• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1131-1140
• /
• 2017

This study is concerned with a design methodology of optimized fuzzy clustering-based neural network classifier for classifying black plastic. Since the amount of waste plastic is increased every year, the technique for recycling waste plastic is getting more attention. The proposed classifier is on a basis of architecture of radial basis function neural network. The hidden layer of the proposed classifier is composed to FCM clustering instead of activation functions, while connection weights are formed as the linear functions and their coefficients are estimated by the local least squares estimator (LLSE)-based learning. Because the raw dataset collected from Raman spectroscopy include high-dimensional variables over about three thousands, principal component analysis(PCA) is applied for the dimensional reduction. In addition, artificial bee colony(ABC), which is one of the evolutionary algorithm, is used in order to identify the architecture and parameters of the proposed network. In experiment, the proposed classifier sorts the three kinds of plastics which is the most largely discharged in the real world. The effectiveness of the proposed classifier is proved through a comparison of performance between dataset obtained from chemical analysis and entire dataset extracted directly from Raman spectroscopy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.354-359
• /
• 2008

Clustering is a method to classify the given data set with same property into several classes. To cluster data, many methods such as K-Means, Fuzzy C-Means(FCM), Mountain Method(MM), and etc, have been proposed and used. But the clustering results of conventional methods are sensitively influenced by initial values given for clustering in each method. Especially, FCM is very sensitive to noisy data, and cluster center distortion phenomenon is occurred because the method dose clustering through minimization of within-clusters variance. In this paper, we propose a clustering method which reduces cluster center distortion through merging the nearest data based on the data weight, and not being influenced by initial values. We show the effectiveness of the proposed through experimental results applied it to various types of data sets, and comparison of cluster centers with those of FCM.

• Smart Structures and Systems
• /
• v.25 no.3
• /
• pp.323-335
• /
• 2020

Magnetorheological elastomer (MRE), a smart material, is an innovative material for base isolation system. It has magnetorheological (MR) effect that can control the stiffness in real-time. In this paper, a new hybrid base isolation system combining two electromagnetic closed circuits and the roller bearing is proposed. In the proposed system, the roller part can support the vertical load. Thus, the MRE part is free from the vertical load and can exhibit the maximum MR effect. The MRE magnetic loop is constructed in the free space of the roller bearing and forms a strong magnetic field. To demonstrate the performance of the proposed hybrid base isolation system, dynamic characteristic tests and performance evaluation were carried out. Dynamic characteristic tests were performed under the extensive range of strain of the MRE and the change of the applied current. Performance evaluation was carried out using the hybrid simulation under five earthquakes (i.e., El Centro, Kobe, Hachinohe, Northridge, and Loma Prieta). Especially, semi-active fuzzy control algorithm was applied and compared with passive type. From the performance evaluation, the comparison shows that the new hybrid base isolation system using fuzzy control algorithm is superior to passive type in reducing the acceleration and displacement responses of a target structure.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.03a
• /
• pp.187-194
• /
• 2008

Because the types and severities of most engine faults are various and complex, it is not easy that the conventional model based fault detection approach like the GPA(Gas Path Analysis) method can monitor all engine fault conditions. Therefore this study proposed newly a diagnostic algorithm for isolating and diagnosing effectively the faulted components of the smart UAV propulsion system, which has been developed by KARI(Korea Aerospace Research Institute), using the fuzzy logic and the neural network algorithms. A precise performance model should be needed to perform the model-based diagnostics. The based engine performance model was developed using SIMULINK. For the work and mass flow matching between components of the steady-state simulation, the state-flow library was applied. The proposed steady-state performance model can simulate off-design point performance at various flight conditions and part loads, and in order to evaluate the steady-state performance model their simulation results were compared with manufacturer's performance deck data. According to comparison results, it was confirm that the steady-state model well agreed with the deck data within 3% in all flight envelop. The diagnosis procedure of the proposed diagnostic system has the following steps. Firstly after obtaining database of fault patterns through performance simulation, then secondly the diagnostic system was trained by the FFBP networks. Thirdly after analyzing the trend of the measuring parameters due to fault patterns, then fourthly faulted components were isolated using the fuzzy logic. Finally magnitudes of the detected faults were obtained by the trained neural networks. Because the detected faults have almost same as degradation values of the implanted fault pattern, it was confirmed that the proposed diagnostic system can detect well the engine faults.

• 한국사회정책
• /
• v.25 no.4
• /
• pp.301-321
• /
• 2018

The purpose of this paper is to analyze whether any combination of the quantitative and qualitative aspects of the public pension system is a causal factor for the elderly poverty reduction rate. For this, fuzzy-set qualitative comparison analysis was conducted with the poverty reduction rate as the outcome condition variable, the public pension expenditure ratio, the redistributive index, the first floor public pension weight, the second floor public pension weight and the second floor forced private pension weight did. As a result of the analysis, the combination of high public pension expenditure ratio, low two - tier public pension share and high two - tier compulsory private pension share has become a cause of high poverty reduction rate of the elderly. And more various forms of association were found as the cause of low poverty reduction rate of the elderly. This paper suggests policy proposals based on the above findings.

• Smart Structures and Systems
• /
• v.23 no.5
• /
• pp.449-466
• /
• 2019

Cable-stayed bridges are attractive due to their beauty, reducing material consumption, less harm to the environment and so on, in comparison with other kinds of bridges. As a massive structure with long period and low damping (0.3 to 2%) under many dynamic loads, these bridges are susceptible to fatigue, serviceability disorder, damage or even collapse. Tuned Mass Damper (TMD) is a suitable controlling system to reduce the vibrations and prevent the threats in such bridges. In this paper, Multi Tuned Mass Damper (MTMD) system is added to the Ahvaz cable stayed Bridge in Iran, to reduce its seismic vibrations. First, the bridge is modeled in SAP2000 followed with result verification. Dead and live loads and the moving loads have been assigned to the bridge. Then the finite element model is developed in OpenSees, with the goal of running a nonlinear time-history analysis. Three far-field and three near-field earthquake records are imposed to the model after scaling to the PGA of 0.25 g, 0.4 g, 0.55 g and 0.7 g. Two MTMD systems, passive and active, with the number of TMDs from 1 to 8, are placed in specific points of the main span of bridge, adding a total mass ratio of 1 to 10% to the bridge. The parameters of the TMDs are optimized using Genetic Algorithm (GA). Also, the optimum force for active control is achieved by Fuzzy Logic Control (FLC). The results showed that the maximum displacement of the center of the bridge main span reduced 33% and 48% respectively by adding passive and active MTMD systems. The RMS of displacement reduced 37% and 47%, the velocity 36% and 42% and also the base shear in pylons, 27% and 47%, respectively by adding passive and active systems, in the best cases.

• Geomechanics and Engineering
• /
• v.34 no.6
• /
• pp.697-726
• /
• 2023

Brittleness as an important property of rock plays a crucial role both in the failure process of intact rock and rock mass response to excavation in engineering geological and geotechnical projects. Generally, rock brittleness indices are calculated from the mechanical properties of rocks such as uniaxial compressive strength, tensile strength and modulus of elasticity. These properties are generally determined from complicated, expensive and time-consuming tests in laboratory. For this reason, in the present research, an attempt has been made to predict the rock brittleness indices from simple, inexpensive, and quick laboratory test results namely dry unit weight, porosity, slake-durability index, P-wave velocity, Schmidt rebound hardness, and point load strength index using multiple linear regression, exponential regression, support vector machine (SVM) with various kernels, generating fuzzy inference system, and regression tree ensemble (RTE) with boosting framework. So, this could be considered as an innovation for the present research. For this purpose, the number of 39 rock samples including five igneous, twenty-six sedimentary, and eight metamorphic were collected from different regions of Iran. Mineralogical, physical and mechanical properties as well as five well known rock brittleness indices (i.e., B₁, B₂, B₃, B₄, and B₅) were measured for the selected rock samples before application of the above-mentioned machine learning techniques. The performance of the developed models was evaluated based on several statistical metrics such as mean square error, relative absolute error, root relative absolute error, determination coefficients, variance account for, mean absolute percentage error and standard deviation of the error. The comparison of the obtained results revealed that among the studied methods, SVM is the most suitable one for predicting B₁, B₂ and B₅, while RTE predicts B₃ and B₄ better than other methods.

• Steel and Composite Structures
• /
• v.48 no.2
• /
• pp.179-190
• /
• 2023

Many recent attempts have sought accurate prediction of pile pullout resistance (P_ul) using classical machine learning models. This study offers an improved methodology for this objective. Adaptive neuro-fuzzy inference system (ANFIS), as a popular predictor, is trained by a capable metaheuristic strategy, namely equilibrium optimizer (EO) to predict the P_ul. The used data is collected from laboratory investigations in previous literature. First, two optimal configurations of EO-ANFIS are selected after sensitivity analysis. They are next evaluated and compared with classical ANFIS and two neural-based models using well-accepted accuracy indicators. The results of all five models were in good agreement with laboratory P_uls (all correlations > 0.99). However, it was shown that both EO-ANFISs not only outperform neural benchmarks but also enjoy a higher accuracy compared to the classical version. Therefore, utilizing the EO is recommended for optimizing this predictive tool. Furthermore, a comparison between the selected EO-ANFISs, where one employs a larger population, revealed that the model with the population size of 75 is more efficient than 300. In this relation, root mean square error and the optimization time for the EO-ANFIS (75) were 19.6272 and 1715.8 seconds, respectively, while these values were 23.4038 and 9298.7 seconds for EO-ANFIS (300).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1317-1340
• /
• 2024

With the rapid development of information technology, people's demands on precise indoor positioning are increasing. Wireless sensor network, as the most commonly used indoor positioning sensor, performs a vital part for precise indoor positioning. However, in indoor positioning, obstacles and other uncontrollable factors make the localization precision not very accurate. Ultra-wide band (UWB) can achieve high precision centimeter-level positioning capability. Inertial navigation system (INS), which is a totally independent system of guidance, has high positioning accuracy. The combination of UWB and INS can not only decrease the impact of non-line-of-sight (NLOS) on localization, but also solve the accumulated error problem of inertial navigation system. In the paper, a fused UWB and INS positioning method is presented. The UWB data is firstly clustered using the Fuzzy C-means (FCM). And the Z hypothesis testing is proposed to determine whether there is a NLOS distance on a link where a beacon node is located. If there is, then the beacon node is removed, and conversely used to localize the mobile node using Least Squares localization. When the number of remaining beacon nodes is less than three, a robust extended Kalman filter with M-estimation would be utilized for localizing mobile nodes. The UWB is merged with the INS data by using the extended Kalman filter to acquire the final location estimate. Simulation and experimental results indicate that the proposed method has superior localization precision in comparison with the current algorithms.

• Journal of Korea Water Resources Association
• /
• v.45 no.2
• /
• pp.229-242
• /
• 2012

This study presents a physical habitat modeling of adult Zacco platypus in a reach of the Dalcheon Stream located downstream of the Goesaan Dam. CASiMiR model is used to estimate habitat suitability index based on the fuzzy logic. Results are compared with those from River2D model, which uses habitat preference curve for habitat suitability index. Hydraulic data simulated by River2D are used as input data for CASiMiR model after verification against field measurements. The result shows that the habitat suitability of the adult Zacco platypus is maximum around the riffle area located upstream of the bend. CASiMiR and River2D estimate the maximum weighted usable areas at the discharge rates of 7.23 $m^3/s$ and 9.0 $m^3/s$, respectively. Overall comparison of the two models employed in this study indicates that CASiMiR model overestimates the weighted usable area by 0.3~25.3% compared with River2D model in condition of drought flow (Q355), low flow (Q275), normal flow (Q185), and average-wet flow (Q95).