• 산업경영시스템학회지
• /
• 제39권2호
• /
• pp.54-63
• /
• 2016

As technology has developed and cost for data processing has reduced, big data market has grown bigger. Developed countries such as the United States have constantly invested in big data industry and achieved some remarkable results like improving advertisement effects and getting patents for customer service. Every company aims to achieve long-term survival and profit maximization, but it needs to establish a good strategy, considering current industrial conditions so that it can accomplish its goal in big data industry. However, since domestic big data industry is at its initial stage, local companies lack systematic method to establish competitive strategy. Therefore, this research aims to help local companies diagnose their big data capabilities through a reference model and big data capability assessment system. Big data reference model consists of five maturity levels such as Ad hoc, Repeatable, Defined, Managed and Optimizing and five key dimensions such as Organization, Resources, Infrastructure, People, and Analytics. Big data assessment system is planned based on the reference model's key factors. In the Organization area, there are 4 key diagnosis factors, big data leadership, big data strategy, analytical culture and data governance. In Resource area, there are 3 factors, data management, data integrity and data security/privacy. In Infrastructure area, there are 2 factors, big data platform and data management technology. In People area, there are 3 factors, training, big data skills and business-IT alignment. In Analytics area, there are 2 factors, data analysis and data visualization. These reference model and assessment system would be a useful guideline for local companies.

• 한국컴퓨터정보학회논문지
• /
• 제26권3호
• /
• pp.19-28
• /
• 2021

위내시경 촬영은 조기에 위 병변을 진단하기 위해서 주로 사용한다. 하지만 위내시경을 했음에도 불구하고 위 내부를 자세히 관찰하지 못해서 10~20% 위 병변을 놓치는 경우가 생기는 것으로 보고되고 있다. 미국, 영국, 일본 등의 일부 국가와 세계내시경협회(Wold Endoscopy Organization)에서는 위내시경 시에 맹점 없는 관찰을 위해서 반드시 촬영해야 할 부위에 대한 촬영지침을 제안한 바 있다. 이에 본 논문에서는 수련의가 내시경을 하는 데 있어 위 내부를 자동으로 맹점 없이 관찰하는데 필요한 딥러닝 기술인 해부학적 분류모델을 제안한다. 제안한 모델은 위내시경 이미지에 적합한 전처리 모듈과 데이터 증강 기술들을 사용한다. 실험결과를 통해 최대 F1 점수 99.6% 분류 성능을 확인하였다. 또한, 실제 데이터를 통한 실험결과에서도 에러율이 4% 미만을 보였다. 이러한 성능을 바탕으로 설명 가능한 모델임을 보여 임상에서의 사용 가능성을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3519-3533
• /
• 2020

Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What's more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.

• 한국정밀공학회지
• /
• 제31권4호
• /
• pp.287-295
• /
• 2014

Smart manufacturing (SM) considered as a new trend of modern manufacturing helps to meet objectives associated with the productivity, quality, cost and competiveness. It is characterized by decentralized, distributed, networked compositions of autonomous systems. The model of SM is inherited from the organization of the living systems in biology and nature such as ant colony, school of fish, bee's foraging behaviors, and so on. In which, the resources of the manufacturing system are considered as biological organisms, which are autonomous entities so that the manufacturing system has the advanced characteristics inspired from biology such as self-adaptation, self-diagnosis, and self-healing. To prove this concept, a cloud machining system is considered as research object in which internet of things and cloud computing are used to integrate, organize and allocate the machining resources. Artificial life tools are used for cooperation among autonomous elements in the cloud machining system.

• 한국정밀공학회지
• /
• 제32권1호
• /
• pp.39-47
• /
• 2015

Globalization, unpredictable markets, increased products customization and frequent changes in products, production technologies and machining systems have become a complexity in today's manufacturing environment. One key strategy for coping with the evolution of this situation is to develop or apply an enable technology such as intelligent manufacturing. Intelligent manufacturing system (IMS) is characterized by decentralized, distributed, networked compositions of heterogeneous and autonomous systems. The model of IMS is inherited from the organization of the living systems in biology and nature so that the manufacturing system has the advanced characteristics inspired from biology such as self-adaptation, self-diagnosis, and selfhealing. To prove this concept, an innovative system with applying the advanced information and communication technology such as internet of things, cognitive agent are proposed to integrate, organize and allocate the machining resources. Innovative system is essential for modern machining system to flexibly and quickly adapt to new challenges of manufacturing environment.

• Genomics & Informatics
• /
• 제14권4호
• /
• pp.138-148
• /
• 2016

The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which has been a big hurdle in building risk prediction models. Recently, many statistical approaches based on penalized regression have been developed to solve the "large p and small n" problem. In this report, we evaluated the performance of several statistical methods for predicting a binary trait: stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN). We first built a prediction model by combining variable selection and prediction methods for type 2 diabetes using Affymetrix Genome-Wide Human SNP Array 5.0 from the Korean Association Resource project. We assessed the risk prediction performance using area under the receiver operating characteristic curve (AUC) for the internal and external validation datasets. In the internal validation, SLR-LASSO and SLR-EN tended to yield more accurate predictions than other combinations. During the external validation, the SLR-SLR and SLR-EN combinations achieved the highest AUC of 0.726. We propose these combinations as a potentially powerful risk prediction model for type 2 diabetes.

• 보건행정학회지
• /
• 제24권4호
• /
• pp.380-388
• /
• 2014

Background: The volume of surgery has been examined as a major source of variation in outcome after surgery. This study investigated the direct effect of surgery volume to in hospitals mortality and the moderating effect of structural complexity-the level of diversity and sophistication of technology a hospital applied in patient care-to the volume outcome relationship. Methods: Discharge summary data of 11,827 cancer patients who underwent surgery and were discharged during a month period in 2010 and 2011 were analyzed. The analytic model included the independent variables such as surgery volume of a hospital, structural complexity measured by the number of diagnosis a hospital examined, and their interaction term. This study used a hierarchical logistic regression model to test for an association between hospital complexity and mortality rates and to test for the moderating effect in the volume outcome relationship. Results: As structural complexity increased the probability of in-hospital mortality after cancer surgery reduced. The interaction term between surgery volume and structural complexity was also statistically significant. The interaction effect was the strongest among the patients group who had surgery in low volume hospitals. Conclusion: The structural complexity and volume of surgery should be considered simultaneously in studying volume outcome relationship and in developing policies that aim to reduce mortality after cancer surgery.

• Genomics & Informatics
• /
• 제4권4호
• /
• pp.161-166
• /
• 2006

The establishment of DNA microarray technology has enabled high-throughput analysis and molecular profiling of various types of cancers. By using the gene expression data from microarray analysis we are able to investigate diagnostic applications at the molecular level. The most important step in the application of microarray technology to cancer diagnostics is the selection of specific markers from gene expression profiles. In order to select markers of Immortalization and transformation we used c-myc and $H-ras^{V12}$ oncogene-transfected NIH3T3 cells as our model system. We have identified 8751 differentially expressed genes in the immortalization/transformation model by multivariate permutation F-test (95% confidence, FDR<0.01). Using the support vector machine algorithm, we selected 13 discriminative genes which could be used to predict immortalization and transformation with perfect accuracy. We assayed $H-ras^{V12}$-transfected 'transformed' cells to validate our immortalization/transformation dassification system. The selected molecular markers generated valuable additional information for tumor diagnosis, prognosis and therapy development.

• Nuclear Engineering and Technology
• /
• 제53권2호
• /
• pp.484-497
• /
• 2021

This paper proposes an extended time uncertainty analysis approach in Level 2 human reliability analysis (HRA) considering severe accident management (SAM) strategies. The method is a time-based model that classifies two time distribution functions-time required and time available-to calculate human failure probabilities from delayed action when implementing SAM strategies. The time required function can be obtained by the combination of four time factors: 1) time for diagnosis and decision by the technical support center (TSC) for a given strategy, 2) time for strategy implementation mainly by the local emergency response organization (ERO), 3) time to verify the effectiveness of the strategy and 4) time for portable equipment transport and installation. This function can vary depending on the given scenario and includes a summation of lognormal distributions and a choice regarding shifting the distribution. The time available function can be obtained via thermal-hydraulic code simulation (MAAP 5.03). The proposed approach was applied to assess SAM strategies that use portable equipment and safety depressurization system valves in a total loss of component cooling water event that could cause reactor vessel failure. The results from the proposed method are more realistic (i.e., not conservative) than other existing methods in evaluating SAM strategies involving the use of portable equipment.

• Genomics & Informatics
• /
• 제21권3호
• /
• pp.28.1-28.13
• /
• 2023

Mild cognitive impairment (MCI) is a clinical syndrome characterized by the onset and evolution of cognitive impairments, often considered a transitional stage to Alzheimer's disease (AD). The genetic traits of MCI patients who experience a rapid progression to AD can enhance early diagnosis capabilities and facilitate drug discovery for AD. While a genome-wide association study (GWAS) is a standard tool for identifying single nucleotide polymorphisms (SNPs) related to a disease, it fails to detect SNPs with small effect sizes due to stringent control for multiple testing. Additionally, the method does not consider the group structures of SNPs, such as genes or linkage disequilibrium blocks, which can provide valuable insights into the genetic architecture. To address the limitations, we propose a Bayesian bi-level variable selection method that detects SNPs associated with time of conversion from MCI to AD. Our approach integrates group inclusion indicators into an accelerated failure time model to identify important SNP groups. Additionally, we employ data augmentation techniques to impute censored time values using a predictive posterior. We adapt Dirichlet-Laplace shrinkage priors to incorporate the group structure for SNP-level variable selection. In the simulation study, our method outperformed other competing methods regarding variable selection. The analysis of Alzheimer's Disease Neuroimaging Initiative (ADNI) data revealed several genes directly or indirectly related to AD, whereas a classical GWAS did not identify any significant SNPs.