• Journal of Computing Science and Engineering
• /
• v.1 no.2
• /
• pp.162-176
• /
• 2007

Machine Learning (ML) has become very popular within Data Mining (KDD) and Artificial Intelligence (AI) research and their applications. In the ML and KDD contexts, two main approaches can be used for inducing a Bayesian Network (BN) from data, namely, Conditional Independence (CI) and the Heuristic Search (HS). When a BN is induced for classification purposes (Bayesian Classifier - BC), it is possible to impose some specific constraints aiming at increasing the computational efficiency. In this paper a new CI based approach to induce BCs from data is proposed and two algorithms are presented. Such approach is based on the Markov Blanket concept in order to impose some constraints and optimize the traditional PC learning algorithm. Experiments performed with the ALARM, as well as other six UCI and three artificial domains revealed that the proposed approach tends to execute fewer comparison tests than the traditional PC. The experiments also show that the proposed algorithms produce competitive classification rates when compared with both, PC and Naive Bayes.

• Korean Journal of Computational Design and Engineering
• /
• v.10 no.4
• /
• pp.293-302
• /
• 2005

The research focused quantitative comparisons of protocols occurring in the architectural massing process using two different tools, three-dimensional(3D) modeler and traditional design tools, to aid architectural massing education. Through the protocol analysis from some experiments, the research identified the following conclusions: 1) Usage of traditional tools produced much higher protocol rate in proposing solution, evaluating proposed solution, explicitness of strategies. This result seemed to be from convenience of traditional tools causing faster visual cognitive cycle. 2) Usage of 3D modeler produced much higher protocol rate concerning attempts of making design vocabulary. The result indicated 3D modeler has relatively effective functions for mass generation and orientation, however it still has some weaknesses on display interface which cause designer's lower idea generations compared to traditional design tools.

• Journal of the Korean Society of Safety
• /
• v.27 no.3
• /
• pp.42-48
• /
• 2012

This paper is aimed to analysis of electrical fire risk by overcurrent and series arc signals in traditional market shops Firstly, the field state investigation was conducted for shops at the traditional market (30 shops). At each shop in the traditional market, load characteristics were investigated and thermal characteristics in Panel were analyzed. Thermal characteristics in Panel is an indicator that can determine the impact of overcurrent. Results of the field state investigation found out four shops which showed abnormal thermal characteristics in Panel. Electrical load characteristics of these 4 shops were simulated by experimental setup consists of generator, motor and heater. In order to verify the electrical fire risk by electrical loads of 4 shops, arc and overcurrent experiments were conducted. The waveshapes of arc and overcurrent are investigated in both the time and frequency domains to find signal characteristics. The results obtained in this paper will be very helpful for the prevention of electrical fires occurred at the shops in the traditional market.

• Journal of Ginseng Research
• /
• v.45 no.2
• /
• pp.211-217
• /
• 2021

The treatments of nervous system diseases (NSDs) have long been difficult issues for researchers because of their complexity of pathogenesis. With the advent of aging society, searching for effective treatments of NSDs has become a hot topic. Ginseng polysaccharides (GP), as the main biologically active substance in ginseng, has various biological properties in immune-regulation, anti-oxidant, anti-inflammation and etc. Considering the association between the effects of GP and the pathogenesis of neurological disorders, many related experiments have been conducted in recent years. In this paper, we reviewed previous studies about the effects and mechanisms of GP on diseases related to nervous system. We found GP play an ameliorative role on NSDs through the regulation of immune system, inflammatory response, oxidative damage and signaling pathway. Structure-activity relationship was also discussed and summarized. In addition, we provided new insights into GP as promising neuroprotective agent for its further development and utilization.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.4
• /
• pp.117-126
• /
• 2023

Traditional markets, formed naturally, often feature aged buildings and facilities that are susceptible to fire. However, the lack of adequate fire detection systems in these markets can easily lead to large-scale fires upon ignition. Therefore, this study was conducted with the aim of detecting fires in traditional markets, utilizing thermal imaging cameras for data collection and the YOLOv8 model for object detection experiments. Data were collected in the night markets within traditional markets of xx city and by simulating fire scenarios. A comparative analysis of the Nano and XL models of YOLOv8 revealed that the XL model is more effective in detecting fires. The XL model not only demonstrated higher accuracy in correctly identifying flames but also tended to miss fewer fires compared to the Nano model. In the case of objects other than flames, the XL model showed superior performance over the Nano model. Taking all these factors into account, it is anticipated that with further data collection and improvement in model performance, a suitable fire detection system for traditional markets can be developed.

• Journal of Applied Reliability
• /
• v.4 no.1
• /
• pp.39-64
• /
• 2004

Taguchi's multi-characteristic experiments seek proper choice of levels of contollable factors which satisfy that all reponses of characteristics in a desirable range simultaneously. This aim can be achieved by response surface techniques that allow more flexible in modeling than traditional Taguchi's parameter design. In this article, a multi-response surface modeling and analysis techniques is proposed to deal with the multi-characteristic optimization problem in experimentation with Taguchi's controllable and noise factors.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.409-412
• /
• 2002

There is a growing interest in speaker verification, which verifies someone by his/her voices. This paper explains the traditional text-dependent speaker verification algorithms, DTW and HMM. This paper also introduces SVM and how this can be applied to speaker verification system. Experiments were conducted with Korean database using these algorithms. The results of experiments indicated SVM is superior to other algorithms. The EER of SVM is only 0.5% while that of HMM is 5.4%.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.1
• /
• pp.129-136
• /
• 2017

This paper aims to establish a guideline for ridership capacity of different rail vehicles for military passengers. Previous guideline is limited only to a Mungungwha(hauled by diesel locomotive) vehicle, but this paper expands the limitation to ITX- Saemaeul and urban rail vehicles classified to Electric Motivated Unit(EMU). The guideline considers both with and without personal armor conditions, and based on repetitive ridership experiments. The experiments are designed under considerations of the required number of soldiers for the sample spaces of the different rail vehicles. Moreover, the design tries to establish a concept of optimal capacity additionally to a traditional limiting ridership capacity. In order to do this, ridership comfort is questioned to participant soldiers repetitively over the experiments and all answers of them are surveyed as a results of it. The results of the experiments presented by this paper can be referenced to establish a new guideline on ridership capacity for Korean army.

• The Korean Journal of Applied Statistics
• /
• v.10 no.1
• /
• pp.15-27
• /
• 1997

Randomized block design (RBD) with three replication is very frequently adopted in agricultural experiments of the Rural Development Administration of Korea. Even though it works well in field trials of traditional crops, it may not accomodate trial site conditions and/or experimental environment. In this research report, we deal with two such cases. The first case is for a crop experiment in green houses. In house conditions, RBD may not be appropriate since it cannot reflect two directions of the yield gradient. So, a Latin square design is suggested as an alternative. The second case is for local field experiments of the newly-inbred rice. RBD with three replications is used without doubt for decades, even though the site layout is not appropriately shaped for the design. In this case, we suggest the RBD in two blocks with multiple replicates for control varieties as an alternative. To improve the quality of statistical experimental designs in over one-thousand agricultural trials performed annually in the Rural Development Administration, we need to re-train agricultural researchers on the design and analysis of experiments and call for concerns of Korean statisticians.

• The Korean Journal of Physiology and Pharmacology
• /
• v.27 no.4
• /
• pp.365-374
• /
• 2023

Crohn's disease (CD) is a chronic inflammatory illness of the digestive system with unknown etiology, and its incidence is increasing worldwide. However, there are currently no effective treatments or medications available for individuals with CD. Therefore, novel therapeutic strategies are urgently needed. The bioactive compounds and targets associated with compounds of Qinghua Xiaoyong Formula (QHXYF) were examined using The Traditional Chinese Medicine Systems Pharmacology database, and 5 disease target databases were also used to identify CD-related disease targets. A total of 166 overlapping targets were identified from QHXYF-related and CD-related disease targets and they were found to be enriched in oxidative stress-related pathways and the PI3K/AKT signaling pathway. Molecular docking was then used to predict how the bioactive compounds would bind to the hub targets. It was found that quercetin could be the core bioactive compound and had good binding affinity to the top 5 hub targets. Finally, animal experiments were performed to further validate the findings, and the results revealed that QHXYF or quercetin inhibited 2,4,6-trinitrobenzenesulfonic acid-induced inflammation and oxidative stress processes by inhibiting the PI3K/AKT pathway, thereby improving CD symptoms. These findings suggest that QHXYF and quercetin may be potential novel treatments for CD.