Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 12 of 12 for “"backpropagation method"”.
-
Point source compensation – a backpropagation method for underwater acoustic imaging
The backpropagation method of image reconstruction has been known for some time with the advantage of fast processing due to the use of Fast Fourier Transform. But its applicability to underwater imaging has been limited. At present the shift-and-add method is the more widely used method in …
-
Neural networks applied to signal processing
… called the conjugate gradient optimization method, for calculating the weights and thresholds of a neural network is presented. The performance of the conjugate gradient algorithm is then compared to the well known backpropagation method and shown to be more computationally efficient. A …
-
Tone classification of syllable -segmented Thai speech based on multilayer perceptron
… A multilayer perceptron (MLP) trained by backpropagation method was employed to classify these features. The proposed system was evaluated on 920 test utterances spoken by five male and three female Thai speakers who also uttered the training speech. The proposed system achieved an average …
-
A comparative study of different methods of predicting time series
… work presents a comparative study of different methods for predicting future values of time series data and implement them to predict the currency exchange rates. The current thesis focuses mainly on two approaches in predicting a time series. One of them is the traditional statistical approach …
-
Smart grid framework analysis and artificial neutral network in load forecast
… focuses on load forecasting for micro-grid. BackPropagation method is used to train the Multi-layer Perceptron (MLP) ANN and its results were compared to that from Radial Basis Function (RBF) ANN. Analysis was focused not only on the two networks but also ANN generalization problems and …
-
Model-based machine learning techniques for fiber nonlinearity compensation
… increases. Conventional nonlinear compensation methods, such as digital backpropagation (DBP) and perturbation theory-based nonlinearity compensation (PB-NLC), attempt to compensate for the nonlinearity by approximating analytical solutions to the signal propagation over fibers. However, their …
-
All-optical associative learning element
… (DNNs), are usually carried out using the backpropagation method. In the method, network weights are updated such that the net output better resembles the desired output after each forward-backward iteration, until convergence is met. A distinct approach is presented using associative …
-
Development of Life Cycle Assessment Based Air Quality Modeling and Decision Support System for the Mining Industry
… emission inventory using inverse matrix method, and defined characterization methods are investigated to assess the environmental impact. Artificial neural network model is developed to analyze carbon footprints (CO2 equivalent) using backpropagation method. Mining-zone air dispersion …
-
A self-organizing map artificial neural network to improve k-means algorithm classification in different cancer types
… of this thesis, is introducing an appropriate method in order to clustering input data precisely. So, at first the weakness of K-Means algorithm is shown. For this purpose, the procedure that this algorithm uses to clustering data is presented. It is shown that in this way, different input data …
-
Secure and Reliable Communications over Free-space Optical Channels
… a multiple spatial modes-based QKD system with backpropagation method to increase the total SKR through parallel channels. Regarding the reliability of an optical communication system as well as information reconciliation for both PLS and QKD schemes, the forward error correction (FEC) becomes …
-
Automatická detekce ischemie v EKG
Tato práce se zabývá využitím umělých neuronových sítí (UNS), pro detekci ischemické choroby srdeční (ICHS) ve frekvenční oblasti. První část této práce je zaměřena na teoretické znalosti a popisuje problematiku patologických změn na EKG, převodu EKG do frekvenční oblasti. Popisuje použité …
-
Automatická detekce ischemie v EKG pomocí umělé neuronové sítě
Tato práce se zabývá využitím umělých neuronových sítí (UNS), jako elektrokardiografických (EKG) klasifikátorů ischemické choroby srdeční (ICHS) a infarktu myokardu (IM) v EKG signálu. První část této práce je zaměřena na teoretické znalosti a popisuje problematiku patologických změn na EKG, metody …