• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.202-205
• /
• 2005

Cell phenotypes are determined by the concerted activity of thousands of genes and their products. This activity is coordinated by a complex network that regulates the expression of genes. Understanding this organization is crucial to elucidate cellular activities, and many researches have tried to construct gene regulatory networks from mRNA expression data which are nowadays the most available and have a lot of information for cellular processes. Several computational tools, such as Boolean network, Qualitative network, Bayesian network, and so on, have been applied to infer these networks. Among them, Bayesian networks that we chose as the inference tool have been often used in this field recently due to their well-established theoretical foundation and statistical robustness. However, the relative insufficiency of experiments with respect to the number of genes leads to many false positive inferences. To alleviate this problem, we had developed the algorithm of MONET(MOdularized NETwork learning), which is a new method for inferring modularized gene networks by utilizing two complementary sources of information: biological annotations and gene expression. Afterward, we have packaged and improved MONET by combining dispersed functional blocks, extending species which can be inputted in this system, reducing the time complexities by improving algorithms, and simplifying input/output formats and parameters so that it can be utilized in actual fields. In this paper, we present the architecture of MONET system that we have improved.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.6
• /
• pp.44-55
• /
• 2009

Diagnosis of diseases using gene expression data obtained from microarray chip is an active research area recently. It has been done by general machine learning algorithms, because it is difficult to analyze directly. However, recent research results about the analysis based on the interaction between genes is essential for the gene expression analysis, which means the analysis using the traditional machine learning algorithms has limitations. In this paper, we classify the gene expression data using the hyper-network model that considers the higher-order correlations between the features, and then compares the classification accuracies. And also, we present the new hypo-network model that improve the disadvantage of existing model, and compare the processing performances of the existing hypo-network model based on general sequential processor and the improved hypo-network model implemented on parallel processors. In the experimental results, we show that the performance of our model shows improved and competitive classification performance than traditional machine learning methods, as well as, the existing hypo-network model. We show that the performance is maximized when the hypernetwork model is implemented on our parallel processors.

• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.162-172
• /
• 2017

In this paper, we propose facial expression recognition using CNN (Convolutional Neural Network), one of the deep learning technologies. To overcome the disadvantages of existing facial expression databases, various databases are used. In the proposed technique, we construct six facial expression data sets such as 'expressionless', 'happiness', 'sadness', 'angry', 'surprise', and 'disgust'. Pre-processing and data augmentation techniques are also applied to improve efficient learning and classification performance. In the existing CNN structure, the optimal CNN structure that best expresses the features of six facial expressions is found by adjusting the number of feature maps of the convolutional layer and the number of fully-connected layer nodes. Experimental results show that the proposed scheme achieves the highest classification performance of 96.88% while it takes the least time to pass through the CNN structure compared to other models.

• The Korean Journal of Physiology and Pharmacology
• /
• v.17 no.4
• /
• pp.315-320
• /
• 2013

Here, we show that radicicol, a fungal antibiotic, resulted in marked inhibition of inducible nitric oxide synthase (iNOS) transcription by the pancreatic beta cell line MIN6N8a in response to cytokine mixture (CM: TNF-${\alpha}$, IFN-${\gamma}$, and IL-$1{\beta}$). Treatment of MIN6N8a cells with radicicol inhibited CM-stimulated activation of NF-${\kappa}B$/Rel, which plays a critical role in iNOS transcription, in a dose-related manner. Nitrite production in the presence of PD98059, a specific inhibitor of the extracellular signal-regulated protein kinase-1 and 2 (ERK1/2) pathway, was dramatically diminished, suggesting that the ERK1/2 pathway is involved in CM-induced iNOS expression. In contrast, SB203580, a specific inhibitor of p38, had no effect on nitrite generation. Collectively, this series of experiments indicates that radicicol inhibits iNOS gene expression by blocking ERK1/2 signaling. Due to the critical role that NO release plays in mediating destruction of pancreatic beta cells, the inhibitory effects of radicicol on iNOS expression suggest that radicicol may represent a useful anti-diabetic activity.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.273-276
• /
• 2004

Genome-scale expression data provides us with valuable insights about organisms, but the biological validation of in-silico analysis is difficult and often controversial. Here we present a new approach for integrating previously established knowledge with computational analysis. Based on the known biological evidences, IGAM (Integrated Gene Association Matrix) automatically estimates the relatedness between a pair of genes. We combined this association knowledge to the regulatory network modeling and fuzzy clustering in yeast 5. Cerevisiae. The result was found to be more effective for extracting biological meanings from in-silico inferences for gene expression data.

• The Journal of Information Systems
• /
• v.32 no.2
• /
• pp.87-108
• /
• 2023

Purpose The main purpose of this study is to improve fake news detection performance by using video information to overcome the limitations of extant text- and image-oriented studies that do not reflect the latest news consumption trend. Design/methodology/approach This study collected video clips and related information including news scripts, speakers' facial expression, and video metadata from YouTube to develop fake news detection model. Based on the collected data, seven combinations of related information (i.e. scripts, video metadata, facial expression, scripts and video metadata, scripts and facial expression, and scripts, video metadata, and facial expression) were used as an input for taining and evaluation. The input data was analyzed using six models such as support vector machine and deep neural network. The area under the curve(AUC) was used to evaluate the performance of classification model. Findings The results showed that the ACU and accuracy values of three features combination (scripts, video metadata, and facial expression) were the highest in logistic regression, naïve bayes, and deep neural network models. This result implied that the fake news detection could be improved by using video information(video metadata and facial expression). Sample size of this study was relatively small. The generalizablity of the results would be enhanced with a larger sample size.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.12
• /
• pp.3003-3017
• /
• 2013

In this paper, we investigate the outage performance of a cognitive relay network. We consider mutual interference in an independent, non-identically distributed Nakagmai-m fading environment. We first derive the close-form outage probability expression, which provides an efficient means to evaluate the effects of several parameters. This allows us to study the impact of several parameters on the network's performance. We then derive the asymptotic expression and reveal that the diversity order is strictly determined by the fading severity of the cognitive system. It is not affected by the primary network. Moreover, the primary network only affects the coding gain of the cognitive system. Finally, Monte Carlo simulations are provided, which corroborate the analytical results.

• Asian-Australasian Journal of Animal Sciences
• /
• v.26 no.1
• /
• pp.19-29
• /
• 2013

Marbling (intramuscular fat) is an important trait that affects meat quality and is a casual factor determining the price of beef in the Korean beef market. It is a complex trait and has many biological pathways related to muscle and fat. There is a need to identify functional modules or genes related to marbling traits and investigate their relationships through a weighted gene co-expression network analysis based on the system level. Therefore, we investigated the co-expression relationships of genes related to the 'marbling score' trait and systemically analyzed the network topology in Hanwoo (Korean cattle). As a result, we determined 3 modules (gene groups) that showed statistically significant results for marbling score. In particular, one module (denoted as red) has a statistically significant result for marbling score (p = 0.008) and intramuscular fat (p = 0.02) and water capacity (p = 0.006). From functional enrichment and relationship analysis of the red module, the pathway hub genes (IL6, CHRNE, RB1, INHBA and NPPA) have a direct interaction relationship and share the biological functions related to fat or muscle, such as adipogenesis or muscle growth. This is the first gene network study with m.logissimus in Hanwoo to observe co-expression patterns in divergent marbling phenotypes. It may provide insights into the functional mechanisms of the marbling trait.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.623-626
• /
• 2006

Group of genes controls the functioning of a cell by complex interactions. These interacting gene groups are called Gene Regulatory Networks (GRNs). Two previous data mining approaches, clustering and classification have been used to analyze gene expression data. While these mining tools are useful for determining membership of genes by homology, they don't identify the regulatory relationships among genes found in the same class of molecular actions. Furthermore, we need to understand the mechanism of how genes relate and how they regulate one another. In order to detect regulatory relationships among genes from time-series Microarray data, we propose a novel approach using frequent pattern mining and chain rule. In this approach, we propose a method for transforming gene expression data to make suitable for frequent pattern mining, and detect gene expression patterns applying FP-growth algorithm. And then, we construct gene regulatory network from frequent gene patterns using chain rule. Finally, we validated our proposed method by showing that our experimental results are consistent with published results.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.7
• /
• pp.3313-3317
• /
• 2012

Prostate cancer is a highly prevalent disease in older men of the western world. MicroRNAs (miRNAs) are small RNA molecules that regulate gene expression via posttranscriptional inhibition of protein synthesis. To identify the diagnostic potential of miRNAs in prostate cancer, we downloaded the miRNA expression profile of prostate cancer from the GEO database and analysed the differentially expressed miRNAs (DE-miRNAs) in prostate cancerous tissue compared to non-cancerous tissue. Then, the targets of these DE-miRNAs were extracted from the database and mapped to the STRING and KEGG databases for network construction and pathway enrichment analysis. We identified a total of 16 miRNAs that showed a significant differential expression in cancer samples. A total of 9 target genes corresponding to 3 DE-miRNAs were obtained. After network and pathway enrichment analysis, we finally demonstrated that miR-20 appears to play an important role in the regulation of prostate cancer onset. MiR-20 as single biomarker or in combination could be useful in the diagnosis of prostate cancer. We anticipate our study could provide the groundwork for further experiments.