• Journal of the Korean Chemical Society
• /
• v.58 no.6
• /
• pp.543-552
• /
• 2014

A quantitative structure activity relationship (QSAR) study is performed for modeling and prediction of oral bioavailabilities of 216 diverse set of drugs. After calculation and screening of molecular descriptors, linear and nonlinear models were developed by using multiple linear regression (MLR), artificial neural network (ANN), support vector machine (SVM) and random forest (RF) techniques. Comparison between statistical parameters of these models indicates the suitability of SVM over other models. The root mean square errors of SVM model were 5.933 and 4.934 for training and test sets, respectively. Robustness and reliability of the developed SVM model was evaluated by performing of leave many out cross validation test, which produces the statistic of $Q^2_{SVM}=0.603$ and SPRESS = 7.902. Moreover, the chemical applicability domains of model were determined via leverage approach. The results of this study revealed the applicability of QSAR approach by using SVM in prediction of oral bioavailability of drugs.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.959-963
• /
• 2007

After the year of 2000, the need of safety increases in field of railroad. The project for developing Integrated Centralized Traffic Control(CTC) center started at 2002 to control the full domestic railroad network. A traffic control software was required the safety activity and assessment, according to 'KORAIL Instruction number 2001-49'. There were many trials and errors to perform safety activity because the technology and recognition of safety activity is in primary stage. However the safety activities are gradually stabilized. This paper describes the safety life-cycle and development life-cycle of Integrated CTC S/W and a suitable life-cycle of safety to develop S/W of Integrated CTC.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.518-518
• /
• 2000

We have researched quantitative structure activity relationships between molecular structure of medicines and physiological activity. Since they are non-linear, neural networks are useful tool to research them. There are many ranks for the non-linearity; therefore, the neuron function must be selected carefully. As the results of some trial calculations, Ire find the sigmoid-linear functions pair. We call the neural network constructed of the pair as ANN. The inter- or extrapolation abilities of the ANN are excellent; therefere, ANN is a superior predictor for the relationships. We evaluated the anticarcinogenic medicines, Carboquinone derivatives, by the developed ANN and leave-one-out method.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.5
• /
• pp.75-82
• /
• 1998

Conventional vector quantization (VQ) codebook design methods have several drawbacks such as edge degradation and high computational complexity. In this paper, we first made activity coordinates from the horizonatal and the vertical activity of the input block. Then it is mapped on the 2-dimensional interconnected codebook, and the codebook is designed using kohonen self-organizing map (KSFM) learning algorithm after the search of a codevector that has the minumum distance from the input vector in a small window, centered by the mapped point. As the serch area is restricted within the window, the computational amount is reduced compared with usual VQ. From the resutls of computer simulation, proposed method shows a better perfomance, in the view point of edge reconstruction and PSNR, than previous codebook training methods. And we also obtained a higher PSNR than that of classified vector quantization (CVQ).

• International conference on construction engineering and project management
• /
• 2011.02a
• /
• pp.468-473
• /
• 2011

The goal of a project manager is generally to minimize the cost of the project and also to cope with uncertainty. This paper deals with the problem of project scheduling a set of activities satisfying precedence constraints in order to minimize the sum of the costs associated with the starting times of the activities in the network with imprecise activity durations, represented by means of interval or fuzzy numbers. So far this problem has been completely solved by several authors when the activities durations have crisp values. However, they do not consider the imprecision in activity durations in their models. Here the framework of possibility theory is proposed to solve this problem. In fuzzy arithmetic, usually, the interval calculations are used for the aim of complexity reduction and simplification. Thus the case of interval-valued durations is first addressed, and then extended to fuzzy intervals. A numerical example is used to illustrate the developed concept.

• Journal of Korean Academy of Nursing
• /
• v.45 no.4
• /
• pp.483-494
• /
• 2015

Purpose: This study identified effects of dietary and physical activity interventions including dietary interventions or physical activity interventions alone or combined dietary-physical activity interventions to improve symptoms in metabolic syndrome including abdominal obesity, high triglycerides, low high density lipoprotein cholesterol, elevated blood pressure, and elevated fasting glucose through meta-analysis. Methods: Articles on metabolic syndrome X published from 1988 to 2013 were searched through electronic databases, Google Scholar, and reference reviews. Methodological quality was assessed by the checklist, SIGN (Scottish Intercollegiate Guidelines Network). Results: In the meta-analysis, there were 9 articles reporting 13 interventions with 736 participants. Using random effect models, the dietary and/or physical activity interventions showed a lower mean difference in waist circumference ( - 1.30 cm, 95% CI: - 2.44~ - 0.15, p=.027). The combined dietary-physical activity interventions showed a lower mean difference in waist circumference ( - 2.77 cm, 95% CI: - 4.77~ - 0.76, p=.007) and systolic blood pressure ( - 5.44 mmHg, 95% CI: - 10.76~ - 0.12, p=.044). Additionally, interventions of over 24 weeks yielded a lower mean difference in waist circumference ( - 2.78 cm, 95% CI: - 4.69~ - 0.87, p=.004) and diastolic blood pressure ( - 1.93 mmHg, 95% CI: - 3.63~ - 0.22, p=.026). Conclusion: The findings indicate that dietary and/or physical activity interventions for metabolic syndrome reduce central obesity with no adverse effects. This finding provides objective evidences for dietary and physical activity management on metabolic syndrome as an efficient intervention.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.3
• /
• pp.1168-1188
• /
• 2018

Social Network Aggregators are used to maintain and manage manifold accounts over multiple online social networks. Displaying the Activity feed for each social network on a common dashboard has been the status quo of social aggregators for long, however retrieving the desired data from various social networks is a major concern. A user inputs the query desiring the specific outcome from the social networks. Since the intention of the query is solely known by user, therefore the output of the query may not be as per user's expectation unless the system considers 'user-centric' factors. Moreover, the quality of solution depends on these user-centric factors, the user inclination and the nature of the network as well. Thus, there is a need for a system that understands the user's intent serving structured objects. Further, choosing the best execution and optimal ranking functions is also a high priority concern. The current work finds motivation from the above requirements and thus proposes the design of a query processing system to retrieve information from social network that extracts user's intent from various social networks. For further improvements in the research the machine learning techniques are incorporated such as Latent Dirichlet Algorithm (LDA) and Ranking Algorithm to improve the query results and fetch the information using data mining techniques.The proposed framework uniquely contributes a user-centric query retrieval model based on natural language and it is worth mentioning that the proposed framework is efficient when compared on temporal metrics. The proposed Query Processing System to Retrieve Information from Social Network (QPSSN) will increase the discoverability of the user, helps the businesses to collaboratively execute promotions, determine new networks and people. It is an innovative approach to investigate the new aspects of social network. The proposed model offers a significant breakthrough scoring up to precision and recall respectively.

• Journal of the Korean Regional Science Association
• /
• v.31 no.2
• /
• pp.3-28
• /
• 2015

While industrial ecology theories and policy approaches have been considerably influential in regional economy, the dynamism and limitations of regional venture ecosystem are less clearly examined. In particular, the activities of strategic network brokerage require further research in relation to its internal and external interactions and collaborative mechanisms. Based on the analysis results of conditions of Daegu Gyeongbuk regional venture firms, this article examines the necessities of strategic network brokerage in regional venture ecosystem in the dimensions of network conditions as the intrinsic limitations, of innovation direction method outcome as the extrinsic trends, and of the related regional demands. In particular, this article tries to explore the roles and activity scopes of strategic network brokerage to contribute for making up for the weakness of diverse network infrastructures of regional venture ecosystem, for dealing with the mismatch for the extrinsic change trends of industrial technologies, and for fulfilling the strengthening trends of intrinsic capacities.

• Journal of Digital Convergence
• /
• v.14 no.4
• /
• pp.129-138
• /
• 2016

This study was conducted with the network-related viewpoint to see the aspect of interaction among innovation factors of this country's national innovation system in information and communication sector. For this, the relations in which institutions have conducted a joint study of national R&D projects supported by the government were analyzed by the method of Social Network Analysis. As a result of the analysis, the network of national innovation system in information and communication sector of this country turned out to be "small world network." Based on the result, it was found out that innovation subjects in the sector of this country closely exchange knowledge and information. In addition, among innovation subjects in the network, the proportion of research institutions was relatively high and the proportion of enterprises was relatively low, which confirmed that the activity for technical innovation has been made under the lead of the government. Further study is required to find out what effect the network structure of national innovation system has on the success of innovation.

• Convergence Security Journal
• /
• v.13 no.2
• /
• pp.85-93
• /
• 2013

Today, the structure of terrorist organizations in the form of a variety of network complexity are evolving. However, terrorist organization not combining randomly generated network but preferential attachment a network. So, it's research should be preceded a better understanding about the characteristics and type of terror network for a effective counter-terrorism policy of law enforcement. In addition, the appropriate response strategy have to technique establish in an era of smart media. In particular, homegrown terrorist attacks on unspecified people without boundaries of countries and regions unlike the traditional terrorism. Also, homegrown terrorism are violence and criminal activity by new various of religion, politics, philosophy. Besides the extreme members of homegrown terror networks went grow up through the evolutionary process in the age of smart media. Law enforcement agencies must identify the terrorist network at the national level. Therefore, terror networks evolving in the online space, forming a radical homegrown terror organizations have access to the network. Intelligence community track terrorist networks and to block the negative aspects of the smart media outlets should be considered.