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.
This paper proposes a Real-time optimization (RTO) strategy for Fuel Cell Hybrid Power Sources based on Global Extremum Seeking (GES) control of the air flow. The performance is shown in comparison with Static Feed-Forward RTO strategy.
The paper proposes a solution for measuring the current consumption on the transmission lines for detecting the losses that may occur. The solution is non-invasive: the sensors determine the current by analyzing the electric field around the isolated conductor, it is fully mobile and easy to install: sensors are “clamp” type and can be placed on insulated conductors, data is transmitted wirelessly...
A real-time optimization (RTO) strategy for the Fuel Cell Hybrid Power Sources (FCHPS) is proposed in this paper. The optimization strategy is based on the Global Extremum Seeking (GES) search of the optimal value of the fuel flow rate of the FC stack. The airflow rate is controlled by the FC current as in the Static Feed-Forward (sFF) RTO strategy, where both fueling flow rates are controlled by...
This article presents a solution for tracking a mobile system using an artificial neural network. The mobile system collects data from the environment using an ultrasonic transmitter and receiver then data is processing using a binary artificial neural network. Some templates have been pre-loaded into the system to avoid blockages or additional routes. The solution is implemented on a SOC manufactured...
In this paper the authors propose a solution in which an intelligent algorithm - genetic algorithm in our case - is used to generate commands for a robot in real time, so that the robot can determine the optimal moves considering several aspects: route tracking and low power consumption. Genetic algorithms are intelligent solutions for multi-criteria optimization and using them to find solutions to...
The system presented in this paper consists of an image acquisition module from a video camera, an image processing module, which performs conversion to monochrome format, and a neural network that takes the acquired images and performs the extraction of patterns from them. The system proposed by the authors is used for recognizing the orientation of objects in real time by analyzing images from a...
The quantum computing represents a new field, which is still being researched, that may have numerous applications in the computer arithmetic, in the encryption - decryption systems, rapid search algorithms and physical systems' emulations. The hardware device that can make this type of calculations is still expensive nowadays and the number of the manufacturers is reduced. On the other hand, the...
We present in this paper a method of increasing both the storage capacity of Hopfield neural networks and their capability of error correction. The presented method uses the general principles of generating error-correcting codes in information theory combined with a gradient - an heuristic algorithm. Using this method, there are registered improvements in the growth of network storage capacity (number...
Low Density Parity Check (LDPC) coding is a classical method for the detection and correction of errors. Its problem is the relatively complex operations which must be performed at encoding, and especially at decoding, to detect and correct errors caused by communication channels. We present a solution for the errors correction using regular LDPC and Hopfield network-based associative memories. Our...
This paper presents a solution of design and implementation of a hardware error correction and detection system using associative memories. This type of memory allows search of a stored binary value, having as an input data a partial (or modified) amount of this value. This property can be used in communication, for detection and correction of errors. In our experiments the encoder just associate...
This paper presents a solution of design and implementation of a hardware error correction and detection circuit using associative memories. This type of memory allows search of a stored binary value, having as an input data a partial (or modified) amount of this value. This property can be used in communication, for detection and correction of errors. In our experiments the encoder just associate...
Our paper presents a solution for designing and implementation of a hardware error correction and detection circuit using associative memories. Associative memories allow the searching of a binary stored value, having as an input data a partial (or modified) amount of this value. This associative memories' property can be used in communication for detecting and correcting the errors encountered in...
In this paper we present an evolvable hardware structure based on a Boolean functions network implemented with the basic multiplexer circuit and configured by a hardware genetic algorithm. Even if evolvable hardware is a large research area (beginning in 1996) the main problem which remains is integration in one single chip of the entire system which consists in reconfigurable circuit and the evolvable...
Forward error correction (FEC) and automatic request (ARQ) are common techniques used to treat transmission errors when data are transmitted over noisy channels. In practical applications where feedback is possible, ARQ technique are often more preferable than FEC schemes because error detection requires much simpler decoding equipment and achieves a higher reliability than does error correction....
In this paper we present a solution for designing a Reed-Muller decoder using associative memories based on Hopfield networks. The decoding with classical methods requests high computation resources and needs longer response times. Our solution implies the usage of associative memories in the decoding process, this method being more efficient than the classical ones.
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.