Number of results to display per page
Search Results
1302. Assembly neural network with nearest-neighbor recognition algorithm
- Creator:
- Goltsev, Alexander , Húsek, Dušan, and Frolov, Alexander
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Assembly neural network, unsupervised learning, binary Hebbian rule pattern recognition, texture segmentation, and classification
- Language:
- English
- Description:
- An assembly neural network based on the binary Hebbian rule is suggested for pattern recognition. The network consists of several sub-networks according to the number of classes to be recognized. Each sub-network consists of several neural columns according to the dimensionality of the signal space so that the value of each signal component is encoded by activity of adjacent neurons of the column. A new recognition algorithm is presented which realizes the nearest-neighbor method in the assembly neural network. Computer simulation of the network is performed. The model is tested on a texture segmentation task. The experiments have demonstrated that the network is able to segment reasonably real-world texture images.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
1303. Assessing empirical software data with MLP neural networks
- Creator:
- Musilek, Petr and Meltzer, Jason
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Neural networks, software development, effort estimation, model size, accuracy, and evaluation
- Language:
- English
- Description:
- Software measurements provide developers and software managers with information on various aspects of software systems, such as effectiveness, functionality, maintainability, or the effort and cost needed to develop a software system. Based on collected data, models capturing some aspects of software development process can be constructed. A good model should allow software professionals to not only evaluate current or completed projects but also predict future projects with an acceptable degree of accuracy. Artificial neural networks employ a parallel distributed processing paradigm for learning of system and data behavior. Some network models, such as multilayer perceptrons, can be used to build models with universal approximation capabilities. This paper describes an application in which neural networks are used to capture the behavior of several sets of software development related data. The goal of the experiment is to gain an insight into the modeling of software data, and to evaluate the quality of available data sets and some existing conventional models.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
1304. Assessing methods for the estimation of response times of stream discharge: the role of rainfall duration
- Creator:
- Cuevas , Jaime G., Arumi , José L., and Dörner , José
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- empirical equations, lagtimes, semiempirical equations, streamflow, and time of concentration
- Language:
- Slovak
- Description:
- Lagtimes and times of concentration are frequently determined parameters in hydrological design and greatly aid in understanding natural watershed dynamics. In unmonitored catchments, they are usually calculated using empirical or semiempirical equations developed in other studies, without critically considering where those equations were obtained and what basic assumptions they entailed. In this study, we determined the lagtimes (LT) between the middle point of rainfall events and the discharge peaks in a watershed characterized by volcanic soils and swamp forests in southern Chile. Our results were compared with calculations from 24 equations found in the literature. The mean LT for 100 episodes was 20 hours (ranging between 0.6–58.5 hours). Most formulae that only included physiographic predictors severely underestimated the mean LT, while those including the rainfall intensity or stream velocity showed better agreement with the average value. The duration of the rainfall events related significantly and positively with LTs. Thus, we accounted for varying LTs within the same watershed by including the rainfall duration in the equations that showed the best results, consequently improving our predictions. Izzard and velocity methods are recommended, and we suggest that lagtimes and times of concentration must be locally determined with hyetograph-hydrograph analyses, in addition to explicitly considering precipitation patterns.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
1305. Assessing the evolution of learning capabilities and disorders with a graphical exploratory analysis of surveys containing missing and conflicting answers
- Creator:
- Sánchez , Luciano, Couso , Inés, Otero , José , and Palacios , Ana
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Knowledge surveys, graphical exploratory analysis, multidimensional scaling, and fuzzy fitness-based genetic algorithms
- Language:
- English
- Description:
- The analysis of the evolution of learning with graphical maps is based on the placement of the individuals in positions that are computed on the basis of their answers to certain tests. These techniques are useful for detecting similarities between the knowledge profiles of the subjects and can also be used for assessing the acquisition of capabilities after a course. In this paper, we propose to extend some graphical exploratory analysis techniques to the case where there are missing or conflicting answers in the tests. We will also consider that either a missing or unknown answer, or a set of conflictive answers to a survey, is aptly represented by an interval or a fuzzy set. This representation causes that each individual in the map is no longer a point but a figure whose shape and size determine the coherence of the answers and whose position with respect to its neighbors determines the similarities and differences between the individuals.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
1306. Assessing the evolution of learning capabilities and disorders with a graphical exploratory analysis of surveys containing missing nd conflicting answers
- Creator:
- Sánchez-Monedero, J., Hervás-Martínez , C., Gutiérrez , P. A., Ruz, Mariano Carbonero , Ramírez Moreno , M. C. , and Cruz-Ramírez , M.
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Accuracy, differential evolution, extreme learning machine, multiclass classification, multiobjective, neural networks, and sensitivity
- Language:
- English
- Description:
- Accuracy alone can be deceptive when evaluating the performance of a classifier, especially if the problem involves a high number of classes. This paper proposes an approach used for dealing with multi-class problems, which tries to avoid this issue. The approach is based on the Extreme Learning Machine (ELM) classifier, which is trained by using a Differential Evolution (DE) algorithm. Two error measures (Accuracy, $C$, and Sensitivity, S) are combined and applied as a fitness function for the algorithm. The proposed approach is able to obtain multi-class classifiers with a high classification rate level in the global dataset with an acceptable level of accuracy for each class. This methodology is evaluated over seven benchmark classification problems and one real problem, obtaining promising results.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
1307. Assessment of empirical formulae for determining the hydraulic conductivity of glass beads
- Creator:
- Říha, Jaromír, Petrula, Lubomír, Hala, Mario, and Alhasan, Zakaraya
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- hydraulic conductivity, empirical formulae, porosity, and porosity function configuration
- Language:
- Slovak
- Description:
- Empirical formulae are often used in practice to quickly and cheaply determine the hydraulic conductivity of soil. Numerous relations based on dimensional analysis and experimental measurements have been published for the determination of hydraulic conductivity since the end of 19th century. In this paper, 20 available empirical formulae are listed, converted and re-arranged into SI units. Experimental research was carried out concerning hydraulic conductivity for three glass bead size (diameters 0.2 mm, 0.5 mm and 1.0 mm) and variable porosity. The series of experiments consisted of 177 separate tests conducted in order to obtain relevant statistical sets. The validity of various published porosity functions and empirical formulae was verified with the use of the experimental data obtained from the glass beads. The best fit was provided by the porosity function n3/(1–n)2. In the case of the estimation of the hydraulic conductivity of uniform glass beads, the best fit was exhibited by formulae published by Terzaghi, Kozeny, Carman, Zunker and Chapuis et al.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
1308. Assessment of Facial Expressions in Product Appreciation
- Creator:
- Popa, M. C., Rothkrantz, L. J. M., Wiggers, P., and Shan, C.
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- product emotions, facial expression analysis, geometric features, appearance features, unsupervised learning, and supervised learning
- Language:
- English
- Description:
- In the marketing area, new trends are emerging, as customers are not only interested in the quality of the products or delivered services, but also in a stimulating shopping experience. Creating and influencing customers' experiences has become a valuable differentiation strategy for retailers. Therefore, understanding and assessing the customers' emotional response in relation to products/services represents an important asset. The purpose of this paper consists of investigating whether the customer's facial expressions shown during product appreciation are positive or negative and also which types of emotions are related to product appreciation. We collected a database of emotional facial expressions, by presenting a set of forty product related pictures to a number of test subjects. Next, we analysed the obtained facial expressions, by extracting both geometric and appearance features. Furthermore, we modeled them both in an unsupervised and supervised manner. Clustering techniques proved to be efficient at differentiating between positive and negative facial expressions in 78\% of the cases. Next, we performed more refined analysis of the different types of emotions, by employing different classification methods and we achieved 84\% accuracy for seven emotional classes and 95\% for the positive vs. negative.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
1309. Assessment of HRV after maximal exercise in trained postmenopausal women
- Creator:
- Orri, J. C, Hughes, E. M, Mistry, D. G, and Scala, A
- Format:
- print, bez média, and svazek
- Type:
- model:article and TEXT
- Subject:
- menopauza, menopause, training intensity, cardioprotection, 14, and 612
- Language:
- English
- Description:
- Increased parasympathetic tone achieved with endurance training may provide cardioprotection after menopause. To compare heart rate variability (HRV) from rest through maximal exercise and recovery in trained postmenopausal women. Thirtysix postmenopausal women who self-reported training at either moderate (MOD; 3-5.9 METS; 58.9±4.4 year) or vigorous (VIG; >6 METS; 59.7±5.2 year) intensities participated. HRV was measured for 5 min in the supine position, in the last minute of the VO2max test and after 2 min of active recovery. HRV in MOD and VIG was compared using a factorial ANOVA with repeated measures on time. MOD and VIG responded similarly over the three time periods for root mean square of sequential deviations (rMSSD), and high (HF) and low frequency (LF) power (p>0.05). Maximal exercise lowered rMSSD (3.3±0.08 vs. 1.2±0.06) and lnLF (4.1±0.05 vs. 3.3±0.13) and increased lnHF (3.3±0.14 vs. 4.0±0.10; p<0.01) from resting. However, active recovery restored lnHF (3.3±0.11) and lnLF (4.1±0.08) from maximal values (p<0.01). Our findings suggest that moderate and vigorous exercise training may enhance HRV recovery following one bout of maximal exercise in older women., J. C. Orri, E. M. Hughes, D. G. Mistry, A. Scala., and Obsahuje bibliografii
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
1310. Assessment of models to predict surface subsidence in the Czech part of the upper Silesian coal basin - case study
- Creator:
- Jiránková, Eva, Waclawik, Petr, and Nemcik, Jan
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- longwall mining, surface subsidence, great depth, finite element method, and Knothe method
- Language:
- English
- Description:
- This case study presents the verification of two surface subsidence prediction models for longwall mining at depths greater than 400 m. The surface subsidence points were surveyed and compared for both models. The first model uses empirical calculations to predict the surface subsidence. This method is reliable for predicting surface subsidence at shallower depths. At present, however, coal mining has progressed to great depths. The second model is the 2-dimensional finite element method to predict surface subsidence. In contrast to the first method, this method is based on the regional parameters and uses the rock mass properties to evaluate surface subsidence for multi-seams at any depth. Results show that the finite element method gives a better approximation of the measured surface subsidence than the Knothe method. The maximum surface subsidence, which was determined by the FEM method, was used to adjust the extraction coefficient in the Knothe's method. The predicted value differs from the measured value by 8 %. The slope of the predicted subsidence trough was within the range of 2‒8 % from the surveyed subsidence. This case study proposes a procedure for using both models to successfully predict the surface subsidence.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public