• Structural Engineering and Mechanics
• /
• 제27권4호
• /
• pp.409-424
• /
• 2007

In this paper, an identification method of impact force is proposed for composite structures. In this method, the relation between force histories and strain responses is first formulated. The transfer matrix, which relates the strain responses of sensors and impact force information, is constructed from the finite element method (FEM). Based on this relation, an optimization model to minimize the difference between the measured strain responses and numerically evaluated strain responses is built up to obtain the impact force history. The identification of force history is performed by a modified least-squares method that imposes the penalty on the first-order derivative of the force history. Moreover, from the relation of strain responses and force history, an error vector indicating the force location is defined and used for the force location identification. The above theory has also been extended into the cases when using acceleration information instead of strain information. The validity of the present method has been verified through two experimental examples. The obtained results demonstrate that the present approach works very well, even when the internal damages in composites happen due to impact events. Moreover, this method can be used for the real-time health monitoring of composite structures.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권3호
• /
• pp.234-240
• /
• 1999

This paper presents a new approach for large-scale generator maintenance scheduling optimizations. The generator preventive maintenance scheduling problems are typical discrete dynamic n-dimensional vector optimization ones with several inequality constraints. The considered objective function to be minimized a subset of{{{{ { R}^{n } }}}} space is the variance (i.g., second-order momentum) of operating reserve margin to levelize risk or reliability during a year. By its nature of the objective function, the optimal solution can only be obtained by enumerating all combinatorial states of each variable, a task which leads to computational explosion in real-world maintenance scheduling problems. This paper proposes a new priority search mechanism based on each generator's discrete sensitivity value which was analytically developed in this study. Unlike the conventional capacity-based priority search, it can prevent the local optimal trap to some extents since it changes dynamically the search tree in each iteration. The proposed method have been applied to two test systems (i.g., one is a sample system with 10 generators and the other is a real-world lage scale power system with 280 generators), and the results anre compared with those of the conventional capacith-based search method and combinatorial optimization method to show the efficiency and effectiveness of the algorithm.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2005년도 공동추계학술대회
• /
• pp.516-525
• /
• 2005

Case-based reasoning (CBR) has been widely used in various areas due to its convenience and strength in complex problem solving. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However, designing a good matching and retrieval mechanism for CBR systems is still a controversial research issue. Most prior studies have tried to optimize the weights of the features or selection process of appropriate instances. But, these approaches have been performed independently until now. Simultaneous optimization of these components may lead to better performance than in naive models. In particular, there have been few attempts to simultaneously optimize the weight of the features and selection of the instances for CBR. Here we suggest a simultaneous optimization model of these components using a genetic algorithm (GA). We apply it to a customer classification model which utilizes demographic characteristics of customers as inputs to predict their buying behavior for a specific product. Experimental results show that simultaneously optimized CBR may improve the classification accuracy and outperform various optimized models of CBR as well as other classification models including logistic regression, multiple discriminant analysis, artificial neural networks and support vector machines.

• Journal of Communications and Networks
• /
• 제4권3호
• /
• pp.230-245
• /
• 2002

Usually the network-throughput maximization problem for constant-bit-rate (CBR) circuit-switched traffic is posed for a fixed offered load profile. Then choices of routes and of admission control policies are sought to achieve maximum throughput (usually under QoS constraints). However, similarly to the notion of channel “capacity,” it is also of interest to determine the “network capacity;” i.e., for a given network we would like to know the maximum throughput it can deliver (again subject to specified QoS constraints) if the appropriate traffic load is supplied. Thus, in addition to determining routes and admission controls, we would like to specify the vector of offered loads between each source/destination pair that “achieves capacity.” Since the combined problem of choosing all three parameters (i.e., offered load, admission control, and routing) is too complex to address, we consider here only the optimal determination of offered load for given routing and admission control policies. We provide an off-line algorithm, which is based on Lagrangian techniques that perform robustly in this rigorously formulated nonlinear optimization problem with nonlinear constraints. We demonstrate that significant improvement is obtained, as compared with simple uniform loading schemes, and that fairness mechanisms can be incorporated with little loss in overall throughput.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2078-2093
• /
• 2019

Visual smoke recognition is a challenging task due to large variations in shape, texture and color of smoke. To improve performance, we propose a novel smoke recognition method by combining dual-encoded features that are extracted from both spatial and Curvelet domains. A Curvelet transform is used to filter an image to generate fifty sub-images of Curvelet coefficients. Then we extract Local Binary Pattern (LBP) maps from these coefficient maps and aggregate histograms of these LBP maps to produce a histogram map. Afterwards, we encode the histogram map again to generate Dual-encoded Local Binary Patterns (Dual-LBP). Histograms of Dual-LBPs from Curvelet domain and Completed Local Binary Patterns (CLBP) from spatial domain are concatenated to form the feature for smoke recognition. Finally, we adopt Gaussian Kernel Optimization (GKO) algorithm to search the optimal kernel parameters of Support Vector Machine (SVM) for further improvement of classification accuracy. Experimental results demonstrate that our method can extract effective and reasonable features of smoke images, and achieve good classification accuracy.

• 한국초전도ㆍ저온공학회논문지
• /
• 제23권3호
• /
• pp.41-44
• /
• 2021

We developed an optimization process of the pulsed laser deposition method to grow epitaxial CeCoIn₅ thin films on MgF₂ substrates. The effects of different deposition parameters on film growth were extensively studied by analyzing the measured X-ray diffraction patterns. All the deposited films contained small amounts of CeIn₃ impurity phase and misoriented CeCoIn₅, for which the c-axis of the unit cell is perpendicular to the normal vector of the substrate surface. The deposition temperature, target composition, laser energy density, and repetition rate were found effective in the formation of (00l)-oriented CeCoIn₅ as well as the undesired phases such as CeIn₃, misoriented CeCoIn₅ along the (112) and (h00). Our results provide a set of deposition parameters that produce high-quality epitaxial CeCoIn₅ thin films with sufficiently low amounts of impurity phases and can serve as a reference for future studies to optimize the deposition process further.

• Steel and Composite Structures
• /
• 제42권6호
• /
• pp.733-745
• /
• 2022

This study proposed a robust artificial intelligence (AI) model based on the social behaviour of the imperialist competitive algorithm (ICA) and artificial neural network (ANN) for modelling the deflection of reinforced concrete beams, abbreviated as ICA-ANN model. Accordingly, the ICA was used to adjust and optimize the parameters of an ANN model (i.e., weights and biases) aiming to improve the accuracy of the ANN model in modelling the deflection reinforced concrete beams. A total of 120 experimental datasets of reinforced concrete beams were employed for this aim. Therein, applied load, tensile reinforcement strength and the reinforcement percentage were used to simulate the deflection of reinforced concrete beams. Besides, five other AI models, such as ANN, SVM (support vector machine), GLMNET (lasso and elastic-net regularized generalized linear models), CART (classification and regression tree) and KNN (k-nearest neighbours), were also used for the comprehensive assessment of the proposed model (i.e., ICA-ANN). The comparison of the derived results with the experimental findings demonstrates that among the developed models the ICA-ANN model is that can approximate the reinforced concrete beams deflection in a more reliable and robust manner.

• ETRI Journal
• /
• 제44권4호
• /
• pp.613-623
• /
• 2022

Autism spectrum disorder (ASD) is a developmental disorder associated with cognitive and neurobehavioral disorders. It affects the person's behavior and performance. Autism affects verbal and non-verbal communication in social interactions. Early screening and diagnosis of ASD are essential and helpful for early educational planning and treatment, the provision of family support, and for providing appropriate medical support for the child on time. Thus, developing automated methods for diagnosing ASD is becoming an essential need. Herein, we investigate using various machine learning methods to build predictive models for diagnosing ASD in children using facial images. To achieve this, we used an autistic children dataset containing 2936 facial images of children with autism and typical children. In application, we used classical machine learning methods, such as support vector machine and random forest. In addition to using deep-learning methods, we used a state-of-the-art method, that is, automated machine learning (AutoML). We compared the results obtained from the existing techniques. Consequently, we obtained that AutoML achieved the highest performance of approximately 96% accuracy via the Hyperpot and tree-based pipeline optimization tool optimization. Furthermore, AutoML methods enabled us to easily find the best parameter settings without any human efforts for feature engineering.

• Journal of Microbiology and Biotechnology
• /
• 제21권1호
• /
• pp.93-99
• /
• 2011

Amongst a number of potential nonviral vectors, cationic liposomes have been actively researched, with both gemini surfactants and bola amphiphiles reported as being in possession of good structures in terms of cell viability and in vitro transfection. In this study, a cholesterol-based diquaternary ammonium gemini surfactant (Chol-GS) was synthesized and assessed as a novel nonviral gene vector. Chol-GS was synthesized from cholesterol by way of four reaction steps. The optimal efficiency was found to be at a weight ratio of 1:4 of lipid:DOPE (1,2-dioleoyl-L-${\alpha}$- glycero-3-phosphatidylethanolamine), and at a ratio of between 10:1~15:1 of liposome:DNA. The transfection efficiency was compared with commercial liposomes and with Lipofectamine, 1,2-dimyristyloxypropyl-3-dimethylhydroxyethylammonium bromide (DMRIE-C), and N-[1-(2,3-dioleoyloxy)propyl]-N,N,N-trimethylammonium chloride (DOTAP). The results indicate that the efficiency of Chol-GS is greater than that of all the tested commercial liposomes in COS7 and Huh7 cells, and higher than DOTAP and Lipofectamine in A549 cells. Confirmation of these findings was observed through the use of green fluorescent protein expression. Chol-GS exhibited a moderate level of cytotoxicity, at optimum concentrations for efficient transfection, indicating cell viability. Hence, the newly synthesized Chol-GS liposome has the potential of being an excellent nonviral vector for gene delivery.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1614-1632
• /
• 2017

Bag of visual words is a popular model in human action recognition, but usually suffers from loss of spatial and temporal configuration information of local features, and large quantization error in its feature coding procedure. In this paper, to overcome the two deficiencies, we combine sparse coding with spatio-temporal pyramid for human action recognition, and regard this method as the baseline. More importantly, which is also the focus of this paper, we find that there is a hierarchical structure in feature vector constructed by the baseline method. To exploit the hierarchical structure information for better recognition accuracy, we propose a tree regularized classifier to convey the hierarchical structure information. The main contributions of this paper can be summarized as: first, we introduce a tree regularized classifier to encode the hierarchical structure information in feature vector for human action recognition. Second, we present an optimization algorithm to learn the parameters of the proposed classifier. Third, the performance of the proposed classifier is evaluated on YouTube, Hollywood2, and UCF50 datasets, the experimental results show that the proposed tree regularized classifier obtains better performance than SVM and other popular classifiers, and achieves promising results on the three datasets.