• Structural Engineering and Mechanics
• /
• v.83 no.3
• /
• pp.293-304
• /
• 2022

In this work, a novel reliability approach for combined high and low cycle fatigue (CCF) estimation is developed by combining active learning strategy with least squares support vector machines (LS-SVM) (named as ALS-SVM) surrogate model to address the multi-resources uncertainties, including working loads, material properties and model itself. Initially, a new active learner function combining LS-SVM approach with Monte Carlo simulation (MCS) is presented to improve computational efficiency with fewer calls to the performance function. To consider the uncertainty of surrogate model at candidate sample points, the learning function employs k-fold cross validation method and introduces the predicted variance to sequentially select sampling. Following that, low cycle fatigue (LCF) loads and high cycle fatigue (HCF) loads are firstly estimated based on the training samples extracted from finite element (FE) simulations, and their simulated responses together with the sample points of model parameters in Coffin-Manson formula are selected as the MC samples to establish ALS-SVM model. In this analysis, the MC samples are substituted to predict the CCF reliability of turbine blades by using the built ALS-SVM model. Through the comparison of the two approaches, it is indicated that the reliability model by linear cumulative damage rule provides a non-conservative result compared with that by the proposed one. In addition, the results demonstrate that ALS-SVM is an effective analysis method holding high computational efficiency with small training samples to gain accurate fatigue reliability.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.15-24
• /
• 2008

For high-dimensional classification tasks, such as face recognition, the number of samples is smaller than the dimensionality of the samples. In such cases, a problem encountered in linear discriminant analysis-based methods for dimension reduction is what is known as the small sample size (SSS) problem. Recently, to solve the SSS problem, a way of employing a dissimilarity-based classification(DBC) has been investigated. In DBC, an object is represented based on the dissimilarity measures among representatives extracted from training samples instead of the feature vector itself. In this paper, we propose a new method of optimizing DBCs using multi-level fusion strategies(MFS), in which fusion strategies are employed to represent features as well as to design classifiers. Our experimental results for benchmark face databases demonstrate that the proposed scheme achieves further improved classification accuracies.

• Wind and Structures
• /
• v.32 no.4
• /
• pp.355-369
• /
• 2021

Shape optimization of tall buildings is an efficient approach to mitigate wind-induced effects. Several studies have demonstrated the potential of shape modifications to improve the building's aerodynamic properties. On the other hand, it is well-known that the cross-section geometry has a direct impact in the floor area availability and subsequently in the building's profitability. Hence, it is of interest for the designers to find the balance between these two design criteria that may require contradictory design strategies. This study proposes a surrogate-based multi-objective optimization framework to tackle this design problem. Closed-form equations provided by the Eurocode are used to obtain the wind-induced responses for several wind directions, seeking to develop an industry-oriented approach. CFD-based surrogates emulate the aerodynamic response of the building cross-section, using as input parameters the cross-section geometry and the wind angle of attack. The definition of the building's modified plan shapes is done adopting the reduced basis approach, advancing the current strategies currently adopted in aerodynamic optimization of civil engineering structures. The multi-objective optimization problem is solved with both the classical weighted Sum Method and the Weighted Min-Max approach, which enables obtaining the complete Pareto front in both convex and non-convex regions. Two application examples are presented in this study to demonstrate the feasibility of the proposed strategy, which permits the identification of Pareto optima from which the designer can choose the most adequate design balancing profitability and occupant comfort.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.4
• /
• pp.143-152
• /
• 2021

It is very important to learn behavioral policies that allow multiple agents to work together organically for common goals in various real-world applications. In this multi-agent reinforcement learning (MARL) environment, most existing studies have adopted centralized training with decentralized execution (CTDE) methods as in effect standard frameworks. However, this multi-agent reinforcement learning method is difficult to effectively cope with in a dynamic environment in which new environmental changes that are not experienced during training time may constantly occur in real life situations. In order to effectively cope with this dynamic environment, this paper proposes a novel multi-agent reinforcement learning system, C-COMA. C-COMA is a continual learning model that assumes actual situations from the beginning and continuously learns the cooperative behavior policies of agents without dividing the training time and execution time of the agents separately. In this paper, we demonstrate the effectiveness and excellence of the proposed model C-COMA by implementing a dynamic mini-game based on Starcraft II, a representative real-time strategy game, and conducting various experiments using this environment.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Smart Structures and Systems
• /
• v.10 no.4_5
• /
• pp.443-458
• /
• 2012

The structural health monitoring (SHM) benchmark study on optimal sensor placement problem for the instrumented Canton Tower has been launched. It follows the success of the modal identification and model updating for the Canton Tower in the previous benchmark study, and focuses on the optimal placement of vibration sensors (accelerometers) in the interest of bettering the SHM system. In this paper, the sensor placement problem for the Canton Tower and the benchmark model for this study are first detailed. Then an information entropy based sensor placement method with the purpose of damage detection is proposed and applied to the benchmark problem. The procedure that will be implemented for structural damage detection using the data obtained from the optimal sensor placement strategy is introduced and the information on structural damage is specified. The information entropy based method is applied to measure the uncertainties throughout the damage detection process with the use of the obtained data. Accordingly, a multi-objective optimal problem in terms of sensor placement is formulated. The optimal solution is determined as the one that provides equally most informative data for all objectives, and thus the data obtained is most informative for structural damage detection. To validate the effectiveness of the optimally determined sensor placement, damage detection is performed on different damage scenarios of the benchmark model using the noise-free and noise-corrupted measured information, respectively. The results show that in comparison with the existing in-service sensor deployment on the structure, the optimally determined one is capable of further enhancing the capability of damage detection.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.47-55
• /
• 2016

As one of recent issues in the information and communication industry, internet of things has attracted attention to provide intelligent infrastructure services which connect and share data and information between real and virtual world. According to the development of these internet of things technologies, types of machines, telecommunication devices, and terminals are increasing tremendously. In this situation, connectivity and interoperability between internet of things components are important issues to build a hyper connected society. To visualize this society, it is important to set up and develop information and communication technology (ICT) standards among stakeholders. However, under limited budget and human resources, it is essential to rank standardization work items for setting standards with respect to efficiency. The purpose of this study is to provide a method for setting standardization strategies within group decision making. As a multi-criteria group decision making tool, analytic hierarchy process (AHP) is adopted and applied to determine the priorities of setting work items. The proposed method first defines decision making problem with objective, criteria, and alternatives which produces a hierarchy consisting of upper and lower criteria. Then, pairwise comparisons of academy and public sector experts are performed with respect to their relative meaning and importance. Individual surveys of expert groups are collected and summarized to determine relative criteria importance measures. Furthermore, to deliver reliable importance criteria measures, differences between academy and public sector expert groups are compared and tested using Mann-Whitney non-parametric test. The results are illustrated for useful guidelines to practical group decision making in standardization strategy establishments.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.6
• /
• pp.2227-2235
• /
• 2018

Under the current policies and compensation rules in South Korea, Photovoltaic (PV) generation supplier can maximize the profit by combining PV generation with Energy Storage System (ESS). However, the existing operational strategy of ESS is not able to maximize the profit due to the limitation of ESS capacity. In this paper, new ESS scheduling algorithm is introduced by utilizing the System Marginal Price (SMP) and PV generation forecasting to maximize the profits of PV generation supplier. The proposed algorithm determines the charging time of ESS by ranking the charging schedule from low to high SMP when PV generation is more than enough to charge ESS. The discharging time of ESS is determined by ranking the discharging schedule from high to low SMP when ESS energy is not enough to maintain the discharging. To compensate forecasting error, the algorithm is updated every hour to apply the up-to-date information. The simulation is performed to verify the effectiveness of the proposed algorithm by using actual PV generation and ESS information.

• Smart Structures and Systems
• /
• v.4 no.1
• /
• pp.47-66
• /
• 2008

The present work utilizes system identification technique for health monitoring of shear building, wherein Parametric State Space modeling has been adopted. The method requires input excitation to the structure and also output acceleration responses of both undamaged and damaged structure obtained from numerically simulated model. Modal parameters like eigen frequencies and eigen vectors have been extracted from the State Space model after introducing appropriate transformation. Least square technique has been utilized for the evaluation of the stiffness matrix after having obtained the modal matrix for the entire structure. Highly accurate values of stiffness of the structure could be evaluated corresponding to both the undamaged as well as damaged state of a structure, while considering noise in the simulated output response analogous to real time scenario. The damaged floor could also be located very conveniently and accurately by this adopted strategy. This method of damage detection can be applied in case of output acceleration responses recorded by sensors from the actual structure. Further, in case of even limited availability of sensors along the height of a multi-storeyed building, the methodology could yield very accurate information related to structural stiffness.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.4
• /
• pp.375-383
• /
• 2012

Together with the GPS-based approach, geolocation through mobile communication networks is a key technology for location-based service. Since the Mobile WiMAX system is considered as a candidate for fourth-generation mobile systems, it is important to investigate its location capability. The geolocation of Mobile WiMAX can be realized when the preamble symbols in the down-link channel are appropriately used for a TDOA (Time-Difference-of-Arrival) approach. However, the cellular structure of Mobile WiMAX inevitably generates co-channel interference, and it is difficult for the mobile terminal to acquire distance measurements from multiple base stations. Therefore, for geolocation via multilateration using the Mobile WiMAX network, it is very important to increase hearability. This paper proposes a geolocation method for Mobile WiMAX which employs interference cancellation and preamble signal overlapping for the enhancement of hearability. A novel interference cancellation strategy for complex-valued Mobile WiMAX signals is presented which has an iterative structure. Simulation results show that the proposed geolocation method provides the user's position with an accuracy of less than 20 m through the Mobile WiMAX cellular network if there is no multi-path or NLOS (None-Line-of-Sight).