Incremental Fuzzy Research Articles

Incremental Fuzzy Clustering-Based Neural Networks Driven With the Aid of Dynamic Input Space Partition and Quasi-Fuzzy Local Models.

Fuzzy clustering-based neural networks (FCNNs) based on information granulation techniques have been shown to be effective Takagi-Sugeno (TS)-type fuzzy models. However, the existing FCNNs could not cope well with sequential learning tasks. In this study, we introduce incremental FCNNs (IFCNNs), which could dynamically update themselves whenever new learning data (e.g., single datum or block data) are incorporated into the dataset. Specifically, we employ dynamic (incremental) fuzzy C-means (FCMs) clustering algorithms to reveal a structure in data and divide the entire input space into several subregions. In the aforementioned partition, the dynamic FCM adaptively adjusts the position of its prototypes by using sequential data. Due to the time-sharing arrival of training data, compared with batch learning models, incremental learning methods may lose classification (prediction) accuracy. In order to tackle this challenge, we utilize quasi-fuzzy local models (QFLMs) based on modified Schmidt neural networks to replace the popular linear functions in TS-type fuzzy models to refine and enhance the ability to represent the behavior of fuzzy subspaces. Meanwhile, the recursive least square error (LSE) estimation is utilized to update the weights of QFLMs from one-by-one or block-by-block (fixed or varying block size) learning data. In addition, the L2 regularization is considered to ameliorate the deterioration of generalization abilities caused by potential overfitting when carrying out weight estimation. The proposed method leads to the construction of FCNNs in a new way, which can effectively deal with incremental data as well as deliver sound generalization capability. Extensive machine-learning datasets and a real-world application are employed to show the validity and performance of the presented methods. From the experimental results, we show that the proposal can maintain sound classification accuracy when effectively processing sequential data.

Fuzzy Decision Rule-Based Online Classification Algorithm in Fuzzy Formal Decision Contexts

Formal concept analysis (FCA) extracts interpretable rules by using implication relationships between concepts, which is an effective method for acquiring knowledge. In this paper, a fuzzy decision rule-based online classification algorithm called OFRCA is designed by combining online learning theory and FCA in a fuzzy formal decision context. First, the original weight vector of all attributes is obtained by fusing the original deterministic decision rules. Second, incremental fuzzy decision rules are obtained according to the added objects. Then for the incremental fuzzy decision rules, OFRCA updates the weight vector based on minimizing the loss function. At the end of the process, all the rules are fused into an attributeweighted classifier with the final weight vector. In this paper, we employ the regret to obtain a learning guarantee for OFRCA. The growth rate of OFRCA's regret converges to 0 as the number of iterations increases in the ideal state, which provides an effective learning guarantee for OFRCA. To verify the effectiveness of the proposed algorithm, this paper conducted numerical experiments and systematically analyzed the experimental results, which demonstrated that OFRCA achieved the highest advanced classification performance among the compared algorithms.

An incremental fuzzy approach to risk-based evaluation of process equipment isolation schemes

Any time that process equipment needs to be out of service for inspection, maintenance, cleaning, or repair, sufficient isolation should be applied to isolate the equipment from the hazardous energies. Opting and implementing a proper scheme to isolate such equipment is critical to prevent accidents in process plants.Conventional risk-based methods to determine the isolation schemes are not so effective in dealing with subjective errors and uncertainties. Therefore, in this study we have developed an incremental fuzzy system to cope with the aforesaid limitations of conventional risk-based methods. In the proposed model, a numerical technique is applied for developing membership functions to reduce the uncertainty. In the incremental fuzzy model, three fuzzy inference systems in three levels are generated to calculate a release factor, outcome factor, and isolation level.Applying the proposed model to a three-phase separator, the results of the proposed model were compared with those of a conventional risk-based method, demonstrating that the proposed model can effectively handle the uncertainty while keeping the simplicity of the conventional approaches. The results are more transparent, detailed, and thus of greater value in identifying isolation schemes. Therefore, the proposed model can be an effective alternative to the conventional methods currently used in process plants for determination of isolation schemes.

Incremental Fuzzy Clustering Based on Feature Reduction

In the era of big data, more and more datasets are gradually beyond the application scope of traditional clustering algorithms because of their large scale and high dimensions. In order to break through the limitations, incremental mechanism and feature reduction have become two indispensable parts of current clustering algorithms. Combined with single-pass and online incremental strategies, respectively, we propose two incremental fuzzy clustering algorithms based on feature reduction. The first uses the Weighted Feature Reduction Fuzzy C-Means (WFRFCM) clustering algorithm to process each chunk in turn and combines the clustering results of the previous chunk into the latter chunk for common calculation. The second uses the WFRFCM algorithm for each chunk to cluster at the same time, and the clustering results of each chunk are combined and calculated again. In order to investigate the clustering performance of these two algorithms, six datasets were selected for comparative experiments. Experimental results showed that these two algorithms could select high-quality features based on feature reduction and process large-scale data by introducing the incremental strategy. The combination of the two phases can not only ensure the clustering efficiency but also keep higher clustering accuracy.

Coronary Heart Disease Diagnosis Through Self-Organizing Map and Fuzzy Support Vector Machine with Incremental Updates

The trade-off between computation time and predictive accuracy is important in the design and implementation of clinical decision support systems. Machine learning techniques with incremental updates have proven its usefulness in analyzing large collection of medical datasets for diseases diagnosis. This research aims to develop a predictive method for heart disease diagnosis using machine learning techniques. To this end, the proposed method is developed by unsupervised and supervised learning techniques. In particular, this research relies on Principal Component Analysis (PCA), Self-Organizing Map, Fuzzy Support Vector Machine (Fuzzy SVM), and two imputation techniques for missing value imputation. Furthermore, we apply the incremental PCA and FSVM for incremental learning of the data to reduce the computation time of disease prediction. Our data analysis on two real-world datasets, Cleveland and Statlog, showed that the use of incremental Fuzzy SVM can significantly improve the accuracy of heart disease classification. The experimental results further revealed that the method is effective in reducing the computation time of disease diagnosis in relation to the non-incremental learning technique.

Decentralized Incremental Fuzzy Reinforcement Learning for Multi-Agent Systems

We present a new incremental fuzzy reinforcement learning algorithm to find a sub-optimal policy for infinite-horizon Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs). The algorithm addresses the high computational complexity of solving large Dec-POMDPs by generating a compact fuzzy rule-base for each agent. In our method, each agent uses its own fuzzy rule-base to make the decisions. The fuzzy rules in these rule-bases are incrementally created and tuned according to experiences of the agents. Reinforcement learning is used to tune the behavior of each agent in such a way that maximum global reward is achieved. In addition, we propose a method to construct the initial rule-base for each agent using the solution of the underlying MDP. This drastically improves the performance of the algorithm in comparison with random initialization of the rule-base. We assess the performance of our proposed method using several benchmark problems in comparison with some state-of-the-art methods. Experimental results show that our algorithm achieves better or similar reward when compared with other methods. However, from the runtime point of view, our method is superior to all previous methods. Using a compact fuzzy rule-base not only decreases the amount of memory used but also significantly speeds up the learning phase.

A robust FACTS based fuzzy control scheme for dynamic stabilization of generator station

Abstract The paper presents a Flexible Alternating Current Transmission Systems (FACTS) based dynamic stabilization scheme using a modified series–parallel switched filter compensation (MSPFC). The proposed dynamic scheme is controlled by an Incremental Fuzzy Logic controller (MIFLC) to ensure fast response dynamic voltage stabilization and efficient energy utilization. The MIFLC employs a multi loop dynamic error driven time-descaled regulation to ensure the fast response of the dynamic controller. A second Weighted Modified PID controller with fixed gains is assessed with the proposed MIFLC controller. The modified control schemes are validated under normal and fault operating situations to ensure fast dynamic control, ac power quality, feeder loss reduction, efficient energy utilization and dynamic AC voltage stabilization regulation. The performance of the proposed controllers is assessed using statistical studies and qualitative comparison that prove the high ability of the proposed MIFLC compared with modified PID controller.

Incremental Fuzzy Association Rule Mining for Classification and Regression

The aim of mining fuzzy association rules is to find both the association and the casual relationships between the itemsets. With the arrival of dynamic data, the fuzzy association rules should be updated in real time. However, most of the existing algorithms must remine the updated database and can only be applied in classification. This paper proposes an incremental fuzzy association rule mining algorithm to solve classification and regression problems. First, the sliding window is adopted to divide the fuzzy dataset. Second, the dynamic fuzzy variable selection algorithm is adopted to select variables for reducing the search space of the fuzzy association rule mining. Finally, in each sliding window, the result of variable selection is used to incrementally mine the causal fuzzy association rules with the fuzzy Eclat algorithm. When new data are added, the process judges whether concept drift occurs, and if so, the rule set is updated; otherwise, the original rule set is still applied. The weights of the rules are calculated to find the evolving relationship. The simulation result shows that this algorithm can improve accuracy and efficiency.

Mobile Target Coverage and Tracking on Drone-Be-Gone UAV Cyber-Physical Testbed

Mobile wireless sensor networks have been extensively deployed for enhancing environmental monitoring and surveillance. The availability of low-cost mobile robots equipped with a variety of sensors makes them promising in target coverage tasks. They are particularly suitable where quick, inexpensive, or nonlasting visual sensing solutions are required. In this paper, we consider the problem of low complexity target tracking to cover and follow moving targets using flying robots. We tackle this problem by clustering targets while estimating the camera location and orientation for each cluster separately through a cover-set coverage method. We also leverage partial knowledge of target mobility to enhance the efficiency of our proposed algorithms. Three computationally efficient approaches are developed: predictive fuzzy, predictive incremental fuzzy, and local incremental fuzzy. The objective is to find a compromise among coverage efficiency, traveled distance, number of drones required, and complexity. The targets move according to one of the following three possible mobility patterns: random waypoint, Manhattan grid, and reference point group mobility patterns. The feasibility of our algorithms and their performance are also tested on a real-world indoor testbed called drone-be-gone, using Parrot AR.Drone quadcopters. The deployment confirms the results obtained with simulations and highlights the suitability of the proposed solutions for real-time applications.

Developing Communication Strategy for Multi-Agent Systems with Incremental Fuzzy Model

Communication can guarantee the coordinated behavior in the multi-agent systems. However, in many real-world problems, communication may not be available at every time because of limited bandwidth, noisy environment or communication cost. In this paper, we introduce an algorithm to develop a communication strategy for cooperative multi-agent systems in which the communication is limited. This method employs a fuzzy model to estimate the benefit of communication for each possible situation. This specifies minimal communication that is necessary for successful joint behavior. An incremental method is also presented to create and tune our fuzzy model that reduces the high computational complexity of the multi-agent systems. We use several standard benchmark problems to assess the performance of our proposed method. Experimental results show that the generated communication strategy can improve the performance as well as full-communication strategy, while the agents utilize little communication.

Incremental fuzzy cluster ensemble learning based on rough set theory

To deal with the uncertainty, vagueness and overlapping distribution within the data sets, a novel incremental fuzzy cluster ensemble method based on rough set theory (IFCERS) is proposed by the idea of combining clustering analysis task with classification techniques. Firstly, on the basis of soft clustering results, the positive region, boundary region and negative region of clustering ensemble are obtained by applying the construction of rough approximation in rough set theory, and then a group structure within data points of positive region is obtained by adopting a fuzzy cluster ensemble method. Secondly, by combining with the supervised ensemble learning method, e.g., random forests, the obtained group structure is used to construct the random forests classifier to classify the data points in boundary region. Finally, all the acquired group structure is used to train the random forests classifier to classify the data points of negative region. Experimental evaluations on UCI machine learning repository datasets verify the effectiveness of the proposed method. It is also shown that the quality of the final solution has a weak correlation with the ensemble size, the parameter setting on the rough approximations construction is appropriate, and the proposed method is robust towards the diversity from hard clustering members.

Nanocrystalline Silicon Oxide Impedance Immunosensors for Sub-Femtomolar Mycotoxin Estimation in Corn Samples by Incremental Fuzzy Approach

Detection of trace quantities of common mycotoxins (which have carcinogenic effects) in food samples with sufficient accuracy when present with large quantities of non-target toxins is an existing challenge. To address the problem, in this paper, we have deployed nanocrystalline silicon oxide impedance immunosensor array coupled with incremental fuzzy logic. These sensors have been reported earlier to be more sensitive and specific, compared with others. But toxin estimation becomes sufficiently imprecise especially when the concentration of the non-target toxin is significantly more than that of the target toxin. It is, therefore, expected that this problem will aggravate for real food samples. Thus, to make these sensors commercially viable, the sensor data have been processed by the incremental fuzzy approach. The flexibility in this approach has enabled estimation of three mycotoxins in corn samples procured from two different geographical locations of India. The detection limit achieved is as low as 0.1 fg/ml with 93% accuracy even in presence of large quantities of non-target toxins and with limited calibration data set. In comparison with the existing reports, this is the most sensitive and selective approach for mycotoxin estimation in real food samples with negligible effect of food matrix interference.

Incremental Fuzzy Clustering With Multiple Medoids for Large Data

As an important technique of data analysis, clustering plays an important role in finding the underlying pattern structure embedded in unlabeled data. Clustering algorithms that need to store all the data into the memory for analysis become infeasible when the dataset is too large to be stored. To handle such large data, incremental clustering approaches are proposed. The key idea behind these approaches is to find representatives (centroids or medoids) to represent each cluster in each data chunk, which is a packet of the data, and final data analysis is carried out based on those identified representatives from all the chunks. In this paper, we propose a new incremental clustering approach called incremental multiple medoids-based fuzzy clustering (IMMFC) to handle complex patterns that are not compact and well separated. We would like to investigate whether IMMFC is a good alternative to capturing the underlying data structure more accurately. IMMFC not only facilitates the selection of multiple medoids for each cluster in a data chunk, but also has the mechanism to make use of relationships among those identified medoids as side information to help the final data clustering process. The detailed problem formulation, updating rules derivation, and the in-depth analysis of the proposed IMMFC are provided. Experimental studies on several large datasets that include real world malware datasets have been conducted. IMMFC outperforms existing incremental fuzzy clustering approaches in terms of clustering accuracy and robustness to the order of data. These results demonstrate the great potential of IMMFC for large-data analysis.

Development an Adaptive Incremental Fuzzy PI Controller for a HVAC System

This paper presents an adaptive incremental fuzzy PI controller (AIFPI) for a heating, ventilating, and air conditioning (HVAC) system capable of maintaining comfortable conditions under varying thermal loads. The HVAC system has two subsystems and is used to control indoor temperature and humidity in a thermal zone. As the system has strong-coupling and non-linear characteristics, fixed PI controllers have poor control performance and more energy consumption. Aiming to solve the problem, fuzzy control and PI control are combined together organically. In the proposed control scheme, the error of the system output and its derivative are taken as two parameters necessary to adapt the proportional (P) and integral (I) gains of the PI controller based on fuzzy reasoning according to practical control experiences. To evaluate the effectiveness of the proposed control methods in the HVAC system, it is compared with a fixed well-tuned PI controller. The results demonstrate that the AIFPI controller has more superior performance than the latter.

Incremental Fuzzy Mining of Gene Expression Data for Gene Function Prediction

Due to the complexity of the underlying biological processes, gene expression data obtained from DNA microarray technologies are typically noisy and have very high dimensionality and these make the mining of such data for gene function prediction very difficult. To tackle these difficulties, we propose to use an incremental fuzzy mining technique called incremental fuzzy mining (IFM). By transforming quantitative expression values into linguistic terms, such as highly or lowly expressed, IFM can effectively capture heterogeneity in expression data for pattern discovery. It does so using a fuzzy measure to determine if interesting association patterns exist between the linguistic gene expression levels. Based on these patterns, IFM can make accurate gene function predictions and these predictions can be made in such a way that each gene can be allowed to belong to more than one functional class with different degrees of membership. Gene function prediction problem can be formulated both as classification and clustering problems, and IFM can be used either as a classification technique or together with existing clustering algorithms to improve the cluster groupings discovered for greater prediction accuracies. IFM is characterized also by its being an incremental data mining technique so that the discovered patterns can be continually refined based only on newly collected data without the need for retraining using the whole dataset. For performance evaluation, IFM has been tested with real expression datasets for both classification and clustering tasks. Experimental results show that it can effectively uncover hidden patterns for accurate gene function predictions.

Dynamic Fuzzy Pattern Matching for the monitoring of non stationary processes

In the domain of diagnosis by Pattern Recognition, a pattern is a simplified observation about the system state and each class, containing similar patterns, represents a functioning mode. Classes issued of non stationary processes are dynamic and their characteristics vary over the time. In this paper, the classification method Incremental Fuzzy Pattern Matching (IFPM) is developed for the monitoring of non stationary processes. This development is based on the monitoring of the accumulative changes in the data distribution. When these changes reach a threshold prefixed by an expert, the data distribution will be recursively updated online using the recent and useful patterns.

Design of an advanced incremental fuzzy logic controller for laser surface heat treatments

This work presents an innovative incremental PI fuzzy logic controller developed specifically to laser surface heat treatments, analyzing the specific issues related to the monitoring and control of the process. This real time control system improves considerably the treatment uniformity, reducing the rejection rate and increasing the productivity and final quality of the obtained products. An interesting contribution of this work is the characterization of the developed control strategy in terms of several quantitative criteria not usually analyzed, specially the design time and the experience and knowledge needed to develop and tune the control algorithm, without forgetting the classical validation criteria, such as the rise and settling time, the overshoot, and the steady state error, etc.

Design of incremental fuzzy PI controllers for a gas-turbine plant

In this paper, incremental fuzzy proportional integral (PI) speed and temperature controllers for a heavy-duty gas-turbine plant are presented. To improve performance, an analysis of incremental fuzzy PI control is provided, and new fuzzy control rules are proposed. In applying the fuzzy PI control to a gas-turbine plant, all gains are optimized by an adaptive genetic algorithm. We show the performance improvement of the proposed controller compared with conventional PI controller via simulations.

Adaptive neuro-fuzzy and fuzzy decision tree classifiers as applied to seafloor characterization

This paper investigates the influence of various backscattered echo parameters collected at an echosounder frequency of 200 kHz on the performance of the neuro-fuzzy and fuzzy decision tree classifiers of a seabed. In particular, the wavelet coefficients of the bottom echo were investigated along with other echo parameters like energy, amplitude, slope of the falling part of the echo, etc. The data were processed in an Adaptive Neuro Fuzzy Inference System (ANFIS), which was implemented in two multistage structures, viz.; Incremental Fuzzy Neural Network (IFNN) and Aggregated Fuzzy Neural Network (AFNN). The number of input parameters for the networks was reduced by using the Principal Component Analysis (PCA). A fuzzy decision tree algorithm was developed and used directly (without PCA data reduction) in the classification procedure utilizing the same data. The performances of both approaches were analyzed and compared.

Coordinative Control of Different Kind of Manipulators Using an Incremental Fuzzy Compensator

A coordinative motion control is described for two different kind of manipulators by using a master-slave concept. Here, the master part consists of a pantagraph-type two link manipulator driven by a torque command, whereas the slave part is an industrial manipulator driven by a position command with a force torque sensor. To achieve a desired contact force between the slave manipulator and an object, a compensative position command is generated by using an incremental fuzzy reasoning with the force sensor information. The effectiveness is verified by experiments.