A Compare of Fuzzy Logic and Entropy Models : A Case Study of Assessment Analysis of Geohazard Susceptibility in Jianshi County of Qingjiang River Basin

Ningtao Wang,Tingting Shi,Ke Peng,Zhipeng Lian,Yiyong Li,Qing Wang,Wen Chen,Bolin Huang 보안공학연구지원센터 2015 International Journal of u- and e- Service, Scienc Vol.8 No.4

Fuzzy logic model and entropy model are useful for the geohazard susceptibility zonation in Jianshi County of Qingjiang River Basin. In this paper, the same impact factors were chosen and the geohazard samples were considered in two cases with quantitative analysis method. The first case 162 geohazards chosen as samples and the other one all of 182 geohazards chose as samples. The authors completed the susceptibility zonation in the two different cases using the two models in order to analysis the effects of the two models. The results of the two models in different cases were almost the same in space, except small differences in some areas. The entropy model was more accurate for the analysis of relationship between impact factors and geohazards, but not stable for different geohazard samples. The fuzzy logic model was better for less geohazard samples. According to the analysis process, it was found that the fuzzy γ operation was the best which was defined in terms of the fuzzy algebraic product and the fuzzy algebraic sum. The results of fuzzy logic model were most useful when γ was 0.20. The fuzzy logic model and entropy model were useful for the geohazard susceptibility which was scientific and useful for the government to manage the geohazards and make the preliminary development plans.

Hybrid fuzzy model to predict strength and optimum compositions of natural Alumina-Silica-based geopolymers

Ata Allah Nadiri,Somayeh Asadi,Hamed Babaizadeh,Keivan Naderi 사단법인 한국계산역학회 2018 Computers and Concrete, An International Journal Vol.21 No.1

This study introduces the supervised committee fuzzy model as a hybrid fuzzy model to predict compressive strength (CS) of geopolymers prepared from alumina-silica products. For this purpose, more than 50 experimental data that evaluated the effect of Al2O3/SiO2, Na2O/Al2O3, Na2O/H2O and Na/[Na+K] on (CS) of geopolymers were collected from the literature. Then, three different Fuzzy Logic (FL) models (Sugeno fuzzy logic (SFL), Mamdani fuzzy logic (MFL), and Larsen fuzzy logic (LFL)) were adopted to overcome the inherent uncertainty of geochemical parameters and to predict CS. After validating the model, it was found that the SFL model is superior to MFL and LFL models, but each of the FL models has advantages to predict CS. Therefore, to achieve the optimal performance, the supervised committee fuzzy logic (SCFL) model was developed as a hybrid method to combine the benefits of individual FL models. The SCFL employs an artificial neural network (ANN) model to re-predict the CS of three FL model predictions. The results also show significant fitting improvement in comparison with individual FL models.

Establishment of grinding conditions utilizing the fuzzy logic and pre-estimation model

Kim, Gunhoi 전주대학교 공학기술종합연구소 2003 전주대학교 공학기술종합연구소 학술논문집 Vol.9 No.1

This paper has presented an application of grinding conditions and pre-estimation model utilizing the fuzzy logic, and it will be suggested an effective mechanism for their based on the fuzzy set theory. This system can handle vague and uncertain knowledge, and presents a scheme for integrating data with various kinds of grinding knowledge. Especially, in order to deal with uncertain and qualitative grinding knowledge, it designs on the grinding conditions to cylindrical grinding utilizing a fuzzy production rule and the fuzzy linear regression model, and pre-estimation model of the grinding result for grinding power and surface roughness, which is strongly dependent upon the grinding trouble and surface quality, are identified by the fuzzy regression model. In this paper, it tries to establish the grinding conditions utilizing fuzzy production rule and the fuzzy regression model, and per-estimation of grinding result for grinding power and surface roughness utilizing the fuzzy regression model, which are strongly related with surface quality and detection of trouble, is devised by the fuzzy multi- regression model.

C-Means 클러스터링 기반의 Type-2 퍼지 논리 시스템을 이용한 비선형 모델 설계

백진열(Jin-Yeol Baek),이영일(Young-Il Lee),오성권(Sung-Kwun Oh) 한국지능시스템학회 2008 한국지능시스템학회논문지 Vol.18 No.6

본 논문에서는 비선형 모델의 설계를 위해 Type-2 퍼지 논리 집합을 이용하여 불확실성 문제를 다룬다. 제안된 모델은 규칙의 전ㆍ후반부가 Type-2 퍼지 집합으로 주어진 Type-2 퍼지 논리 시스템을 설계하고 불확실성의 변화에 대한 비선형 모델의 성능을 해석한다. 여기서 규칙 전반부 멤버쉽 함수의 정점 선택은 C-means 클러스터링 알고리즘을 이용하고, 규칙 후반부 퍼지 집합의 정점 결정에는 경사 하강법(Gradient descent method)을 이용한 오류 역전파 알고리즘을 사용하여 학습한다. 또한, 제안된 모델에 관련된 파라미터는 입자 군집 최적화(Particle Swarm Optimization; PSO) 알고리즘으로 동조한다. 제안된 모델은 모의 데이터집합(Synthetic dadaset), Mackey-Glass 시계열 공정 데이터를 적용하여 논증되고, 기존 Type-1 퍼지 논리 시스템과의 근사화 및 일반화 능력에 대하여 비교ㆍ토의한다. This paper deal with uncertainty problem by using Type-2 fuzzy logic set for nonlinear system modeling. We design Type-2 fuzzy logic system in which the antecedent and the consequent part of rules are given as Type-2 fuzzy set and also analyze the performance of the ensuing nonlinear model with uncertainty. Here, the apexes of the antecedent membership functions of rules are decided by C-means clustering algorithm and the apexes of the consequent membership functions of rules are learned by using back-propagation based on gradient decent method. Also, the parameters related to the fuzzy model are optimized by means of particle swarm optimization. The proposed model is demonstrated with the aid of two representative numerical examples, such as mathematical synthetic data set and Mackey-Glass time series data set and also we discuss the approximation as well as generalization abilities for the model.

The fuzzy logic-based modeling of a micro-scale sloped solar chimney power plant

Muhammed Huseyin Guzel,Recep Emre Unal,Ahmet Onder,Muhammed Arif Sen,Faruk Kose 대한기계학회 2021 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.35 No.3

The energy demand of world is increasing worldwide because of increasing population and developing technology. The use of environmentally friendly renewable resources is very important in providing the increasing energy needs. In the renewable energy sources, the solar energy has a strategic importance because of its huge potential and unlimited. The production of electrical energy by solar chimney power plants is one of the reliable and profitable methods. Fuzzy logic-based approaches are commonly used for modeling different systems in many fields. Also, a renewable energy system can be modelled by fuzzy definitions. In this way, it can provide efficiently and quickly theoretical estimates of systems with productive simulations. In this study, using the experimental data obtained from the micro-scale sloped solar chimney power plant in carried on scientific research project by authors, the obtaining and verifying a fuzzy logic-based model (FLBM) that can calculate the change in air velocity at turbine according to the change of radiation and temperature is presented. The air velocity at the turbine inlet is the considerable variable determining the electricity generation in a solar chimney. Thus, the output of the model is determined as this air velocity. In changes in the radiation and temperature values are defined as inputs. A two input-one output fuzzy model is obtained, in which the inference method is designed in the form of Mamdani and the membership functions in the form of the triangle, making inferences according to the rule base determined by the experience achieved from the experimentally studies. In order to investigate the accuracy of the FLBM, the simulation results and the data get from experimental setup in April 2019 are compared and evaluated. The validation of the FLBM compared to the experimental system is investigated using different error evaluation criteria. It is proved that the results of FLBM and experimental data are realized at a high rate (95.95 %) close to each other and similarly.

Modeling of the Drivers’ Decision-Making Behavior During Yellow Phase

Sabyasachi Biswas,Indrajit Ghosh 대한토목학회 2018 KSCE JOURNAL OF CIVIL ENGINEERING Vol.22 No.11

Stop and go modeling at signalized intersections under heterogeneous traffic conditions has remained one of the most sought-after fields. Drivers are often caught up in the dilemma zone and unable to take quick decisions whether to stop or cross the intersection. This hampers the traffic movement and may lead to accidents. These variables include distance-to-stop line, time-to-stop line, approach speed, acceleration/deceleration and category of the vehicle. Further, using external validation, the overall accuracy levels of the drivers' decision models based on Logistic regression (81.5 percent), Fuzzy Logic (86.98 percent) and ANN (88.67 percent) were compared. Further, a hybrid surrogate model, incorporating the ‘Weighted Average’ technique was developed so that the individual disparities were diminished and the overall accuracy for both stopping and crossing vehicles was improved. This Weighted Average Hybrid Model (WAHM), formulated by coupling Fuzzy Logic and ANN, yielded a highly accurate result (96.15 percent) and outperformed both ANN and Fuzzy Logic.

안티 포렌식 행위 탐지를 위한 퍼지 전문가 시스템

김세령 ( Se Ryoung Kim ),김휘강 ( Huy Kang Kim ) 한국인터넷정보학회 2011 인터넷정보학회논문지 Vol.12 No.5

최근 사이버 범죄의 증가와 그 대상 시스템의 다양화로 인하여 디지털 포렌식의 중요성이 커지고 있다. 일부 시스템들은 전원이나 네트워크를 차단하지 않고 수사하는 live forensic의 방법을 채택하고 있는데, 인터넷 사용이 일반화됨에 따라 live forensic 방법이 채택되는 횟수가 증가하고 있다. 그러나 live forensic 기술이 상당한 발전을 거듭하였음에도 불구하고 원격으로 접근하여 행해지는 Anti-forensic 행위에는 여전히 취약한 실정이다. 이와 같은 문제를 해결하기 위하여 첫 번째로 우리는 Anti-forensic 행위를 5개의 계층으로 분류하고 각 계층별로 가능한 Anti-forensic 행위의 시나리오를 생성하는 방법을 제안하였다. 두 번째로 fuzzy 전문가 시스템을 제안하여 효과적으로 Anti-forensic 행위를 탐지할 수 있도록 하였다. 몇몇 Anti-forensic행위에 사용되는 명령어들은 일반적인 시스템 관리를 위하여 사용되는 명령어와 매우 유사하다. 따라서 우리는 fuzzy logic을 사용하여 모호한 데이터를 다룰 수 있도록 하였다. 미리 정의된 시나리오에서 명령어와 옵션 및 인자 값을 이용하여 룰을 생성하고 fuzzy 전문가 시스템에 이 룰을 학습하도록 하여 유사한 행위가 탐지되었을 때 추론을 통하여 수사관에게 얼마나 위험한 행위인지 알려준다. 이 시스템은 live forensic 수사가 진행될 때 발생할 수 있는 Anti-forensic 행위를 실시간으로 탐지할 수 있도록 하여 증거 데이터의 무결성을 유지하도록 한다. Recently, the importance of digital forensic has been magnified because of the dramatic increase of cyber crimes and the increasing complexity of the investigation of target systems such as PCs, servers, and database systems. Moreover, some systems have to be investigated with live forensic techniques. However, even though live forensic techniques have been improved, they are still vulnerable to anti-forensic activities when the target systems are remotely accessible by criminals or their accomplices. To solve this problem, we first suggest a layer-based model and the anti-forensic scenarios which can actually be applicable to each layer. Our suggested model, the Anti-Forensic Activites layer-based model, has 5 layers - the physical layer, network layer, OS layer, database application layer and data layer. Each layer has possible anti-forensic scenarios with detailed commands. Second, we propose a fuzzy expert system for effectively detecting anti-forensic activities. Some anti-forensic activities are hardly distinguished from normal activities. So, we use fuzzy logic for handling ambiguous data. We make rule sets with extracted commands and their arguments from pre-defined scenarios and the fuzzy expert system learns the rule sets. With this system, we can detect anti-forensic activities in real time when performing live forensic.

Genetic-fuzzy approach to model concrete shrinkage

Wilson Ricardo Leal da Silva,Petr Štemberka 사단법인 한국계산역학회 2013 Computers and Concrete, An International Journal Vol.12 No.2

This work presents an approach to model concrete shrinkage. The goal is to permit the concrete industry’s experts to develop independent prediction models based on a reduced number of experimental data. The proposed approach combines fuzzy logic and genetic algorithm to optimize the fuzzy decision-making, thereby reducing data collection time. Such an approach was implemented for an experimental data set related to self-compacting concrete. The obtained prediction model was compared against published experimental data (not used in model development) and well-known shrinkage prediction models. The predicted results were verified by statistical analysis, which confirmed the reliability of the developed model. Although the range of application of the developed model is limited, the genetic-fuzzy approach introduced in this work proved suitable for adjusting the prediction model once additional training data are provided. This can be highly inviting for the concrete industry’s experts, since they would be able to fine-tune their models depending on the boundary conditions of their production processes.

Estimation of submerged-arc welding design parameters using Taguchi method and fuzzy logic

Lee, Jongsoo,Song, Chang-Yong SAGE Publications 2013 PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGIN Vol.227 No.4

<P>Fuzzy logic with the Taguchi method is proposed for estimating submerged-arc welding design parameters. Design of experiments based on the submerged-arc welding simulation is applied to the proposed approach. The finite element analysis of a steel plate is carried out to simulate the submerged-arc welding process using thermomechanical and temperature-dependent material properties. Welding simulation results on thermal–mechanical coupled physical phenomena are compared with welding test. The proposed fuzzy model is generated with triangle membership functions and fuzzy if–then rules using training data obtained from design of experiments and the Taguchi method. The objective of the present study is to develop a Taguchi method-based fuzzy model to effectively approximate the optimized arc weld parameters. To validate the fuzzy model, an approximate model based on response surface method is generated from the Taguchi design data, and then the results are reviewed by the outcomes obtained from the fuzzy model. This proposed study facilitates a quantitative decision of weld factors such as speed and output of weld that are generally expressed by qualitative linguistic terms in the welding process.</P>

Development of Temperature-based Weather Forecasting Models Using Neural Networks and Fuzzy Logic

L. Al-Matarneh,A. Sheta,S. Bani-Ahmad,J.Alshaer,I.Al-oqily 보안공학연구지원센터 2014 International Journal of Multimedia and Ubiquitous Vol.9 No.12

In critical fields such as flight, agriculture, tourism, etc, forecasting is an important issue due to its effectiveness in human life to know what will happen for unpredictable situations and events. Weather forecasts provide critical information about future weather conditions. Actually, weather forecasting plays an important role in our daily life by predicting what the weather will be tomorrow and it is reflected in a wide area of applications in our life so, we can prevent huge damages by forecasting the coming of storms or typhoons or get benefits from the forecasting activities. The temperature warnings are important forecasts because they are used to protect life and property and to improve the efficiency of operations. We propose computer-based models for weather forecasting based on temperature to predict the daily temperature using two techniques, artificial neural networks and fuzzy logic. The main purpose from this study is to develop different weather forecasting models based on the two techniques over different regions. The developed models show that the objectives of the study were achieved successfully. Finally, the models have been tested and the results confirm that the proposed models are capable to forecast the daily temperatures.