• Smart Structures and Systems
• /
• 제31권1호
• /
• pp.45-56
• /
• 2023

Vibration-based structural health monitoring is used to ensure the safety of structures by installing sensors in structures. The peak picking method, one of the applications of vibration-based structural health monitoring, is a method that analyze the dynamic characteristics of a structure using the peaks of the frequency response function. However, the results may vary depending on the person predicting the peak point; further, the method does not predict the exact peak point in the presence of noise. To overcome the limitations of the existing peak picking methods, this study proposes a new method to automate the modal analysis process by utilizing long short-term memory, a type of recurrent neural network. The method proposed in this study uses the time series data of the frequency response function directly as the input of the LSTM network. In addition, the proposed method improved the accuracy by using the phase as well as amplitude information of the frequency response function. Simulation experiments and lab-scale model experiments are performed to verify the performance of the LSTM network developed in this study. The result reported a modal assurance criterion of 0.8107, and it is expected that the dynamic characteristics of a civil structure can be predicted with high accuracy using data without experts.

• Asian Journal of Innovation and Policy
• /
• 제2권2호
• /
• pp.240-264
• /
• 2013

The study compares network structures that emerged in three inter-organisational projects set up under the MSC Malaysia initiative by the Government of Malaysia. These consortia are seen as policy-driven inter-organisational networks and, with data collected through interviews; the links among the organisations are mapped to gain an understanding of the structures that emerged in these networks. The findings provide lessons for other emerging countries that are embarking on similar projects i.e. cluster-oriented developments with policy-driven inter-organisational networks. These findings are seen as particularly useful when emerging countries invest in technology-related projects and invite multinational companies to work together with local firms.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 춘계학술대회 학술발표 논문집
• /
• pp.71-74
• /
• 1998

In recent years, advances in construction techniques and materials have given rese to flexible light-weight structures like high-rise buildings and long-span bridges. Because these structures extremely susceptible to environmental loads, such as earthquakes and strong winds, these random loadings usually produce large deflection and acceleration on these structures. Vibration control system of structures are becoming an integral part of the structural system of the next generation of tall building. The proposed control system is applied to single degree of structure with mass damping and compared with conventional PID and neural network PID control system.

• 지식경영연구
• /
• 제12권2호
• /
• pp.69-80
• /
• 2011

This paper reports on a structural view of a knowledge network comprised of clubs and organisationsexpressly concerned with cultural activities in a regional Australian city. Social network analysis showed an uneven distribution of power, influence, and prominence in the network. The network structure consisted of two modules of vertices clustered around particular categories of creative arts and these modules were linked most frequently by several organisations acting as communication hubs and boundary spanners. The implications of the findings include 'network weaving' for improving the network structure and developing a systemic approach for exploring the structures of social action that form community-based knowledge networks.

• Asian Journal of Business Environment
• /
• 제11권1호
• /
• pp.27-37
• /
• 2021

Purpose: This article aims to provide a balanced understanding of the structural conditions and social processes involved in the creation and diffusion of innovation. Research design, data and methodology: Drawing on organizational and economic sociology and strategic management literature, this article offers a conceptual framework that highlights the two dimensions of network structures: the vertical dimension focusing on power and legitimacy vs. the horizontal dimension highlighting information value. By organizing the literature on the functions and consequences of network, this paper advances a theoretical perspective in understanding the vast array of empirical studies on innovation involving network analysis. Results: Using the proposed framework, this article explains how the mechanisms of power, legitimacy, and information value work together with social structural factors, thus enriching our understanding of innovation. This study reveals that the information mechanism (horizontal dimension) has been most important in innovation creation and diffusion, and that trust, credibility, and legitimacy are operative in innovation diffusion. Conclusions: This paper contributes to the literature by responding to calls to extend existing frameworks to better account for the dynamics between innovation and network. In addition, this article highlights how conceptualizing innovation within the horizontal-vertical dimensions of network structures, creates new opportunities for future research.

• Educational Technology International
• /
• 제21권2호
• /
• pp.193-216
• /
• 2020

This study investigated university students' perspectives on good class and instructional practices through social network analysis. The subjects were 321 students in the third and fourth academic years in a Korean university. The subjects completed four open-ended questions, asking about experience of good class, good instructors' teaching practice, and their feelings and attitudes when participating in good class. As social network analysis, KrKwic (Korea Key Words in Context) was used to compute word frequencies and analyze semantic network structures and Ucinet Netdraw to assess centrality in the social network, consisting of degree centrality, closeness centrality, and between centrality. The results are as follows. First, students showed 5 keywords to depict what good class is, including 'understanding', 'example', 'video', 'interest', and 'communication'. Second, the characteristics of teaching methods by professors who practice good class indicate 'assignments', 'questions', 'understanding', 'example', and 'feedback'. Third, the top 5 keywords of students' attitudes as participating in good class are 'active', 'participation', 'focus', 'listening', and 'asking'. Last, keywords depicting desirable class that students most wanted to take next time are 'assignments', 'rewards', 'understanding', 'difficulty', and 'interest'. The findings from this study include the meanings of the semantic network structures of words in the text making up messages. Also this study can provide empirical evidence for educators and educational practitioners in higher education to create effective learning environments.

• Computers and Concrete
• /
• 제10권2호
• /
• pp.197-217
• /
• 2012

This research deals with the prediction of compressive strength of normal and high strength concrete using neural networks. The compressive strength was modeled as a function of eight variables: quantities of cement, fine aggregate, coarse aggregate, micro-silica, water and super-plasticizer, maximum size of coarse aggregate, fineness modulus of fine aggregate. Two networks, one using raw variables and another using grouped dimensionless variables were constructed, trained and tested using available experimental data, covering a large range of concrete compressive strengths. The neural network models were compared with regression models. The neural networks based model gave high prediction accuracy and the results demonstrated that the use of neural networks in assessing compressive strength of concrete is both practical and beneficial. The performance of model using the grouped dimensionless variables is better than the prediction using raw variables.

• Smart Structures and Systems
• /
• 제26권1호
• /
• pp.63-75
• /
• 2020

Substructure pseudo-dynamic hybrid simulation (SPDHS) combining the advantages of physical experiments and numerical simulation has become an important testing method for evaluating the dynamic responses of structures. Various parameter identification methods have been proposed for online model updating. However, if there is large model gap between the assumed numerical models and the real models, the parameter identification methods will cause large prediction errors. This study presents an ANN (artificial neural network) method based on forgetting factor. During the SPDHS of model updating, a dynamic sample window is formed in each loading step with forgetting factor to keep balance between the new samples and historical ones. The effectiveness and anti-noise ability of this method are evaluated by numerical analysis of a six-story frame structure with BRBs (Buckling Restrained Brace). One BRB is simulated in OpenFresco as the experimental substructure, while the rest is modeled in MATLAB. The results show that ANN is able to present more hysteresis behaviors that do not exist in the initial assumed numerical models. It is demonstrated that the proposed method has good adaptability and prediction accuracy of restoring force even under different loading histories.

• Smart Structures and Systems
• /
• 제15권3호
• /
• pp.543-553
• /
• 2015

The condition of the vehicular bridge network in New York City, as represented by ratings obtained during biennial inspections is reviewed over a period of three decades. Concurrently, the bridges comprising the network are considered as networks of structural elements whose condition defines the overall bridge condition according to New York State assumptions. A knowledge-based matrix of assessments is used in order to determine each element's vulnerability and impact within the network of an individual structure and the network of City bridges. In both networks expansion deck joints emerge as the weak link. Typical joint failures are illustrated. Bridge management options for maintenance, preservation, rehabilitation and replacement are examined in the context of joint performance.

• 한국전산구조공학회논문집
• /
• 제23권6호
• /
• pp.667-673
• /
• 2010

Recently, structures are becoming longer and higher because of the developments of new materials and construction techniques. However, such modern structures are more susceptible to excessive structural vibrations which cause deterioration in serviceability and structural safety. A modified probabilistic neural network(MPNN) approach is proposed to reduce the structural vibration. In this study, the global probability density function(PDF) of MPNN is reflected by summing the heterogeneous local PDFs automatically determined in the individual standard deviation of each variable. The proposed algorithm is applied for the vibration control of a three-story shear building model under Northridge earthquake. When the control results of the MPNN are compared with those of conventional PNN to verify the control performance, the MPNN controller proves to be more effective than PNN methods in decreasing the structural responses.