A Modified Neuro-Fuzzy System Using Metaheuristic Approaches for Data Classification

Salleh, Mohd Najib Mohd; Talpur, Noureen; HussainTalpur, Kashif

doi:10.5772/intechopen.75575

Cited by 19 publications

(21 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training process stops whenever the maximum epoch number is reached or the training error goal is achieved. For splitting the data into training and testing purpose, according to literature (Salleh et al, 2018;Shrivastava and Srid-haran, 2013) most researchers practiced the 70% training and 30% testing because the more data applied for the training, the more optimal and accurate results a system generates. Therefore, in this study the 70% of the dataset instances were selected for training set and the remaining 30% of the dataset instances were chosen for testing set.…”

Section: Resultsmentioning

confidence: 99%

Utilization of Artificial Intelligence for Sensitivity Analysis in the Stock Market

Janková

Dostál

2019

Acta Univ. Agric. Silvic. Mendelianae Brun.

View full text Add to dashboard Cite

The main contribution of this paper is to perform sensitivity analysis using artificial intelligence methods on the US stock market using alternative psychological indicators. The Takagi-Sugeno fuzzy model applies investor sentiment represented by VIX index and monitors the impact of economic optimism, political stability and control of the corruption index on the S&P 500 stock index. Alternative psychological indicators have been chosen that have not been explored in the context of stock index performance sensitivity. Investors primarily use fundamental and technical analysis as a source to determine when and what to buy into an investment portfolio. However, psychological factors that may indicate the strength of reaction to the market are often neglected. Fuzzy rules are determined and tested using a neuro-fuzzy inference system and then the rules are reduced by fuzzy clustering to improve performance of ANFIS. The membership function is defined as a Gaussian function because it has the least RMSE value. The sensitivity analysis confirmed that there is a significant impact of the political stability index and the economic optimism index on the S&P 500 performance. Conversely, the sensitivity analysis, unlike the previous study, did not confirm the strong impact of VIX on equity index performance. Results indicate that incorporating psychological indicators in macroeconomic models leads to better supervision and control of the financial markets.

show abstract

Section: Resultsmentioning

confidence: 99%

Utilization of Artificial Intelligence for Sensitivity Analysis in the Stock Market

Janková

Dostál

2019

Acta Univ. Agric. Silvic. Mendelianae Brun.

View full text Add to dashboard Cite

show abstract

“…Basic structure of the ANFIS. Source: Salleh et al, 2018. Layer 3: Is a normalization layer that normalizes the strength of all rules according to the following equation:…”

Section: Adaptive Neuro-fuzzy Inference Systemmentioning

confidence: 99%

“…It is a very promising tool that needs to be explored in solving various non-linear and complex problems. However, as further described by Salleh et al (2017), the ANFIS computational costs are high due to complex structure and gradient learning. This is a significant problem especially for large input applications.…”

Section: Adaptive Neuro-fuzzy Inference Systemmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of European Stock Indexes Using Neuro-fuzzy Technique

Janková

Dostál

2020

Trends Economics and Management

View full text Add to dashboard Cite

Purpose of the article: The paper is focused on the forecast of stock markets of the Central European countries, known as V4, by means of soft computing. The tested model is constructed by a combination of fuzzy logic and artificial neural networks. A total of four SAX, PX, BUX, WIG stock indices differing in their liquidity and efficiency are selected for the forecast. Methodology/methods: The methods of analysis, synthesis and techniques of mathematical neuro-fuzzy modelling were used to achieve this goal. The proposed neuro-fuzzy decisionmaking model consists of 3 input variables, one block of rules (with 21 fuzzy rules) and one output variable predicting the normalized price of stock indexes of the selected countries. The input variables have three attributes (L-large, M-medium, and S-small). Scientific aim: The aim of the paper is to create a suitable model that will be used to forecast stock indices of the Central European countries with a relatively low error. Findings: The developed ANFIS model is a suitable tool for predicting stock indexes. The importance of the neuro-fuzzy model can be seen especially in the fact that it shows a strong predictive capacity of both efficient and less efficient stock markets. Conclusions: The paper discussed the design of the neuro-fuzzy model as a supporting tool for predicting the selected stock indexes listed on the European stock markets. For further research, it would be appropriate to extend the proposed model with other significant fundamental indicators, or to incorporate technical and psychological indicators and to monitor the strength of the revised model also in several stock markets, for example according to the geographical distribution.

show abstract

“…Adaptive neuro-fuzzy inference system (ANFIS) was introduced by Jang in 1993 [20]. This model has produced efficient results as compared to several other machine learning techniques [21]. The architecture of ANFIS comprises of five layers which transform inputs to the approximated outcome, by performing fuzzification, generating rules, and defuzzification for computing output.…”

Section: Adaptive Neur-fuzzy Inference System (Anfis)mentioning

confidence: 99%

A Novel Metaheuristic Approach to Optimization of Neuro-Fuzzy System for Students' Performance Prediction

Hussain¹,

Talpur²,

Aftab³

et al. 2020

JSCDM

View full text Add to dashboard Cite

Today, technology is aggressively adopted by educational institutes to maximize output of existing resources, to benefit both students and the teachers. The use of technology-based learning makes it possible to collect enormous amount of data pertaining to student and teacher performance. This data is then used for extracting meaningful information that deems useful for administration in making efficient decisions. For this purpose, literature shows significant advantages of data mining and machine learning techniques with regards to educational data mining [1,2,3]. Utilizing behavioral and performance data of students and teachers, researchers have applied these methods to discover knowledge in hidden patterns, to assess the effectiveness of courses, teaching methodologies, curriculum, and overall education system [4]. More specifically, the educational data mining is now being used to predict students' performances in order to identify the vulnerable ones at risk of failing the upcoming examinations so that more focus could be drawn on them to solve any difficulties [5,6].

show abstract

A Modified Neuro-Fuzzy System Using Metaheuristic Approaches for Data Classification

Cited by 19 publications

References 16 publications

Utilization of Artificial Intelligence for Sensitivity Analysis in the Stock Market

Utilization of Artificial Intelligence for Sensitivity Analysis in the Stock Market

Prediction of European Stock Indexes Using Neuro-fuzzy Technique

A Novel Metaheuristic Approach to Optimization of Neuro-Fuzzy System for Students' Performance Prediction

Contact Info

Product

Resources

About