A diffusion-neural-network for learning from small samples

Huang, Chongfu; Moraga, Claudio

doi:10.1016/j.ijar.2003.06.001

Cited by 151 publications

(62 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, historical records of disaster losses are often insufficient and incompatible for using traditional statistical methods to build vulnerability curves [58]. To simulate nonlinear and complex relations from small samples, Huang [58][59][60] proposed the hybrid fuzzy neural network model by combining the information diffusion method and the backpropagation algorithm (BP) for neural network.…”

Section: Vulnerability Assessment Of Wheat Frost Riskmentioning

confidence: 99%

“…They found that the IDM can change the contradictory patterns from a limited number of historical seismic records into more compatible ones, which can effectively train the neural network with backpropagation algorithm to obtain the accurate relationship. The hybrid fuzzy neural network model has been widely used in many studies [59][60][61][62][63][64], which shows that this model can effectively resolve the problems related to contradictory patterns from small samples and improve the accuracy of risk assessments. In this paper, a hybrid fuzzy neural network model approach was adopted to assess the wheat vulnerability [58,61].…”

Section: Vulnerability Assessment Of Wheat Frost Riskmentioning

confidence: 99%

“…The BP neural network has been widely used in disaster assessment and other relevant fields [58][59][60][61]. In this paper, we first employed the abovementioned information diffusion method to get diffused derivative samples.…”

Section: Vulnerability Curving Of Winter Wheat Based On Diffused Histmentioning

confidence: 99%

See 2 more Smart Citations

Assessing Wheat Frost Risk with the Support of GIS: An Approach Coupling a Growing Season Meteorological Index and a Hybrid Fuzzy Neural Network Model

et al. 2016

View full text Add to dashboard Cite

Abstract:Crop frost, one kind of agro-meteorological disaster, often causes significant loss to agriculture. Thus, evaluating the risk of wheat frost aids scientific response to such disasters, which will ultimately promote food security. Therefore, this paper aims to propose an integrated risk assessment model of wheat frost, based on meteorological data and a hybrid fuzzy neural network model, taking China as an example. With the support of a geographic information system (GIS), a comprehensive method was put forward. Firstly, threshold temperatures of wheat frost at three growth stages were proposed, referring to phenology in different wheat growing areas and the meteorological standard of Degree of Crop Frost Damage (QX/T 88-2008). Secondly, a vulnerability curve illustrating the relationship between frost hazard intensity and wheat yield loss was worked out using hybrid fuzzy neural network model. Finally, the wheat frost risk was assessed in China. Results show that our proposed threshold temperatures are more suitable than using 0 • C in revealing the spatial pattern of frost occurrence, and hybrid fuzzy neural network model can further improve the accuracy of the vulnerability curve of wheat subject to frost with limited historical hazard records. Both these advantages ensure the precision of wheat frost risk assessment. In China, frost widely distributes in 85.00% of the total winter wheat planting area, but mainly to the north of 35 • N; the southern boundary of wheat frost has moved northward, potentially because of the warming climate. There is a significant trend that suggests high risk areas will enlarge and gradually expand to the south, with the risk levels increasing from a return period of 2 years to 20 years. Among all wheat frost risk levels, the regions with loss rate ranges from 35.00% to 45.00% account for the largest area proportion, ranging from 58.60% to 63.27%. We argue that for wheat and other frost-affected crops, it is necessary to take the risk level, physical exposure, and growth stages of crops into consideration together for frost disaster risk prevention planning.

show abstract

Section: Vulnerability Assessment Of Wheat Frost Riskmentioning

confidence: 99%

Section: Vulnerability Assessment Of Wheat Frost Riskmentioning

confidence: 99%

See 1 more Smart Citation

Assessing Wheat Frost Risk with the Support of GIS: An Approach Coupling a Growing Season Meteorological Index and a Hybrid Fuzzy Neural Network Model

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The concept of information diffusion (Huang, 1997) was first introduced in function learning from a small sample of data (Huang and Moraga, 2004). The approximate reasoning of information diffusion was used to estimate probabilities and fuzzy relationships from scant, incomplete data for grassland wildfires (Liu et al, 2010).…”

Section: Normal Diffusion Technique For Risk Assessmentmentioning

confidence: 99%

Multiple Internet of Intelligences for Risk Analysis

Huang¹

2014

JRACR

Self Cite

View full text Add to dashboard Cite

In this study, we define a multiple Internet of intelligences (M-IOI) as the processing of homological information in layers. If agents in an M-IOI not only provide information in response to a question asked by a customer but also review information from other agents and summarize it, we refer to this as a summarizing M-IOI. The fuzzy mathematics method of normal diffusion is suggested to transform the summaries into fuzzy sets so that a satisfactory answer to the question is given. A summarizing M-IOI is used in a case study of typhoon dynamic risk in Wenzhou, China, where an insurance company wants to know whether the level of the risk will increase significantly. The effective knowledge in a summarizing M-IOI is measured to evaluate the quality of the answer. We also discuss the relation between IOIs and a global brain.

show abstract

“…studied a non-linear function fitting problem with one-dimensional input and one-dimensional output by segmentation technique and artificial sample generation. C. F. Huang [6] utilized diffusion-neural-network to fill the information gaps caused by data incompleteness. It seems that adding some samples have a more positive effect in lessening the modeling errors compared with cross-validation, but all these proposed sample generation methods are only used in one-dimensional input set problem, which still cannot be applied to DOE data of material ingredients.…”

Section: Introductionmentioning

confidence: 99%

Material Ingredient Optimization Based on Design of Experiment and Neural Network with Artificial Sample Generation

Chen¹,

Sun²,

Feng³

et al. 2015

IJMMM

View full text Add to dashboard Cite

Abstract-Material ingredient optimization is favorably and widely studied by using design of experiment (DOE) and artificial neural network (ANN). But the nonlinear mapping relationship model trained by the insufficient DOE samples can always cause non-negligible errors. This paper suggests a method adding some artificial samples into the neural network training data to get a better material ingredient optimization .In this method, artificial sample generation is combined with dimensionality reduction and segmentation technique. A simulation showed at the end of this paper indicates that compared with the model learning only from real DOE data, the accuracy can be significantly improved by adding some artificial training samples.Index Terms-Material ingredient optimization, DOE, artificial sample generation, insufficient samples. I. INTRODUCTIONProportion of raw materials is of great importance to a product's performance and lifetime. Many researchers [1], [2] have studied the method of combing design of experiment(DOE) and artificial neural network(ANN) together to get the relationship model between the material ingredients and the related performance indicators of a product, which can then help to get a best-valued product by re-setting the ingredient parameters.DOE can effectively figure out whether a factor has significant effect on the indicators or not. But its limitation in insufficient samples make the related ANN model have a non-negligible difference to the real relationship model, forcing it less practical in scientific and industrial use. Many researchers have studied the small sample problems in mapping relationship models and their findings can be summarized as below: 1.cross-validation.In this way, the scarce samples are divided into two sets, one set is used to train the model and the other one is applied to test the model. Y. M. Du [3] studied the effect of V-fold cross validation in remodeling back-propagation neural network (BPNN). U. Naonori [4] compared the accuracy of leave-one-out cross validation method and bootstrap analysis in ANN with the conventional training method.2.Adding some samples. These methods consider generating some artificial samples by information diffusion and training the relationship model by both samples to get a more accurate result. T. I. Tsai [5] Manuscript received February 6, 2015; revised April 10, 2015. This work was supported by National Natural Science Foundation of China under Grant No. 61273041.The authors are with the School of Information Systems and Management, National University of Defense Technology, Sanyi Ave, Changsha, China (e-mail: 18874771120@163.com, sunquan@nudt.edu.cn). studied a non-linear function fitting problem with one-dimensional input and one-dimensional output by segmentation technique and artificial sample generation. C. F. Huang [6] utilized diffusion-neural-network to fill the information gaps caused by data incompleteness. It seems that adding some samples have a more positive effect in lessening the modeling errors compared with c...

show abstract

A diffusion-neural-network for learning from small samples

Cited by 151 publications

References 17 publications

Assessing Wheat Frost Risk with the Support of GIS: An Approach Coupling a Growing Season Meteorological Index and a Hybrid Fuzzy Neural Network Model

Assessing Wheat Frost Risk with the Support of GIS: An Approach Coupling a Growing Season Meteorological Index and a Hybrid Fuzzy Neural Network Model

Multiple Internet of Intelligences for Risk Analysis

Material Ingredient Optimization Based on Design of Experiment and Neural Network with Artificial Sample Generation

Contact Info

Product

Resources

About