Neeraj Kumar Gupta

Automated diagnosis of coronary heart disease using neuro-fuzzy integrated system

Computational intelligence combines fuzzy systems, neural network and evolutionary computing. In this paper, Neuro-fuzzy integrated system for coronary heart disease is presented. In order to show the effectiveness of the proposed system, Simulation for automated diagnosis is performed by using the realistic causes of coronary heart disease. The results suggest that this kind of hybrid system is suitable for the identification of patients with high/low cardiac risk.

Neuro-fuzzy integrated system with its different domain applications

Computational intelligence combines fuzzy systems, neural network and evolutionary computing. In this paper, architecture of a neuro-fuzzy integrated system is presented. A new kind of error backpropagation algorithm to adjust the membership functions of each variable and optimise fuzzy rules is developed. To minimise the output error, a variational method for determining globally optimal learning parameters and learning rules for online gradient descent training of multilayer neural network has been proposed. In order to show the effectiveness of the proposed system, simulation for different variety of domain has been performed. The controller for inverted pendulum has been demonstrated. The controller uses error backpropagation algorithm to adjust the membership functions of each variable, optimise fuzzy rules, and identify the inverted pendulum. Neuro-fuzzy integrated system for coronary heart disease has also been simulated. The results suggest that this kind of hybrid system is also suitable for the identification of patients with high/low cardiac risk.

MIPS-NF instructions for fourth generation processor

In this paper we describe general purpose RISC processor with specialized Neurofuzzy control operations to achieve high Neurofuzzy processing performance. As a case study we show the definition & evaluation of instruction set extension for Neurofuzzy processing. We have extended the MIPS instruction set architecture with only a few new instructions to significantly speed up Neurofuzzy computation. These instructions are based on the use of subword parallelism to fully exploit the processors resources by processing multiple data steam in parallel. We have found that a simple instruction optimized to perform Neurofuzzy rule evaluation offers the most benefit to improve Neurofuzzy processing performance.

Automatic Diagnosis of Asthma Using Neurofuzzy System

In this paper, automatic diagnosis of asthma usingneurofuzzy approaches are presented. Adaptive Neural Fuzzy Inference System(ANFIS) is put in the framework of adaptive systems to facilitate learning and adaptation which uses back propagation algorithm to reduce the error in the output. In first phase input variables are prepared by taking a healthy person as a reference and in second phase these inputs with asthma patient are given to ANFIS to obtain output. Simulated result shows the proposed work for automated diagnosis, which have performed by using the realistic causes of asthma disease are effective.

Adaptive neurofuzzy system for tuberculosis

In this paper, a neurofuzzy system for tuberculosis (TB) is presented. This proposed work is rule-based fuzzy system which is form of intelligent technique and contain symptoms as its input variables in certain specified ranges & possible cures or referrals to doctors as its output. The adaptability of proposed work is depending upon the rule based algorithm which has decision-making ability and backpropagation learning of neurofuzzy system. Simulated results show the proposed work for automated diagnosis, which have performed by using the realistic causes of tuberculosis disease are effective.

Early detection of diabetes patients using soft computing

In this paper, diagnosis of diabetes using soft computing is presented. This research work is based on the fuzzy if-then rules and tuning of the parameters by neural network. A variational method for determining, globally optimal learning parameters and learning rules for on-line gradient descent training has been proposed in the paper. Neurofuzzy system is put in the framework to facilitate learning and adaptation for reducing the error in the output. A knowledge based system has been developed in client server for analysis of the disease and for storing the corresponding solution into the database. Simulated results show the proposed work is effective and after the analysis of the diagnosis result of the patients, the client server sends a message for first aid treatment.

Smart wheelchair using fuzzy inference system

In this paper “Smart Wheelchair using Fuzzy Inference System” has been presented, which has a user friendly guidance system and has ability to avoid obstacles. For guiding the wheelchair Finger Tip Control is used and for obstacle avoidance Ultrasonic Sensors have been used. The fuzzy If-Then rules have been defined which govern the functioning of the wheelchair in different conditions. The system is simulated on fuzzy tool box and results have been generated. The use of fuzzy control allows the use of inexpensive and imprecise sensors, which will keep the overall system cost and complexity low. Using fuzzy logic control makes the implementation of the system much more practical which is the number one goal.

Adaptive neurofuzzy system for brain tumor

This paper emphasizes on brain tumor detection and hereby minimizing the deviation of target value and actual value using back-propagation algorithm. In this paper, a structure of adaptive system is proposed with the help of Adaptive neurofuzzy inference system (ANFIS) for diagnosis of brain tumor. Investigation of brain tumor is performed based on predefined rules. Investigation of brain tumor by the proposed system is illustrated and good performance is achieved. In this paper, the prototype consisting of six symptoms of brain tumor and using different rules have been explained. The behavioral pattern of EEG with normal and abnormal activities has also been shown.

Neuro-Fuzzy integrated system and its VLSI design for generating membership function

In this paper, a Neuro-Fuzzy integrated system, which is based on fuzzy inference system using on-line learning ability of neural network is presented. By using on-line learning procedure, the proposed neuro-fuzzy integrated system (NFIS) can be used to construct an input-output mapping based on fuzzy if-then rules and the tuning of the parameters of membership function. The membership functions for NFIS have been realized using operational transconductance amplifier (OTA). Attention is given to design the circuits with low power consumption 2.91mW and size less than 0.65 mm2 within the neuro-fuzzy chip. SPICE simulations showed that they are suitable to real time application.

Echo Cancellation in Cellphone Using Neurofuzzy Filter

Computational intelligence combines neural network, fuzzy systems and evolutionary computing. In this manuscript a neurofuzzy filter (NFF) is presented, which is based on fuzzy if-then rules (structure learning) and the tuning of the parameters of membership function (parameter learning). In the structure learning, fuzzy rules are found based on the matching of input-output clusters. In the parameter learning, the consequent parameters are tuned optimally by either least mean square (LMS) or recursive least squares (RLS) algorithms and the pre condition parameters are tuned by backpropagation algorithm. Both the structure and parameter learning are performed simultaneously as the adaptation proceeds. Simulation for echo cancellation in cellphone is performed. Good performance is achieved by applying the NFF to echo cancellation on a cellphone.