• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1561-1567
• /
• 2015

Abstract Semi-supervised learning is an area in machine learning that employs both labeled and unlabeled data in order to train a model and has the potential to improve prediction performance compared to supervised learning. Graph-based semi-supervised learning has recently come into focus with two phases: graph construction, which converts the input data into a graph, and label inference, which predicts the appropriate labels for unlabeled data using the constructed graph. The inference is based on the smoothness assumption feature of semi-supervised learning. In this study, we propose an enhanced label inference algorithm by incorporating the importance of each vertex. In addition, we prove the convergence of the suggested algorithm and verify its excellence.

• Corrosion Science and Technology
• /
• v.10 no.6
• /
• pp.199-204
• /
• 2011

Hot dip metallic coated steels like as galvanized (GI), zinc-aluminium (GL) and aluminium coated steels are mostly used where corrosion resistance is needed. There are two kinds (type 1 and type 2) of aluminium coated steel being commercially used among them. Type 1 aluminium coated steel is coated with an Al-5~11 wt%Si alloy and Type 2 aluminium coated steel consists of commercially pure aluminium. Type 1 Al coated steel is generally used in automotive components and electrical appliances while type 2 aluminium coated steel is mainly used in construction applications such as building cladding panels, air conditioning and ventilation system. In this study, Type 1 aluminium coated steels have tested by accelerated conditions (salt spray or corrosive gas) and outdoor exposure condition in order to understand their corrosion behaviour. Due to the distinct corrosion mechanism of Al which exposes to the severe chloric condition, Salt Spray Test cannot predict the ordinary atmospheric corrosion of Al based coated materials. In addition, the test results and their corrosion feature of Al coated steel sheets will be discussed comparing with other metallic coated steel sheets of GI and GL.

• Journal of Korean Society on Water Environment
• /
• v.24 no.1
• /
• pp.44-53
• /
• 2008

To recognize the spatial and temporal variability of water temperature and dissolved oxygen in the Youngsan reservoir formed after dike construction, water temperature and dissolved oxygen data have been observed and analyzed from April, 2002 until March, 2003. As the results, certain stratifications were not distinctly observed in the Youngsan reservoir during summer, which was estimated due to the drainage characteristic from the Youngsan water gates. The yearly variation of water temperature in the Youngsan reservoir is shown seasonally ups and downs by the heat exchange between the atmosphere and the reservoir. On the other hand, dissolved oxygen and water temperature in the Youngsan reservoir have been shown inversed proportional correlation. As the calculation results of residence time and water exchange rate, it is considered that the feature of oxygen distribution is determined by the drainage characteristics caused the shortest residence time during summer, which also disturbed the formation of stratification in the Youngsan reservoir.

• Korean Management Science Review
• /
• v.24 no.2
• /
• pp.157-176
• /
• 2007

Fuzzy cognitive map(FCM) has long been used as an effective way of constructing the human's decision making process explicitly. By taking advantage of this feature, FCM has been extensively used in providing what-if solutions to a wide variety of business decision making problems. In contrast, the goal-seeking analysis mechanism by using the FCM is rarely observed in literature, which remains a research void in the fields of FCM. In this sense, this study proposes a new type of the FCM-based goal-seeking analysis which is based on utilizing the genetic algorithm. Its main recipe lies in the fact that the what-if analysis as well as goal-seeking analysis are enabled very effectively by incorporating the genetic algorithm into the FCM-driven inference process. To prove the empirical validity of the proposed approach, valid questionnaires were gathered from a number of experts on software sales, and analyzed statistically. Results showed that the proposed approach is robust and significant.

• Korean Institute of Interior Design Journal
• /
• v.15 no.4 s.57
• /
• pp.81-88
• /
• 2006

The form and function of modern museum present more a variety of aspects in need of transition of the mature civil society and culture than the past. Considering that an art museum is the space where a multitude of unspecified visitors inspect simultaneously, exhibitions and adequate construction make visitors lead to successively visual contact. Consequently a goal of this study is to analyze that there is correlation between exhibit space and exhibitions and to suggest an alternative plan at exhibition through relationship among exhibitions, exhibit space and spectators' behavior. Two Art galleries (one is a large-sized gallery and the other is a small-sized one) located in Pyung-Chang dong were selected to analyze the correlation and suggest the better display for the exhibition. The finding of the study is following. The exhibit space which spectators recognize is assumed diverse forms by an unique characteristics of exhibits and space and an arrangement of exhibitions and the path of flow of spectator who walking ahead have an huge effect on a spectators' behavior. In other words, spectators' watching patterns are affected by display of exhibitions and the path of flow. That is to say, the spectators' behavior and the concentration to watch exhibitions is decided by the exhibit form in the museum, and the quality of watching experience is depended on the spectators' relevant knowledge prior to exhibitions.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.7-21
• /
• 2003

Sums-of-Products models were built for segment duration prediction of spoken Korean. An experiment for the modelling was carried out to apply the results to Korean text-to-speech synthesis systems. 670 read sentences were analyzed. trained and tested for the construction of the duration models. Traditional sequential rule systems were extended to simple additive, multiplicative and additive-multiplicative models based on Sums-of-Products modelling. The parameters used in the modelling include the properties of the target segment and its neighbors and the target segment's position in the prosodic structure. Two optimisation strategies were used: the downhill simplex method and the simulated annealing method. The performance of the models was measured by the correlation coefficient and the root mean squared prediction error (RMSE) between actual and predicted duration in the test data. The best performance was obtained when the data was trained and tested by ' additive-multiplicative models. ' The correlation for the vowel duration prediction was 0.69 and the RMSE. 31.80 ms. while the correlation for the consonant duration prediction was 0.54 and the RMSE. 29.02 ms. The results were not good enough to be applied to the real-time text-to-speech systems. Further investigation of feature interactions is required for the better performance of the Sums-of-Products models.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.3
• /
• pp.349-357
• /
• 2012

This paper presents a hybrid motor prototype convenient to modify the magnet and reluctance torques. The rotor of the prototype consists of magnet and reluctance parts, so the generated torque includes both magnet and reluctance torques. A considerable feature of the motor is that the ratio of the magnet and reluctance parts can be modified on the rotor and the rotor hybridization ratio can be varied. Another important point is the mechanical angle between the parts changed by means of the suitable construction of the parts on the rotor shaft. Finite element (FE) analysis was carried out for the proposed motor and static torque measurements were realized. The FE results were compared with the experimental results. Average torque and maximum torque values were obtained and three dimensional 3-D graphs were formed by using the experimental data. It is possible to make different combinations by changing the parts and the angle between the parts due to the proposed motor. So the magnet and reluctance torques are modified and different combinations give different torque behavior.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.4 no.1
• /
• pp.3-12
• /
• 2002

This research work is to investigate influences of the Opera House in Arts Center caused by the twin tunnel construction. The Opera House of 3D structural feature with various type of foundations and adjacent twin tunnels are modeled in 3-Dimensional mesh for FEM analysis. Confirmation of safety is essential for this particular type of structure, and attention level and warning level of control criteria are examined for the protection of the Opera House by means of the analytical results.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.6
• /
• pp.20-26
• /
• 2003

This study proposes the construction of attractor quadrant method for high-precision cutting characteristics evaluation of non-ferrous metals. Also this paper aims to find the optimal cutting conditions of diamond turning machine by measuring surface form and roughness to perform the cutting experiment of non-ferrous metals, which are aluminum, with diamond tool. As well, according to change cutting conditions such as feed rate, using diamond turning machine to Perform cutting Processing, by measuring cutting force and surface roughness and according to cutting conditions the aluminum about cutting properties. Trajectory changes in the attractor indicated a substantial difference in fractal characteristics and attractor quadrant characteristics. In quantitative quadrant feature extraction, 1,309 point in the case of A17075 (one quadrant) and 1,406 point (one quadrant) in the case of brass were proposed on the basis of attractor reconstruction. Proposed attractor quadrant method can be used for high-precision cutting characteristics evaluation of non-ferrous metals.

• Journal of the Korean Society for Geothermal and Hydrothermal Energy
• /
• v.8 no.4
• /
• pp.32-40
• /
• 2012

Geothermal heat pump(GHP) systems use vertical borehole heat exchangers to transfer heat to and from the surrounding ground via a heat carrier fluid that circulates between the borehole and the heat pump. An Important feature associated with design parameters and system performance is the local thermal resistances between the heat carrier flow channels in the borehole and the surrounding ground. This paper deals with the in-situ experimental determination of the effective thermal properties of the ground. The recorded thermal responses together with the line-source theory are used to determine the thermal conductivity and thermal diffusivity, and the steady-state borehole thermal resistance. In addition, this paper compares the experimental borehole resistance with the results from the different empirical and theoretical relations to evaluate this resistance. Further, the performance simulation of a GHP system with vertical borehole heat exchangers was conducted to analyze the effect of the borehole thermal resistance on the system performance.