Adaptive Resonance Theory Map Research Articles

Imbalanced dataset classification using fuzzy ARTMAP and computational intelligence techniques

Recently, fuzzy adaptive resonance theory mapping (ARTMAP) neural networks are applied to solving complex problems due to their plasticity-stability capability and resonance property. An imbalanced dataset occurs when there is the presence of one class containing a greater number of instances than other classes. It is skewed representation of data. Many standard algorithms have failed in mitigating imbalanced dataset problems. There are four paradigms used-data level, algorithm level, cost-sensitive, and ensemble method in solving imbalanced dataset problems. Here we put forward a method to solve the imbalanced dataset problem by a brain-neuron framework and an ensemble of a special type of artificial neural network (ANN) called fuzzy ARTMAP thereafter we applied a clustering algorithm known as fuzzy C-means clustering to handle missing value and also propose to make fuzzy ARTMAP cost-sensitive. Results indicate 100% accuracy in classification.

Online Feature Selection Using Sparse Gradient

Feature Selection (FS) is an important preprocessing step in data analytics. It is used to select a subset of the original feature set such that the selected subset does not affect the classification performance significantly. Its objective is to remove irrelevant and redundant features from the original dataset. FS can be done either in offline mode or in online mode. The basic assumption in the former mode is that the entire dataset has been available for the FS algorithm; and the FS algorithm takes multiple epochs to select optimal feature subset that gives good accuracy. In contrast, the FS algorithms in online mode take input data one instance at a time and accumulate knowledge by learning each one of them. In online mode each instance of the original dataset is considered as training and testing sample as well. The offline FS algorithms require long time periods, if the data to be processed is large such as Big data. Whereas online FS algorithms will take only one epoch to learn the entire data and can produce the results swiftly which is highly desirable in the case of Big data. This paper deals with the online FS problem and provides a novel Feature Selection algorithm which uses the Sparse Gradient method to build a sparse classifier. In this proposed method, an online classifier is built and maintained throughout the learning process and feature weights, which are limited to a particular boundary limit, are reduced in a step by step decrement process. This method creates sparsity in the classifier. Effectively, the built classifier is used to select optimal feature subset from the incoming data. As this method reduces the weights in the classifier in step by step manner, only those important features which have value higher than the boundary survive from this repeated decrement process. The resultant optimal feature subset is formed using these non-zero weighted features. Most significantly, this particular method can be used with any learning algorithm. To show its applicability with different learning algorithms, various online feature selection models have been built using Learning Vector Quantization, Radial Basis Function Networks and Adaptive Resonance Theory MAP. In all these models, the proposed Sparse Gradient method is used. The encouraging results shows the effectiveness of the proposed method with different learning algorithms in medium and large sized benchmark datasets.

SELF-ORGANIZING RESERVOIR NETWORK FOR ACTION RECOGNITION

Current research in human action recognition (HAR) focuses on efficient and effective modelling of the temporal features of human actions in 3-dimensional space. Echo State Networks (ESNs) are one suitable method for encoding the temporal context due to its short-term memory property. However, the random initialization of the ESN's input and reservoir weights may increase instability and variance in generalization. Inspired by the notion that input-dependent self-organization is decisive for the cortex to adjust the neurons according to the distribution of the inputs, a Self-Organizing Reservoir Network (SORN) is developed based on Adaptive Resonance Theory (ART) and Instantaneous Topological Mapping (ITM) as the clustering process to cater deterministic initialization of the ESN reservoirs in a Convolutional Echo State Network (ConvESN) and yield a Self-Organizing Convolutional Echo State Network (SO-ConvESN). SORN ensures that the activation of ESN’s internal echo state representations reflects similar topological qualities of the input signal which should yield a self-organizing reservoir. In the context of HAR task, human actions encoded as a multivariate time series signals are clustered into clustered node centroids and interconnectivity matrices by SORN for initializing the SO-ConvESN reservoirs. By using several publicly available 3D-skeleton-based action recognition datasets, the impact of vigilance threshold and reservoir perturbation of SORN in performing clustering, the SORN reservoir dynamics and the capability of SO-ConvESN on HAR task have been empirically evaluated and analyzed to produce competitive experimental results.

Design of ensemble recurrent model with stacked fuzzy ARTMAP for breast cancer detection

PurposeIn time and accurate detection of cancer can save the life of the person affected. According to the World Health Organization (WHO), breast cancer occupies the most frequent incidence among all the cancers whereas breast cancer takes fifth place in the case of mortality numbers. Out of many image processing techniques, certain works have focused on convolutional neural networks (CNNs) for processing these images. However, deep learning models are to be explored well.Design/methodology/approachIn this work, multivariate statistics-based kernel principal component analysis (KPCA) is used for essential features. KPCA is simultaneously helpful for denoising the data. These features are processed through a heterogeneous ensemble model that consists of three base models. The base models comprise recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU). The outcomes of these base learners are fed to fuzzy adaptive resonance theory mapping (ARTMAP) model for decision making as the nodes are added to the F_2ˆa layer if the winning criteria are fulfilled that makes the ARTMAP model more robust.FindingsThe proposed model is verified using breast histopathology image dataset publicly available at Kaggle. The model provides 99.36% training accuracy and 98.72% validation accuracy. The proposed model utilizes data processing in all aspects, i.e. image denoising to reduce the data redundancy, training by ensemble learning to provide higher results than that of single models. The final classification by a fuzzy ARTMAP model that controls the number of nodes depending upon the performance makes robust accurate classification.Research limitations/implicationsResearch in the field of medical applications is an ongoing method. More advanced algorithms are being developed for better classification. Still, the scope is there to design the models in terms of better performance, practicability and cost efficiency in the future. Also, the ensemble models may be chosen with different combinations and characteristics. Only signal instead of images may be verified for this proposed model. Experimental analysis shows the improved performance of the proposed model. This method needs to be verified using practical models. Also, the practical implementation will be carried out for its real-time performance and cost efficiency.Originality/valueThe proposed model is utilized for denoising and to reduce the data redundancy so that the feature selection is done using KPCA. Training and classification are performed using heterogeneous ensemble model designed using RNN, LSTM and GRU as base classifiers to provide higher results than that of single models. Use of adaptive fuzzy mapping model makes the final classification accurate. The effectiveness of combining these methods to a single model is analyzed in this work.

An Enhanced Weight Update Method for Simplified ARTMAP to Classify Groundwater Data

The groundwater for aquatic purposes must be assessed prior to its consumption. Huge number of conventional methods are existing for assessing the quality of groundwater. The water quality index is one of the important conventional methods to assess the groundwater quality. But the conventional methods alone are not enough to assess groundwater quality as well as classify based on its purity. In this paper, we propose an enhanced weight update method for Simplified Fuzzy Adaptive Resonance Theory model to classify the groundwater quality depending on the relative weights of the groundwater quality parameters. Finding the optimal weights is the key to achieve better accuracy of the model, most of the nonlinear models fails to exhibit good accuracy if they fail to learn the optimal weights in the learning process. The aim of the work is to find the good fit between the predicted and the actual groundwater quality grades by identifying the optimal weights of the network by the enhanced weight update method. The Simplified Fuzzy Adaptive Resonance Theory map with the enhanced weight update method performance is justified by comparing it with the Simplified Fuzzy Adaptive Resonance Theory Map. The enhanced weight update method improves the accuracy of the Simplified Fuzzy Adaptive Resonance Theory Map in classifying and predicting the groundwater quality.

Optimized Bayesian adaptive resonance theory mapping model using a rational quadratic kernel and Bayesian quadratic regularization

Optimized Bayesian adaptive resonance theory mapping model using a rational quadratic kernel and Bayesian quadratic regularization

Diagnosing Metabolic Syndrome Using Genetically Optimised Bayesian ARTMAP

Metabolic Syndrome (MetS) constitutes of metabolic abnormalities that lead to non-communicable diseases, such as type II diabetes, cardiovascular diseases, and cancer. Early and accurate diagnosis of this abnormality is required to prevent its further progression to these diseases. This paper aims to diagnose the risk of MetS using a new non-clinical approach called “genetically optimized Bayesian adaptive resonance theory mapping” (GOBAM). We evolve the Bayesian adaptive resonance theory mapping (BAM) by using genetic algorithm to optimize the parameters of BAM and its training input sequence. We use the GOBAM algorithm to classify individuals as either being at risk of MetS or not at risk of MetS with a related posterior probability, which ranges between 0 and 1. A data set of 11 237 Malaysians from the CLUSTer study stratified by age and gender into four subcategories was used to evaluate the proposed GOBAM algorithm. The comparative evaluation of our results suggested that the GOBAM performs significantly better than other classical adaptive resonance theory mapping models on the area under the receiver operating characteristic curves (AUC) and others criteria. Our algorithm gives an AUC of 86.42 %, 87.04 %, 91.08 %, and 89.24 % for the young female, middle aged female, young male, and middle-aged male subcategories, respectively. The proposed model can be used to support medical practitioners in accurate and early diagnosis of MetS.

Energy Disaggregation of Appliances Consumptions Using HAM Approach

Non-intrusive load monitoring (NILM) makes it possible for users to track the energy consumption of a household. In this paper, we present a new hybrid energy disaggregation approach named HAM. This event-based load disaggregation algorithm uses an improved multi-layer Hungarian algorithm to match appliances transient features and a supervised adaptive resonance theory mapping neural network (ARTMAP) to cluster steady features. This approach using a modified dual sliding window-based cumulative sum control chart algorithm (DSWC) to detect the transient event first, and we convert the multi-dimensional electrical features of appliances into a bipartite graph matching problem. This way, an improved Hungarian algorithm is proposed to find the perfect matching when appliances are in different states. For classification and identification, the ARTMAP network is used to learn and classify the steady features of appliances. Furthermore, we introduced a grey correlation evaluation and multiple matching strategies to increase the fitness and accuracy of the approach. Experimental results demonstrate that the proposed HAM outperforms the comparative algorithm in both our resident appliances dataset (RAD) and BLUED public dataset. The proposed approach could also facilitate NILM more applicable for common households.

HearthBot: An Autonomous Agent Based on Fuzzy ART Adaptive Neural Networks for the Digital Collectible Card Game HearthStone

Digital collectible card games, as partially observable games based on alternating turns, such as HearthStone, have been the most played card games in recent years, where the main challenge is the creation of strategies capable of subdue the enemy's moves. From the artificial intelligence perspective, the space of possible strategies is large and dynamic due to the number of cards and actions combinations and also to randomness, which makes the design of efficient autonomous agents a hard problem. This paper presents HearthBot, an autonomous agent that plays HearthStone through an adaptive neural network inspired in the fuzzy adaptive resonance associative map and adaptive resonance theory map. This paper also proposes a new mechanism to categorize and predict information to overcome the overgeneralization problem from those networks. Furthermore, the proposed solution was implemented as a parallel adaptive neural network for a graphics processing unit that achieves a performance compatible with the ones obtained for deep learning methods. HearthBot win rate was evaluated in two experiments playing against a Monte Carlo tree search heuristic with competitive decks on a HearthStone simulator called Metastone. Results show that the proposed solution allows HearthBot to obtain an average win rate performance of 80% against known decks and 70% against unknown decks.

Assessment of bearing degradation by using intrinsic mode functions and k-medoids clustering

Recently, the prognostic is much attention in the field of vibration-based bearing monitoring and it plays a significant role to avoid accidents. In rotary machines, the bearing failure is one of the major causes of machinery shutdown. The bearing degradation monitoring is a great concern for prevention of bearing failures. This paper presents an approach for the bearing degradation evaluation based on empirical mode decomposition and k-medoids clustering. The bearing fault features are extracted from vibration data using an intrinsic mode function of empirical mode decomposition process. The extracted features are then subjected to k-medoids clustering for obtaining normal and failure state. Assurance values curve, which is based on dissimilarity data of test object to the normal state is found and retained as degradation indicator for evaluation of bearing health. Experiment was conducted to verify and assess the effectiveness of proposed method for the evaluation of performance of bearing degradation. To justify the preeminence of recommended approach, the root mean square and kurtosis features of time domain, envelope analysis of diagnosis method, and degradation assessment classifiers, i.e. simplified fuzzy adaptive resonance theory map are commonly used in the bearing analysis compared with the proposed method. Early stage detection of degradation more accurately, the recommended method is better than the time-domain features and simplified fuzzy adaptive resonance theory map based on performance degradation assessment on bearing. Moreover, envelope analysis can be used to verify the early stage defect detected by the proposed method. In this study, it has been seen that the k-medoids clustering is an efficient tool to assess the performance of degradation of bearings.

Online residual useful life prediction of large-size slewing bearings—A data fusion method

To decrease breakdown time and improve machine operation reliability, accurate residual useful life (RUL) prediction has been playing a critical role in condition based monitoring. A data fusion method was proposed to achieve online RUL prediction of slewing bearings, which consisted of a reliability based RUL prediction model and a data driven failure rate (FR) estimation model. Firstly, an RUL prediction model was developed based on modified Weibull distribution to build the relationship between RUL and FR. Secondly, principal component analysis (PCA) was introduced to process multi-dimensional life-cycle vibration signals, and continuous squared prediction error (CSPE) and its time-domain features were employed as equipment performance degradation features. Afterwards, an FR estimation model was established on basis of the degradation features and relevant FRs using simplified fuzzy adaptive resonance theory map (SFAM) neural network. Consequently, real-time FR of equipment can be obtained through FR estimation model, and then accurate RUL can be calculated through the RUL prediction model. Results of a slewing bearing life test show that CSPE is an effective indicator of performance degradation process of slewing bearings, and that by combining actual load condition and real-time monitored data, the calculation time is reduced by 87.3% and the accuracy is increased by 0.11%, which provides a potential for online RUL prediction of slewing bearings and other various machineries.

A Novel Clustering Method Combining ART with Yu’s Norm for Fault Diagnosis of Bearings

Clustering methods have been widely applied to the fault diagnosis of mechanical system, but the characteristic that the number of cluster needs to be determined in advance limits the application range of the method. In this paper, a novel clustering method combining the adaptive resonance theory (ART) with the similarity measure based on the Yu’s norm is presented and applied to the fault diagnosis of rolling element bearings, which can be adaptive to generate the number of cluster by the vigilance parameter test. Time-domain features, frequency-domain features, and time series model parameters are extracted to demonstrate the fault-related information about the bearings, and then considering the irrelevance or redundancy of some features many salient features are selected by an improved distance discriminant technique and input into the proposed clustering method to diagnose the faults of bearings. The experiment results confirmed that the proposed clustering method can diagnose the fault categories accurately and has better diagnosis performance compared with fuzzy ART and Self-Organizing Feature Map (SOFM).

Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations

In this work, an effort is made to characterize seven bearing states depending on the energy entropy of Intrinsic Mode Functions (IMFs) resulted from the Empirical Modes Decomposition (EMD). Three run-to-failure bearing vibration signals representing different defects either degraded or different failing components (roller, inner race and outer race) with healthy state lead to seven bearing states under study. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are used for feature reduction. Then, six classification scenarios are processed via a Probabilistic Neural Network (PNN) and a Simplified Fuzzy Adaptive Resonance Theory Map (SFAM) neural network. In other words, the three extracted feature data bases (EMD, PCA and LDA features) are processed firstly with SFAM and secondly with a combination of PNN–SFAM. The computation of classification accuracy and scattering criterion for each scenario shows that the EMD–LDA–PNN–SFAM combination is the suitable strategy for online bearing fault diagnosis. The proposed methodology reveals better generalization capability compared to previous works and it is validated by an online bearing fault diagnosis. The proposed strategy can be applied for the decision making of several assets.

Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network

Accurate remaining useful life (RUL) prediction of critical assets is an important challenge in condition based maintenance to improve reliability and decrease machine’s breakdown and maintenance’s cost. Bearing is one of the most important components in industries which need to be monitored and the user should predict its RUL. The challenge of this study is to propose an original feature able to evaluate the health state of bearings and to estimate their RUL by Prognostics and Health Management (PHM) techniques.In this paper, the proposed method is based on the data-driven prognostic approach. The combination of Simplified Fuzzy Adaptive Resonance Theory Map (SFAM) neural network and Weibull distribution (WD) is explored. WD is used just in the training phase to fit measurement and to avoid areas of fluctuation in the time domain. SFAM training process is based on fitted measurements at present and previous inspection time points as input. However, the SFAM testing process is based on real measurements at present and previous inspections. Thanks to the fuzzy learning process, SFAM has an important ability and a good performance to learn nonlinear time series. As output, seven classes are defined; healthy bearing and six states for bearing degradation. In order to find the optimal RUL prediction, a smoothing phase is proposed in this paper. Experimental results show that the proposed method can reliably predict the RUL of rolling element bearings (REBs) based on vibration signals. The proposed prediction approach can be applied to prognostic other various mechanical assets.

Affect classification using genetic-optimized ensembles of fuzzy ARTMAPs

Training neural networks in distinguishing different emotions from physiological signals frequently involves fuzzy definitions of each affective state. In addition, manual design of classification tasks often uses sub-optimum classifier parameter settings, leading to average classification performance. In this study, an attempt to create a framework for multi-layered optimization of an ensemble of classifiers to maximize the system's ability to learn and classify affect, and to minimize human involvement in setting optimum parameters for the classification system is proposed. Using fuzzy adaptive resonance theory mapping (ARTMAP) as the classifier template, genetic algorithms (GAs) were employed to perform exhaustive search for the best combination of parameter settings for individual classifier performance. Speciation was implemented using subset selection of classification data attributes, as well as using an island model genetic algorithms method. Subsequently, the generated population of optimum classifier configurations was used as candidates to form an ensemble of classifiers. Another set of GAs were used to search for the combination of classifiers that would result in the best classification ensemble accuracy. The proposed methodology was tested using two affective data sets and was able to produce relatively small ensembles of fuzzy ARTMAPs with excellent affect recognition accuracy.

A Monte Carlo simulation based two-stage adaptive resonance theory mapping approach for offshore oil spill vulnerability index classification

In this paper, a Monte Carlo simulation based two-stage adaptive resonance theory mapping (MC-TSAM) model was developed to classify a given site into distinguished zones representing different levels of offshore Oil Spill Vulnerability Index (OSVI). It consisted of an adaptive resonance theory (ART) module, an ART Mapping module, and a centroid determination module. Monte Carlo simulation was integrated with the TSAM approach to address uncertainties that widely exist in site conditions. The applicability of the proposed model was validated by classifying a large coastal area, which was surrounded by potential oil spill sources, based on 12 features. Statistical analysis of the results indicated that the classification process was affected by multiple features instead of one single feature. The classification results also provided the least or desired number of zones which can sufficiently represent the levels of offshore OSVI in an area under uncertainty and complexity, saving time and budget in spill monitoring and response.

Identification of early-stage Alzheimer׳s disease using SFAM neural network

Alzheimer׳s disease (AD), the most common form of dementia, is a complex and very serious nervous disease. Currently no medication is really effective against it. Even, its diagnosis and management remain challenging research problem for scientists. This paper aims towards identifying early-stage AD based upon the characteristics of the non-oscillatory independent components (ICs) of the auditory event related potential (AERP) waveforms of an oddball task for healthy and newly diagnosed AD subjects. Using 27 sensors to record P300 Evoked Potentials (EPs) as features vectors to train the simplified fuzzy adaptive resonance theory map (SFAM) neural network as a classifier, normal and AD subjects were classified with higher than 95% of success. The use of the ARTMAP-familiarity discrimination (ARTMAP-FD) shows that the separation of the two populations was achieved with high success and without any mistake.

Multi-agent Gaussian Adaptive Resonance Theory Map for building energy control and thermal comfort management of UCLan's WestLakes Samuel Lindow Building

This paper presents a Gaussian Adaptive Resonance Theory Map (gARTMAP) incorporated to a multi-agent system (MAS) for building intelligent heat management system (IHMS), or the gARTMAP-MAS IHMS. The gARTMAP aims to maintain the desired space temperature defined by the building occupants (thermal comfort management) and improve energy efficiency by intelligently controlling the energy flow and usage in the building (building energy control) with minimal waste. The gARTMAP-MAS IHMS is a three-layer MAS, consisting of an agent in the Source Layer responsible for building energy control, agents in the User Layer for thermal comfort management, and an agent in the Mediator Layer which mediates the communication between the other two layers. Existing MAS typically uses a rule-based approach for its agents, and the rules are generally pre-defined. The incorporation of the gARTMAP to the agents provides additional adaptive capabilities via the use of its online learning mechanism. Simulation results demonstrated that the gARTMAP-MAS IHMS provides better (automated) energy control and thermal comfort management for a building environment in comparison to the existing rule-based MAS approach.

Hybrid Method for Vehicle Detection from CCTV Captured Image

This paper presents a hybrid method for vehicle detection from CCTV captured image. In order to overwhelm such complex details of the color image, the system combines artificial intelligence techniques to achieve automatic vehicle detection. These are techniques 2D principal component analysis (2DPCA), Fuzzy adaptive resonance theory (Fuzzy ART), genetic algorithm (GA) and self-organizing map. The proposed system can detect different vehicle sizes from different proportional image area. Bilinear interpolation is used to resize each proportional image area to vehicle feature matrix. The proposed system can detect various types of vehicles from the difference image background.

Classification Function of Radial-Basis Adaptive Resonance Theory Map and Its Application

This paper presents a radial basis ART-map and its application to classification problems. In order to classify input data, the system generates radial basis categories. Two key parameters can control the number and size of the categories. Performing numerical experiments for two types of traditional expectant mothers, we have investigated effects of key parameters on the classification functions.