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.
In this work, we propose a regularized learning method that is able to take into account the deviation of the memristor-mapped synaptic weights from the target values determined during the training process. Experimental results obtained when utilizing the MNIST data set show that compared to the conventional learning method which considers the learning and mapping processes separately, our learning...
Millions of people around the world suffer from epilepsy. It is very important to provide a method to efficiently monitor the seizures and alert the caregivers to help patients. It is proven that EEG signals are the best markers for diagnosis of the epileptic seizures. In this paper, we used the frequency domain features (normalized in-band power spectral density) to extract information from EEG signals...
Recent studies suggest that epidural stimulation of the spinal cord could increase the motor pattern both in motor and sensory complete spinal cord injury (SCI) patients. However, choosing the optimal epidural stimulation variables, such as the frequency, intensity, and location of the stimulation, significantly affects maximal motor functionality. This paper presents a novel technique using machine...
As a popular deep learning technique, convolutional neural network has been widely used in many tasks such as image classification and object recognition. Convolutional neural network exploits spatial correlations in the images by performing convolution operations in local receptive fields. Convolutional neural networks are preferred over fully connected neural networks because they have fewer weights...
In this paper a Siamese-Twin Random Projection Neural Network (ST-RPNN) is proposed for unsupervised binary hashing of images. ST-RPNN is made of two identical random projection neural networks with hard threshold neurons where the binary code is taken as the neuron outputs. The learning objective is to produce similar binary codes for similar input image pairs and different binary codes otherwise...
Spiking Neural Networks (SNNs) are the third generation of artificial neural networks that closely mimic the time encoding and information processing aspects of the human brain. It has been postulated that these networks are more efficient for realizing cognitive computing systems compared to second generation networks that are widely used in machine learning algorithms today. In this paper, we review...
The paper presents the results of research on the use of Deep Neural Networks (DNN) for automatic classification of the skin lesions. The authors have focused on the most effective kind of DNNs for image processing, namely Convolutional Neural Networks (CNN). In particular, three kinds of CNN were analyzed: VGG19, Residual Networks (ResNet) and the hybrid of VGG19 CNN with the Support Vector Machine...
The impressive evolution of neural networks and deep learning techniques during the last few years has offered new incomparable routes to solve many complex problems. Moreover, the fact that neural networks are structured and supervised has made it possible to perform automatic parameter tuning that guarantees convergence to the best expressive model for the problem assessed. In this work, we investigated...
This paper presents an artificial neural network (ANN) model based design for Hénon chaotic systems, and its equivalent hardware model for hardware co-simulation using Field Programmable Gate Arrays (FPGA). Chaotic generators can be used for the study of chaotic behaviors of brain activities captured by Electroencephalogram (EEG). The ANN model is designed with different fixed-point data format and...
Acoustic analysis is a non-invasive technique that supports voice disease screening, especially the detection and diagnosis of distinction between chosen voice pathologies and healthy control group. This work put en effort on creation of efficient and accurate system for automatic detection and differentiation of normal and three different voice pathologies. This system ensures non-invasive and fully...
Temperature resolution is a key factor for the performance of a Distributed Temperature Sensor (DTS). One can define the resolution as the degree of uncertainty in the temperature information. Thus, the temperature measured in a steady-state condition at a given point in the fiber will vary between successive measurements and between adjacent points that are at the same temperature. Temperature resolution...
In this study, we investigate the control performance of an adaptive-type feedforward feedback controller using multilayer hypercomplex-valued neural network. The control system consists of a neural network and a feedback controller, whereby the control input of a plant is synthesised online by using the sum of the multilayer hypercomplex-valued neural network and the feedback controller to track...
Speaker recognition has been developed over many years and it comes with many different methods. MFCC is one of more the successful methods due to it being generally modeled on the human auditory system. It represents high success rate of recognition and strong robustness against noise in the lower frequency regions. However, in the higher frequency regions, it captures speaker characteristics information...
In this paper, we present a novel approach for studying Boolean function in a graph-theoretic perspective. In particular, we first transform a Boolean function $f$ of $n$ variables into an induced subgraph $H_{f}$ of the $n$ -dimensional hypercube, and then, we show the properties of linearly separable Boolean functions on the basis of the analysis of the structure of $H_{f}$ . We define a...
Automatic image description generation is a challenging task in computer vision and computational linguistics. It helps people to get access to social media images easily. Content generation and surface realization are two important phases of this task. Deep learning techniques have a major role in content generation phase. The important scenario in content generation is object recognition. Deep learning...
In order to avoid the serious loss caused by the fire, to achieve the initial fire alarm, multi-sensor system is widely used in fire prediction. In the processing method, it is essentially different from the traditional classical signal. The multi-sensor information fusion system can be merged at different levels. It can be abstracted distributed into three levels: information fusion layer, feature...
Atmospheric aerosol is one of the most important factors that cause the random variation of solar radiation intensity. In view of the problem that the atmospheric aerosol optical depth (AOD) is difficult to obtain real-timely and conveniently with high accuracy, estimation model of AOD using PM concentration is proposed in this paper. Two kinds of modeling methods BP neural network and support vector...
Neural network is a kind of machine learning algorithm, applied in many ways. The traditional predictive guidance of aerocraft is hard to resolve the contradiction among robustness, real-time and the guidance of precision. The paper provides a predictive guidance algorithm for aerocraft, by combining neural network with predictive guidance to solve this problem. This research about the new style guidance...
Word2vec is a novel technique for the study and application of natural language processing(NLP). It trains a word embedding neural network model with a large training corpus. After the model is trained, each word is represented by a vector in the specified vector space. The vectors obtained possess many interesting and useful characteristics that are implicitly embedded with the original words. The...
This paper examines the application of a deep learning approach to converting night-time images to day-time images. In particular, we show that a convolutional neural network enables the simulation of artificial and ambient light on images. In this paper, we illustrate the design of the deep neural network and some preliminary results on a real indoor environment and two virtual environments rendered...
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.