Subtractive Clustering Algorithm Research Articles

An intelligent digital twinning approach for complex circuits

The digital twinning process is essential for transferring real-world objects to the Metaverse by creating accurate digital versions, known as digital twins. However, complex systems pose challenges in this process. With the increasing utilization of microwave components and circuits in telecommunication systems such as IoT, 5 G, and 6 G, the need for digital twins of these components arises. Nevertheless, high-frequency components exhibit intricate behavior, requiring advanced modeling techniques. Artificial intelligence (AI) provides a powerful tool for enhancing the reliability and accuracy of estimated models in such cases. In this study, a microstrip lowpass filter (LPF) is designed, fabricated, and measured as the physical twin. An intelligent digital twinning approach is employed using a machine learning method based on an adaptive neuro-fuzzy inference system (ANFIS), trained by a subtractive clustering algorithm. The resulting digital twin of the LPF proves valuable for communication networks and IoT applications. Moreover, this research showcases the applicability and accessibility of machine learning in creating digital twins of electromagnetic components for communication cyber-physical systems (CPSs) and the Metaverse. Furthermore, the proposed method exhibits adaptability to various passive and active electrical or electronic circuits. By harnessing the potential of AI and digital twinning, this study presents a robust and accurate approach for modeling and analyzing complex circuits, specifically in the context of communication systems and their integration into the Metaverse. The findings highlight the advantages of an intelligent digital twinning approach and its potential for advancing various domains involving complex circuitry.

Simulation-Enhanced MQAM Modulation Identification in Communication Systems: A Subtractive Clustering-Based PSO-FCM Algorithm Study

Signal modulation recognition is often reliant on clustering algorithms. The fuzzy c-means (FCM) algorithm, which is commonly used for such tasks, often converges to local optima. This presents a challenge, particularly in low-signal-to-noise-ratio (SNR) environments. We propose an enhanced FCM algorithm that incorporates particle swarm optimization (PSO) to improve the accuracy of recognizing M-ary quadrature amplitude modulation (MQAM) signal orders. The process is a two-step clustering process. First, the constellation diagram of the received signal is used by a subtractive clustering algorithm based on SNR to figure out the initial number of clustering centers. The PSO-FCM algorithm then refines these centers to improve precision. Accurate signal classification and identification are achieved by evaluating the relative sizes of the radii around the cluster centers within the MQAM constellation diagram and determining the modulation order. The results indicate that the SC-based PSO-FCM algorithm outperforms the conventional FCM in clustering effectiveness, notably enhancing modulation recognition rates in low-SNR conditions, when evaluated against a variety of QAM signals ranging from 4QAM to 64QAM.

An Adaptive Network-Based Approach for Advanced Forecasting of Cryptocurrency Values

This paper describes an architecture for predicting the price of cryptocurrencies for the next seven days using the Adaptive Network Based Fuzzy Inference System (ANFIS). Historical data of cryptocurrencies and indexes that are considered are Bitcoin (BTC), Ethereum (ETH), Bitcoin Dominance (BTC.D), and Ethereum Dominance (ETH.D) in adaily timeframe. The methods used to teach the data are hybrid and backpropagation algorithms, as well as grid partition, subtractive clustering, and Fuzzy C-means clustering (FCM) algorithms, which are used in data clustering. The architectural performance designed in this paper has been compared with different inputs and neural network models in terms of statistical evaluation criteria. Finally, the proposed method can predict the price of digital currencies in a short time.

Subtractive clustering Takagi-Sugeno position tracking for humans by low-cost inertial sensors and velocity classification

In this work, open-loop position tracking using low-cost inertial measurement units is aided by Takagi-Sugeno velocity classification using the subtractive clustering algorithm to help generate the fuzzy rule base. Using the grid search approach, a suitable window of classified velocity vectors was obtained and then integrated to generate trajectory segments. Using publicly available experimental data, the reconstruction accuracy of the method is compared against four competitive pedestrian tracking algorithms. The comparison on selected test data, has demonstrated more competitive relative and absolute trajectory error metrics. The proposed method in this paper is also verified on an independent experimental data set. Unlike the methods which use deep learning, the proposed method has shown to be transparent (fuzzy rule base). Lastly, a sensitivity analysis of the velocity classification models to perturbations from the training orientation at test time is investigated, to guide developers of such data-driven algorithms on the granularity required in an ensemble modeling approach. The accuracy and transparency of the approach may positively influence applications requiring low-cost inertial position tracking such as augmented reality headsets for emergency responders.

Generalized predictive control using improved recurrent fuzzy neural network for a boiler-turbine unit

The ultra supercritical (USC) for the boiler-turbine unit has become an advanced power generation technology due to its high combustion efficiency and low-carbon emission. Considering the complex nonlinearity and uncertainty in USC boiler-turbine units, a novel recurrent fuzzy neural network (RFNN) is produced to model dynamic responses of nonlinear systems and improve the control performance of the outputs in the boiler-turbine unit. However, the number of fuzzy rules in previous networks is mostly predefined with experts’ experience, which contributes to the decline in the generalization and efficiency of system modeling. This challenge is tackled in this paper by a subtractive clustering (SC) algorithm, which can determine the optimal number of fuzzy sets in the proposed RFNN. Additionally, aiming at minimizing the tracking errors of the outputs in the boiler-turbine unit, a global generalized predictive control (GPC) strategy is further designed to control the fuel flow, the feedwater flow, and the steam governor valve in the boiler-turbine unit. With the real-time data generated in a 1000MW USC boiler-turbine unit, the proposed SC-RFNN-based GPC can achieve a testing root mean-square-error (RMSE) of 0.0411 as well as the lower integral absolute error (IAE) values of system outputs.

GPS Receivers Spoofing Detection Based on Subtractive, FCM and DBSCAN Clustering Algorithms

GPS receivers have a wide range of applications, but are not always secure. A spoofing attack is one source of conscious errors in which the counterfeit signal overcomes the authentic GPS signal and takes control of the receiver’s operation. Recently, GPS spoofing attack detection based on computational algorithms, such as machine learning, classification, wavelet transform and clustering, has been developing. This paper proposes multiple clustering algorithms for accurately clustering the authentic and spoofing signals, called subtractive, FCM and DBSCAN clustering. The spoofing attack is recognized using two distinct features: moving phase detector variance and norms of correlators. Spoofing and authentic signals have different patterns in the proposed features. According to the Dunn and Silhouette indexes, the validation of the results is investigated. The Dunn values for the proposed approaches are 0.8592, 0.5285 and 0.6039 for DBSCAN, FCM and subtractive clustering, respectively. Also, the DBSCAN algorithm is implemented at the RTL level because of its highest value for the Dunn index and algorithm verifiability. Using the Vivado tools, this algorithm is implemented and designed on a Xilinx Virtex 7 xc7vx690tffg1930-3 hardware device for two-dimensional data with 32-bit accuracy and 130 data points.

О выборе метода построения нечеткой модели прогнозирования состояния аккумулятора

Battery-powered electric vehicles are being currently considered to replace conventional non-environmental vehicles. Batteries could not be used without a control system, which development requires a mathematical model to predict the state of a separate battery. The Takagi --- Sugeno fuzzy system (fuzzy model) could become such a model. There are methods for automatic construction of fuzzy models according to the table of observations. However, unambiguous criteriafor selecting the appropriate method in each specific case are missing. The problem is considered of determining a method making it possible to obtain a fuzzy model that predicts the lithiumion battery voltage from the load current and the state of charge when discharging with direct current with the lowest meansquare error. The existing methods and their classes were reviewed, and five methods were selected for comparison. Prediction error by all the models obtained was unevenly distributed along the axis of the charge state, and it took the highest values in the range of 97--100 %. The lowest meansquare error was registered in the model built by the combined method using subtractive clustering, least squares method and adaptive network based on the adaptive neurofuzzy inference system. The error in such model was changing stepwise, which was associated with feature of the subtractive clustering algorithm, i.e., the formed clusters were of the same size

Lithofacies discrimination of the Ordovician unconventional gas-bearing tight sandstone reservoirs using a subtractive fuzzy clustering algorithm applied on the well log data: Illizi Basin, the Algerian Sahara

The main objective of this paper is to prove the capability of the fuzzy clustering algorithm for discriminating between lithofacies that are derived from the borehole log data of Ordovician tight sandstone reservoirs in the Illizi Basin of the Algerian South-Eastern Sahara. The technique is based on applying an unsupervised machine learning fuzzy algorithm on the natural gamma-ray, the photoelectric factor, the sonic log, the neutron porosity, and the bulk density well log data as an input to discriminate lithology into four lithofacies types: clay, sand, clayey sand, and sandy clay. The primary advantage of the fuzzy algorithms is that they can handle uncertainties and errors associated with the inaccurate or incomplete data of any measurements. Furthermore, it has a broader scope and a higher level of generality than the binary logic, which means that the results and interpretations that are based on this approach can be more appropriate and probable than other possible interpretations. A comparison between our algorithm's results and the results from the Kohonen Self-organizing Maps (SOM) and the Multilayer Perceptron (MPL) has also been carried out which proved that our approach provides better results than the other commonly applied neural networks. The obtained lithofacies types are highly comparable with that obtained from the core description data with minimal estimated errors. Therefore, this fuzzy algorithm can be applied as an alternative, fast, and low-cost technique for adequate lithofacies discrimination in case of lacking the core data.

Detecting fishing URLs using fuzzy clustering algorithms with global optimization

An algorithm for detecting phishing URLs (classifier) using fuzzy clustering is proposed, which includes choosing the type of intelligent classifier and justifying its parameters using global optimization methods. The following were studied as intellectual classifiers: subtractive clustering and fuzzy clustering of C-means. To find (adjust) the optimal (for a specific task) parameters of intelligent classifiers, the use of global optimization methods is justified, including genetic algorithm, direct random search, annealing simulation method, multicriteria optimization and threshold acceptance method. As a criterion of global optimization, a combined criterion was used, which includes the definition of the regularity criterion calculated on the test sample and the bias (minimum shift) criterion based on the analysis of solutions. By modeling in the Matlab environment with the help of standard and developed programs, the evaluated efficiency of using the proposed algorithm is evaluated on the example of experimental data – a set of 150 phishing and 150 secure URLs. The set of experimental data included information about the domain name registrar, the lifetime of the domain, the geolocation of the hosting server, the presence of a secure connection with a valid certificate. By simulation it is established that the fuzzy classifier with the subtractive clustering algorithm and using the Sugeno structure and 6 clusters meets the minimum of the combined criterion. All phishing URLs that were mistakenly classified as secure were found to have a secure con-nection with a valid certificate. Thus, further research should be aimed at exploring additional informative attributes (features) that could allow better separation of phishing and secure URLs.

ANFIS with input space division for modeling magnetorheological energy absorber

A magnetorheological energy absorber (MREA) is a promising actuator for vibration and shock mitigation due to its continuous and controllable damping force. To take full advantage of this feature, a high-fidelity model that can accurately predict the MREA dynamic force is required. Therefore, this study focuses on proposing adaptive neural-fuzzy inference system (ANFIS) models for MREA that use the impact speed, displacement, velocity, acceleration and current as inputs and the MREA force as output. Three types of ANFIS models are developed based on different input space division methods, namely, the grid partition (GP) method, subtractive clustering (SC) algorithm and fuzzy c-means (FCM) algorithm. The best ANFIS model is chosen from each category by six criteria, i.e., mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), coefficient of variation (cov), coefficient of determination (R2) and training time. In addition, the desirability function is proposed to further decide the best model because these criteria do not have a uniform trend. Then, a comprehensive comparative analysis of the three best models is performed. The results show that the ANFIS model with 53 FIS rules generated by the FCM algorithm has the largest global desirability of 0.66782, demonstrating that it is the best one to predict the dynamic force of MREA under high-speed impacts. Accordingly, the values of MAE, MAPE, RMSE, cov and R2 of this model varied in ranges of 0.31679-0.57118, 4.34181-8.43942, 0.44808-1.03095, 6.14134-15.23283 and 0.98973-0.99834, respectively, for various data sets.

Research for Fault Diagnosis Method and System for Diesel Engine Based on ANFIS

<p>After compliance verification, operating vehicles can enter the road transportation market. Diesel engine is the main power source of these vehicles, there will be some typical faults during the use of diesel engine, which will affect the technical status of vehicles. According to the fault diagnosis problem of diesel engine, a fault diagnosis method based on Adaptive-Network-Based Fuzzy Inference System(ANFIS) was proposed, Subtractive clustering algorithm was used to confirm the original structure of fuzzy inference model, and ANFIS was used to build an original fault diagnosis model of diesel engine. Hybrid algorithm is used to train the parameter of fuzzy rule, and the final model is established. Simulation experiment results show that the modeling algorithm based on subtractive clustering-ANFIS is effective. It has been found that the average error is 7%, the recognition accuracy is 93.33%. Simulation results show that the fitting ability, convergence speed and recognition accuracy of ANFIS model are all superior to back propagation neural networks (BPNN), and much more suitable as diesel engine fault diagnosis model. Finally, an effective fault diagnosis system is developed by using the given method.</p> <p> </p>

Natural Language Processing through the Subtractive Mountain Clustering Algorithm - A Medication Intake Chatbot

In this work, the subtractive mountain clustering algorithm has been adapted to the problem of natural languages processing in view to construct a chatbot that answers questions posed by the user. The implemented algorithm version allosws for the association of a set of words into clusters. After finding the centre of every cluster — the most relevant word, all the others are aggregated according to a defined metric adapted to the language processing realm. All the relevant stored information (necessary to answer the questions) is processed, as well as the questions, by the algorithm. The correct processing of the text enables the chatbot to produce answers that relate to the posed queries. Since we have in view a chatbot to help elder people with medication, to validate the method, we use the package insert of a drug as the available information and formulate associated questions. Errors in medication intake among elderly people are very common. One of the main causes for this is their loss of ability to retain information. The high amount of medicine intake required by the advanced age is another limiting factor. Thence, the design of an interactive aid system, preferably using natural language, to help the older population with medication is in demand. A chatbot based on a subtractive cluster algorithm is the chosen solution.

Adaptive Neuro-Fuzzy Inference System to Predict the Dynamic Modulus of Hot Mix Asphalt

The dynamic modulus |E*| of hot mix asphalt (HMA) plays a fundamental role in the mechanistic–empirical pavement design. The Witczak regression-based predictive model can be considered as the most fundamental and widely used model to estimate the |E*| of HMA. However, the effect of confining stress has not been considered in this model. In this paper, the feasibility of applying the robust machine learning technique called “adaptive neuro-fuzzy inference system” (ANFIS) was investigated to predict the |E*| of HMA using 1,320 test results performed at the University of Maryland. Asphalt mix parameters, testing frequency, temperature, and the level of confining stress were considered as the model inputs. Also, intercept of temperature susceptibility relationship (A) and slope of temperature susceptibility relationship (VTS). Two new ANFIS models were developed using two different structures, including fuzzy C-mean clustering (FCM) and subtractive clustering (SC) algorithms. In addition, two computer programs were developed for optimizing the structure of the FCM ANFIS and SC ANFIS models to achieve the highest predicting accuracy. The obtained results indicate that the SC and FCM ANFIS models predict the |E*| of HMA with high coefficients of determination of R2=0.948 and 0.945, respectively. Moreover, a sensitivity analysis was conducted to evaluate the level of influence of model inputs, and the results show that the confining stress has a significant impact on the |E*|. Also, the results demonstrate that the standard results for the ANFIS model and real data are in complete agreement.

Improved RBF Network Intrusion Detection Model Based on Edge Computing with Multi-algorithm Fusion

Edge computing is difficult to deploy a complete and reliable security strategy due to its distributed computing architecture and inherent heterogeneity of equipment and limited resources. When malicious attacks occur, the loss will be immeasurable. RBF neural network has strong nonlinear representation ability and fast learning convergence speed, which is suitable for intrusion detection of edge detection industrial control network. In this paper, an improved RBF network intrusion detection model based on multi-algorithm fusion is proposed. kernel principal component analysis (KPCA) is used to extract data dimension and simplify data representation. Then subtractive clustering algorithm(SCM) and grey wolf algorithm(GWO) are used to jointly optimize RBF neural network parameters to avoid falling into local optimum, reduce the calculation of model training and improve the detection accuracy. The algorithm can better adapt to the edge computing platform with weak computing ability and bearing capacity, and realize real-time data analysis.The experimental results of BATADAL data set and Gas data set show that the accuracy of the algorithm is over 99% and the training time of larger samples is shortened by 50 times for BATADAL data set. The results show that the improved RBF network is effective in improving the convergence speed and accuracy in intrusion detection.

Application of Neural Network Models and ANFIS for Water Level Forecasting of the Salve Faccha Dam in the Andean Zone in Northern Ecuador

Despite the importance of dams for water distribution of various uses, adequate forecasting on a day-to-day scale is still in great need of intensive study worldwide. Machine learning models have had a wide application in water resource studies and have shown satisfactory results, including the time series forecasting of water levels and dam flows. In this study, neural network models (NN) and adaptive neuro-fuzzy inference systems (ANFIS) models were generated to forecast the water level of the Salve Faccha reservoir, which supplies water to Quito, the Capital of Ecuador. For NN, a non-linear input–output net with a maximum delay of 13 days was used with variation in the number of nodes and hidden layers. For ANFIS, after up to four days of delay, the subtractive clustering algorithm was used with a hyperparameter variation from 0.5 to 0.8. The results indicate that precipitation was not influencing input in the prediction of the reservoir water level. The best neural network and ANFIS models showed high performance, with a r > 0.95, a Nash index > 0.95, and a RMSE < 0.1. The best the neural network model was t + 4, and the best ANFIS model was model t + 6.

Segmentation of image based on k-means and modified subtractive clustering

Image segmentation has widespread applications in medical science, for example, classification of different tissues, identification of tumors, estimation of tumor size, surgery planning, and atlas matching. Clustering is a widely implemented unsupervised technique used for image segmentation mainly because of its simplicity and fast computation. However, the quality and efficiency of clustering-based segmentation is highly depended on the initial value of the cluster centroid. In this paper, a new hybrid segmentation approach based on k-means clustering and modified subtractive clustering is proposed. K-means clustering is a very efficient and powerful algorithm but it requires initialization of cluster centroid. And, the consistency of the clustering outcomes of k-means algorithm depends on the initial selection of the cluster center. To overcome this drawback, a modified subtractive clustering algorithm based on distance relations between cluster centers and data points is proposed which finds a more accurate cluster centers compared to the conventional subtractive clustering. These cluster centroids obtained from the modified subtractive clustering are used in k-means algorithm for segmentation of the image. The proposed method is compared with other existing conventional segmentation methods by using several synthetic and real images and experimental finding validates the superiority of the proposed method.

Performance Analysis of Subtractive Clustering Algorithm in Determining the Number and Position of Cluster Centers

The basic concept of the subtractive clustering algorithm is to choose a data point that has the highest density (potential) in a space (variable) as the center of the cluster. The number and position of the cluster centers formed are influenced by the given radius (r) parameter value. If the radius value is very small, it will result in the neglect of potential data points around the center of the cluster. If the value of the radius parameter is too large, it increases the contribution of all potential data points, thereby canceling the effect of cluster density. The number of cluster centers in the subtractive clustering algorithm is determined based on the iteration process in finding data points with the highest number of neighbors. This study uses the clustering partition as a parameter value to determine a data point (candidate cluster center) will be selected to determine the effect of the radius (r) parameter value on the subtractive clustering algorithm in generating clustering. From the experiments that have been carried out on 4 datasets, the results have been obtained, for dataset 1 the highest average value of fuzzy silhouette with a parameter value of radius (r) 0.35 is 0.9088 and the number of clusters 2. While in dataset 2, the average value The highest fuzzy silhouette with a parameter value of radius (r) 0.40 is 0.6742 and the number of clusters 3. While in dataset 3, the average value of the highest fuzzy silhouette with a parameter value of radius (r) 0.50 is 0.7434 and the number of clusters 3. While in the dataset the last is the fourth dataset, the highest fuzzy silhouette average value with a radius (r) parameter value of 0.50 is 0.6630 and the number of clusters 2. This subscractive clustering algorithm is widely applied in the fields of transportation, GIS, big data, control of electric voltages, electrical energy needs, knowing the area of population density to health such as breast cancer diagnosis, which is related to the needs of human life.

Analisis Kinerja Fuzzy C-Means (FCM) dan Fuzzy Subtractive (FS) dalam Clustering Data Alumni STMIK STIKOM Indonesia

In this study, clustering data on STMIK STIKOM Indonesia alumni using the Fuzzy C-Means and Fuzzy Subtractive methods. The method used to test the validity of the cluster is the Modified Partition Coefficient (MPC) and Classification Entropy (CE) index. Clustering is carried out with the aim of finding hidden patterns or information from a fairly large data set, considering that so far the alumni data at STMIK STIKOM Indonesia have not undergone a data mining process. The results of measuring cluster validity using the Modified Partition Coefficient (MPC) and Classification Entropy (CE) index, the Fuzzy C-Means Clustering algorithm has a higher level of validity than the Fuzzy Subtractive Clustering algorithm so it can be said that the Fuzzy C-Means algorithm performs the cluster process better than with the Fuzzy Subtractive method in clustering alumni data. The number of clusters that have the best fitness value / the most optimal number of clusters based on the CE and MPC validity index is 5 clusters. The cluster that has the best characteristics is the 1st cluster which has 514 members (36.82% of the total alumni). With the characteristics of having an average GPA of 3.3617, the average study period is 7.8102 semesters and an average TA work period of 4.9596 months.

RBF Neural Network-Based Frequency Band Prediction for Future Frequency Hopping Communications

On the basis of the chaotic features of the frequency hopping signal, frequency band prediction for frequency hopping signal can enhance the interference effect of the signal greatly. However, poor prediction accuracy often limits its development in the military field. Therefore, for the sake of enhancing the frequency band prediction accuracy of frequency hopping signal, this paper studies the radial basis function (RBF) neural network frequency hopping signal frequency band prediction model based on the gradient descent method and improved the particle swarm optimization algorithm, respectively. The former uses a step-by-step algorithm to optimize the center value and weight so that the network can find the most suitable initial state. Then, the clustering selection optimization algorithm is employed to optimize the central value. In addition, it optimizes the weight by using a gradient descent method of the optimal learning rate. The latter optimizes the structure of the RBF neural network through the combination of the subtractive clustering algorithm and improved the particle swarm optimization (PSO) algorithm. Simulation results demonstrate that the gradient RBF algorithm model performs better in terms of accuracy, but time efficiency is lower, while the PSO-RBF algorithm has better time efficiency.

Composite Error-Based Intelligent Adaptive Sliding Mode Control for Uncertain Bilaterally Symmetrical Hybrid Robot with Variational Desired Trajectories

Some challenging issues exist in trajectory tracking control of an uncertain bilaterally symmetrical hybrid robot (UBSHR) with variational desired trajectories, mainly the uncertainty problem of UBSHR, the synchronization problem of UBSHR’s active joints and bilateral symmetrical hybrid mechanisms, and the flexible control problem of active adaption to different technological requirements without artificially adjusting the control parameters or switching the hardware system. To solve these problems, an adaptive fuzzy neural network in conjunction with subtractive clustering algorithm (SC-AFNN) for UBSHR is proposed. More specifically, a novel composite error is incorporated into the second-order sliding mode control method to generate ideal training data samples and to improve the uncertain system robustness and synchronization performance simultaneously. Furthermore, the SC-AFNN is introduced to realize self-learning and self-adjusting of control rules and control parameters and to enhance the flexible control performance of UBSHR with variational desired trajectories. Strict theoretical proof of the defined errors’ relationship and the stability of the poposed control method is given. Ultimately, simulations and experiments for the prototype system of an UBSHR are conducted to verify the effectiveness of the proposed control method.