• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.1-14
• /
• 2024

Time-series forecasting is extensively used in the actual world. Recent research has shown that Transformers with a self-attention mechanism at their core exhibit better performance when dealing with such problems. However, most of the existing Transformer models used for time series prediction use the traditional encoder-decoder architecture, which is complex and leads to low model processing efficiency, thus limiting the ability to mine deep time dependencies by increasing model depth. Secondly, the secondary computational complexity of the self-attention mechanism also increases computational overhead and reduces processing efficiency. To address these issues, the paper designs an efficient multi-layer attention-based time-series forecasting model. This model has the following characteristics: (i) It abandons the traditional encoder-decoder based Transformer architecture and constructs a time series prediction model based on multi-layer attention mechanism, improving the model's ability to mine deep time dependencies. (ii) A cross attention module based on cross attention mechanism was designed to enhance information exchange between historical and predictive sequences. (iii) Applying a recently proposed sparse attention mechanism to our model reduces computational overhead and improves processing efficiency. Experiments on multiple datasets have shown that our model can significantly increase the performance of current advanced Transformer methods in time series forecasting, including LogTrans, Reformer, and Informer.

• 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.

• Korean Institute of Interior Design Journal
• /
• v.20 no.4
• /
• pp.101-108
• /
• 2011

When observing an object in a space, a part of it is remembered into our perception in the time for paying attention or conscious observation and it reaches to our visual understanding. In this study, it examined characteristics by each subject through the process of visual understanding by changes in such observation time. The results from this study are summarized as belows: First, through analysis of the observation data focused on the distance between the observed points, it was able to apply those visual theories organized before to the analysis of characteristics of the time for understanding by each subject. Second, there showed big differences in the time for visual understanding by each subject according to changes in the observation time so that it was found that there were big differences according to the characteristics of subject's intention or purpose of the observation of a space. Third, as the number of continuous observation gives an important clue in judgement of how well the space was understood, it was able to compare and organize the mutual characteristics of the time the attention was concentrated, the time observed intentionally and the time understood visually. Fourth, it was found that the shorter subjects gave the intentional observation in observing a space, the longer they spent the time for paying attention, while the less they could understand it visually.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.101-107
• /
• 2020

For Korean language processing, morphological analysis is a critical component that requires extensive work. This morphological analysis can be conducted in an end-to-end manner without requiring a complicated feature design using a sequence-to-sequence model. However, the sequence-to-sequence model has a time complexity of O(n²) for an input length n when using the attention mechanism technique for high performance. In this study, we propose a linear-time Korean morphological analysis model using a local monotonic attention mechanism relying on monotonic alignment, which is a characteristic of Korean morphological analysis. The proposed model indicates an extreme improvement in a single threaded environment and a high morphometric F1-measure even for a hard attention model with the elimination of the attention mechanism formula.

• Journal of Digital Convergence
• /
• v.11 no.10
• /
• pp.731-736
• /
• 2013

Recently attention deficit of children has caused various social problems. Those children who has symptoms like ADHD (Attention Deficit/Hyperactivity Disorder) has to be provided with methods which can enhance their attention level in a child-friendly way such as 3D games. This paper shows a research on how to measure the level of attention for attention deficit children using their favorite 3D games. Firstly, we speculated on the methods about attention measurement used in the medical area. And then we searched measurement variables which can effectively evaluate the level of attention during a game play time. Secondly, we have conducted experiment whether there exists difference about the value of the measurement variables between the two groups, normal children group and attention deficit children group. Those variables are omission error, commission error, average response time, and standard deviation of response time. Though our experiment has only been limited to visual attention level, four measurement variables revealed mutual differences.

• Journal of Korean Society for Quality Management
• /
• v.49 no.4
• /
• pp.569-579
• /
• 2021

Purpose: The purpose of this study is the time series analysis for predicting the yield of crops applicable to each farm using environmental variables measured by smart farms cultivating tomato. In addition, it is intended to confirm the influence of environmental variables using a deep learning model that can be explained to some extent. Methods: A time series analysis was performed to predict production using environmental variables measured at 75 smart farms cultivating tomato in two periods. An LSTM-based encoder-decoder model was used for cases of several farms with similar length. In particular, Dual Attention Mechanism was applied to use environmental variables as exogenous variables and to confirm their influence. Results: As a result of the analysis, Dual Attention LSTM with a window size of 12 weeks showed the best predictive power. It was verified that the environmental variables has a similar effect on prediction through wieghtss extracted from the prediction model, and it was also verified that the previous time point has a greater effect than the time point close to the prediction point. Conclusion: It is expected that it will be possible to attempt various crops as a model that can be explained by supplementing the shortcomings of general deep learning model.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.27 no.2
• /
• pp.155-161
• /
• 2017

When a military vehicle is driven on a cross-country road, the occupants are exposed to vibration at a body resonance. In case that the exposure continues for too long period, the attention ability of the occupant could be affected by the vibration exposure. In the study, it was experimentally tried to find if there is a correlation between degradation of attention and vibration exposure. Two kinds of test among various psychological attention tests were employed, which were selected with considering a situation of carrying out military mission on vehicle. At the result, the searching test for controlled attention showed significant degradation in the accuracy and performance time in case of exposure at the vibration. And the attention degradation appeared to be greater when the vibration exposure increases. The dual task test for divided attention showed the difference between vibration and non-vibration condition, but showed it is insignificant for the attention to degrade by increasing exposure time.

• Journal of Korean Elementary Science Education
• /
• v.39 no.1
• /
• pp.133-144
• /
• 2020

The purpose of this study is to identify the effect of Teacher Participation-oriented Education Program (TPEP) for Elementary School Teachers to Improve Class Expertise in Science Classes with a focus on visual attention. The participants were two elementary school teachers in Seoul and taught science subjects. The lesson topic applied to this study were 'Structure and Function of Our Body' in the second semester of fifth grade and 'Volcano and Earthquake' in the second semester of fourth grade. The mobile eye tracker SMI's ETG 2w, which is a binocular tracking system was used in this study. In this study, the actual practice time, participant's visual attention, visual intake time average, and visual intake time average were analyzed by class phase. The results of the study are as follows. First, as a result of analyzing the actual class execution time, the actual class execution time was almost in line with the lesson plan after the TPEP application. Second, visual attention in the areas related to teaching and learning activities was high after applying TPEP. Factors affecting the progress of the class and cognitive burdens were identified quantitatively and objectively through visual attention. Third, as a result of analyzing the visual intake time average of participants, there was a statistically significant difference in all classes. Fourth, as a result of analyzing the visual intake time average of participants, the results were statistically significant in the introduction(video), activity 1, activity 2, and activity 3 stages in the lecture type class. The Teacher Participation-oriented Education Program (TPEP) for Elementary School Teachers to Improve Class Expertise in Science Classes can extend elementary science class expertise such as self-class analysis, eye tracking, linguistic, gesture, and class design beyond traditional class analysis and consulting.

• Korean Institute of Interior Design Journal
• /
• v.24 no.6
• /
• pp.145-153
• /
• 2015

For this research with the objects of spaces in two department stores which can be referred to as representative facility of commercial space, observation test has carried out to estimate how much visitors rivet their eyes to the display of shops. In addition, to find out what effect the difference among the department types has on the selective attention to space element, the observation time was applied as a medium for estimation. The followings are the result from analyzing the observation frequency and the observation intensity feature of each section where the characteristics of design could be found at attention. First, both images of A and B had concentrative dominant-observation at left shops. In case of Image A, Customers began to observe the right shops very attentively after 25 seconds, and with Image B, the attentive observation at right and left took place alternatively after 35 seconds. In other words, regardless of the characteristics of shop displays, the left shops were observed first while in case of the observation after the early and middle time-frame the characteristics of shops were found to have effects on observation. Second, the normal observation showed some difference among attention sections over time while on the whole both images of A and B had the same highly attentive observation at the middle space. Accordingly, it could be concluded that the middle space was playing a faithful role as background for commercial spaces. Third, the ignorant observation, which is the opposite to the attentive observation, was found different between the images of A and B. When the ignorant observation is considered to have intentionality, it will be possible to set up the display which may attract the attention aggressively by the process of figuring out the characteristics of ignored shops.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.10
• /
• pp.5003-5011
• /
• 2013

This paper measured whether neural and behavior responses to attention-emotion task were reflected to emotion regulation capacities. For this purpose, Nineteen healthy right-handed graduates participated in the emotion-attention task three times for three days. Before and after the negative and positive video clips were shown, the participants performed emotion-attention task. EEG and response time were recorded during emotion-attention task. There was positive correlation between ERP P100 and P300 component. The larger the P100 amplitudes at the specific positions, the longer the P300 latencies at these same positions during attention-emotion task. The longer the P300 latencies at the specific positions, the longer the delay in response time. Also, there is and individual differences in ERP components and response time during attention-emotion integration task. Individuals who had lower amplitude and shorter latency of ERP showed faster response time during attention-emotion task, regardless of the type of video clips. This characteristic was interpreted to the lower emotional controls due to premature response for target identification.