The identification and prediction of simulated network attacks using artificialneuralnetworks have achieved the prediction of simulated network attacks and transformed them into clear information for security manage...
详细信息
Non-metric proximity measures got wide interest in various domains such as life sciences, robotics and imageprocessing. The majority of learning algorithms for these data are focusing on classification problems. Here...
详细信息
ISBN:
(纸本)9783319686127;9783319686110
Non-metric proximity measures got wide interest in various domains such as life sciences, robotics and imageprocessing. The majority of learning algorithms for these data are focusing on classification problems. Here we derive a regression algorithm for indefinite data representations based on the support vector machine. The approach avoids heuristic eigen spectrum modifications or costly proxy matrix approximations, as used in general. We evaluate the method on a number of benchmark data using an indefinite measure.
Software Effort Estimation models are hot topic of study over 3 decades. Several models have been developed in these decades. Providing accurate estimations of software is still very challenging. The major reason for ...
详细信息
Software Effort Estimation models are hot topic of study over 3 decades. Several models have been developed in these decades. Providing accurate estimations of software is still very challenging. The major reason for such disappointments in projects are because of inaccurate software development norms;effort estimation is one such practice. Dynamically fluctuating environment of technology in software development industry make effort estimation further perplexing. One of the most commonly used algorithmic model for estimating effort in industry is COCOMO. Capability of machine learning particularly artificialneuralnetworks is to adjust a complex set of bond among the various independent and dependent variables. The paper proposes usage of ANN (artificialneural Network) based model technologically advanced using Multi Layered Feed Forward neural Network which is given training with Back Propagation training method. COCOMO data-set is accustomed to test and train the network. Mean-Square-Error (MSE) and Mean Magnitude of Relative-Error (MMRE) are used as performance measurement indices. The experiment outputs suggest that the suggested model can provide better results and accurately forecast the software development effort. (C) 2016 The Authors. Published by Elsevier B.V.
A frame work for static sign language recognition using descriptors which represents 2D images in 1D data and artificialneuralnetworks is presented in this work. The 1D descriptors were computed by two methods, firs...
详细信息
ISBN:
(纸本)9780819492166
A frame work for static sign language recognition using descriptors which represents 2D images in 1D data and artificialneuralnetworks is presented in this work. The 1D descriptors were computed by two methods, first one consists in a correlation rotational operator.(1) and second is based on contour analysis of hand shape. One of the main problems in sign language recognition is segmentation;most of papers report a special color in gloves or background for hand shape analysis. In order to avoid the use of gloves or special clothing, a thermal imaging camera was used to capture images. Static signs were picked up from 1 to 9 digits of American Sign Language, a multilayer perceptron reached 100% recognition with cross-validation
artificialneuralnetworks are applied to fiber-optic transmission. Two fiber-optic transmission techniques using neuralnetworks are proposed. One is an optical WDM (wavelength division multiplexing) demultiplexer co...
详细信息
artificialneuralnetworks are applied to fiber-optic transmission. Two fiber-optic transmission techniques using neuralnetworks are proposed. One is an optical WDM (wavelength division multiplexing) demultiplexer composed of a simple optical component and all electrical neural network. The other is a fiber-optic image-transmission technique using a multimode fiber and a neural network. In either technique, propagation modes, in an optical multimode guide, play an important role in the signal processing. Initial experimental results are presented for these techniques. The combination of optics and neuralnetworks have, so far, produced only the concept of optical neuralnetworks. The techniques described can be regarded as different approaches to this combination
The term Deep Learning or Deep neural Network refers to artificialneuralnetworks (ANN) with multi layers. Over the last few decades, it has been considered to be one of the most powerful tools, and has become very p...
详细信息
ISBN:
(纸本)9781538619490
The term Deep Learning or Deep neural Network refers to artificialneuralnetworks (ANN) with multi layers. Over the last few decades, it has been considered to be one of the most powerful tools, and has become very popular in the literature as it is able to handle a huge amount of data. The interest in having deeper hidden layers has recently begun to surpass classical methods performance in different fields;especially in pattern recognition. One of the most popular deep neuralnetworks is the Convolutional neural Network (CNN). It take this name from mathematical linear operation between matrixes called convolution. CNN have multiple layers;including convolutional layer, non-linearity layer, pooling layer and fully-connected layer. The convolutional and fully-connected layers have parameters but pooling and non-linearity layers don't have parameters. The CNN has an excellent performance in machine learning problems. Specially the applications that deal with image data, such as largest image classification data set (image Net), computer vision, and in natural language processing (NLP) and the results achieved were very amazing. In this paper we will explain and define all the elements and important issues related to CNN, and how these elements work. In addition, we will also state the parameters that effect CNN efficiency. This paper assumes that the readers have adequate knowledge about both machine learning and artificialneural network.
Since speech is one of the most direct and effective means of human communication, it's natural to apply biomimetic processing mechanism to automatic speech recognition to solve the existing speech recognition pro...
详细信息
ISBN:
(纸本)9781424417230
Since speech is one of the most direct and effective means of human communication, it's natural to apply biomimetic processing mechanism to automatic speech recognition to solve the existing speech recognition problems. In this paper, three typical techniques were selected respectively: simulated evolutionary computation(SEQ, artificialneural network(ANN) and fuzzy logic and reasoning technique, from intelligence building processing simulation, intelligence structure simulation and intelligence behavior simulation, to identify their applications in different stages of speech recognition. A SEC usage and the corresponding algorithm were presented to generate training speech data, and a method of Elman network as acoustic model was also presented.
image analysis is an important requirement of many artificial intelligence systems. Though great effort has been devoted to inventing efficient algorithms far image analysis, there is still much work to be done. It is...
详细信息
ISBN:
(纸本)0819437654
image analysis is an important requirement of many artificial intelligence systems. Though great effort has been devoted to inventing efficient algorithms far image analysis, there is still much work to be done. It is natural to turn to mammalian vision systems for guidance because they are the best known performers of visual tasks. The pulse-coupled neural network (PCNN) model of the cat visual cortex has proven to have interesting properties for imageprocessing. This article describes the PCNN application to the processing of images of heterogeneous materials;specifically PCNN is applied to image denoising and image segmentation. Our results show that PCNNs do well at segmentation if we perform image smoothing prior to segmentation. We use PCNN for both smoothing and segmentation. Combining smoothing and segmentation enable us to eliminate PCNN sensitivity to the setting of the various PCNN parameters whose optimal selection can be difficult and can vary even for the same problem. This approach makes imageprocessing based on PCNN more automatic in our application and also results in better segmentation.
Time-sequential imagery can be acquired by film - based motion cameras or electronic video cameras. In this case, there are several factors related to imaging sensor limitations that contribute to the graininess (nois...
详细信息
ISBN:
(纸本)0819431184
Time-sequential imagery can be acquired by film - based motion cameras or electronic video cameras. In this case, there are several factors related to imaging sensor limitations that contribute to the graininess (noise) of resulting images. Further, in the case of image sequence compression, random noise increases the entropy of the image sequence and therefore hinders effective compression. Thus, filtering of time-sequential imagery for noise suppression is often a desirable preprocessing step. Some of video image filtering methods use the information about motion in video for reduction of noise (so-called motion - compensation approaches). The most of them are based on 3-D median or average filters, which supports are along motion trajectories. In this approach, it is difficult to design the proper structure of the 3-D filter by analytic methods. The artificialneuralnetworks can be useful tool for creating the structures of the filters. In this paper the novel neuralnetworks approach to motion compensated temporal and spatio-temporal filtering is proposed. The multilayer perceptrons and functional - link nets are used for the 3-D filtering. The spatio - temporal patterns are creating from read motion video images. The neuralnetworks learn these patterns. The practical examples of the filtering are shown and compared with traditional (non neural) motion - compensated filters.
Instance segmentation of images is an important tool for automated scene understanding. neuralnetworks are usually trained to optimize their overall performance in terms of accuracy. Meanwhile, in applications such a...
详细信息
ISBN:
(纸本)9781665408981
Instance segmentation of images is an important tool for automated scene understanding. neuralnetworks are usually trained to optimize their overall performance in terms of accuracy. Meanwhile, in applications such as automated driving, an overlooked pedestrian seems more harmful than a falsely detected one. In this work, we present a false negative detection method for image sequences based on inconsistencies in time series of tracked instances given the availability of image sequences in online applications. As the number of instances can be greatly increased by this algorithm, we apply a false positive pruning using uncertainty estimates aggregated over instances. To this end, instance-wise metrics are constructed which characterize uncertainty and geometry of a given instance or are predicated on depth estimation. The proposed method serves as a post-processing step applicable to any neural network that can also be trained on single frames only. In our tests, we obtain an improved trade-off between false negative and false positive instances by our fused detection approach in comparison to the use of an ordinary score value provided by the instance segmentation network during inference.
暂无评论