Neural Network Fuzzy Inference Research Articles

Greedy Kernel Components Acting on ANFIS to Predict BOF Steelmaking Endpoint

In order to make overall consideration of the information from the original variables in the basic oxygen furnace (BOF) steelmaking dynamic process, an adaptive neural network fuzzy inference system (ANFIS) model based on kernel and greedy components is proposed. This kind of model can improve the endpoint predicting precision of the steel carbon contents and temperature. After hidden information is exposed in the high feature space through the kernel function transformation, greedy algorithm is used to remove redundant information and reduce the dimensions. The extracted components are used as the new inputs of ANFIS, and the implication relation among the inputs is reflected by rules, which simulate the operators experience, and consequently reduce the influence resulted from different operators. When the practical data are simulated, the simulated results are close to the practical values. The method is effective.

Moving object recognition by a shape-based neural fuzzy network

Moving object recognition by a shape-based neural fuzzy network is proposed in this paper. The moving objects considered in this paper include pedestrians, vehicles, motorcycle, and dogs. Given the shape of the moving object, its contour is calculated by contour following. The distance between the contour center and each contour point is calculated and smoothed. Parts of the feature vector are obtained from discrete Fourier transform coefficients of the smoothed distances. The length-to-width ratio of the object's shape, which is derived from vertical and horizontal projection of the shape of the object, is also used as a feature. Based on the feature vector, the self-constructing neural fuzzy inference network (SONFIN) is used for recognition. To verify the performance of the proposed approach, two experiments were performed. In the first experiment, the shape of an object was extracted manually. In the second experiment, the shape of an object was extracted automatically from a series of image processes, including gray-based and edge-based image subtractions and morphological operations. The experiments show that the proposed approach can recognize moving objects with high accuracy. SONFIN performance is also shown to be better than back-propagation neural network and radial basis function network performance.

EEG-Based Assessment of Driver Cognitive Responses in a Dynamic Virtual-Reality Driving Environment

Accidents caused by errors and failures in human performance among traffic fatalities have a high death rate and become an important issue in public security. They are mainly caused by the failures of the drivers to perceive the changes of the traffic lights or the unexpected conditions happening accidentally on the roads. In this paper, we devised a quantitative analysis for assessing driver's cognitive responses by investigating the neurobiological information underlying electroencephalographic (EEG) brain dynamics in traffic-light experiments in a virtual-reality (VR) dynamic driving environment. The VR technique allows subjects to interact directly with the moving virtual environment instead of monotonic auditory and visual stimuli, thereby provides interactive and realistic tasks without the risk of operating on an actual machine. Independent component analysis (ICA) is used to separate and extract noise-free ERP signals from the multi-channel EEG signals. A temporal filter is used to solve the time-alignment problem of ERP features and principle component analysis (PCA) is used to reduce feature dimensions. The dimension-reduced features are then input to a self-constructing neural fuzzy inference network (SONFIN) to recognize different brain potentials stimulated by red/green/yellow traffic events, the accuracy can be reached 87% in average eight subjects in this visual-stimuli ERP experiment. It demonstrates the feasibility of detecting and analyzing multiple streams of ERP signals that represent operators' cognitive states and responses to task events.

A fuzzified neural fuzzy inference network for handling both linguistic and numerical information simultaneously

A fuzzified Takagi–Sugeno–Kang (TSK)-type neural fuzzy inference network (FTNFIN) that is capable of handling both linguistic and numerical information simultaneously is proposed in this paper. FTRNFN solves the disadvantages of most existing neural fuzzy systems which can only handle numerical information. The inputs and outputs of FTNFIN may be fuzzy numbers with any shapes or numerical values. Structurally, FTNFIN is a fuzzy network constructed from a series of fuzzy if–then rules with TSK-type consequent parts. The α-cut technique is used in input fuzzification and consequent part computation, which enables the network to simultaneously handle both numerical and linguistic information. There are no rules in FTNFIN initially since they are constructed on-line by concurrent structure and parameter learning. FTNFIN is characterized by small network size and high learning accuracy, and can be applied to linguistic information processing. The network has been applied to the learning of fuzzy if–then rules, a mathematical function with fuzzy inputs and outputs, and truck backing control problem. Good simulation results are achieved from all these applications.

A novel distance protection scheme using time-frequency analysis and pattern recognition approach

This paper presents a new approach for distance protection of transmission lines using time-frequency analysis. The proposed technique consists of preprocessing the fault current signal samples using hyperbolic S-transform to yield the change in energy and standard deviation at the appropriate window variation. From these two features, a decision of fault or no-fault on any phase or multiple phases of the transmission line can be made. The ground detection is done by a proposed indicator with a threshold value. The fault distance from the relaying point can be accurately estimated using cubic polynomial interpolation technique, Feed forward Neural Network and Adaptive Network Fuzzy Inference System (ANFIS).

Multipurpose image recognition based on active search and adaptive fuzzy inference neural network

AbstractThis paper presents a versatile image recognition method, combining conventional pattern matching and a learning system. The proposed system first quickly determines candidate regions containing the target object in the image, and then examines the result by using the learning system. In the pattern matching, “active search” is used, which quickly extracts the target object using multiple two‐dimensional reference images. As a learning system, an adaptive fuzzy inference neural network (AFINN) is used, which can perform knowledge processing. The AFINN automatically constructs the inference model, such as the selection of the necessary input information, and automatically acquires the inference rules through learning. Consequently, by applying the AFINN to the image recognition problem, highly versatile object recognition is realized without requiring explicit knowledge for recognition. The proposed system can be applied to a wide range of problems, since diversified objects can be recognized by simply modifying the registered reference images. In this paper, the method is applied to a sample problem, consisting of an image of the laboratory containing various objects, such as computers, monitors, and chairs, and it is verified that high recognition accuracy can be realized. © 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 37(3): 69–79, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.20269

Application of DA-Preconditioned FINN for Electric Power System Fault Detection

This paper proposes a hybrid method of Deterministic Annealing (DA) and Fuzzy Inference Neural Network (FINN) for electric power system fault detection. It extracts features of input data with two-staged precondition of Fast Fourier Transform (FFT) and DA. FFT is useful for extracting the features of fault currents while DA plays a key role to classify input data into clusters in a sense of global classification. FINN is a more accurate estimation model than the conventional artificial neural networks (ANNs). The proposed method is successfully applied to data obtained by the Tokyo Electric Power Company (TEPCO) power simulator.

A high-order recurrent neuro-fuzzy system with internal dynamics: Application to the adaptive noise cancellation

A high-order recurrent neuro-fuzzy system (HO-RNFS) is suggested in this paper, suitable for modeling highly complex nonlinear temporal processes. Feedback connections are introduced in the network including the context and the feedback nodes that serve as a means to memorize the firing history. The feedback paths in the firing loop are implemented through finite impulse response (FIR) synaptic filters leading to a higher-order network with enhanced temporal capabilities. The inference mechanism of the HO-RNFS is implemented by means of dynamic fuzzy rules where multiple steps-ahead predictions are provided for the internal variables, at the consequent part. Its structure is organized in an on-line fashion using a concurrent structure and parameter algorithm. Structure learning generates dynamically the input and output clusters of the rules, while parameter learning adjusts the network weights. The HO-RNFS is compared to the recurrent self-organizing neural fuzzy inference network (RSONFIN), being a special case of the suggested network. The experimental setup includes a benchmark temporal system and the adaptive noise cancellation problem. Extensive experimentation reveals that HO-RNFS exhibits superior speech enhancement performance as contrasted to RSONFIN, when complex noise passages are considered.

Neural-network-based optimal fuzzy controller design for nonlinear systems

A neural-learning fuzzy technique is proposed for T–S fuzzy-model identification of model-free physical systems. Further, an algorithm with a defined modelling index is proposed to integrate and to guarantee that the proposed neural-based optimal fuzzy controller can stabilize physical systems; the modelling index is defined to denote the modelling-error evolution, and to ensure that the training data for neural learning can describe the physical system behavior very well; the algorithm, which integrates the neural-based fuzzy modelling and optimal fuzzy controlling process, can implement off-line modelling and on-line optimal control for model-free physical systems. The neural-fuzzy inference network is a self-organizing inference system to learn fuzzy membership functions and fuzzy-subsystems’ parameters as data feeding in. Based on the generated T–S fuzzy models for the continuous mass–spring–damper system and Chua's chaotic circuit, discrete-time model car system and articulated vehicle, their corresponding fuzzy controllers are formulated from both local-concept and global-concept fuzzy approach, respectively. The simulation results demonstrate the performance of the proposed neural-based fuzzy modelling technique and of the integrated algorithm of neural-based optimal fuzzy control structure.

追加学習可能なファジィ推論ニューラルネットワークの提案と画像認識への応用(<特集>理解技術におけるソフトコンピューティング)

本論文では、動的にルールならび分類対象の追加が可能なニューラルネットワークFINNALE(Fuzzy inference neural network with additional learning)を提案した。FINNALEは、ファジィニューラルネットワークに柔軟な追加学習の機能を融合することにより、学習により入力データから自動的にルールを生成可能なだけでなく、システムの肥大化を抑えながら必要に応じて、動的なルールおよび分類対象の追加を可能にしている。FINNALEを英文認識問題に適用させた実験では、予めすべての情報がそろわない状態でも、従来のバックプロパゲーションニューラルネットワークと同等の良好な識別能力を確認した。また、その追加学習機能を利用することにより、画像認識問題など分類の対象が非常に広い分野へも応用が可能であることが確認できた。

Adaptive fuzzy inference neural network

An adaptive fuzzy inference neural network (AFINN) is proposed in this paper. It has self-construction ability, parameter estimation ability and rule extraction ability. The structure of AFINN is formed by the following four phases: (1) initial rule creation, (2) selection of important input elements, (3) identification of the network structure and (4) parameter estimation using LMS (least-mean square) algorithm. When the number of input dimension is large, the conventional fuzzy systems often cannot handle the task correctly because the degree of each rule becomes too small. AFINN solves such a problem by modification of the learning and inference algorithm.

A novel prosodic-information synthesizer based on recurrent fuzzy neural network for the Chinese TTS system.

In this paper, a new technique for the Chinese text-to-speech (TTS) system is proposed. Our major effort focuses on the prosodic information generation. New methodologies for constructing fuzzy rules in a prosodic model simulating human's pronouncing rules are developed. The proposed Recurrent Fuzzy Neural Network (RFNN) is a multilayer recurrent neural network (RNN) which integrates a Self-cOnstructing Neural Fuzzy Inference Network (SONFIN) into a recurrent connectionist structure. The RFNN can be functionally divided into two parts. The first part adopts the SONFIN as a prosodic model to explore the relationship between high-level linguistic features and prosodic information based on fuzzy inference rules. As compared to conventional neural networks, the SONFIN can always construct itself with an economic network size in high learning speed. The second part employs a five-layer network to generate all prosodic parameters by directly using the prosodic fuzzy rules inferred from the first part as well as other important features of syllables. The TTS system combined with the proposed method can behave not only sandhi rules but also the other prosodic phenomena existing in the traditional TTS systems. Moreover, the proposed scheme can even find out some new rules about prosodic phrase structure. The performance of the proposed RFNN-based prosodic model is verified by imbedding it into a Chinese TTS system with a Chinese monosyllable database based on the time-domain pitch synchronous overlap add (TD-PSOLA) method. Our experimental results show that the proposed RFNN can generate proper prosodic parameters including pitch means, pitch shapes, maximum energy levels, syllable duration, and pause duration. Some synthetic sounds are online available for demonstration.

Tracking a maneuvering target using neural fuzzy network.

A fast target maneuver detecting and highly accurate tracking technique using a neural fuzzy network based on Kalman filter is proposed in this paper. In the automatic target tracking system, there exists an important and difficult problem: how to detect the target maneuvers and fast response to avoid miss-tracking? The traditional maneuver detection algorithms, such as variable dimension filter (VDF) and input estimation (IE) etc., are computation intensive and difficult to implement in real time. To solve this problem, neural network algorithms have been issued recently. However, the normal neural networks such as backpropagation networks usually produce the extra problems of low convergence speed and/or large network size. Furthermore, the way to decide the network structure is heuristic. To overcome these defects and to make use of neural learning ability, a developed standard Kalman filter with a self-constructing neural fuzzy inference network (KF-SONFIN) algorithm for target tracking is presented in this paper. By generating possible target trajectories including maneuver information to train the SONFIN, the trained SONFIN can detect when the maneuver occurred, the magnitude of maneuver values and when the maneuver disappeared. Without having to change the structure of Kalman filter nor modeling the maneuvering target, this new algorithm, SONFIN, can always find itself an economic network size with a fast learning process. Simulation results show that the KF-SONFIN is superior to the traditional IE and VDF methods in estimation accuracy.

Knowledge extraction from scenery images and recognition using fuzzy inference neural networks

AbstractA new method of extracting various types of human knowledge from scenery images in linguistic form and labeling the various regions of unknown images in an effective manner is proposed. In this system, partitioning of the input/output space can be performed in a self‐organizing manner. Rule extraction is performed in parallel and automatically by using a knowledge extraction network (KEN). Depending on the type of image to be learned, two‐phase processing including a self‐organization phase and an LMS learning phase is performed by several KENs. The overall network output is then unified and knowledge extraction and region recognition are performed linguistically. Software that performs a series of such operations has been implemented and it has been confirmed that knowledge extraction and better image recognition can be performed linguistically even if human knowledge is not provided. © 2003 Wiley Periodicals, Inc. Electron Comm Jpn Pt 2, 86(3): 82–90, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjb.10138

Single-channel speech enhancement in variable noise-level environment

Discusses the problem of single-channel speech enhancement in variable noise-level environment. Commonly used, single-channel subtractive-type speech enhancement algorithms always assume that the background noise level is fixed or slowly varying. In fact, the background noise level may vary quickly. This condition usually results in wrong speech/noise detection and wrong speech enhancement process. In order to solve this problem, we propose a subtractive-type speech enhancement scheme. This new enhancement scheme uses the RTF (refined time-frequency parameter)-based RSONFIN (recurrent self-organizing neural fuzzy inference network) algorithm we developed previously to detect the word boundaries in the condition of variable background noise level. In addition, a new parameter (MiFre) is proposed to estimate the varying background noise level. Based on this parameter, the noise level information used for subtractive-type speech enhancement can be estimated not only during speech pauses, but also during speech segments. This new subtractive-type enhancement scheme has been tested and found to perform well, not only in variable background noise level condition, but also in fixed background noise level condition.

Study of synthesis identification in the cutting process with a fuzzy neural network

With the development of intelligent manufacturing systems, the requirements of the stability and reliability are increasingly more important, especially in the NC cutting process. The method of traditional and single working condition monitoring cannot be fully satisfied. In this paper, an artificial neural network with fuzzy logic, signal processing and other techniques is composed, and a method of synthesis identification and diagnosis of the working condition with a model of a compound fuzzy inference neural network has been tested and has yielded good result, so that the stability and reliability of on-line monitoring and diagnosis is rationally expected to be realized.

Scenery image recognition and interpretation using fuzzy inference neural networks

In this paper, we propose a new image recognition and interpretation system. The proposed system is composed of three processes: (1) regional segmentation process; (2) image recognition process; and (3) image interpretation process. As a pre-processing in the regional segmentation process, an input image is divided into some proper regions using techniques based on K-means algorithm. In both the image recognition and the interpretation processes, fuzzy inference neural networks (FINNs) working in parallel are employed to achieve a high level of recognition and interpretation. Scenery images are used and it is confirmed that the system has an average of 71.9% accuracy rate in the recognition process and good results in the interpretation process without heuristic knowledge. In addition, it is also confirmed that the proposed system has an ability to extract proper rules for the image recognition and interpretation.

A NEW NEUROFUZZY NETWORK FOR SELFORGANIZING CONTROL

In this paper a novel neural fuzzy inference network (NFIN) it is proposed. The NFIN represent a modified Takagi-Sugeno-Kang (TSK) type fuzzy rule based model with neural network learning ability. The rules in the NFIN are created and adapted in an on-line learning algorithm. The structure learning together with the parameter learning forms the learning algorithms for the neural fuzzy network. It is proved that NFIN can greatly reduce the training time, avoid the overtuned phenomenon and has perfect regulation ability.

ファジー推論ニューラルネットワークによる位置関係を考慮した風景画像の認識

In this paper, we propose a new system for recognition of scenery images, by learning. The proposed system consists of 2 parts. One is the part which infers based on absolute position of target. The other is the part which infers based on relative position of target. Each part consists of Fuzzy Inference Neural Network (FINN) which can extract fuzzy if-then rules automatically. So the system can extract knowledge about absolute position and relative position. Through computer experiments, it can be seen that the proposed system can recognize the image much correctly.

A recurrent neural fuzzy network for word boundary detection in variable noise-level environments

This paper discusses the problem of automatic word boundary detection in the presence of variable-level background noise. Commonly used robust word boundary detection algorithms always assume that the background noise level is fixed. In fact, the background noise level may vary during the procedure of recording. This is the major reason that most robust word boundary detection algorithms cannot work well in the condition of variable background noise level. In order to solve this problem, we first propose a refined time-frequency (RTF) parameter for extracting both the time and frequency features of noisy speech signals. The RTF parameter extends the (time-frequency) TF parameter proposed by Junqua et al. from single band to multiband spectrum analysis, where the frequency bands help to make the distinction between speech signal and noise clear. The RTF parameter can extract useful frequency information. Based on this RTF parameter, we further propose a new word boundary detection algorithm by using a recurrent self-organizing neural fuzzy inference network (RSONFIN). Since RSONPIN can process the temporal relations, the proposed RTF-based RSONFIN algorithm can find the variation of the background noise level and detect correct word boundaries in the condition of variable background noise level. As compared to normal neural networks, the RSONFIN can always find itself an economic network size with high-learning speed. Due to the self-learning ability of RSONFIN, this RTF-based RSONFIN algorithm avoids the need for empirically determining ambiguous decision rules in normal word boundary detection algorithms. Experimental results show that this new algorithm achieves higher recognition rate than the TF-based algorithm which has been shown to outperform several commonly used word boundary detection algorithms by about 12% in variable background noise level condition, It also reduces the recognition error rate due to endpoint detection to about 23%, compared to an average of 47% obtained by the TF-based algorithm in the same condition.