The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Software defect (Bug) prediction plays an important role in improving software quality. Many software defect prediction approaches have been proposed and achieved great effects in the real-world. However, the existing works are usually constrained in only one project, hence their effectiveness on cross-project defect prediction (cross-prediction) is usually poor. This is mainly because of the problem...
A Deep Neural Network (DNN) using the same activation function for all hidden neurons has an optimization limitation due to its single mathematical functionality. To solve it, a new DNN with different activation functions is designed to globally optimize both parameters (weights and biases) and function selections. In addition, a novel Genetic Deep Neural Network (GDNN) with different activation functions...
The comparison of two classifiers, the Extreme Learning Machine (ELM) and the Support Vector Machine (SVM) is considered for performance, resources used (neurons or support vector kernels) and computational complexity (speed). Both implementations are of similar type (C++ compiled as Octave .mex files) to have a better evaluation of speed and computational complexity. Our results indicate that ELM...
This paper proposes a fuzzy neural network model which is dynamic and uses wavelet functions in its processing units. Because of that this new model is called as dynamic fuzzy wavelet neural network (DFWNN). In the DFWNN model, IF part of the fuzzy rules are comprised of Mexican Hat wavelet membership functions and THEN part of the rules are differential equations of linear functions. For nonlinear...
Deep learning attract the interests of many researchers. Multidimensional algorithms require large data storage space. This paper proposes a modeling of the combustion system used for Circulating Fluidized Bed Boiler (CFBB), which is based on the method of auto-encoder of deep learning. The 20 dimensional input samples set is the input layer, and then the units of hidden layer are calculated. The...
Action Unit (AU) detection from facial images is an important classification task in affective computing. However most existing approaches use carefully engineered feature extractors along with off-the-shelf classifiers. There has also been less focus on how well classifiers generalize when tested on different datasets. In our paper, we propose a multi-label convolutional neural network approach to...
This paper presents a novel emotion transformation scheme of speech signal which is text independent and speaker independent. Speech signals as many other signals are inherently multi-scale in nature, owing to contributions from events occurring with different localizations in time and frequency. Therefore, emotion dependent spectral parameters those characterized by single scale features, approximate...
In this study, seismic attributes have been used to estimate well logs in one of the Iranian petroleum reservoirs. Three static methods have been evaluated: the linear model, the multilayer perceptron (MLP) and the radial basis function (RBF). For linear case, the selection of appropriate attributes was determined by forward selection and for nonlinear one, the selection was based on the genetic algorithm...
It is a serious problem of tax evasion in all domains. Because of the narrow human factors, there are case-by-case basis not to examine reported tax cases. Hence, it is a very demanding challenge to grow an effective tax evasion detection mechanism. In this paper, we use the proposed rule extractor approaches (PFHRCNN) to detect tax evasion. The experiment results show the proposed PFHRCNN for tax...
A method based on sparse denoising autoencoder for denoising hybrid noises in image is proposed in this paper. The method is experimented on natural images and the performance is evaluated in terms of peak signal to noise ratio (PSNR). By specifically designing the training process of sparse denoising autoencoder, our model not only achieves good performance on single kind of noises, but also is relatively...
Although deep learning has achieved outstanding performances on several difficult machine learning applications, there are multiple issues that make its application on new problems difficult: speed of training, local minima, and manual selection of hyper-parameters. To overcome these problems, this paper proposes a new evolutionary method, EvoAE, to train auto encoders for deep learning networks....
Detecting anomaly behavior in large network traffic data has presented a great challenge in designing effective intrusion detection systems. We propose an adaptive model to learn majority patterns under a dynamic changing environment. We first propose unsupervised learning on data abstraction to extract essential features of samples. We then adopt incremental majority learning with iterative evolutions...
Artificial neural networks (ANNs) usually require a very large number of computation nodes and can be implemented either in software or directly in hardware, such as FPGAs. Software-based approaches are offline and not suitable for real-time applications, but they support a large number of nodes. FPGA-based implementations, in contrast, can greatly speedup the computation time. However, resource limitations...
One important factor for the patients in a postoperative recovery is hypothermia. The doctor must decide whether the patients should be sent to another place with better medical therapy. We therefore adopt the proposed PSO (particle swarm optimization) based Fuzzy classifier to retrieve the crisp rules from the postoperative given medical data from UCI machine learning database, where the rules can...
Most works related to convolutional neural networks (CNN) use the traditional CNN framework which extracts features in only one scale. We propose multi-scale convolutional neural networks (MSCNN) which can not only extract multi-scale features but also solve the issues of the previous methods which use CNN to extract multi-scale features. With the assumption of label-inheritable (LI) property, we...
There have been considerable advances in multimedia recognition recently as powerful computing capabilities and large, representative datasets become ubiquitous. A fundamental assumption of traditional recognition techniques is that the data available for training are accurately labelled. Given the scale and diversity of web data, it takes considerable annotation effort to reduce label noise to acceptable...
This paper presents a method for touch-based gesture recognition that can be used in human-centered interfaces for ambient intelligence applications. Gestures are associated with shapes and they are represented using Fourier coefficients. Neural Networks, Decision Trees, Naïve Bayes and a set of classifiers (based on Linear Discriminant Analysis) are tested for gesture recognition. All these methods...
Financial fraud is a criminal act, which violates the law, rules or policy to gain unauthorized financial benefit. The major consequences are loss of billions of dollars each year, investor confidence or corporate reputation. A study area called Financial Fraud Detection (FFD) is obligatory, in order to prevent the destructive results caused by financial fraud. In this study, we propose a new method...
Rainfall is a very crucial weather parameter. The information on rainfall is also used for certain fields including farming, transportation, and flood early warning system. The significant fluctuation of rainfall in Bandung recently causes the difficulty in rainfall forecasting. The study analyzes and implements Soft Computing algorithm for rainfall forecasting in Bandung Regency. The algorithms belong...
In this research, the writer proposed feature extraction method using Centroid to Boundary. Centroid to Boundary has processing time better than some other methods, this method is also invariant to size and rotation of image. The method will get a feature of character based on distance from center point of character to its contour. For classification, Backpropagation Neural Network can improve the...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.