Comparative Performance of Neuro-Fuzzy PSS Architectures with Adaptive Input Link Weights and Nonlinear Functions

One of most prominent features that social networks or e-commerce sites now provide is recommendation of items. However, the recommendation task is challenging as high degree of accuracy is required. This paper analyzes the improvement in recommendation of movies using Fuzzy Inference System (FIS) and Adaptive Neuro Fuzzy Inference System (ANFIS). Two similarity measures have been used: one by taking account similar users' choice and the other by matching genres of similar movies rated by the user. For similarity calculation, four different techniques, namely Euclidean Distance, Manhattan Distance, Pearson Coefficient and Cosine Similarity are used. FIS and ANFIS system are used in decision making. The experiments have been carried out on Movie Lens dataset and a comparative performance analysis has been reported. Experimental results demonstrate that ANFIS outperforms FIS in most of the cases when Pearson Correlation metric is used for similarity calculation.

Download Full-text

An Improved and Adaptive Approach in ANFIS to Predict Knee Diseases

International Journal of Healthcare Information Systems and Informatics ◽

10.4018/ijhisi.2020040102 ◽

2020 ◽

Vol 15 (2) ◽

pp. 22-37 ◽

Cited By ~ 1

Author(s):

Ranjit Kaur ◽

Kamaldeep Kaur ◽

Aditya Khamparia ◽

Divya Anand

Keyword(s):

Fuzzy System ◽

Inflammatory Diseases ◽

Medical Science ◽

Research Work ◽

Membership Functions ◽

Anfis Model ◽

Comparative Performance ◽

Medical Practitioners ◽

Neuro Fuzzy ◽

Testing Accuracy

Artificial intelligence is emerging as a persuasive tool in the field of medical science. This research work also primarily focuses on the development of a tool to automate the diagnosis of inflammatory diseases of the knee joint. The tool will also assist the physicians and medical practitioners for diagnosis. The diseases considered for this research under inflammatory category are osteoarthritis, rheumatoid arthritis and osteonecrosis. A five-layer adaptive neuro-fuzzy (ANFIS) architecture was used to model the system. The ANFIS system works by mapping input parameters to the input membership functions, input membership functions are mapped to the rules generated by the ANFIS model which are further mapped to the output membership function. A comparative performance analysis of fuzzy system and ANFIS system is also done and results generated shows that the ANFIS system outperformed fuzzy system in terms of testing accuracy, sensitivity and specificity.

Download Full-text

A Comparative Performance Analysis of Indirect Vector Controlled Induction Motor Drive Using Optimized AI Techniques

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2020.8692 ◽

2020 ◽

Vol 17 (1) ◽

pp. 464-472

Author(s):

B. T. Venu Gopal ◽

E. G. Shivakumar

Keyword(s):

Induction Motor ◽

Fuzzy Controller ◽

Induction Machines ◽

Pi Controller ◽

Motor Drive ◽

Induction Motor Drive ◽

Comparative Performance ◽

Neuro Fuzzy ◽

Novel Method ◽

Enhance Efficiency

This paper exhibits a point by point comparison between Neuro Fuzzy and Genetic Algorithm GA based control systems of Induction Motor drive, underlining favorable circumstances and drawbacks. Industries are advancing and upgrading generation line to enhance efficiency and quality. Induction machines are considered by nonlinear, time varying dynamics, inaccessibility of few states and thus can be considered as a challenging issue. In this paper, a novel method using modified GA is presented to limit electric losses of Induction Motor and it is compared with Neuro Fuzzy Controller. GA is a subordinate of AI, whose principle relies upon Darwin’s theory—struggle for existence and the survival of the fittest. The technique for deciding the gain parameters of PI controller utilizing GA whose output is utilized to control the torque applied to the Induction Motor in this way controlling its speed. The gains of PI controller are improved with the assistance of GA to upgrade the performance of IM drive. The results are simulated in MATLAB Simulink and are related with the conventional PI controller and Adaptive Neuro Fuzzy controller (NFC). NFC is less complicated and gives great speed precision yet GA based PI controller produces significantly reduced torque and speed ripples compared with other controllers, in this way limiting losses in IM drives.

Download Full-text

COMPARATIVE STUDY OF WAVELET BASED NEURAL NETWORK AND NEURO-FUZZY SYSTEMS

International Journal of Wavelets Multiresolution and Information Processing ◽

10.1142/s0219691307002099 ◽

2007 ◽

Vol 05 (06) ◽

pp. 879-906 ◽

Cited By ~ 4

Author(s):

AHMAD BANAKAR ◽

MOHAMMAD FAZLE AZEEM ◽

VINOD KUMAR

Keyword(s):

Neural Network ◽

Comparative Study ◽

Fuzzy Systems ◽

Universal Approximation ◽

Wavelet Network ◽

Nonlinear Functions ◽

Neuron Models ◽

Orthogonal Wavelet ◽

Neuro Fuzzy ◽

Feed Forward Neural Networks

Based on the wavelet transform theory and its well emerging properties of universal approximation and multiresolution analysis, the new notion of the wavelet network is proposed as an alternative to feed forward neural networks and neuro-fuzzy for approximating arbitrary nonlinear functions. Earlier, two types of neuron models, namely, Wavelet Synapse (WS) neuron and Wavelet Activation (WA) functions neuron have been introduced. Derived from these two neuron models with different non-orthogonal wavelet functions, neural network and neuro-fuzzy systems are presented. Comparative study of wavelets with NN and NF are also presented in this paper.

Download Full-text

Movie Recommendation System Based on Fuzzy Inference System and Adaptive Neuro Fuzzy Inference System

International Journal of Fuzzy System Applications ◽

10.4018/ijfsa.2015100103 ◽

2015 ◽

Vol 4 (4) ◽

pp. 31-69 ◽

Cited By ~ 1

Author(s):

Mahfuzur Rahman Siddiquee ◽

Naimul Haider ◽

Rashedur M. Rahman

Keyword(s):

Fuzzy Inference System ◽

Recommendation System ◽

Fuzzy Inference ◽

Pearson Correlation ◽

Similarity Measures ◽

Manhattan Distance ◽

Comparative Performance ◽

Inference System ◽

Neuro Fuzzy ◽

Similarity Calculation

One of most prominent features that social networks or e-commerce sites now provide is recommendation of items. However, the recommendation task is challenging as high degree of accuracy is required. This paper analyzes the improvement in recommendation of movies using Fuzzy Inference System (FIS) and Adaptive Neuro Fuzzy Inference System (ANFIS). Two similarity measures have been used: one by taking account similar users' choice and the other by matching genres of similar movies rated by the user. For similarity calculation, four different techniques, namely Euclidean Distance, Manhattan Distance, Pearson Coefficient and Cosine Similarity are used. FIS and ANFIS system are used in decision making. The experiments have been carried out on Movie Lens dataset and a comparative performance analysis has been reported. Experimental results demonstrate that ANFIS outperforms FIS in most of the cases when Pearson Correlation metric is used for similarity calculation.

Download Full-text