• International Journal of Computer Science & Network Security
• /
• v.21 no.4
• /
• pp.214-222
• /
• 2021

Recently, the growth of e-commerce in Saudi Arabia has been exponential, bringing new remarkable challenges. A naive approach for product matching and categorization is needed to help consumers choose the right store to purchase a product. This paper presents a machine learning approach for product matching that combines deep learning techniques with standard artificial neural networks (ANNs). Existing methods focused on product matching, whereas our model compares products based on unstructured descriptions. We evaluated our electronics dataset model from three business-to-consumer (B2C) online stores by putting the match products collectively in one dataset. The performance evaluation based on k-mean classifier prediction from three real-world online stores demonstrates that the proposed algorithm outperforms the benchmarked approach by 80% on average F1-measure.

• Food Science of Animal Resources
• /
• v.39 no.2
• /
• pp.222-228
• /
• 2019

This research was motivated by our encounter with the situation where an optimization was done based on statistically non-significant models having poor fits. Such a situation took place in a research to optimize manufacturing conditions for improving storage stability of coffee-supplemented milk beverage by using response surface methodology, where two responses are $Y_1$=particle size and $Y_2$=zeta-potential, two factors are $F_1$=speed of primary homogenization (rpm) and $F_2$=concentration of emulsifier (%), and the optimization objective is to simultaneously minimize $Y_1$ and maximize $Y_2$. For response surface analysis, practically, the second-order polynomial model is almost solely used. But, there exists the cases in which the second-order model fails to provide a good fit, to which remedies are seldom known to researchers. Thus, as an alternative to a failed second-order model, we present the heterogeneous third-order model, which can be used when the experimental plan is a two-factor central composite design having -1, 0, and 1 as the coded levels of factors. And, for multi-response optimization, we suggest a modified desirability function technique. Using these two methods, we have obtained statistical models with improved fits and multi-response optimization results with the predictions better than those in the previous research. Our predicted optimum combination of conditions is ($F_1$, $F_2$)=(5,000, 0.295), which is different from the previous combination. This research is expected to help improve the quality of response surface analysis in experimental sciences including food science of animal resources.

• 한국신재생에너지학회:학술대회논문집
• /
• 2011.11a
• /
• pp.39.2-39.2
• /
• 2011

The new and renewable energy today has a great interest in all countries around the world. In special it has need more limit of the fossil fuel that needs of low carbon emission among the social necessary conditions. Recently, the high-rise building demand the structural safety, the economic feasibility and the functional design. The high-rise building spends enormous energy and it satisfied the design in solving energy requirements. The requirements of energy for the building depends on the partly form wind energy due to the cladding of the building that came from the surroundings of the high-rise building. In this study of the wind energy, the cladding of the building was assessed a tentative study. The wind energy obtains from several small wind powers that came from the building or the surrounding of the building. In making a cladding the wind energy forms with wind pressure by means of energy transformation methods. The assessment for the building cladding was surrounded of wind speed and wind pressure that was carried out as a result of numerical simulation of wind environment and wind pressure which is coefficient around the high-rise building with the computational fluid dynamics. In case of the obtained wind energy from the pressure of the building cladding was estimated by the simulation of CFD of the building. The wind energy at this case was calculated by energy transform methods: the wind pressure coefficients were obtained from the simulated model for wind environment using CFD as follow. The concept for the factor of $E_f$ was suggested in this study. $$C_p=\frac{P_{surface}}{0.5{\rho}V^{2ref}}$$ $$E_c=C_p{\cdot}E_f$$ Where $C_p$ is wind pressure coefficient from CFD, $E_f$ means energy transformation parameter from the principle of the conservation of energy and $E_c$ means energy from the building cladding. The other wind energy that is $E_p$ was assessed by wind power on the building or building surroundings. In this case the small wind power system was carried out for wind energy on the place with the building and it was simulated by computational fluid dynamics. Therefore the total wind energy in the building was calculated as the follows. $$E=E_c+E_p$$ The energy transformation, which is $E_f$ will need more research and estimation for various wind situation of the building. It is necessary for the assessment to make a comparative study about the wind tunnel test or full scale test.

• Journal of Environmental Science International
• /
• v.21 no.9
• /
• pp.1069-1078
• /
• 2012

This study was performed to evaluate the asbestos exposure levels and to calculate excess lifetime cacer risks(ELCRs) in asbestos-containing buildings for maintenance and management. The range of airborne asbestos concentration of 33 buildings was 0.0018 ~ 0.0126 f/cc and one site exceeded indoor air-quality recommended limit 0.01 f/cc. And ELCRs based on US EPA IRIS(Integrated risk information system) model are 1.5E-06 ~ 3.9E-05 levels, and there was no site showed 1.0E-04 (one person per million) level or more, and 11 sites showed 1.0E-05 (one person per 100,000 people) level or more. To prevent the release of asbestos fibers, it needs operation and maintenance of asbestos-containing building materials, and there are some methods such as removal, repairment, enclosure and encapsulation. In conclusion, a risk-based air action level for asbestos in air is an appropriate metric for asbestos-containing building management.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1292-1295
• /
• 1987

In noninvasive temperature measurement within body, this paper is presented temperature measurement method in security and with effect from Applicator by electromagnetic, and it is analyzed heat generation quantity or temperature rise distribution by computer simulation within body. In this paper, two-dimensional model is considered and temperature distribution produced by RF capacitive heating system is analyzed by using Finit Element Method (F.E.M). A passibility of temperature distribution control is examined based on the position and size of Applicator.

• Korean Journal of Child Studies
• /
• v.27 no.6
• /
• pp.69-79
• /
• 2006

This study investigated intergenerational transmission from mother's attachment representation to infant's attachment pattern and the associations between maternal attachment representation and their childhood experiences. Subjects were forty 12- to 15-month-old infants and their mothers. The Adult Attachment Interview (Main & Goldwyn, 1984) was used to assess mother's attachment representation. The Strange Situation (Ainsworth, 1978) was used to classify infant's attachment relationship. Mothers were classified as autonomous (F), dismissing (Ds), preoccupied (E), or unresolved/disorganized (Ud). Infants were classified as secure (B), insecure-avoidant (A), insecure-resistant (C), or insecure-disorganized (D). Exact A/B/C/D and Ds/F/E/Ud agreement was observed in 30 of 40 dyads(75%). Maternal childhood experiences were related to maternal attachment representation.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.818-820
• /
• 2004

This paper is described the insulation design and 3-D electromagnetic analysis of 6.6kV main transformer for a vessel by F.E.M.. To obtain the optimal design of insulation structure, the electric field stress is analyzed and estimated the proposed model A and B for the characteristics investigation according to the insulation thickness and position. And the performance characteristics of 6.6kV transformer are estimated as the equivalent circuit parameters computed by F.E.M. analysis.

• Journal of Environmental Science International
• /
• v.7 no.6
• /
• pp.745-751
• /
• 1998

The well-mixed room model has been traditionally used to predict the concentrations of contaminants in indoor environments. However, this is inappropriate because the flow fields in many indoor environments distribute contaminants non-uniformly, due to imperfect air mixing. Thus, some means used to describe an imperfectly mixed room are needed. The simplest model that accounts for imperfect air mixing is a two-zone model. Therefore, this study on development of computer program far the two-zone model is carried out to propose techniques of estimating the concentration of contaminants in the room. To do this, an important consideration is to divide a room into two-zone, i.e. the lower and upper zone assuming that the air and contaminants are well mixed within each zone. And between the zones the air recirculation is characterized through the air exchange parameter. By this basic assumption, the equations for the conservation of mass are derived for each zone. These equations are solved by using the computational technique. The language used to develope the program is a VISUAL BASIC. The value of air exchange coefficient($f_12$) is the most difficult to forecast when the concentrations of contaminants in an imperfectly mixed room are estimated by the two-zone model. But, as the value of $f_12$ increases, the air exchange between each zone increases. When the value of $f_12$ is approximately 15, the concentrations in both zone approach each other, and the entire room may be approximately treated as a single well-mixed room. Therefore, this study is available for designing of the ventilation to improve the air quality of indoor environments. Also, the two-zone model produces the theoretical base which may be extended to the theory for the multi-zone model, that will be contributed to estimate the air pollution in large enclosures, such as shopping malls, atria buildings, atria terminals, and covered sports stadia.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.8
• /
• pp.71-78
• /
• 2001

In GMA(Gas Metal Arc)Welding, the weld size that is a locally melted area of a workpiece is one of the most important considerations in determining the strength of a welded structure. Variations in the weld power and the welding heat flux may affect the weld pool formation and ultimately the size of the weld. Therefore, an accurate prediction of the weld size requires a precise analysis of the weld thermal cycle. In this study, a model which can estimate the weld bead geometry and a method for thermal analysis, including the model, are suggested. In order to analyze the weld bead geometry, a mathematical model was developed with transformed coordinates to apply to the horizontal fillet joints. A heat flow analysis was performed with a two dimensional finite element model that was adopted for computing the base metal melting zone. The reliability of the proposed model and the thermal analysis was evaluated through experiments, and the results showed that the proposed model was very effective for predicting the weld bead shape and good correspondence in melting zone of the base metal.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.3
• /
• pp.107-116
• /
• 1993

In the design and operation of robitic arm with flexible links, the equation of motion are required to exactly model the interaction between rigid body motion and elastic motion and to be formulated efficientlyl. In this paper, the flexible link is represented by applying the D-H rigid link representation method to measure the elestic deformation. And the equations of motion of robotic arm, which are configured by the generalized coordinates of elastic and rigid degrees of freedom, are formulated from the principle of virtual power. Dynamic characteristics due to elastic deformation of each link are obtained by using F. E. M to model complex shaped link acurately and by eliminating elastic modes of higher order that do not largely affect motion to reduce the number of elastic degrees of freedom. Also presented is the result of simulation of flexible robotic arms whose joints are controlled by direct or PD control.