• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.39-55
• /
• 2019

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.

• Journal of Korea Technology Innovation Society
• /
• v.17 no.2
• /
• pp.380-420
• /
• 2014

We increasingly see the importance of employees acquiring enough expert capability or innovation capability to prepare for ever growing uncertainties in their operation domains. However, despite the above circumstances, there have not been an enough number of researches on how operational input components for employees' innovation outcome, innovation activities such as acquisition, exercise and promotion effort of employee's innovation capability, and their resulting innovation outcome interact with each other. This trend is believed to have been resulted because most of the current researches on innovation focus on the units of country, industry and corporate entity levels but not on an individual corporation's innovation input components, innovation outcome and innovation activities themselves. Therefore, this study intends to avoid the currently prevalent study frames and views on innovation and focus more on the strategic policies required for the enhancement of an organization's innovation capabilities by quantitatively analyzing employees' innovation outcomes and their most suggested relevant innovation activities. The research model that this study deploys offers both linear and structural model on the trio of learning, innovation capability and innovation outcome, and then suggests the 4 relevant hypotheses which are quantitatively tested and analyzed as follows: Hypothesis 1] The different levels of innovation capability produce different innovation outcomes (accepted, p-value = 0.000<0.05). Hypothesis 2] The different amounts of learning time produce different innovation capabilities (rejected, p-value = 0.199, 0.220>0.05). Hypothesis 3] The different amounts of learning time produce different innovation outcomes. (accepted, p-value = 0.000<0.05). Hypothesis 4] the innovation capability acts as a significant parameter in the relationship of the amount of learning time and innovation outcome (structural modeling test). This structural model after the t-tests on Hypotheses 1 through 4 proves that irregular on-the-job training and e-learning directly affects the learning time factor while job experience level, employment period and capability level measurement also directly impacts on the innovation capability factor. Also this hypothesis gets further supported by the fact that the patent time absolutely and directly affects the innovation capability factor rather than the learning time factor. Through the 4 hypotheses, this study proposes as measures to maximize an organization's innovation outcome. firstly, frequent irregular on-the-job training that is based on an e-learning system, secondly, efficient innovation management of employment period, job skill levels, etc through active sponsorship and energization community of practice (CoP) as a form of irregular learning, and thirdly a model of Yί=f(e, i, s, t, w)+${\varepsilon}$ as an innovation outcome function that is soundly based on a smart system of capability level measurement. The innovation outcome function is what this study considers the most appropriate and important reference model.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• Fire Science and Engineering
• /
• v.15 no.1
• /
• pp.23-33
• /
• 2001

The utility tunnels are the important facility as a mainstay of country because of the latest communication developments. However, the utilities tunnel is difficult to deal with in case of a fire accident. When a cable burns, the black smoke containing poisonous gas will be reduced. This black smoke goes into the tunnel, and makes it difficult to extinguish the fire. Therefore, when there was a fire in the utility tunnel, the central nerves of the country had been paralyzed, such as property damage, communication interruption, in addition to inconvenience for people. This paper is based on the fire occurred in the past, and reenacting the fire by making the real utilities tunnel model. The aim of this paper is the scientific analysis of the character image of the fire, and the verification of each fire protection system whether it works well after process of setting up a fire protection system in the utilities tunnel at a constant temperature. The fire experiment was equipped with the linear heat detector, the fire door, the connection water spray system and the ventilation system in the utilities tunnel. Fixed portion of an electric power supply cable was coated with a fire retardant coating, and a heating tube was covered with a fireproof. The result showed that the highest temperature was $932^{\circ}c$ and the linear heat detector was working at the constant temperature, and it pointed at the place of the fire on the receiving board, and Fixed portion of the electric power supply cable coated with the fire retardant coating did not work as the fireproof. The heating tube was covered with the fireproof about 30 minutes.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.35 no.1
• /
• pp.61-67
• /
• 2015

Recently, the initiation of outside diameter stress corrosion cracking (ODSCC) at the tube support plate region of domestic steam generators (SG) with Alloy600 HTMA tubes has been increasing. As a result, SGs with Alloy600 HTMA tubes must be replaced early or are scheduled to be replaced prior to their designed lifetime. ODSCC is one of the biggest threats to the integrity of SG tubes. Therefore, the accurate evaluation of tube integrity to determine ODSCC is needed. Eddy current testing (ECT) is conducted periodically, and its results could be input as parameters for evaluating the integrity of SG tubes. The reliability of an ECT inspection system depends on the performance of the inspection technique and abilty of the analyst. The detection probability and ECT sizing error of degradation are considered to be the performance indices of a nondestructive evaluation (NDE) system. This paper introduces an optimized evaluation method for ECT, as well as the sizing error, including the analyst performance. This study was based on the results of a round robin program in which 10 inspection analysts from 5 different companies participated. The analysis of ECT sizing results was performed using a linear regression model relating the true defect size data to the measured ECT size data.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• Journal of Navigation and Port Research
• /
• v.31 no.5 s.121
• /
• pp.325-332
• /
• 2007

This study develops a control algorithm on berthing/unberthing system using a joystick for ships with thrusters and a rudder. A nonlinear mathematical model for low speed maneuvering of typical container ships is used to develop a MIMO(multi-input multi-output) nonlinear control algorithm for velocity feedback joystick control. Also a virtual HILS(hardware in the loop simulation) software program for berthing/unberthing is developed to test the performance of the nonlinear and a PID control algorithm. The program is developed using LabWindow/CVI, and a user can see current position and desired trajectory of ship in a monitor, then he can control forward and yaw velocities of a ship using a joystick. The simulation results show that the nonlinear mfd the PID controller have superior performance over a simple open loop joystick control algorithm.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.3
• /
• pp.156-162
• /
• 2007

The parallel beam SPECT system acquires projection data by using collimators in conjunction with photon detectors. The projection data of the parallel beam SPECT system is, however, blurred by the point response function of the collimator that is used to define the range of directions where photons can be detected. By increasing the number of parallel holes per unit area in collimator, one can reduce such blurring effect. This approach also, however, has the blurring problem if the distance between the object and the collimator becomes large. In this paper we consider correction methods for artifacts caused by non-circular orbit of parallel beam SPECT with many parallel holes per detector cell. To do so, we model the relationship between the object and its projection data as a linear system, and propose an iterative reconstruction method including artifacts correction. We compute the projector and the backprojector, which are required in iterative method, as a sum of convolutions with distance-dependent point response functions instead of matrix form, where those functions are analytically computed from a single function. By doing so, we dramatically reduce the computation time and memory required for the generation of the projector and the backprojector. We conducted several simulation studies to compare the performance of the proposed method with that of conventional Fourier method. The result shows that the proposed method outperforms Fourier methods objectively and subjectively.

• Restorative Dentistry and Endodontics
• /
• v.28 no.4
• /
• pp.341-347
• /
• 2003

This study was conducted to evaluate the temperature rise on the root surface while the root canal is being obturated using continuous wave of condensation technique. Maxillary central incisor was prepared for repeated canal obturation. Ten thermocouples (Omega Engineering Inc., Stanford, USA) were placed at 1 mm increment from the anatomical root apex. The real temperature of Buchanan plugger was recorded before insertion into the root canal. The root canal was obturated with continuous wave of condensation technique as described by Buchanan and the root surface temperature was recorded during obturation at $150^{\circ}C,{\;}200^{\circ}C,{\;}250^{\circ}C{\;}and{\;}300^{\circ}C$ temperature settings of System B HeatSource (Model 1005, Analytic technologies, Redmond, WA, USA). After completion of the temperature recording, the dentinal-cementum thickness at each sites was measured. The data were analyzed using one-way ANOVA followed by Scheffe's test and linear regression test. The results were as follows. 1. When the temperature was set at $150^{\circ}C,{\;}200^{\circ}C,{\;}250^{\circ}C{\;}and{\;}300^{\circ}C$ on the digital display of System B HeatSource, the real temperature of the plugger at the 1mm point from the tip revealed $130.82{\pm}2.96^{\circ}C,{\;}158.00{\pm}5.26^{\circ}C,{\;}215.92{\pm}6.91^{\circ}C{\;}and{\;}249.88{\pm}3.65^{\circ}C$ respectively. 2. The position of 8 mm from the anatomical apex showed the highest temperature increase at each temperature settings and it was significantly higher than those of other positions (p<0.0l). The temperature rise was constantly increased toward coronal portion from apex of the root. 3. The maximum temperature increase on the root surface was $2.37{\pm}0.09^{\circ}C{\;}at{\;}150^{\circ}C{\;}setting,{\;}3.11{\pm}0.12^{\circ}C{\;}at{\;}200^{\circ}{\;}setting,{\;}3.93{\pm}0.09^{\circ}C{\;}at{\;}250^{\circ}C{\;}setting{\;}and{\;}5.69{\pm}0.15^{\circ}C{\;}at{\;}300^{\circ}C$ setting respectively. These results suggest that it be relatively kind to the supporting tissues of the root that the root canal is obturated using continuous wave of condensation technique at $150^{\circ}C,{\;}200^{\circ}C,{\;}250^{\circ}C{\;}and{\;}300^{\circ}C$ temperature settings on digital temperature display of System B HeatSource.

• Journal of the Korean Electrochemical Society
• /
• v.1 no.1
• /
• pp.40-44
• /
• 1998

The LAPS device of fast response and high sensitivity, based on electrochemical potential difference, and its system were fabricated for the precise measurement of pH changes and its characteristic were investigated. The electrostatic variation characteristics of LAPS according to the pH changes and parameters in the device were verified through a simulation using LAPS equivalent circuit model. The LAPS device and its system were fabricated on the basis of the result of simulation. The fabricated LAPS system showed linear sensitivity (about 56 mV/pH within the range of pH 2 to pH 11. In order to overcome the defect of general urea sensor (especially slow response time), urease immobilized nitrocellulose membrane was attached on the LAPS and resulted in the very fast response time, 0.29 mV/sec, 0.86 mV/sec at urea concentration of $50{\mu}g/ml,\; 500{\mu}g/ml$, respectively. And also in order to measure the uranyl ion, the uranyl ion selective sensing membrane with calix[6]arene derivative was used and its sensitivity was 25mV/concentration decade in the wide uranyl ion concentration range of $10^{-11}M\;to\;10^{-4}M$.