Novel weighting in single hidden layer feedforward neural networks for data classification

Seifollahi, Sattar; Yearwood, John; Ofoghi, Bahadorreza

doi:10.1016/j.camwa.2012.01.042

Cited by 11 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that each rule of the system analyzes only one metric. In case when there is more than one indicator, the set of input fuzzy concepts in the rule parcel is combined by the fuzzy "I" operation (Luckin (2017); Seifollahi et al (2012):…”

mentioning

confidence: 99%

Artificial intelligence components and fuzzy regulators in entrepreneurship development

Bogachov¹,

Kwiliński²,

Miethlich³

et al. 2020

JESI

View full text Add to dashboard Cite

The article provides a comparative study of the possibility of entrepreneurship development based on fuzzy signals of business activity and applied elements of artificial intelligence. The principal research methods that determine the logic and practical basis of the application of fuzzy logic in entrepreneurship are highlighted. It has been determined that fuzzy modeling is effective when technological processes are too complex for analysis using generally accepted quantitative methods, or when available sources of information in the business environment are interpreted poorly, inaccurately, and indefinitely. It has been shown experimentally that fuzzy logic gives better results compared to those obtained with generally accepted algorithms for analyzing the quality of doing business. A model of a neurofuzzy regulator has been developed and measures for its implementation in the business environment have been proposed. A neural network model in entrepreneurial development has been formed. Studies have shown the possibility of effective use of the principles of artificial intelligence and modeling in solving problems of developing entrepreneurial potential and making business decisions under conditions of uncertainty. This ensures objective and well-grounded decision-making in solving various applied problems of business development and taking into account environmental factors. The applied tasks of supporting the adoption of entrepreneurial decisions in the conditions are formulated; uncertainty; indicating that approaches to decision-making under conditions of uncertainty based on artificial intelligence and fuzzy logic tools are universal and require appropriate careful study and adaptation to a specific applied problem in the business environment.

show abstract

mentioning

confidence: 99%

Artificial intelligence components and fuzzy regulators in entrepreneurship development

Bogachov¹,

Kwiliński²,

Miethlich³

et al. 2020

JESI

View full text Add to dashboard Cite

show abstract

“…In the case of an NN classifier, the number of hidden layers is also a relevant that decisively conditions the final model and its results. In this work, the model NN classifier has been created with only one hidden layer because of two reasons: fi is the most frequent value in the literature for binary classifiers in terms of time comp [72,73,74], and second, because the size and complexity of the dataset were small en In part 'a', results from with 1 to 50 estimators are shown, which allows us to evaluate performance at large scale, every 10 estimators. The resulting accuracy curve fluctuates (Figure 6a), not improving as the number of estimators increases.…”

Section: Neural Network Classifiermentioning

confidence: 99%

“…In the case of an NN classifier, the number of hidden layers is also a relevant factor that decisively conditions the final model and its results. In this work, the model of the NN classifier has been created with only one hidden layer because of two reasons: first, it is the most frequent value in the literature for binary classifiers in terms of time complexity [72][73][74], and second, because the size and complexity of the dataset were small enough to overcome any overfitting problem with only one hidden layer. Following the same strategy we adopted in the case of the RF classifier, a curve was plotted to compare the accuracy depending on the number of neurons used in the hidden layer to be able to select the number of neurons to obtain the best results with our dataset.…”

Section: Neural Network Classifiermentioning

confidence: 99%

A Crowdsourcing Recommendation Model for Image Annotations in Cultural Heritage Platforms

Kamel,

Gil-Solla,

Guerrero-Vásquez

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Cultural heritage is one of many fields that has seen a significant digital transformation in the form of digitization and asset annotations for heritage preservation, inheritance, and dissemination. However, a lack of accurate and descriptive metadata in this field has an impact on the usability and discoverability of digital content, affecting cultural heritage platform visitors and resulting in an unsatisfactory user experience as well as limiting processing capabilities to add new functionalities. Over time, cultural heritage institutions were responsible for providing metadata for their collection items with the help of professionals, which is expensive and requires significant effort and time. In this sense, crowdsourcing can play a significant role in digital transformation or massive data processing, which can be useful for leveraging the crowd and enriching the metadata quality of digital cultural content. This paper focuses on a very important challenge faced by cultural heritage crowdsourcing platforms, which is how to attract users and make such activities enjoyable for them in order to achieve higher-quality annotations. One way to address this is to offer personalized interesting items based on each user preference, rather than making the user experience random and demanding. Thus, we present an image annotation recommendation system for users of cultural heritage platforms. The recommendation system design incorporates various technologies intending to help users in selecting the best matching images for annotations based on their interests and characteristics. Different classification methods were implemented to validate the accuracy of our work on Egyptian heritage.

show abstract

“…However, the application of fuzzy inference in RBFN was only tested in classification problem, and the setting of the fuzzy rule is a challenging task for regular researchers that do not have fuzzy theory background. In contrary, the used of statistical method in obtaining suitable weight for RBFN were reported in numerous literatures [45][46][47][48], that uses stochastic method, Grover searching algorithm, Hierarchy Markovian matrix and attributed class correlation method for that purposes. Furthermore, it is also reported that the learning algorithm for networks training may perform worse with the increases of dataset [49].…”

Section: Related Workmentioning

confidence: 99%

An Improved Radial Basis Function Networks in Networks Weights Adjustment for Training Real-World Nonlinear Datasets

Aik

Hong

Junoh

2019

IJ-AI

View full text Add to dashboard Cite

In neural networks, the accuracies of its networks are mainly relying on two important factors which are the centers and the networks weight. The gradient descent algorithm is a widely used weight adjustment algorithm in most of neural networks training algorithm. However, the method is known for its weakness for easily trap in local minima. It suffers from a random weight generated for the networks during initial stage of training at input layer to hidden layer networks. The performance of radial basis function networks (RBFN) has been improved from different perspectives, including centroid initialization problem to weight correction stage over the years. Unfortunately, the solution does not provide a good trade-off between quality and efficiency of the weight produces by the algorithm. To solve this problem, an improved gradient descent algorithm for finding initial weight and improve the overall networks weight is proposed. This improved version algorithm is incorporated into RBFN training algorithm for updating weight. Hence, this paper presented an improved RBFN in term of algorithm for improving the weight adjustment in RBFN during training process. The proposed training algorithm, which uses improved gradient descent algorithm for weight adjustment for training RBFN, obtained significant improvement in predictions compared to the standard RBFN. The proposed training algorithm was implemented in MATLAB environment. The proposed improved network called IRBFN was tested against the standard RBFN in predictions. The experimental models were tested on four literatures nonlinear function and four real-world application problems, particularly in Air pollutant problem, Biochemical Oxygen Demand (BOD) problem, Phytoplankton problem, and forex pair EURUSD. The results are compared to IRBFN for root mean square error (RMSE) values with standard RBFN. The IRBFN yielded a promising result with an average improvement percentage more than 40 percent in RMSE.

show abstract

Novel weighting in single hidden layer feedforward neural networks for data classification

Cited by 11 publications

References 14 publications

Artificial intelligence components and fuzzy regulators in entrepreneurship development

Artificial intelligence components and fuzzy regulators in entrepreneurship development

A Crowdsourcing Recommendation Model for Image Annotations in Cultural Heritage Platforms

An Improved Radial Basis Function Networks in Networks Weights Adjustment for Training Real-World Nonlinear Datasets

Contact Info

Product

Resources

About