• Korean Journal of Artificial Intelligence
• /
• v.6 no.2
• /
• pp.11-15
• /
• 2018

Breast cancer is one of the leading causes of cancer related death among women. So prediction of overall survival status is important into decided in adjuvant treatment. Deep belief network is a kind of artificial intelligence (AI). We intended to construct prediction model by deep belief network using associated clinicopathologic factors. 103881 cases were found in the Korean Breast Cancer Registry. After preprocessing of data, a total of 15733 cases were enrolled in this study. The median follow-up period was 82.4 months. In univariate analysis for overall survival (OS), the patients with advanced AJCC stage showed relatively high HR (HR=1.216 95% CI: 0.011-289.331, p=0.001). Based on results of univariate and multivariate analysis, input variables for learning model included 17 variables associated with overall survival rate. output was presented in one of two states: event or cencored. Individual sensitivity of training set and test set for predicting overall survival status were 89.6% and 91.2% respectively. And specificity of that were 49.4% and 48.9% respectively. So the accuracy of our study for predicting overall survival status was 82.78%. Prediction model based on Deep belief network appears to be effective in predicting overall survival status and, in particular, is expected to be applicable to decide on adjuvant treatment after surgical treatment.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.9
• /
• pp.103-108
• /
• 2019

The purpose of this study is to identify the factors that may affect the 5-year survival of colon cancer through network model and to use it as a clinical decision supporting system for colorectal cancer patients. This study was conducted using data from 2,540 patients who underwent colorectal cancer surgery from 1996 to 2018. Eleven factors related to survival of colorectal cancer were selected by consulting medical experts and previous studies. Analysis was proceeded from the data sorted out into 1,839 patients excluding missing values and outliers. Logistic regression analysis showed that age, BMI, and heart disease were statistically significant in order to identify factors affecting 5-year survival of colorectal cancer. Additionally, a correlation analysis was carried out age, BMI, heart disease, diabetes, and other diseases were correlated with 5-year survival of colorectal cancer. Sex was related with BMI, lung disease, and liver disease. Age was associated with heart disease, heart disease, hypertension, diabetes, and other diseases, and BMI with hypertension, diabetes, and other diseases. Heart disease was associated with hypertension, diabetes, hypertension, diabetes, and other diseases. In addition, diabetes and kidney disease were associated. In the correlation analysis, the network model was constructed with the Network Correlation Coefficient less than p <0.001 as the weight. The network model showed that factors directly affecting survival were age, BMI levels, heart disease, and indirectly influencing factors were diabetes, high blood pressure, liver disease and other diseases. If the network model is used as an assistant indicator for the treatment of colorectal cancer, it could contribute to increasing the survival rate of patients.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.6
• /
• pp.1189-1198
• /
• 2015

For the effects of the global financial crisis cause hedge funds to have a strong influence on financial markets, it is needed to study new approach method to predict hedge fund survival. This paper proposes to organize fuzzy neural network using hedge fund data as input to predict hedge fund survival. The variables of hedge fund data are ambiguous to analyze and have internal uncertainty and these characteristics make it challenging to predict their survival from the past records. The object of this study is to evaluate the predictability of fuzzy neural network which uses grades of membership to predict survival. The results of this study show that proposed system is effective to predict the hedge funds survival and can be a desirable solution which helps investors to support decision-making.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.747-752
• /
• 2020

The maintenance of sensor networks, especially sensor networks installed in a wide area for regional monitoring has been an issue for a long time. In this study, a system that supplies energy to the sensor network using a robot is proposed, and the survival conditions of the sensor network are identified using the energy consumption rate of the sensor network, the energy transfer rate, and the moving distance of the robot as variables. Through numerical verification and robot charging simulation, the proposed system survival conditions are shown to be valid, and the feasibility of the maintenance method of the sensor network using the robot is validated through actual charging experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.297-299
• /
• 2022

Malignant glioma has a poor prognosis with the reported median survival of between 6 months to 14 months. Thus, it is crucial to predict the accurate survival of patients with malignant glioma. In this paper, we propose a convolutional neural network to predict the overall survival and age of the patients. A total of four MRI modalities, T1, T1-contrast enhanced, T2, and fluid-attenuated inversion recovery, which effectively capture spatial characteristics of malignant glioma, were used as input images. Age is an important factor impacting the overall survival, thus incorporating it into the model will thereby improve the performance of the proposed model. Our model successfully predicted overall survival and age of the patients with pearson correlation coefficients of 0.1748 and 0.3056, respectively.

• Journal of Biomedical Engineering Research
• /
• v.33 no.1
• /
• pp.1-7
• /
• 2012

Hemorrhagic shock is a common cause of death in emergency rooms. Early diagnosis of hemorrhagic shock makes it possible for physicians to treat patients successfully. Therefore, the purpose of this study was to select an optimal survival prediction model using physiological parameters for the two analyzed periods: two and five minutes before and after the bleeding end. We obtained heart rates, mean arterial pressures, respiration rates and temperatures from 45 rats. These physiological parameters were used for the training and testing data sets of survival prediction models using an artificial neural network (ANN) and support vector machine (SVM). We applied a 5-fold cross validation method to avoid over-fitting and to select the optimal survival prediction model. In conclusion, SVM model showed slightly better accuracy than ANN model for survival prediction during the entire analysis period.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1013-1021
• /
• 2020

Malware Authorship Attribution is a research field for identifying malware by comparing the author characteristics of unknown malware with the characteristics of known malware authors. The authorship attribution method using binaries has the advantage that it is easy to collect and analyze targeted malicious codes, but the scope of using features is limited compared to the method using source code. This limitation has the disadvantage that accuracy decreases for a large number of authors. This study proposes a method of 'Defining semantic features from binaries' and 'Defining allowable ranges for redundant features using the concept of survival network' to complement the limitations in the identification of binary authors. The proposed method defines Opcode-based graph features from binary information, and defines the allowable range for selecting unique features for each author using the concept of a survival network. Through this, it was possible to define the feature definition and feature selection method for each author as a single technology, and through the experiment, it was confirmed that it was possible to derive the same level of accuracy as the source code-based analysis with an improvement of 5.0% accuracy compared to the previous study.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.10
• /
• pp.3772-3778
• /
• 2010

The leaders such as The Robert Foundation of the U.S., Social Firms U.K., EMES European Research Network worldwide are groping for the survival strategies of social enterprises and of their developmental methods with the utilization of social capital. Along with the way the world economy goes on, this study is first of all to empirically analyze how the diversity and strength of network as independent variables work with the studies of the survival of enterprises of Granovetter Mark, Burt Ronald, Coleman James, Peter Witt, Andreas Schroeter, Christin Merz, Helen Haugh, mainly concerned with the increase in employment, the increment in sales, delegation of authorization as dependent variables and secondly it is to present a theoretical possibility of optimizing the development of social enterprises. The object of this study consists of 25 companies recommended by experts out of the current national 295 social enterprises in 2009 through the analysis of sources of SPSS 12.0, appropriateness, reliability, interrelation, etc; besides, hypotheses are proved by multiple regression analysis. A result of the investigation indicates that there is the necessity of network in all the processes of the survival of enterprises, the growth in employment, the increase in sales, delegation of authorization; especially, it suggests that it is necessary to manage, maintain and develop primary factors relating to a variety of networks to improve sales, and relating to the intensity of network for the survival of corporations. At last, I think that this study could be a help to the strategies of utilizing social capital in order for many companies or nonprofit social organizations in Korea to develop into constant enterprises.

• Journal of Microbiology and Biotechnology
• /
• v.32 no.3
• /
• pp.365-377
• /
• 2022

Mammalian target of rapamycin (mTOR) is a serine-threonine kinase member of the cellular phosphatidylinositol 3-kinase (PI3K) pathway, which is involved in multiple biological functions by transcriptional and translational control. mTOR is a downstream mediator in the PI3K/Akt signaling pathway and plays a critical role in cell survival. In cancer, this pathway can be activated by membrane receptors, including the HER (or ErbB) family of growth factor receptors, the insulin-like growth factor receptor, and the estrogen receptor. In the present work, we congregated an electronic network of mTORC1 built on an assembly of data using natural language processing, consisting of 470 edges (activations/interactions and/or inhibitions) and 206 nodes representing genes/proteins, using the Cytoscape 3.6.0 editor and its plugins for analysis. The experimental design included the extraction of gene expression data related to five distinct types of cancers, namely, pancreatic ductal adenocarcinoma, hepatic cirrhosis, cervical cancer, glioblastoma, and anaplastic thyroid cancer from Gene Expression Omnibus (NCBI GEO) followed by pre-processing and normalization of the data using R & Bioconductor. ExprEssence plugin was used for network condensation to identify differentially expressed genes across the gene expression samples. Gene Ontology (GO) analysis was performed to find out the over-represented GO terms in the network. In addition, pathway enrichment and functional module analysis of the protein-protein interaction (PPI) network were also conducted. Our results indicated NOTCH1, NOTCH3, FLCN, SOD1, SOD2, NF1, and TLR4 as upregulated proteins in different cancer types highlighting their role in cancer progression. The MCODE analysis identified gene clusters for each cancer type with MYC, PCNA, PARP1, IDH1, FGF10, PTEN, and CCND1 as hub genes with high connectivity. MYC for cervical cancer, IDH1 for hepatic cirrhosis, MGMT for glioblastoma and CCND1 for anaplastic thyroid cancer were identified as genes with prognostic importance using survival analysis.

• IMMUNE NETWORK
• /
• v.10 no.5
• /
• pp.153-163
• /
• 2010

Background: In addition to TCR and costimulatory signals, cytokine signals are required for the differentiation of activated CD8 T cells into memory T cells and their survival. Previously, we have shown that IL-12 priming during initial antigenic stimulation significantly enhanced the survival of activated CD8 T cells and increased the memory cell population. In the present study, we analyzed the mechanisms by which IL-12 priming contributes to activation and survival of CD8 T cells. Methods: We observed dramatically decreased expression of CD43 in activated CD8 T cells by IL-12 priming. We purified $CD43^{lo}$ and $CD43^{hi}$ cells after IL-12 priming and analyzed the function and survival of each population both in vivo and in vitro. Results: Compared to $CD43^{hi}$ effector cells, $CD43^{lo}$ effector CD8 T cells exhibited reduced cytolytic activity and lower granzyme B expression but showed increased survival. $CD43^{lo}$ effector CD8 T cells also showed increased in vivo expansion after adoptive transfer and antigen challenge. The enhanced survival of $CD43^{lo}$ CD8 T cells was also partly associated with CD62L expression. Conclusion: We suggest that CD43 expression regulated by IL-12 priming plays an important role in differentiation and survival of CD8 T cells.