This paper aims to investigate the characteristics of medical images. A novel diagnostic scheme to develop quantitative indexes of diabetes is introduced in this paper. To achieve a better image-processing result, an ...
详细信息
This paper aims to investigate the characteristics of medical images. A novel diagnostic scheme to develop quantitative indexes of diabetes is introduced in this paper. To achieve a better image-processing result, an appropriate image-processing algorithm is adopted in this work. The computation time increases as the image size grows. Fortunately, the computation can be partitioned and performed in parallel in a high performance system and a grid computing system can be a good infrastructure for it. An important fractal feature introduced in this paper is the measure of lacunarity, which describes the characteristics of fractals that have the same fractal dimension but different appearances. In this study, the measure of lacunarity and the moment of inertia have shown their significance in the classification of diabetes and are adequate for use as quantitative indexes.
Along with increasing popularity of wireless LAN, problem of location determination for mobile users becomes more important. The strengths of RF signals arriving from several access points can be used for location det...
详细信息
ISBN:
(纸本)9537044041
Along with increasing popularity of wireless LAN, problem of location determination for mobile users becomes more important. The strengths of RF signals arriving from several access points can be used for location determination of the mobile terminal. In indoor environments the received signal level is very complex function of the distance. The solution can be found in the area of artificial neural networks. The neural networks can be learned to classify data. Labeled data examples of signal strengths at known locations must be collected by the measurement. This data will serve for the training of the network with appropriate training algorithm. The trained network is capable to determine location on the base of new signal strengths as a process of generalization. The advantage of the method is that it doesn't need any extra hardware, while with flexible neural network model achieves lower distance errors in determining position comparable with other methods. For successful position determination only what is needed are a map of indoor space and several identified locations to train the network.
A Multi-layered Feed-forward Artificial Neural Network (ANN) trained by back-propagation algorithm is used to solve the problem of Combined Economic and Emission Dispatch in this paper. The system of generation associ...
详细信息
ISBN:
(纸本)9810557027
A Multi-layered Feed-forward Artificial Neural Network (ANN) trained by back-propagation algorithm is used to solve the problem of Combined Economic and Emission Dispatch in this paper. The system of generation associates thermal generators and emission involves. oxides of nitrogen only. Equality constraints on power balance as well as inequality constraints on generation capacity limits of the generators and transmission loss are also considered. The idea is to minimize total fuel cost of the system and control emission. The problem is first optimized by Lagrange Multiplier technique and the result is used to train the ANN wherein tuning parameters eta & alpha are altered to check their effect on convergence rate. The trained ANN is then used to generate test data. It is found that the convergence characteristic of the algorithm is excellent and the results achieved by the proposed method are quite accurate and faster in comparison to the conventional method.
An approach to modelling the behaviour of dimensions of PM parts during the sintering process for the prediction of dimensional changes is given. The model is developed on the basis of significant process factors by a...
详细信息
An approach to modelling the behaviour of dimensions of PM parts during the sintering process for the prediction of dimensional changes is given. The model is developed on the basis of significant process factors by applying a multilayer neural network architecture with the backpropagation learning algorithm. Results of the simulation in the form of diagrams and tables are presented. The presented model gives better results than the one based on statistical analysis of experimental data, i.e. less total mean approximation errors of the part dimensions for 11.4%. A practical result of the model is the determination of compact dimensions to compensate for dimensional changes during sintering.
The pressurized water reactor (PWR) generally operates in the forced convection or nucleate boiling regime. However, if the fuel rod is operating at a high power density, the nucleate boiling that is characterized by ...
详细信息
The pressurized water reactor (PWR) generally operates in the forced convection or nucleate boiling regime. However, if the fuel rod is operating at a high power density, the nucleate boiling that is characterized by extremely high heat transfer rates becomes film boiling with severely reduced heat transfer capability, which is called Departure from Nucleate Boiling (DNB). In this work, the axial DNB Ratio (DNBR) distribution at the hot pin position is predicted by the fuzzy neural networks using the measured signals of the reactor coolant system. The fuzzy neural network is a fuzzy inference system equipped with a training algorithm. The fuzzy neural network is trained by a hybrid method combined with a back-propagation algorithm and a least-squares algorithm. The proposed method is applied to the first cycle of the Yonggwang 3 nuclear power plant. The relative 2-sigma error averaged for 13 axial locations of the hot rod is 1.97%. The fuzzy neural networks estimate DNBRs more accurately at central parts that have relatively lower DNBR values which are more important in safety aspects. From these simulation results, it is known that this algorithm can provide reliable protection and monitoring information for the nuclear power plant operation and diagnosis by accurately predicting the DNBR each time step.
In general, we describe three different methods to select an appropriatedistribution form: histogram, probability plots, and hypothesis test. The life distribution isrecognized by a neural network method. The relation...
详细信息
In general, we describe three different methods to select an appropriatedistribution form: histogram, probability plots, and hypothesis test. The life distribution isrecognized by a neural network method. The relationship among life distribution with life data isdescribed through threshold and weight of neural networks. The method is convenient to use. Anexample is presented to validate this method, and the results are satisfactory.
A prediction model based on Rough Set and Neural Network is *** the model,we remove some redundant *** attributes that are necessary for rule discovery are kept as the input units of Neural *** input dimensions of Neu...
详细信息
A prediction model based on Rough Set and Neural Network is *** the model,we remove some redundant *** attributes that are necessary for rule discovery are kept as the input units of Neural *** input dimensions of Neural NetWork are *** the meantime,we give some improvement to tradition back-propagation Neural *** last,we present an applied instance.
In general, we describe three different methods to select an appropriate distribution form:bistogram, probability plots, and hypothesis test. The life distribution is recognized by a neural network method. The relatio...
详细信息
In general, we describe three different methods to select an appropriate distribution form:bistogram, probability plots, and hypothesis test. The life distribution is recognized by a neural network method. The relationship among life distribution with life data is described through threshold and weight of neural networks. The method is convenient to use. An example is presented to validate this method, and the results are satisfactory.
An artificial neural network (ANN) model of emulsion liquid membrane (ELM) process is proposed in the present study which is able to predict solute concentration in feed during extraction operation and ultimate % extr...
详细信息
An artificial neural network (ANN) model of emulsion liquid membrane (ELM) process is proposed in the present study which is able to predict solute concentration in feed during extraction operation and ultimate % extraction at different initial solute concentration in feed phase, internal reagent concentration, treat ratio, volume fraction of internal aqueous phase in emulsion and time. Because of the complexity in generalization of the phenomenon of ELM process by any mathematical model, the neural network proves to be a very promising method for the purpose of process simulation. The network uses the back-propagation algorithm (BPA) for evaluating the connection strengths representing the correlations between inputs (initial solute concentration in feed phase, internal reagent concentration, treat ratio, volume fraction of internal aqueous phase in emulsion and time) and outputs (solute concentration in feed during extraction operation and % extraction). The network employed in the present study uses five input nodes corresponding to the operating variables and two output nodes corresponding to the measurement of the performance of the network (solute concentration in feed during extraction and % extraction). Batch experiments are performed for separation of nickel(II) from aqueous sulphate solution of initial concentration in the 200-100 mg/l ranges. The network employed in the present study uses two hidden layers of optimum number of nodes being thirty and twenty. A leaning rate of 0.3 and momentum factor of 0.4 is used. The model predicted results in good agreement with the experimental data and the average deviations for all the cases are found to be well within +/-10%. (C) 2003 Elsevier B.V. All rights reserved.
The prediction of clinical outcome of patients after breast cancer surgery plays an important role in medical tasks such as diagnosis and treatment planning. Different prognostic factors for breast cancer outcome appe...
详细信息
The prediction of clinical outcome of patients after breast cancer surgery plays an important role in medical tasks such as diagnosis and treatment planning. Different prognostic factors for breast cancer outcome appear to be significant predictors for overall survival, but probably form part of a bigger picture comprising many factors. Survival estimations are currently performed by clinicians using the statistical techniques of survival analysis. In this sense, artificial neural networks are shown to be a powerful tool for analysing datasets where there are complicated non-linear interactions between the input data and the information to be predicted. This paper presents a decision support tool for the prognosis of breast cancer relapse that combines a novel algorithm TDIDT (control of induction by sample division method, CIDIM), to select the most relevant prognostic factors for the accurate prognosis of breast cancer, with a system composed of different neural networks topologies that takes as input the selected variables in order for it to reach good correct classification probability. In addition, a new method for the estimate of Bayes' optimal error using the neural network paradigm is proposed. Clinical-pathological data were obtained from the Medical Oncology Service of the Hospital Clinico Universitario of Malaga, Spain. The results show that the proposed system is an useful tool to be used by clinicians to search through large datasets seeking subtle patterns in prognostic factors, and that may further assist the selection of appropriate adjuvant treatments for the individual patient. (C) 2002 Elsevier Science B.V. All rights reserved.
暂无评论