• Smart Media Journal
• /
• v.12 no.3
• /
• pp.30-37
• /
• 2023

Alzheimer's disease (AD) symptoms are being treated by early diagnosis, where we can only slow the symptoms and research is still undergoing. In consideration, using T1-weighted images several classification models are proposed in Machine learning to identify AD. In this paper, we consider the improvised feature selection, to reduce the complexity by using wrapping techniques and Restricted Boltzmann Machine (RBM). This present work used the subcortical and cortical features of 278 subjects from the ADNI dataset to identify AD and sMRI. Multi-class classification is used for the experiment i.e., AD, EMCI, LMCI, HC. The proposed feature selection consists of Forward feature selection, Backward feature selection, and Combined PCA & RBM. Forward and backward feature selection methods use an iterative method starting being no features in the forward feature selection and backward feature selection with all features included in the technique. PCA is used to reduce the dimensions and RBM is used to select the best feature without interpreting the features. We have compared the three models with PCA to analysis. The following experiment shows that combined PCA &RBM, and backward feature selection give the best accuracy with respective classification model RF i.e., 88.65, 88.56% respectively.

• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.75-85
• /
• 2021

In this paper, we present a deep neural network-based prediction model that processes and analyzes the corporate credit and personal credit information of individual business owners as a new method to predict the default rate of individual business more accurately. In modeling research in various fields, feature selection techniques have been actively studied as a method for improving performance, especially in predictive models including many features. In this paper, after statistical verification of macroeconomic indicators (macro variables) and credit information (micro variables), which are input variables used in the default rate prediction model, additionally, through the credit information feature selection method, the final feature set that improves prediction performance was identified. The proposed credit information feature selection method as an iterative & hybrid method that combines the filter-based and wrapper-based method builds submodels, constructs subsets by extracting important variables of the maximum performance submodels, and determines the final feature set through prediction performance analysis of the subset and the subset combined set.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.3
• /
• pp.457-462
• /
• 2020

Osteoporosis is a disease that occurs mainly in the elderly and increases the risk of fractures due to structural deterioration of bone mass and tissues. The purpose of this study are to assess the relationship between nutritional components and osteoporosis and to evaluate models for predicting osteoporosis based on nutrient components. In experimental method, association was performed using binary logistic regression, and predictive models were generated using the naive Bayes algorithm and variable subset selection methods. The analysis results for single variables indicated that food intake and vitamin B2 showed the highest value of the area under the receiver operating characteristic curve (AUC) for predicting osteoporosis in men. In women, monounsaturated fatty acids showed the highest AUC value. In prediction model of female osteoporosis, the models generated by the correlation based feature subset and wrapper based variable subset methods showed an AUC value of 0.662. In men, the model by the full variable obtained an AUC of 0.626, and in other male models, the predictive performance was very low in sensitivity and 1-specificity. The results of these studies are expected to be used as the basic information for the treatment and prevention of osteoporosis.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.94-97
• /
• 2003

Various bioinformatics tools for biological data processing have been developed and most of them are available in public. Most bioinformatics works are carried out by a composite application of those tools. Several integration approaches have been proposed for easy use of the tools. This paper proposes a new multiagent system architecture to integrate bioinformatics tools in the perspective of workflow since the composite applications of tools can be regarded as workflows. For the easy integration, the proposed architecture employs wrapper agents for existing tools, uses XML-based messages in the inter-agent communication, and agents are supposed to extract necessary information from the received messages. This allows new tools to be easily added on the integration framework. The proposed method allows various control structures in workflow definition and provides the progress monitoring capability of the on-going workflows. We implemented a prototype system of the proposed architecture for annotating the genes of a bacterium called Sphingomonas Chungbukensis DJ77.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.2
• /
• pp.133-137
• /
• 2003

Various bioinformatics tools for biological data processing have been developed and most of them are available in public. Most bioinformatics works are carried out by a composite application of those tools. Several integration approaches have been proposed for easy use of the tools. This paper proposes a new multi agent system to integrate bioinformatics tools in the perspective of workflow since the composite applications of tools can be regarded as workflows. For the easy integration, the proposed system employs wrapper agents for existing tools, uses XML-based messages in the inter-agent communication, and agents are supposed to extract necessary information from the received messages. This allows new tools to be easily added on the integration framework. The proposed method allows various control structures in workflow definition and provides the progress monitoring capability of the on-going workflows. In particular, agents in this system have the rule-based architecture which allows the defined rule set to be a special role agent. This feature provides fast and flexible agent development to aid in managing the complexity of bioinformatics application. This system has been partially implemented and has been proven to be a viable implementation for workflow-based bioinformatics tool integration.

• IE interfaces
• /
• v.22 no.2
• /
• pp.126-134
• /
• 2009

As product quality and yield are essential factors in semiconductor manufacturing, monitoring the main manufacturing steps is a critical task. For the purpose, FDC(Fault detection and classification) is used for diagnosing fault states in the processes by monitoring data stream collected by equipment sensors. This paper proposes an FDC model based on decision tree which provides if-then classification rules for causal analysis of the processing results. Unlike previous decision tree approaches, we reflect the structural aspect of the data stream to FDC. For this, we segment the data stream into multiple subregions, define structural features for each subregion, and select the features which have high relevance to results of the process and low redundancy to other features. As the result, we can construct simple, but highly accurate FDC model. Experiments using the data stream collected from etching process show that the proposed method is able to classify normal/abnormal states with high accuracy.

• Journal of Mushroom
• /
• v.19 no.3
• /
• pp.210-215
• /
• 2021

For sterilization of microorganisms of the Listeria genus contaminating enoki mushroom, pilot mushroom grower equipped with air sterilization devices were developed. Sterilization experiments were performed using physical and chemical treatments. Internal temperature and humidity were controlled, maintaining 6.62℃±0.30 in the upper shelves, 6.46℃±0.24 in the middle shelves, and 6.48℃±0.25 in the lower shelves. Humidities were 79.97%±4.42, 79.43%±4.06, and 79.94±4.30%, respectively, with a temperature setting of 6.5℃, and a relative humidity of 75%. A suitable enoki mushroom cultivation stage for air sterilizer application was during the growth stage, with temperature in the 6.5~8.5℃ range, and humidity of 70~80%. At these same internal conditions, the ozone concentration in the mushroom cultivator was found to be 160 ppb during ion-cluster generator operation. After physical sterilization, the Listeria innocua survival rate was 0.1 to 0.9% using ion cluster sterilization, and 9.3 to 10.6% using UV air sterilization. The Listeria innocua survival rates on different materials were 9.3~10.6% on the metal specimen, and 9.9~16.2% on the plastic wrapper. The survival rate was particularly high on the rough side of the plastic wrapper. Ion cluster air sterilization is a labor-saving and effective method for suppressing the occurrence of Listeria bacteria on mushroom growers walls and shelves. For the plastic wrapper, chemical sterilization is more effective than physical sterilization.

• Proceedings of the KSME Conference
• /
• 2001.06c
• /
• pp.369-375
• /
• 2001

For Optimization technology Was Developed in 1960, the Optimization Technology have grown into a full-featured, robust, highly rated and highly used. And Optimization techniques, having reached a degree of maturity over the past several years, are being used in a wide spectrum of industries, including aerospace, automotive, chemical, electrical, and manufacturing industries. With rapidly advancing computer technology, computers are becoming more powerful, and correspondingly, the size and the complexity of the problems being solved using Optimization techniques are also increasing. But Optimization techniques with analysis solver have many problems. For instance, the difficulties that a particular interface must be coded for each design problem and that the designer should be familiar with the optimization program as well as the analysis program. The purpose of this paper is Optimal Design Framework for Mechanical systems design. This Design Framework has two Optimizers, ADS (local optimizer) and RSM(Response Surface Method), and graphic user interfaces for formulation and optimum design problem and controlling the design process. Current Design Framework tested by two analysis solver, ADAMS and ANSYS. First this paper focused on the core Framework and their conception. In the second of the paper, I cover subjects such as Design Framework Operation. Next, The validity and effectiveness of Design Framework are shown by applying it to many practical design problems and obtaining satisfactory results. Finally, if you are an advanced Operator, you might want to use Response Surface Method, so that cover the result applied by RSM. here.

• The KIPS Transactions:PartD
• /
• v.8D no.6
• /
• pp.771-780
• /
• 2001

EJB(Enterprise JavaBeans) is the server-side component model and its purpose is to reduce the complexity of software development and to increase software reusability. Many concerns for development of EJB components have recently been raised. However, it is difficult to compose EJB components provided by third parties through the plug-and-play method. Therefore, the composition method by lego block styles is needed for EJB components. In this paper, we propose an approach to composition of EJB components using the C2 architectural style. In order to support EJB composition, we modified the general C2 architecture framework. We propose how to create EJB wrappers that can compose EJB components according to the C2 framework. Our approach also enables developers to create a new composite EJB that uses a C2 architecture which is composed of EJB components. To do this, we propose how to create a new composite EJB.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.36 no.11
• /
• pp.1197-1207
• /
• 2012

This study provides information for the design of pediatric inpatient uniforms with functionality and aesthetic beauty through a questionnaire-survey of the conditions of providing, wearing, preferences and improvement requirements for pediatric inpatient uniforms. As a result of the survey, intravenous injections were mostly given on the back of the hand, and the method of changing uniforms after intravenous injections was (in most cases) to pass the injection bottle through a sleeve or pant leg while the needle is inserted. The respondents answered that the sleeve length and pant length did not match. As a result of the preference of the pediatric inpatient design survey, respondents indicated they preferred pajama type, yellow color and medium size animal patterns. A similar ratio of set-in and raglan with no collar but with 3/4 length sleeve of round neck, front end, sleeve top opening, button closing and two pockets were preferred for shirts; however, a 3/4 length with rubber string on the waist, no opening and inner opening were preferred at the same ratio for pants. As for the method to adjust the length to assign functionality to pediatric inpatient uniforms, the most preferred sleeve was a roll-up sleeve with a strap and the most preferred pants were length adjusted pants that used a strap for both shirts and pants with a both sides strap. In addition, the majority of the respondents answered that a hand wrapper that protects the injection location during intravenous injections needs be developed. As for the development type, a half glove type and glove type were preferred in sequential order.