• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1231-1242
• /
• 2019

This paper presents a two-dimensional attention-based long short-memory (2D-ALSTM) model for stock index prediction, incorporating input attention and temporal attention mechanisms for weighting of important stocks and important time steps, respectively. The proposed model is designed to overcome the long-term dependency, stock selection, and stock volatility delay problems that negatively affect existing models. The 2D-ALSTM model is validated in a comparative experiment involving the two attention-based models multi-input LSTM (MI-LSTM) and dual-stage attention-based recurrent neural network (DARNN), with real stock data being used for training and evaluation. The model achieves superior performance compared to MI-LSTM and DARNN for stock index prediction on a KOSPI100 dataset.

• Journal of the Ergonomics Society of Korea
• /
• v.23 no.2
• /
• pp.25-36
• /
• 2004

The effects of task characteristics on the relative efficiency of visual display dimension were studied using a simulated tele-robotic task. Through a conventional method of task analysis. the tele-robotic task was divided into two categories: the task element requiring focused attention (FA task) and the task element requiring global attention (CA task). Time-ta-completion data were collected for a total of 120 trials involving 10 participants. For the CA task. there was no significant difference between the multiple two-dimensional (20) display and the three-dimensional (3D) monocular display. For the FA task. however. the multiple 20 display was superior to the 3D monocular display. The results suggest that the characteristics of a given task have a considerable effect on the choice of display dimensionality and the multiple 3D display is better for human operators to effectively judge depth if the task requires frequent use of focused attention.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3458-3478
• /
• 2022

Automatic modulation recognition is the core algorithm in the field of modulation classification in communication systems. Our investigations show that deep learning (DL) based modulation recognition techniques have achieved effective progress for multiple-input multiple-output (MIMO) systems. However, network complexity is always an additional burden for high-accuracy classifications, which makes it impractical. Therefore, in this paper, we propose a low-complexity dimensional interactive lightweight network (DilNet) for MIMO systems. Specifically, the signals received by different antennas are cooperatively input into the network, and the network calculation amount is reduced through the depth-wise separable convolution. A two-dimensional interactive attention (TDIA) module is designed to extract interactive information of different dimensions, and improve the effectiveness of the cooperation features. In addition, the TDIA module ensures low complexity through compressing the convolution dimension, and the computational burden after inserting TDIA is also acceptable. Finally, the network is trained with a penalized statistical entropy loss function. Simulation results show that compared to existing modulation recognition methods, the proposed DilNet dramatically reduces the model complexity. The dimensional interactive lightweight network trained by penalized statistical entropy also performs better for recognition accuracy in MIMO systems.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1081-1092
• /
• 2021

Electroencephalography (EEG) recordings taken during the perception of music tempo contain information that estimates the tempo of a music piece. If information about this tempo stimulus in EEG recordings can be extracted and classified, it can be effectively used to construct a music-based brain-computer interface. This study proposes a novel convolutional recurrent attention model (CRAM) to extract and classify features corresponding to tempo stimuli from EEG recordings of listeners who listened with concentration to the tempo of musics. The proposed CRAM is composed of six modules, namely, network inputs, two-dimensional convolutional bidirectional gated recurrent unit-based sample encoder, sample-level intuitive attention, segment encoder, segment-level intuitive attention, and softmax layer, to effectively model spatiotemporal features and improve the classification accuracy of tempo stimuli. To evaluate the proposed method's performance, we conducted experiments on two benchmark datasets. The proposed method achieves promising results, outperforming recent methods.

• Communications for Statistical Applications and Methods
• /
• v.28 no.1
• /
• pp.39-57
• /
• 2021

Time series prediction is an area of great interest to many people. Algorithms for time series prediction are widely used in many fields such as stock price, temperature, energy and weather forecast; in addtion, classical models as well as recurrent neural networks (RNNs) have been actively developed. After introducing the attention mechanism to neural network models, many new models with improved performance have been developed; in addition, models using attention twice have also recently been proposed, resulting in further performance improvements. In this paper, we consider time series prediction by introducing attention twice to an RNN model. The proposed model is a method that introduces H-attention and T-attention for output value and time step information to select useful information. We conduct experiments on stock price, temperature and energy data and confirm that the proposed model outperforms existing models.

• Proceedings of the KSME Conference
• /
• 2001.06e
• /
• pp.512-517
• /
• 2001

In this study, spin-up flows in a rectangular container are analysed by using three-dimensional computation. In the numerical computation, we use the parallel computer system of PC-cluster type. We compared our results with those obtained by two-dimensional computation. Effect of velocity and vorticity on the flow is studied. The result shows that two-dimensional solution is in good agreement with the 3-D result. Attention is given to the region where the 3-D flow is significant.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.12 s.177
• /
• pp.16-21
• /
• 2005

Photonic crystals, periodic structure with a high refractive index contrast modulation, have recently become very interesting platform for the manipulation of light. The existence of a photonic bandgap, a frequency range in which the propagation of light is prevented in all directions, makes photonic crystal very useful in application where the spatial localization of light is required, for example waveguide, beam splitter, and cavity. However, the fabrication of 3 dimensional photonic crystals is still difficult process. A concept that has recently attracted a lot of attention is a planar photonic crystal based on a dielectric membrane, suspended in the air and perforated with two dimensional lattice of hole. The fabrication of Si master with pillar structure using hot embossing process is investigated for two dimensional, low-index-contrast photonic crystal waveguide. From our research we show that the multiple stamp copy process proved to be feasible and useful.

• Proceedings of the Optical Society of Korea Conference
• /
• 2000.08a
• /
• pp.96-98
• /
• 2000

Room-temperature continuous operation of two-dimensional photonic crystal lasers is achieved at 1.6 ${\mu}{\textrm}{m}$ by using InGaAsP slab-waveguide triangular photonic crystal on top of wet-oxidized aluminum oxide. The main difficulty in the realization of photonic bandgap (OBG) structures has been the nontrivial difficulties in nanofabrication, especially for 3-dimensional PBG structures. Recently, 2-D PBG structures have attracted a great deal of attention due to their simplicity in fabrication and theoretical study as compared to the three-dimensional counterparts [1]. Recently, air-gulfed 2-D slab PBG lasers were reported by Caltech group [2]. However, this air-slab structure is mechanically fragile and thermally unforgiving. Therefore, a new structure that can remove this thermal limitation is dearly sought after for 2-D PBG laser to have practical meaning. In this talk, we report room-temperature continuous operation of 2-D photonic bandgap lasers that are thermally and mechanically stable.

• Journal of the Korean Ceramic Society
• /
• v.56 no.1
• /
• pp.24-36
• /
• 2019

Recently, considerable progress and many breakthroughs have been achieved in the growth of two-dimensional materials, especially transition metal dichalcogenides (TMDCs), which attract significant attention owing to their unique properties originating from their atomically thin layered structure. Chemical vapor deposition (CVD) has shown great promise to fabricate large-scale and high-quality TMDC films with exceptional electronic and optical properties. However, the scalable growth of high-quality TMDCs by CVD is yet to meet industrial criteria. Therefore, growth mechanisms should be unveiled for a deeper understanding and further improvement of growth methods are required. This review summarizes the recent progress in the growth methods of TMDCs through CVD and other modified approaches to gain insights into the growth of large-scale and high-quality TMDCs.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2000.06a
• /
• pp.142-149
• /
• 2000

Two dimensional slow viscous flow around two counter-rotating equal cylinders is Investigated based on Stokes' approximation. An exact formal expression of the stream function is obtained by using the bipolar cylinder coordinates and Fourier series expansion. From the stream function obtained, the streamline patterns around the cylinders are shown and the pressure distribution In the flow field is determined. By Integrating the stress distribution on the cylinder, the force and the moment exerted on the cylinder are calculated. The flow rate through the gap between the two cylinders is determined as the distance between two cylinders vary. It Is also revealed that the velocity at the far field has finite non-zero value. Special attention is directed to the case of very small distances between two cylinders by way of the lubrication theory.