Fuzzy Prediction Research Articles

Fuzzy time-series prediction model based on text features and network features

The prediction of time-series data is a challenging and complex issue. For many practical applications, network topology information and text information can play a perfect role in time-series prediction. This article takes stock data as an example by constructing a graph, connecting each stock’s upstream and downstream industries, and obtaining useful text features and topological features to predict the stock time-series. Based on the time-series data features, text features, and the topological features of the stock industry chain of machine learning, we compared our prediction model with other fuzzy time-series prediction methods, which are only based on historical features. The experiment shows that our method is better than the other methods in terms of the performance of multiple stocks in each stock’s time-series prediction. The experimental results show that the stock topology based on the industrial chain effectively improved time-series forecasting accuracy.

Fuzzy Logic-Based Prediction of Drilling-Induced Temperatures at Varying Cutting Conditions along with Analysis of Chips Morphology and Burrs Formation

Friction and plastic deformation at the tool–chips interaction during a dry drilling process results in temperature rise and promotes tool wear and surface roughness. In most of the components produced in industries, a drilling process is used to make a hole for final assembly. Therefore, knowledge of temperatures produced during drilling operation at various machining input parameters is required for the best quality product. A fuzzy logic-based algorithm is developed to predict the temperature generated in the drilling process of AISI 1018 mild steel. The algorithm used speed and feed rate of the drill bit as input parameters to the fuzzy domain. A set of rules was used in the fuzzy domain to predict maximum temperature produced in the drilling process. The developed algorithm is simulated for various input speed and feed rate parameters and was verified through the maximum temperature measured during drilling of the studied material at selected speed–feed combinations. Experiments were conducted to validate the results of developed fuzzy logic-based algorithm by using non-contact infrared pyrometer for drilling of AISI 1018 steel. A good agreement between the predicted and experimentally measured maximum temperature was observed with an error less than 6%. It is found that temperature increases with increase in cutting speed and feed rate. Size of roll back burr formation at the hole perimeter significantly increases with increase in drill speed and feed rate. Segmental continuity in spiral or helix chips morphology is more at low feed and high cutting speed. Chip radius increases with increase in feed rate and results in damaging of the machined surface and causes burr formation while the radius decreases with cutting speed along with improved hole surface finish.

Combined Fuzzy Time Series Prediction Method for Fault Prediction of EML Pulse Capacitors

Metallized film capacitors are an important part of the electromagnetic rail launch system. It is of great significance to predict its failure. In engineering, the failure law of capacitor is obtained by cyclic pulse accelerated life test of capacitor module with a small number of samples, and is used to predict the actual failure of capacitor in electromagnetic launch (EML) system. This method has the following problems: first, there are few samples of capacitor in life test at affordable cost, which cannot include all capacitor characteristics; second, the time interval of actual EML missions and the voltage of the capacitors are both changing and inconsistent with the conditions used in the life test; third, the statistical law is affected by the measurement and other errors. For these reasons, the prediction accuracy of the existing methods is limited. In this article, a new combined time series prediction method is proposed by using the high-order fuzzy time series prediction theory. Based on the capacitor used in the prototype of an electromagnetic railgun, the life test data of 20 pulse capacitors are used as the prior knowledge input, and the prediction model is obtained. Five groups of capacitor life test data simulating real launch conditions are used as test data to verify that the prediction accuracy of the proposed method is better than that of the traditional method, and the prediction accuracy of capacitor capacitance, which made by different processes, is much higher than that of the traditional method.

Fuzzy predictor for parallel dynamic task allocation in multi-robot systems

This paper presents a model to decompose complex tasks in the form of elemental tasks executed in parallel by multi robots. In this model, a criterion of accuracy in the parallel dynamic tasks allocation process (APDTA) is defined. Through this APDTA, a predictor based on fuzzy logic called FP-TE is developed to evaluate the importance of elemental tasks in the system. The inputs of this predictor are described as observations acquired from sensor data. The FP-TE output will be used to allow each robot to individually decide what task should be executed. Simulation results on goods transportation by mobile robots are presented to demonstrate the effectiveness of this fuzzy predictor.

Review on Fuzzy and Neural Prediction Interval Modelling for Nonlinear Dynamical Systems

The existing uncertainties during the operation of processes could strongly affect the performance of forecasting systems, control strategies and fault detection systems when they are not considered in the design. Because of that, the study of uncertainty quantification has gained more attention among the researchers during past decades. From this field of study, the prediction intervals arise as one of the techniques most used in literature to represent the effect of uncertainty over the future process behavior. Thus, researchers have focused on developing prediction intervals based on the use of fuzzy systems and neural networks, thanks to their usefulness for represent a wide range of processes as universal approximators. In this work, a review of the state-of-the-art of methodologies for prediction interval modelling based on fuzzy systems and neural networks is presented. The main characteristics of each method for prediction interval construction are presented and some recommendations are given for selecting the most appropriate method for specific applications. To illustrate the advantages of these methodologies, a comparative analysis of selected methods of prediction intervals is presented, using a benchmark series and real data from solar power generation of a microgrid.

Quantitative evaluation of industrial and commercial management’s promotion to economic growth based on hierarchical constraints

In order to improve the quantitative evaluation ability of industrial and commercial management on promoting economic growth, the design method of quantitative evaluation model of industrial and commercial management on promoting economic growth based on hierarchical constraints is proposed. the descriptive statistical analysis method to realize big data fusion mining for quantitative evaluation of business administration’s promotion to economic growth is used, and a hierarchical constraint parameter analysis model to realize node deployment model design of hierarchical constraint parameter analysis model is designed, fuzzy control and adaptive feature parameter identification are realized in the process of quantitative evaluation of industrial and commercial administration’s promotion to economic growth. Convergence control is realized in the process of quantitative evaluation based on pattern recognition and association distributed fusion. Fuzzy degree identification and optimization prediction of quantitative evaluation of industrial and commercial administration’s promotion to economic growth are realized in hierarchical constraint parameter analysis model. The simulation results show that the output accuracy and system stability of the quantitative evaluation of the promotion of business administration to economic growth are good.

Fuzzy predictor for parallel dynamic task allocation in multi-robot systems

Fuzzy predictor for parallel dynamic task allocation in multi-robot systems

Big data-based fuzzy prediction and evaluation of performance of cold recycled asphalt pavement

Cold recycling of asphalt pavement is important in realizing sustainable development of highway transportation. Understanding change laws of cold recycled asphalt pavement (RAP) performance is important in the correct evaluation of pavement quality and scientific formulation of maintenance strategies. Various performance indexes were analytically demonstrated to predict and evaluate change laws of the cold RAP performance. The proposed cold recycled pavement evaluation indexes were divided into three fuzzy grades of evaluation indexes and subindexes. Integral algorithms from four indexes, namely, pavement surface condition index, riding quality index, rutting depth index, and pavement structure strength index (PSSI), were combined on the basis of the traditional gray prediction model GM (1,1). Index weights were determined according to improved analytic hierarchy process, and a performance index database system based on historical data was established for the cold RAP. Finally, an evaluation system was set up on the basis of the prediction model GM (1,1), and prediction and evaluation results were analyzed with existing data. Results showed the excellent performance of the proposed method with the maximum weight of PSSI and a cold recycled pavement evaluation index score of 77.45. Goodness of fit between the prediction curve and original data is favorable with minimal relative errors. The curve analysis of evaluation indexes demonstrated the satisfactory performance of the pavement with the overall slow declining trend of pavement performance indexes. The research results of this study can provide a reference for evaluating performance variation trends of road network-level cold RAPs.

Multiconstraint Fuzzy Prediction Analysis Improved the Algorithm in Internet of Things

Multiconstraint prediction is a research hotspot and difficulty in the Internet of Things. Aiming at the main problems existing in the process of multiconstraint fuzzy prediction, this paper studies the related key technologies and methods and proposes an improved multiconstraint fuzzy prediction analysis algorithm in the application of Internet of Things. This paper introduces the multiconstraint attribute analysis, multiconstraint attribute normalization processing, multiconstraint attribute weight processing, multiconstraint attribute prediction analysis granularity setting, etc. and systematically calculates the ambiguity of multiconstraint attributes and realizes the multiconstraint fuzzy prediction analysis algorithm. Finally, combined with relevant cases, the algorithm is compared with the existing research results, which shows the effectiveness and feasibility of the algorithm in the Internet of Things.

Fuzzy Estimate of the Development of Passenger Cars Production in the Czech Republic

The global outbreak of the COVID-19 and the measures taken, disrupted fundamentally economies around the world. Almost all sectors were affected. The experts have long emphasised the Czech economy’s dependence on the automotive industry. Car producers and companies linked to them have been loaded by severe difficulties after the pandemic outbreak. The article shows one of the constructive ways how to forecast a change in the passenger cars production in the Czech Republic in 2020. Metodologically we lean on a procedure of the fuzzy approach. The prediction itself cannot be derived from the series of historical data of the variables that are related to the target output variable as shown in the fuzzy prediction of GDP for 2018 by this author. Due to the extreme situation caused by pandemic outbreak, the role of expert predictions come intensively into play with their outcomes becoming the set of input data to the fuzzy model. The result of the fuzzy forcast of a change in the cars production in CZ for 2020 shows a greater drop than the official statistical model claims.

Prediction of Polypropylene Yarn Shrinkage in the Heat-Setting Process Using the Fuzzy Inference System

In the carpet industry, yarn shrinkage is a very important specification, the percent of shrinkage affected by heat setting parameters, time and temperature. In order to obtain the best uniform appearance of carpets, the shrinkage of pile yarns should be minimum in the carpet sizing process. An inappropriate heat set yarn may cause an undesirable shrinkage result and uneven pile height on carpets after the sizing process. It could be useful for manufacturers to understand the optimum condition of heat setting to obtain the low shrinkage of heat set yarns before weaving. Therefore, a fuzzy logic model is designed to predict the shrinkage percentage of polypropylene yarn in different heat setting conditions. Time and temperature are taken into account as input variables and yarn shrinkage is predicted as output. For validation of the model, the yarn samples heat set under various sets of time and temperature and finally yarn shrinkages have been measured experimentally. The result of the fuzzy model prediction compared to regression results and signify the fuzzy results present good and better match with experimental results with the acceptable R2=0.97 and average error (2.59%).

The application research of neural network and BP algorithm in stock price pattern classification and prediction

Under the background of big data and Internet finance, quantitative investment is becoming more and more critical, and the prediction of the stock price has become the focus of investors’ concern and research. The purpose of this work is to apply neural network and BP algorithm onto the classification and prediction of stock price patterns. The method is to use the BP algorithm neural network for the transaction data of 5 consecutive days as input samples, so there are 20 input layer nodes. The final value of the next day is used as the output sample, and the number of nodes in the output layer is 1. The purpose of network training is to find 20 spline functions. After the training of the BP algorithm neural network, the test data (stock price data for 5 consecutive days) independent of the training data is leveraged as the input of the neural network, and the closing price of the next day is used as the target output of the network. Through the error between the actual output and the target output, the stock price prediction performance of the network model is analyzed. The results have shown that the prediction accuracy of the stock price is 62.12% under the prediction of deep learning fuzzy algorithm and 73.29% under the prediction of the BP algorithm neural network. When the prediction range is between 15 days, the error of 30 prediction values relative to the real value is within ± 10%, accounting for 90% of the total days, and the prediction effect is the best. By analyzing the prediction of the number of hidden layers on the stock price and different ranges, it can be concluded that the prediction of the stock price trend prediction model of BP algorithm neural network is better than that of the deep learning fuzzy algorithm prediction model. This algorithm provides investors with a certain value for stock forecasting, which makes government gain a more active position in macroeconomic regulation and control.

Research on earthquake damage prediction of stone structure in southern Fujian based on fuzzy comprehensive evaluation

Based on fuzzy mathematics method, earthquake damage prediction of stone structure houses in Southern Fujian is studied. The subsets of earthquake damage affecting factors applicable to stone structures and their fuzzy relation with earthquake damage levels are established. Furthermore, the earthquake damage prediction model of stone structure houses in southern Fujian is developed based on fuzzy comprehensive evaluation method. Taking the two-storey stone structure house as an example, the model is applied to predict and evaluate the damage state of the two-storey stone structure house after earthquake damage. The results show that, according to the fuzzy comprehensive prediction and evaluation model, the stone structure house suffers serious damage degree in the earthquake damage, the evaluation grade of earthquake damage is C, and the evaluation result is consistent with the actual damage state. The model of earthquake damage prediction is clear and easy to calculate, which provides a theoretical basis for earthquake damage prediction and reinforcement and maintenance of stone structure houses in southern Fujian.

Robust Resilient Control for Nonlinear Systems Under Denial-of-Service Attacks

This article is concerned with the design of robust resilient control strategy for nonlinear systems under Denial-of-Service (DoS) attacks. First, Takagi–Sugeno fuzzy model is employed to approximate the nonlinear dynamics, and an improved sensor system is constructed by fuzzy observer and fuzzy predictor. By applying periodic event-triggered control strategy, the relationship between the estimated state and predicted state is obtained by event-triggering mechanism, which can reduce transmission attempts significantly in the sensor-to-controller channel. Second, caused by DoS attacks, the transmission attempts may be denied over the communication network. Under the proposed transmission policy with a bounded update period, input-to-state stability (ISS) of closed-loop systems can be guaranteed. Moreover, the maximum frequency and duration of DoS attacks are calculated. Finally, simulation results are provided to show the effectiveness of the proposed method.

2차 추세 차분형 LERP 기반 IT2TSK 퍼지 예측시스템 설계 및 전력부하 예측

2차 추세 차분형 LERP 기반 IT2TSK 퍼지 예측시스템 설계 및 전력부하 예측

A Metrics Based Fuzzy Logic Model for Predicting the Reusability of Object Oriented Software

Software reusability facilitates the engineering of new software or systems functionalities without having to start coding from scratch. This software quality provides numerous merits to the software developers including coming up with larger systems within a short time, with reduced development cost and reduced developer effort. However, software reusability is an external software quality attribute that is not measurable directly, and this is a major hindrance factor to its adoption in the software engineering process. This indicates that there is a need to come up with an approach to measure or predict software reusability to give advisories to the software developers on the prediction of software reusability. Therefore, this study aims at coming up with a prediction model to estimate software reusability by employing the use of a fuzzy logic approach, the study focused on Object-Oriented software. The research followed a guideline of four objectives and assumed descriptive and diagnostic methodology. It started by considering the existing ISO/IEC 25010 software quality model to determine and describe the main factors affecting the reusability of Object-Oriented software. The main factors identified were Abstraction, Cohesion and Coupling, thereafter, it was followed by the definition of metrics to measure each of the three factors identified, to operationalize these metrics, they were then validated using Weyuker’s nine properties. After this, the researchers developed a metrics tool to automate the process of computing the metrics values of the defined metrics. Finally, a fuzzy logic prediction model that predicts the reusability of Object-Oriented software was developed based on the metrics values computed by the metrics tool. This model was then validated using the Analytical Hierarchical Process (AHP) framework. The outcome of the four objectives was presented, discussed and future works of this study outlines. This research work is a contribution to the software development industry where the software developers can apply it to engineer reusable software.

A Fuzzy-Statistical Tolerance Interval from Residuals of Crisp Linear Regression Models

Linear regression is a simple but powerful tool for prediction. However, it still suffers from some deficiencies, which are related to the assumptions made when using a model like normality of residuals, uncorrelated errors, where the mean of residuals should be zero. Sometimes these assumptions are violated or partially violated, thereby leading to uncertainties or unreliability in the predictions. This paper introduces a new method to account for uncertainty in the residuals of a linear regression model. First, the error in the estimation of the dependent variable is calculated and transformed to a fuzzy number, and this fuzzy error is then added to the original crisp prediction, thereby resulting in a fuzzy prediction. The results are compared to a fuzzy linear regression with crisp input and fuzzy output, in terms of their ability to represent uncertainty in prediction.

Design of an IoT-Based Fuzzy Approximation Prediction Model for Early Fire Detection to Aid Public Safety and Control in the Local Urban Markets

Fire monitoring in local urban markets within East Africa (EA) has been seriously neglected for a long time. This has culminated in a severe destruction of life and property worth millions. These rampant fires are attributed to electrical short circuits, fuel spillages, etc. Previous research proposes single smoke detectors. However, they are prone to false alarm rates and are inefficient. Also, satellite systems are expensive for developing countries. This paper presents a fuzzy model for early fire detection and control as symmetry’s core contribution to fuzzy systems design and application in computer and engineering sciences. We utilize a fuzzy logic technique to simulate the performance of the model using MATLAB, using six parameters: temperature, humidity, flame, CO, CO2 and O2 vis-à-vis the Estimated Fire Intensity Prediction (EFIP). Results show that, using fuzzy logic, a significant improvement in fire detection is observed with an overall accuracy rate of 95.83%. The paper further proposes an IoT-based fuzzy prediction model for early fire detection with a goal of minimizing extensive damage and promote intermediate fire suppression and control through true fire incidences. This solution provides for future public safety monitoring, and control of fire-related situations among the market community. Hence, fire safety monitoring is significant in providing future fire safety planning, control and management by putting in place appropriate fire safety laws, policies, bills and related fire safety practices or guidelines to be applied in public buildings, market centers and other public places.

UAV‐based training for fully fuzzy classification of Sentinel‐2 fluvial scenes

AbstractAn estimated 76% of global stream area is occupied by channels with widths above 30 m. Sentinel‐2 imagery with resolutions of 10 m could supply information about the composition of river corridors at national and global scales. Fuzzy classification models that infer sub‐pixel composition could further be used to compensate for small channel widths imaged at 10 m of spatial resolution. A major challenge to this approach is the acquisition of suitable training data useable in machine learning models that can predict land‐cover type information from image radiance values. In this contribution, we present a method which combines unmanned aerial vehicles (UAVs) and Sentinel‐2 imagery in order to develop a fuzzy classification approach capable of large‐scale investigations. Our approach uses hyperspatial UAV imagery in order to derive high‐resolution class information that can be used to train fuzzy classification models for Sentinel‐2 data where all bands are super‐resolved to a spatial resolution of 10 m. We use a multi‐temporal UAV dataset covering an area of 5.25 km2. Using a novel convolutional neural network (CNN) classifier, we predict sub‐pixel membership for Sentinel‐2 pixels in the fluvial corridor as divided into classes of water, vegetation and dry sediment. Our CNN model can predict fuzzy class memberships with median errors from −5% to +3% and mean absolute errors from 10% to 20%. We also show that our CNN fuzzy predictor can be used to predict crisp classes with accuracies from 95.5% to 99.9%. Finally, we use an example to show how a fuzzy CNN model trained with localized UAV data can be applied to longer channel reaches and detect new vegetation growth. We therefore argue that the novel use of UAVs as field validation tools for freely available satellite data can bridge the scale gap between local and regional fluvial studies. © 2020 The Authors. Earth Surface Processes and Landforms published by John Wiley & Sons Ltd

A new prediction strategy combining T-S fuzzy nonlinear regression prediction and multi-step prediction for dynamic multi-objective optimization

Abstract Many dynamic multi-objective optimization problems have been widely developed to track the changing optima quickly and effectively in dynamic environments. Prediction-based methods can be used to predict future changes by learning past experience. This paper employed a new prediction strategy combining Takagi-Sugeno fuzzy nonlinear regression prediction and multi-step prediction named TSMP to estimate the new initial Pareto solutions whenever the environment changes. In TSMP, when environmental changes occur, the next initial center of Pareto solutions (PS) is predicted by a Takagi-Sugeno fuzzy nonlinear regression prediction model and then one trail population is generated by combining the predicted center and an approximate manifold of PS. Moreover, the other trail population is generated by a linear multi-step prediction model. Furthermore, the next initial PS is reinitialized by a random hybridization of these two trail populations. The proposed TSMP strategy is systematically compared with re-initialization strategy (RIS), feed-forward prediction strategy (FPS) and population prediction strategy (FPS) under different multi-objective optimizers on benchmark test problems with different features. Experimental results and performance comparisons with other state-of-the-art algorithms indicate that TSMP is effective and promising for solving dynamic multi-objective optimization problems.