• Korea Trade Review
• /
• v.48 no.2
• /
• pp.27-43
• /
• 2023

The maritime industry is playing an increasingly vital part in global economic expansion. Specifically, the Baltic Dry Index is highly correlated with global commodity prices. Hence, the importance of BDI prediction research increases. But, since the global situation has become more volatile, it has become methodologically more difficult to predict the BDI accurately. This paper proposes an integrated machine-learning strategy for accurately forecasting BDI trends. This study combines the benefits of a convolutional neural network (CNN) and long short-term memory neural network (LSTM) for research on prediction. We collected daily BDI data for over 27 years for model fitting. The research findings indicate that CNN successfully extracts BDI data features. On this basis, LSTM predicts BDI accurately. Model R2 attains 94.7 percent. Our research offers a novel, machine-learning-integrated approach to the field of shipping economic indicators research. In addition, this study provides a foundation for risk management decision-making in the fields of shipping institutions and financial investment.

• Journal of the Korea Society for Simulation
• /
• v.33 no.1
• /
• pp.19-26
• /
• 2024

The phase-type, PH, distribution is defined as the time to absorption into a terminal state in a continuous-time Markov chain. As the PH distribution includes family of exponential distributions, it has been widely used in stochastic models. Since the PH distribution is represented and generated by an initial probability vector and a generator matrix which is called the Markovian representation, we need to find a vector and a matrix that are consistent with given set of moments if we want simulate a PH distribution. In this paper, we propose an approach to simulate a PH distribution based on distribution function which can be obtained directly from moments. For the simulation of PH distribution of order 2, closed-form formula and streamlined procedures are given based on the Jordan decomposition and the minimal Laplace transform which is computationally more efficient than the moment matching methods for the Markovian representation. Our approach can be used more effectively than the Markovian representation in generating higher order PH distribution in queueing network simulation.

• Journal of Advanced Navigation Technology
• /
• v.15 no.3
• /
• pp.392-404
• /
• 2011

In this paper, we address the issue of joint detection schemes for uplink cellular system when base station cooperation is possible for multi-user detection in multi-cell scenario. The ZF, ML, MMSE and SIC detection are analyzed and evaluated as a conventional scheme. ML attains the optimal performance but the complexity increases exponentially, ZF/MMSE have simple structure but have poor detection performance and SIC has better performance but it has large complexity and potential of the error propagation. However, they need the increased decoder complexity as the number of iteration is increased. We propose a new joint ML and ZF/MMSE detection scheme, which combines the partial ML decoding and ZF/MMSE detection, in order to decrease the decoder complexity. Simulation results show that the proposed scheme attains same or a little bit better BER performance and expect reduced decoder complexity, specially in the case of large number of Base Station are cooperated each other.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.14 no.7
• /
• pp.769-776
• /
• 2003

This paper presents analysis and design of microstrip Rotman lens operating over wide band and wide steering angle by the contour integral method along with the segmentation method. All mutual coupling, internal reflections between ports and the discontinuity at every junction are taken into account. Equally spaced ports are designed and realized, which make suppress output ripple through the array ports. Impedance matching and mutual coupling between ports are analyzed and optimized using 12 input and 12 output exponential tapers. The measured results of fabricated lens show ${\pm}$ 1.8 dB insertion loss deviation over 6∼18 GHz wide frequency range and beam steering accuracy less than 1$^{\circ}$over ${\pm}$53$^{\circ}$angle and agrees well with the analysis results.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1327-1336
• /
• 2017

In this study, the problems in the short term stock market forecasting are analyzed and the feasibility of the ARIMA method and the backpropagation neural network is discussed. Neural network and genetic algorithm in short term stock forecasting is also examined. Since the backpropagation algorithm often falls into the local minima trap, we optimized the backpropagation neural network and established a genetic algorithm based on backpropagation neural network for forecasting model in order to achieve high forecasting accuracy. The experiments adopted the korea composite stock price index series to make prediction and provided corresponding error analysis. The results show that the genetic algorithm based on backpropagation neural network model proposed in this study has a significant improvement in stock price index series forecasting accuracy.

• The Journal of the Korea Contents Association
• /
• v.20 no.2
• /
• pp.96-104
• /
• 2020

As consumers' consumption activities become more active due to the activation of online shopping malls, companies are conducting item trend analyses to boost sales. The existing item trend analysis methods are analyzed by considering only the activities of users in online shopping mall services, making it difficult to identify trends for new items without purchasing history. In this paper, we propose a trend analysis method that combines data in online shopping mall services and social network data to analyze item trends in users and potential customers in shopping malls. The proposed method uses the user's activity logs for in-service data and utilizes hot topics through word set extraction from social network data set to reflect potential users' interests. Finally, the item trend change is detected over time by utilizing the item index and the number of mentions in the social network. We show the superiority of the proposed method through performance evaluations using social network data.

• Journal of the Korean Institute of Navigation
• /
• v.25 no.1
• /
• pp.53-60
• /
• 2001

This paper presents the fabrication of the LNA which is operating at 2.13 ~ 2.16 GHz for IMT-2000 front-end receiver using series feedback and resistive decoupling circuit. Series feedback added to the source lead of a GaAs FET keeps the low noise characteristics and drops the input reflection coefficient of a low noise amplifier simultaneously. Also, it increases the stability of the LNA. Resistive decoupling circuit is suitable for input stage matching because a signal at low frequency is dissipated by a resistor in the matching network. The amplifier consists of GaAs FET ATF-10136 for low noise stage and VNA-25 which is internally matched MMIC for high gain stage. The amplifier is fabricated with both the RF circuits and self bias circuit on the Teflon substrate with 3.5 permittivity. The measured results of the LNA which is fabricated using the above design technique are presented more than 30 dB in gain, PldB 17 dB and less than 0.7 dB in noise figure, 1.5 in inputㆍoutput SWR(Standing Wave Ratio).

• Polymer(Korea)
• /
• v.26 no.6
• /
• pp.759-766
• /
• 2002

Regular, spherical and isotropic open-microcellular foams having low density were prepared by the high internal phase emulsion (HIPE) polymerization mainly composed of styrene monomer and water The effects of Polymerization conditions. such as the content of water, divinylbenzene as a crosslinking agent and dodecane as a chain transfer agent, were investigated based on the tell size and foam properties. The microstructural morphology was observed using scanning electron microscopy (SEM) and the compression modulus of the foam was evaluated using compression test. The dropwise feeding of the aqueous phase into the oil phase was more effective than the batch feeding in producing the uniform and stable foam. Agitation speed and surfactant strongly influenced on the cell size and the window size between water droplets. Introduction of chain transfer agent increased the cell size, whereas it decreased the window size. Compression modulus increased with the crosslinking agent, but decreased with the chain transfer agent.

• Polymer(Korea)
• /
• v.39 no.2
• /
• pp.240-246
• /
• 2015

Formation of a strong 3-dimensional interfacial network structure via chemical reaction between hydroxyl group on silica surface and NR chain by the addition of bis(triethoxysilylpropyl)tetrasulfide (TESPT) into silica-filled NR compound was observed by using Py-GC/MS and SEM. Addition of TESPT into silica-filled NR compound decreased scorch time ($t_{10}$) due to increased sulfur content, and reduced cure rate index (CRI) via continuous reaction between sulfur atoms in TESPT, which acted as a sulfur donor, and activators and/or accelerators. Addition of TESPT in the compound improved processability and mechanical properties of the compound. Overall, we observed that the addition of TESPT into the silica-filled NR compound formed a silica-TESPT-NR network, and thus the degree of crosslinking was increased resulting in improved mechanical properties.

• Journal of the Korean Magnetics Society
• /
• v.25 no.1
• /
• pp.16-21
• /
• 2015

The micro device, coil, and channel for the biosensor integrated with the GMR-SV device based on the antiferromagnetic IrMn layer was fabricated by the light lithography process. When RBCs coupled with several magnetic beads with a diameter of $1{\mu}m$ passed on the micro channel, the movement of $RBC+{\mu}Beads$ is controlled by the electrical AC input signal. The $RBC+{\mu}Beads$ having a micro-magnetic field captured above the GMR-SV device is changed as the output signals for detection status. From these results, the GMR-SV device having the width magnitude of a few micron size can be applied as the biosensor for the analysis of a new magnetic property as the membrane's deformation of RBC coupled to magnetic beads.