Fuzzy Adaptive Learning Research Articles

Suicide risk factors and suicide vulnerability in various major psychiatric disorders.

There are many known suicide risk factors (SRF) common to major psychiatric disorders, but their impact on suicide vulnerability remains unclear. We used FALCON (Fuzzy Adaptive Learning Control Network) to evaluate those impacts. Staff psychiatrists completed computerized suicide risk scales (CSRS-III) including 21 SRF for 612 patients. Diagnoses were: schizophrenia, schizoaffective, major depression, anxiety disorder, bipolar affective disorder, personality disorder, organic brain syndromes, delusional disorder and other diagnoses. An optimal trained FALCON was obtained by running the network 10 times with 552 CSRS-III, validating with the balance. Medically serious suicide attempts (the vulnerability factor) served as the target variable. The significance of each variable in the trained network was determined by the magnitude of the change in output as affected by the consecutive change in all points of the variable input, then calculating the mean variance of all cases. The direction of influence was determined by the input on the entire scale of each variable, point by point, across all cases, then calculating the mean of all outputs. The impact and direction of influence of the various SRF differed for each diagnosis. Evaluation of the individual patient with his/her specific impact profile, determination of direction of influence of the corresponding SRF's may assist in increasing the accuracy of individual suicide risk assessment.

Reinforcement learning for high-level fuzzy petri nets

The author has developed a reinforcement learning algorithm for the high-level fuzzy Petri net (HLFPN) models in order to perform structure and parameter learning simultaneously. In addition to the HLFPN itself, the difference and similarity among a variety of subclasses concerning Petri nets are also discussed. As compared with the fuzzy adaptive learning control network (FALCON), the HLFPN model preserves the advantages that: 1) it offers more flexible learning capability because it is able to model both IF-THEN and IF-THEN-ELSE rules; 2) it allows multiple heterogeneous outputs to be drawn if they exist; 3) it offers a more compact data structure for fuzzy production rules so as to save information storage; and 4) it is able to learn faster due to its structural reduction. Finally, main results are presented in the form of seven propositions and supported by some experiments.

VLSI implementation of fuzzy adaptive resonance and learning vector quantization

We present a mixed-mode VLSI chip performing unsupervised clustering and classification, implementing models of fuzzy adaptive resonance theory (ART) and learning vector quantization (LVQ), and extending to variants such as Kohonen self-organizing maps (SOM). The parallel processor classifies analog vectorial data into a digital code in a single clock, and implements on-line learning of the analog templates, stored locally and dynamically using the same adaptive circuits for on-chip quantization and refresh. The unit cell performing fuzzy choice and vigilance functions, adaptive resonance learning and long-term analog storage, measures 71 /spl mu/m/spl times/71 /spl mu/m in 2 /spl mu/m CMOS. Experimental learning results are included from a 16-input, 16-category prototype on a 2.2 mm/spl times/2.2 mm chip, operating at 10 ksample/s parallel data rate and 2 mW power dissipation.

Neural network identification of high-risk suicide patients.

A history of medically serious suicide attempts (MSSA) has been considered a major risk factor for suicide. Backpropagation (BP) neural networks (NN) successfully detected patient files of patients who had committed MSSA but failed to identify MSSA patients when trained with data collected during face-to-face interviews. To develop an expert support system for the detection of suicide risk in patients with major psychiatric disorders using fuzzy adaptive learning control networks (FALCON) and BP enhanced with fuzzy logic neural networks. We used four types of input sets: (a) the most significant variables as defined by Garson's calculation of trained BP; (b) variables identified by logistic regression; (c) variables considered significant by experienced clinicians; or (d) the variables considered definitive by the computer programmer. In addition, the complete set of 59 input variables was used. The target variable was the existence of prior MSSA. Four training trials were performed with each input set (75% of the data was used for training and 25% for testing). Data was collected from 197 (50 MSSA, 147 non-MSSA) patients hospitalized at Sha'ar Menashe Mental Health Centre. BP enhanced with fuzzy logic achieved the most accurate results with the three variables chosen by the programmer (mean +/- SD; sensitivity=97% +/- 3.4%, specificity=69.2% +/- 6.9%), and FALCON trained with 15 variables chosen by an expert clinician obtained the highest sensitivity and specificity (mean +/- SD; sensitivity=94% +/- 6.9%, specificity=69% +/- 6.9%). A combined system of BP enhanced with fuzzy logic and FALCON may improve the detection rate of MSSA patients during patient interviews. A prospective validation study testing a combined system across 1, 2 and 5-year spans may provide a reliable instrument to aid in the detection of suicide prone psychiatric patients.

Adaptive fuzzy learning control for a class of nonlinear dynamic systems

Adaptive fuzzy learning control for a class of nonlinear dynamic systems

A GA-based fuzzy adaptive learning control network

This paper addresses the structure and an associated learning algorithm of a feedforward multilayered connectionist network for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed fuzzy adaptive learning control network (FALCON) can be contrasted with the traditional fuzzy logic control systems in their network structure and learning ability. A structure/parameter learning algorithm, called FALCON-GA, is proposed for constructing the FALCON automatically. The FALCON-GA is a three-phase hybrid learning algorithm. In the first phase, the fuzzy ART algorithm is used to do fuzzy clustering in the input/output spaces according to the supervised training data. In the second phase, the genetic algorithm (GA) is used to find proper fuzzy logic rules by associating input clusters and output clusters. Finally, in the third phase, the backpropagation algorithm is used for tuning input/output membership functions. Hence, the FALCON-GA combines the backpropagation algorithm for parameter learning and both the fuzzy ART and GAs for structure learning. It can partition the input/output spaces, tune membership functions and find proper fuzzy logic rules automatically. The proposed FALCON has two important features. First, it reduces the combinatorial demands placed by the standard methods for adaptive linearization of a system. Second, the FALCON is a highly autonomous system. In its learning scheme, only the training data need to be provided from the outside world. The users need not give the initial fuzzy partitions, membership functions and fuzzy logic rules. Computer simulations have been conducted to illustrate the performance and applicability of the proposed system.

Adaptive fuzzy learning control for a class of nonlinear dynamic systems

This paper presents an adaptive iterative learning control scheme that is applicable to a class of nonlinear systems. The control scheme guarantees system stability and bounded-ness by using the feedback controller coupled with the fuzzy compensator and achieves precise tracking by using the iterative learning rules. In the feedback plus fuzzy compensator unit, the feedback control part stabilizes the overall closed-loop system and keeps its error bounded, and the fuzzy compensator estimates and compensates for the nonlinear part of the system, thereby keeping the feedback gains reasonably low in the feedback controller. The fuzzy compensator is designed by applying the fuzzy approximation technique to the uncertain nonlinear term to be compensated. In the iterative learning controller, a simple learning control rule is used to achieve precise tracking of the reference signal and a parameter learning algorithm is used to update the parameters in the fuzzy compensator so as to identify the uncertain nonlinearity as much as possible.

Fuzzy inference systems implemented on neural architectures for motor fault detection and diagnosis

Motor fault detection and diagnosis involves processing a large amount of information of the motor system. With the combined synergy of fuzzy logic and neural networks, a better understanding of the heuristics underlying the motor fault detection/diagnosis process and successful fault detection/diagnosis schemes can be achieved. This paper presents two neural fuzzy (NN/FZ) inference systems, namely, fuzzy adaptive learning control/decision network (FALCON) and adaptive network based fuzzy inference system (ANFIS), with applications to induction motor fault detection/diagnosis problems. The general specifications of the NN/FZ systems are discussed. In addition, the fault detection/diagnosis structures are analyzed and compared with regard to their learning algorithms, initial knowledge requirements, extracted knowledge types, domain partitioning, rule structuring and modifications. Simulated experimental results are presented in terms of motor fault detection accuracy and knowledge extraction feasibility. Results suggest new and promising research areas for using NN/FZ inference systems for incipient fault detection and diagnosis in induction motors.

An ART-based fuzzy adaptive learning control network

This paper addresses the structure and an associated online learning algorithm of a feedforward multilayer neural net for realizing the basic elements and functions of a fuzzy controller. The proposed fuzzy adaptive learning control network (FALCON) can be contrasted with traditional fuzzy control systems in network structure and learning ability. An online structure/parameter learning algorithm, FALCON-ART, is proposed for constructing FALCON dynamically. It combines backpropagation for parameter learning and fuzzy ART for structure learning. FALCON-ART partitions the input state space and output control space using irregular fuzzy hyperboxes according to the data distribution. In many existing fuzzy or neural fuzzy control systems, the input and output spaces are always partitioned into "grids". As the number of variables increases, the number of partitioned grids grows combinatorially. To avoid this problem in some complex systems, FALCON-ART partitions the I/O spaces flexibly based on data distribution. It can create and train FALCON in a highly autonomous way. In its initial form, there is no membership function, fuzzy partition, and fuzzy logic rule. They are created and begin to grow as the first training pattern arrives. Thus, the users need not give it any a priori knowledge or initial information. FALCON-ART can online partition the I/O spaces, tune membership functions, find proper fuzzy logic rules, and annihilate redundant rules dynamically upon receiving online data.

A fuzzy adaptive learning control network with on-line structure and parameter learning.

This paper addresses a general connectionist model, called Fuzzy Adaptive Learning Control Network (FALCON), for the realization of a fuzzy logic control system. An on-line supervised structure/parameter learning algorithm is proposed for constructing the FALCON dynamically. It combines the backpropagation learning scheme for parameter learning and the fuzzy ART algorithm for structure learning. The supervised learning algorithm has some important features. First of all, it partitions the input state space and output control space using irregular fuzzy hyperboxes according to the distribution of training data. In many existing fuzzy or neural fuzzy control systems, the input and output spaces are always partitioned into "grids". As the number of input/output variables increase, the number of partitioned grids will grow combinatorially. To avoid the problem of combinatorial growing of partitioned grids in some complex systems, the proposed learning algorithm partitions the input/output spaces in a flexible way based on the distribution of training data. Second, the proposed learning algorithm can create and train the FALCON in a highly autonomous way. In its initial form, there is no membership function, fuzzy partition, and fuzzy logic rule. They are created and begin to grow as the first training pattern arrives. The users thus need not give it any a priori knowledge or even any initial information on these. In some real-time applications, exact training data may be expensive or even impossible to obtain. To solve this problem, a Reinforcement Fuzzy Adaptive Learning Control Network (RFALCON) is further proposed. The proposed RFALCON is constructed by integrating two FALCONs, one FALCON as a critic network, and the other as an action network. By combining temporal difference techniques, stochastic exploration, and a proposed on-line supervised structure/parameter learning algorithm, a reinforcement structure/parameter learning algorithm is proposed, which can construct a RFALCON dynamically through a reward/penalty signal. The ball and beam balancing system is presented to illustrate the performance and applicability of the proposed models and learning algorithms.

A comparative study of the MAX and SUM machine-learning algorithms using virtual fuzzy sets

This paper presents an adaptive fuzzy learning algorithm for non-linear system identification. The algorithm is based on a concept called a “virtual fuzzy set”. The concept provides a new representation for the consequent part of a fuzzy production rule. A virtual fuzzy set, which consists of two consecutive fuzzy sets with different degrees of membership, is an imaginary fuzzy set located at a location most appropriate for a numerical training data point. The aim of virtual fuzzy set is to increase the system accuracy, at minimum expense in terms of computer resources. The concept is incorporated into a one-pass build-up adaptive algorithm for non-linear system identification. The results show that better performance can be achieved, compared with traditional fuzzy sets. Two variations of the learning algorithm, using the MAX or SUM of rule degrees, are proposed. The performance of these two approaches in identifying processes with different noise levels is evaluated.

Corrections to "Reinforcement Learning for an ART-Based Fuzzy Adaptive Learning Control Network"

Corrections to "Reinforcement Learning for an ART-Based Fuzzy Adaptive Learning Control Network"

Reinforcement learning for an ART-based fuzzy adaptive learning control network

This paper proposes a reinforcement fuzzy adaptive learning control network (RFALCON), constructed by integrating two fuzzy adaptive learning control networks (FALCON), each of which has a feedforward multilayer network and is developed for the realization of a fuzzy controller. One FALCON performs as a critic network (fuzzy predictor), the other as an action network (fuzzy controller). Using temporal difference prediction, the critic network can predict the external reinforcement signal and provide a more informative internal reinforcement signal to the action network. The action network performs a stochastic exploratory algorithm to adapt itself according to the internal reinforcement signal. An ART-based reinforcement structure/parameter-learning algorithm is developed for constructing the RFALCON dynamically. During the learning process, structure and parameter learning are performed simultaneously. RFALCON can construct a fuzzy control system through a reward/penalty signal. It has two important features; it reduces the combinatorial demands of system adaptive linearization, and it is highly autonomous.

Adaptive fuzzy control of unstable nonlinear systems.

This paper addresses the structure and an associated on-line learning algorithm of a feedforward multilayer connectionist network for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed Fuzzy Adaptive Learning Control Network (FALCON) can be contrasted with the traditional fuzzy logic control systems in their network structure and learning ability. An on-line structure/parameter learning algorithm, called FALCON-ART, is proposed for constructing the FALCON dynamically. The FALCON-ART can partition the input/output space in a flexible way based on the distribution of the training data. Hence it can avoid the problem of combinatorial growing of partitioned grids in some complex systems. It combines the backpropagation learning scheme for parameter learning and the fuzzy ART algorithm for structure learning. More notably, the FALCON-ART can on-line partition the input/output spaces, tune membership functions, and find proper fuzzy logic rules dynamically without any a priori knowledge or even any initial information on these. The proposed learning scheme has been successfully used to control two unstable nonlinear systems. They are the seesaw system and the inverted wedge system.

Fuzzy adaptive learning control network with on-line neural learning

This paper addresses the structure and the associated on-line learning algorithms of a feedforward multilayered connectionist network for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed Fuzzy Adaptive Learning COntrol Network (FALCON) can be contrasted with the traditional fuzzy logic control systems in their network structure and learning ability. The connectionist structure of the proposed FALCON can be constructed from training examples by neural learning techniques to find proper fuzzy partitions, membership functions, and fuzzy logic rules. Two complementary on-line structure/parameter learning algorithms, FALCON-FSM and FALCON-ART, are proposed for constructing the FALCON dynamically. The FALCON-FSM combines the backpropagation learning scheme for parameter learning and a fuzzy similarity measure for structure learning. The FALCON-FSN can find proper fuzzy logic rules, membership functions, and the size of output partitions simultaneously. In the FALCON-FSM algorithm, the input and output spaces are partitioned into “grids”. The grid-typed space partitioning certainly makes both the fuzzy logic controller software emulation and fuzzy chip implementation convenient. However, as the number of input/output variables increases, the number of partitioned grids will grow combinatorially. To avoid the problem of combinatorial growth of partitioned grids in some complex systems, the FALCON-ART algorithm is developed, which can partition the input and output spaces in a more flexible way based on the distribution of the training data. The FALCON-ART combines the backpropagation learning scheme for parameter learning and a fuzzy ART algorithm for structure learning. The FALCON-ART can on-line partition the input and output spaces, tune membership functions and find proper fuzzy logic rules dynamically. Computer simulations were conducted to illustrate the performance and applicability of both FALCON-FSM and FALCON-ART learning algorithms.

Fuzzy adaptive learning model of decision-making process

A mathematical model is described which generalizes fuzzy information to adopt to a new situation. This model is able to modify a priori information obtained from experts. Preferences of experts are realized by means of a set of strictly unformed criteria which can be described in terms of a composite linguistic variable. Using a decision maker's selection of a particular alternative from a set of possible ones the model improves its performance. It replaces a priori linguistic rules by refined linguistic rules. These rules correspond to the choice of the decision-maker.