full account the cooperation between populations, which avoids collision between mobile robots and is conductive for each mobile robot to obtain an optimal or near-optimal collision-free path. Simulations are carried out to demonstrate the efficiency of the improved GA and the effectiveness of CIGA.
|
|
| 4. |
- Ioakimidis, I, et al.
(författare)
-
Food intake and chewing in women
- 2012
-
Ingår i: NEUROCOMPUTING. - : Elsevier BV. - 0925-2312. ; 84, s. 31-38
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)
|
|
