• International Journal of Control, Automation, and Systems
• /
• v.3 no.2
• /
• pp.183-194
• /
• 2005

In this study, we introduce an advanced architecture of genetically optimized Hybrid Fuzzy Neural Networks (gHFNN) and develop a comprehensive design methodology supporting their construction. A series of numeric experiments is included to illustrate the performance of the networks. The construction of gHFNN exploits fundamental technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms (GAs). The architecture of the gHFNNs results from a synergistic usage of the genetic optimization-driven hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN). In this tandem, a FNN supports the formation of the premise part of the rule-based structure of the gHFNN. The consequence part of the gHFNN is designed using PNNs. We distinguish between two types of the linear fuzzy inference rule-based FNN structures showing how this taxonomy depends upon the type of a fuzzy partition of input variables. As to the consequence part of the gHFNN, the development of the PNN dwells on two general optimization mechanisms: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the gHFNN, the models are experimented with a representative numerical example. A comparative analysis demonstrates that the proposed gHFNN come with higher accuracy as well as superb predictive capabilities when comparing with other neurofuzzy models.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.6
• /
• pp.251-256
• /
• 2010

In times past, simple numeric password was the commonly used method in security system. For complement this method, the security system using biometric information is appeared. But it usually uses the scheme to utilize portion of biometric information, and has limited application fields. This biometric security system has low reliability because of some problems such as steal, robbery, and so on. Furthermore, it is associated secondary crime as leaking personal information. For this reason new security system using the unique individual biometric is required. In this paper, we propose the security scheme which used face image and iris analysis. While face image processing for specific person identification, it calculate some feature points of face image and iris's features in our proposed scheme. After person identification applying RFID tags in doorway, several feature information is extracted from camera image, and these compare with registered information of our system for final identification.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.1
• /
• pp.40-49
• /
• 2004

In this paper, we propose a new architecture of Genetic Algorithms(GAs)-based Self-Organizing Polynomial Neural Networks(SOPNN), discuss a comprehensive design methodology and carry out a series of numeric experiments. The conventional SOPNN is based on the extended Group Method of Data Handling(GMDH) method and utilized the polynomial order (viz. linear, quadratic, and modified quadratic) as well as the number of node inputs fixed (selected in advance by designer) at Polynomial Neurons (or nodes) located in each layer through a growth process of the network. Moreover it does not guarantee that the SOPNN generated through learning has the optimal network architecture. But the proposed GA-based SOPNN enable the architecture to be a structurally more optimized network, and to be much more flexible and preferable neural network than the conventional SOPNN. In order to generate the structurally optimized SOPNN, GA-based design procedure at each stage (layer) of SOPNN leads to the selection of preferred nodes (or PNs) with optimal parameters- such as the number of input variables, input variables, and the order of the polynomial-available within SOPNN. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. A detailed design procedure is discussed in detail. To evaluate the performance of the GA-based SOPNN, the model is experimented with using two time series data (gas furnace and NOx emission process data of gas turbine power plant). A comparative analysis shows that the proposed GA-based SOPNN is model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• The Journal of Korean Academy of Prosthodontics
• /
• v.26 no.1
• /
• pp.31-49
• /
• 1988

This study was performed to investigate the sound distortion following the alternation of the palatal plate thickness, for this study, 3 subjects who were born in Seoul and spoke Seoul dialect were recruited from K university male student population. First, their sounds of /아(a)/, 어(e)/, 오(o)/, 우(u)/, 으($\.{+}$), 이(i)/,에(e)/ without inserting plate were recorded , and then the sounds with palatal plates of different thickness were recorded, respectively. The palatal plates was constructed to cover the alveolar & palatal surfaces of the maxilla with an approximate thickness of 1.0mm, 2.5mm, and thickness of 2.5mm over the alveolar ridge & 1.0mm elsewhere and, named B, C, D-type, in succession. Series of analysis were administered through Computer (16 bit IBM PC/AT) at analyze the sound distortions. These experiments were analyzed by the LPC, Log Area Ratio. The findings led to the following conclusions: 1. Sound distortions were relatively minute in each condition and informations, however, /이(i)/ was the most distorted vowel in all conditions. 2. By and large, sound distortion was large in C, D-types. However, there was no correlation of the distortion rate on the 3 informants, and all tested vowels. 3. It was similar to LPC, Log Area Ratio distortion rates. 4. It was found that the sound distortion wit]1 plate inserted was verified to the numeric value with LPC and Log Area Ratio method.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.28 no.2
• /
• pp.53-62
• /
• 2020

This study is to evaluate the accuracy of the meteorological information provided for the aircraft operating at low altitude. At first, it is necessary to identify crucial elements of weather information closely related to flight safety during low altitude flights. The study conducted a survey of pilots of low altitude aircraft, divided into pre-flight and in-flight phases, and reached an opinion that wind direction, wind speed, cloud coverage and ceiling and visibility are important items. Related to these items, we compared and calculated the accuracy of TAFs and METARs from Taean Airfield, Seosan Airport and Gunsan Airport because of their high number of domestic low-altitude flights. Accuracy analysis evaluated the accuracy of two numerical variables, Mean Absolute Error(MAE) and Root Mean Square Error(RMSE), and the cloud coverage which is categorical variable was calculated and compared by accuracy. For numeric variables, one-way ANOVA, which is a parameter-test, was approached to identify differences between actual forecast values and observations based on absolute errors for each item derived from the results of MAE and RMSE accuracy analyses. To determine the satisfaction of both normality assumptions and equivalence variability assumptions, the Shapiro-Wilk test was performed to verify that they do not have a normality distribution for numerical variables, and for the non-parametric test, Kruscal-Wallis test was conducted to determine whether or not they are satisfied.

• The Korean Journal of Pain
• /
• v.22 no.3
• /
• pp.229-233
• /
• 2009

Background: Sacroiliac (SI) joint pain is a challenging condition that causes lower back or buttock pain; however, there is no universally accepted long-term treatment. There have been several reports of ligament prolotherapy for SI joint pain, but these have had inconsistent results, probably due to the lack of a specific diagnosis for patient selection and variability in the volume, number and sites of injection. Therefore, this study was conducted to assess the efficacy of intraarticular prolotherapy for relieving SI joint pain diagnosed by local anesthetic intraarticular injection. Methods: Twenty-two patients with SI joint pain confirmed by 50% or more improvement in response to local anesthetic block underwent intraarticular prolotherapy with 25% dextrose water every other week three times. The numeric rating scale (NRS) for pain and Oswestry disability index (ODI) were assessed at the initial visit and after completion of a series of prolotherapy and the NRS was checked during monthly follow-up sessions to evaluate the long-term effectiveness of this technique. Results: Twenty patients completed prolotherapy and followed up as scheduled. The NRS and ODI were significantly improved from 6 (4-8) and $34.1{\pm}15.5$ to 1 (0-3) and $12.6{\pm}9.8$ (P < 0.01), respectively, at 1 month after prolotherapy. The mean duration of pain relief of 50% or more was 12.2 months (95% CI, 10.0-14.3) as determined by Kaplan-Meier survival analysis. Conclusions: Intraarticular prolotherapy provided long-term relief of sacroiliac joint pain and may have more benefits than ligament prolotherapy or neurolysis.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.2
• /
• pp.321-330
• /
• 2015

There have been found many modified malwares which could avoid detection simply by replacing a sequence of characters or a part of code. Since the existing anti-virus program performs signature-based analysis, it is difficult to detect a malware which is slightly different from the well-known malware. This paper suggests a method of detecting modified malwares by extending a hash-value based code comparison. We generated hash values for individual functions and individual code blocks as well as the whole code, and thus use those values to find whether a pair of codes are similar in a certain degree. We also eliminated some numeric data such as constant and address before generating hash values to avoid incorrectness incurred from them. We found that the suggested method could effectively find inherent similarity between original malware and its derived ones.

• Journal of muscle and joint health
• /
• v.22 no.1
• /
• pp.1-12
• /
• 2015

Purpose: The purpose of this study was to explore the relationships among pain, depression, health behaviors, and activities of daily living (ADL) in older adults after femur fracture surgery. Methods: This was a descriptive correlational study. Ninety seven outpatients aged 65 or older were selected, who agreed to participate and visited the four hospitals located in G providence. Numeric Rating Scale (NRS) for pain, a Short form Geriatric Depression Scale (SGDS) for depression, health behavior scale and Korean version of Bathel Index for ADL were used. Data were analyzed using t-test and ANOVA, Pearson's correlation and the hierarchical regression analysis in SPSS 18. Results: Pain and depression were positively correlated (r=.35, p<.001). Pain and health behaviors (r=-.30, p=.010), pain and ADL (r=-.21, p=.044), depression and health behaviors (r=-.51, p<.001), depression and ADL (r=-.29, p=.004) were negatively correlated. The variables affecting the ADL was intake of a painkiller or not (${\beta}$=-.32), age (${\beta}$=-.25), transitional period after discharge (${\beta}$=.23) and depression (${\beta}$=-.23). ADL was accounted for 33.4% in total by these four variables. Conclusion: Interventions for alleviating pain, and managing depression would be effective in enhancing ADL in older adults after femur fracture surgery.

• Structural Engineering and Mechanics
• /
• v.9 no.5
• /
• pp.417-432
• /
• 2000

A comprehensive analytic study has been conducted to investigate the instability problems of metal-plate-connected (MPC) joints in light frame trusses. The primary objective in this study is to determine the governing factors that constitute the buckling of the metal connectors and their effects on the structural response of joints. Another objective is to recommend design curves for the daily structural design of these joints. The numeric data presented in this paper has emerged from a broad base that was founded on over 350 advanced computer simulations, and was supported by available experimental results obtained by others. This basic-to-applied research includes practical engineering parameters such as size of gaps, shear lengths, gauge (plate thickness) of connectors, size of un-braced areas, failure modes, and progressive disintegration of joints. Square-end members have been emphasized though the results cover the custom-made fitted joints. The results indicate that chord shears cause and dominate the buckling of MPC joints, and the shear length has a more pronounced effect than the size of gaps. Further, large gauges and small un-braced areas improve the buckling response. Several practical recommendations have been suggested throughout the paper such as keeping the ratio of gap/shear length below 3/4 for improving the buckling strength. The study reveals that multi-area joints should not be simplified as single web-to-chord MPC joints such as keeping the ratio of gap/shear length below 3/4 for improving the buckling strength, even where one web is in tension and the other in compression. Finally, the results obtained from this study favorably agree with experimental data by others, and the classic buckling theories for other structural components.

• Korean journal of food and cookery science
• /
• v.25 no.3
• /
• pp.317-329
• /
• 2009

In the study, we determined the optimal ingredient mixing ratio for the preparation of sponge cake containing bamboo (Pseudosasa japonica Makino) leaves. This experiment was designed in according with the D-optimal design of mixture design, which involved 14 experimental points including 4 replicates for three independent variables (sugar 110${\sim}$129%, bamboo leaves 3${\sim}$8%, oil 10${\sim}$25%). The results the F-test, specific gravity, volume and color values (L, a, b) decided a linear model, while the viscosity, hardness and sensory characteristics (color, smell, taste, texture and overall acceptance) decided a quadratic model. The results of our fitness analysis demonstrated that in all characteristic, the probabilities were significant within 0.05%; thus, the models were accepted as appropriate. The response surface and trace plot results demonstrated that increasing amounts of added bamboo leaves induced a reduction in brightness, and increasing redness and yellowness. In addition, increasing amounts of bamboo leaves caused increases in hardness, and thus the softness of the cake decreased. And as the level of added oil increased, softness increased. Cake samples received low sensory evaluation scores when sugar, bamboo leaves, and oil were added above their optimal levels. In the numeric optimization, the optimal ingredient amounts were 121.36% sugar, 4.96% bamboo leaves, and 15.69% oil. The above results demonstrate the feasibility of adding bamboo leaves to sponge cake, and therefore, a bamboo leaves as a functional food.