Feedback in Neuro-Evolution is explored and evaluated for its application in devising prediction models for foreign currency exchange rates. A novel approach to foreign currency exchange rates forecasting based on Rec...
详细信息
Feedback in Neuro-Evolution is explored and evaluated for its application in devising prediction models for foreign currency exchange rates. A novel approach to foreign currency exchange rates forecasting based on Recurrent Neuro-Evolution is introduced. cartesian genetic programming (CGP) is the algorithm deployed for the forecasting model. Recurrent cartesian genetic programming evolved Artificial Neural Network (RCGPANN) is demonstrated to produce computationally efficient and accurate model for forex prediction with an accuracy of as high as 98.872% for a period of 1000 days. The approach utilizes the trends that are being followed in historical data to predict five currency rates against Australian dollar. The model is evaluated using statistical metrics and compared. The computational method outperforms the other methods particularly due to its capability to select the best possible feature in real time and the flexibility that the system provides in feature selection, connectivity pattern and network.
In this work, symbolic regression with an evolutionary algorithm called cartesian genetic programming, has been used to derive formulas capable to approximate the graph geodetic number, which measures the minimal-card...
详细信息
In this work, symbolic regression with an evolutionary algorithm called cartesian genetic programming, has been used to derive formulas capable to approximate the graph geodetic number, which measures the minimal-cardinality set of nodes, such that all shortest paths between its elements cover every node of the graph. Finding the exact value of the geodetic number is known to be NP-hard for general graphs. The obtained formulas are tested on random and real-world graphs. It is demonstrated how various graph properties as training data can lead to diverse formulas with different accuracy. It is also investigated which training data are really related to each property.
A new recurrent neural network model which has the ability to learn quickly is explored to devise a load forecasting and management model for the highly fluctuating load of London. Load forecasting plays an significan...
详细信息
ISBN:
(纸本)9781467361279
A new recurrent neural network model which has the ability to learn quickly is explored to devise a load forecasting and management model for the highly fluctuating load of London. Load forecasting plays an significant role in determining the future load requirements as well as the growth in the electricity demand, which is essential for the proper development of electricity infrastructure. The newly developed neuro-evolutionary technique called Recurrent cartesian genetic programming evolved Artificial Neural Networks (RCGPANN) has been used to develop a peak load forecasting model that can predict load patterns for a complete year as well as for various seasons in advance. The performance of the model is evaluated using the load patterns of London for a period of four years. The experimental results demonstrate the superiority of the proposed model to the contemporary methods presented to date.
Battery state-of-charge (SOC) is estimated for electric or hybrid electric vehicles by using Evolvable Hardware (EHW). SOC is a key factor in the management of battery and its estimation is an important and challengin...
详细信息
Battery state-of-charge (SOC) is estimated for electric or hybrid electric vehicles by using Evolvable Hardware (EHW). SOC is a key factor in the management of battery and its estimation is an important and challenging task. We combine EHW and evolutionary algorithm to design a system, which is 16-row and 4-layer with three inputs (voltage, magnification, charge-discharge mode) and one output (estimated SOC). The evolutionary algorithm is used to train the chromosome structure after setting by EHW. The results show that it can obtain battery SOC around the experimental curve after importing a parameter randomly.
Battery state-of-charge(SOC) is estimated for electric or hybrid electric vehicles by using Evolvable Hardware(EHW). SOC is a key factor in the management of battery and its estimation is an important and challenging ...
详细信息
Battery state-of-charge(SOC) is estimated for electric or hybrid electric vehicles by using Evolvable Hardware(EHW). SOC is a key factor in the management of battery and its estimation is an important and challenging *** combine EHW and evolutionary algorithm to design a system,which is 16-row and 4-layer with three inputs(voltage,magnification, charge-discharge mode) and one output(estimated SOC).The evolutionary algorithm is used to train the chromosome structure after setting by *** results show that it can obtain battery SOC around the experimental curve after importing a parameter randomly.
Lossless image coding process predicts the value of current pixel from previously decoded pixel values. Then the prediction error is classified according to the context model. This classification splits the sources wi...
详细信息
ISBN:
(纸本)9781467399623
Lossless image coding process predicts the value of current pixel from previously decoded pixel values. Then the prediction error is classified according to the context model. This classification splits the sources with different distributions and hence reduce the total entropy of the prediction error signals. In the literature, the predictor has been intensively studied. Some evolutionary approaches have been applied to generate a predictor to improve compression performance. However, the context modelling method has not relatively been well studied. We propose and investigate a novel method to automatically obtain evolved pair of pixel predictor and context modeling. Simulation results show 1.32-3.90% bit-rate reduction against the pair of predictor and context modeler of one of the best conventional methods (CALIC). It is also demonstrated that the evolved algorithm's size is more compact than former results. We also found that context modeler is evolved in more complex form than the predictor.
Feedback in Neuro-Evolution is explored and evaluated for its application in devising prediction models for foreign currency exchange rates.A novel approach to foreign currency exchange rates forecasting based on Recu...
详细信息
Feedback in Neuro-Evolution is explored and evaluated for its application in devising prediction models for foreign currency exchange rates.A novel approach to foreign currency exchange rates forecasting based on Recurrent NeuroEvolution is *** geneticprogramming(CGP) is the algorithm deployed for the forecasting *** cartesian genetic programming evolved Artificial Neural Network(RCGPANN) is demonstrated to produce computationally efficient and accurate model for forex prediction with an accuracy of as high as 98.872%for a period of1000 *** approach utilizes the trends that are being followed in historical data to predict five currency rates against Australian *** model is evaluated using statistical metrics and *** computational method outperforms the other methods particularly due to its capability to select the best possible feature in real time and the flexibility that the system provides in feature selection,connectivity pattern and network.
Alzheimer's is a chronic debilitating neurodegenerative disease that is difficult to diagnose; conventional approaches are subjective and can be unreliable. This paper describes work towards an objective assessmen...
详细信息
ISBN:
(纸本)9781605581316
Alzheimer's is a chronic debilitating neurodegenerative disease that is difficult to diagnose; conventional approaches are subjective and can be unreliable. This paper describes work towards an objective assessment that uses an evolutionary algorithm to assess an important symptom of the disease, the loss of visuo-spatial ability. Results are presented for application of the system in assessing the immature visuo-spatial ability of 7-11 year old children, which are used as a model for Alzheimer's disease patients.
暂无评论