• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.187-194
• /
• 2021

A person's behavioral recognition is the recognition of what a person does according to joint movements. To this end, we utilize computer vision tasks that are utilized in image processing. Human behavior recognition is a safety accident response service that combines deep learning and CCTV, and can be applied within the safety management site. Existing studies are relatively lacking in behavioral recognition studies through human joint keypoint extraction by utilizing deep learning. There were also problems that were difficult to manage workers continuously and systematically at safety management sites. In this paper, to address these problems, we propose a method to recognize risk behavior using only joint keypoints and joint motion information. AlphaPose, one of the pose estimation methods, was used to extract joint keypoints in the body part. The extracted joint keypoints were sequentially entered into the Long Short-Term Memory (LSTM) model to be learned with continuous data. After checking the behavioral recognition accuracy, it was confirmed that the accuracy of the "Lying Down" behavioral recognition results was high.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.605-611
• /
• 2023

Accidents at construction sites have a very high rate of fatalities due to the nature of being prone to severe injury patients. In order to reduce the mortality rate of severely injury patients, quick response is required, and some systems that detect accidents using AI technology and cameras have been devised to respond quickly to accidents. However, since existing accident detection systems use only a single camera, there are blind spots, Thus, they cannot detect all accidents at a construction site. Therefore, in this paper, we present the system that minimizes the detection blind spot by using multiple cameras. Our implemented system extracts feature points from the images of multiple cameras with the YOLO-pose library, and inputs the extracted feature points to a Long Short Term Memory-based recurrent neural network in order to detect accidents. In our experimental result, we confirme that the proposed system shows high accuracy while minimizing detection blind spots by using multiple cameras.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.2
• /
• pp.263-272
• /
• 2022

As a result of climate change, the heatwave and urban heat island phenomena have become more common, and the frequency of heatwaves is expected to increase by two to six times by the year 2050. In particular, the heat sensation index felt by workers at construction sites during a heatwave is very high, and the sensation index becomes even higher if the urban heat island phenomenon is considered. The construction site environment and the situations of construction workers vulnerable to heat are not improving, and it is now imperative to respond effectively to reduce such damage. In this study, satellite imagery, land surface temperatures (LST), and long short-term memory (LSTM) were applied to analyze areas above 33 ℃, with the most vulnerable areas with increased synergistic damage from heat waves and the urban heat island phenomena then predicted. It is expected that the prediction results will ensure the safety of construction workers and will serve as the basis for a construction site early-warning system.

• Wind and Structures
• /
• v.38 no.1
• /
• pp.75-91
• /
• 2024

Reliable wind signal reconstruction can be beneficial to the operational safety of long-span bridges. Non-Gaussian characteristics of wind signals make the reconstruction process challenging. In this paper, non-Gaussian wind signals are converted into a combined prediction of two kinds of features, actual wind speeds and wind angles of attack. First, two decomposition techniques, empirical mode decomposition (EMD) and variational mode decomposition (VMD), are introduced to decompose wind signals into intrinsic mode functions (IMFs) to reduce the randomness of wind signals. Their principles and applicability are also discussed. Then, four artificial intelligence (AI) algorithms are utilized for wind signal reconstruction by combining the particle swarm optimization (PSO) algorithm with back propagation neural network (BPNN), support vector regression (SVR), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM), respectively. Measured wind signals from a bridge site in a deep-cutting gorge are taken as experimental subjects. The results showed that the reconstruction error of high-frequency components of EMD is too large. On the contrary, VMD fully extracts the multiscale rules of the signal, reduces the component complexity. The combination of VMD-PSO-Bi-LSTM is demonstrated to be the most effective among all hybrid models.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.14 no.1
• /
• pp.34-39
• /
• 2014

This paper discusses the 3-level charge pumping (CP) method in planar-type Silicon-Oxide-High-k-Oxide-Silicon (SOHOS) and Silicon-Oxide-Nitride-Oxide-Silicon (SONOS) devices to find out the reason of the degradation of data retention properties. In the CP technique, pulses are applied to the gate of the MOSFET which alternately fill the traps with electrons and holes, thereby causing a recombination current Icp to flow in the substrate. The 3-level charge pumping method may be used to determine not only interface trap densities but also capture cross sections as a function of trap energy. By applying this method, SOHOS device found to have a higher interface trap density than SONOS device. Therefore, degradation of data retention characteristics is attributed to the many interface trap sites.

• Architectural research
• /
• v.25 no.2
• /
• pp.29-40
• /
• 2023

The purpose of this study is to analyze the conflicts caused by the spatial expansion in two types of urban heritage in Seoul. To explain the national and professional orientation found in each spatial transformation, the study brought the concept of 'historic state' and 'epitome,' thereby examining the operating system of the conflicts. Field observations and stakeholder interviews were performed based on literature and historical research. The study results are as follows. ①In the case of Gwanghwamun and Donuimun, the spatial expansion is to find the historic state of the sites. Gwanghwamun with high national status and substance, conflicts show a pattern that spreads to memory conflicts. Donuimun is relatively unknown and has no substance so that a flexible method of digital restoration was applied. ② In the case of Ikseon-dong and Bukchon hanok, they show heterogeneous spatial expansion. The conflicts in relation to this is caused by the epitome of hanok. In Ikseon-dong, illegal installation of structures(non-epitome) is prevalent, while in Bukchon, there was a process of transferring the new basement(non-epitome) as part of the hanok. ③Conflicts in Gwanghwamun can be coordinated by referring to the digital restoration of Donuimun, and conflicts in Ikseon-dong can be resolved by taking Bukchon as a precedent.

• Journal of Korean Institute of Industrial Engineers
• /
• v.36 no.3
• /
• pp.193-202
• /
• 2010

The recommender system is a typical software solution for personalized services which are now popular in e-commerce sites. Most of the existing recommender systems are based on customers' explicit rating data on items (e.g., ratings on movies), and it is only recently that recommender systems based on implicit ratings have been proposed as a better alternative. Implicit ratings of a customer on those items that are clicked but not purchased can be inferred from the customer's navigational and behavioral patterns. In this article, a dimensionality reduction (DR) technique is newly applied to the implicit rating-based recommender system, and its effectiveness is assessed using an experimental e-commerce site. The experimental results indicate that the performance of the proposed approach is superior or at least similar to the conventional collaborative filtering (CF)-based approach unless the number of recommended products is 'large.' In addition, the proposed approach requires less memory space and is computationally more efficient.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.5
• /
• pp.51-60
• /
• 2004

Due to the improvements in circuit design and manufacturing technique, the complexity of a circuit is growing. Since the complexity of a circuit causes high frequency of faults, it is very important to locate faults for improvement of yield and reduction of production cost. But unfortunately it takes a long time to find sites of defects by e-beam proving if the physical level. A fault diagnosis algorithm in the Sate level has meaning to reduce diagnosis time by limiting fault sites. In this paper, we propose an efficient fault diagnosis algorithm in the logical level. Our method is hybrid fault diagnosis algorithm using a new fault dictionary and additional fault simulation which minimizes memory consumption and simulation time.

• Journal of Korean Society of Forest Science
• /
• v.100 no.4
• /
• pp.639-649
• /
• 2011

The purpose of this study aimed to analyze factors on motives to tree burial and choice conditions to tree burial site in order to suggest policy direction for the desirable settlement of tree burial. For those purpose, this study performed questionnaire, targeting 522 visitors of funeral hall all around Korea. As the result, the factors of motives to tree burial were extracted as follows: funeral ceremony progressed along with trees, simplicity, memorial site's easy insurance, environmental friendliness and consideration toward descendants. The factors on choice conditions to tree burial sites were extracted as follows: beauty of natural scenery, emotional mood as a memorial site, convenience, stability and economic feasibility. Based on the results of factor analysis, this study suggested policies related to motives to tree burial as follows: develop various types of tree burial sites, develop a funeral ceremony suitable for tree burial, come into wide use of tree burial as a social welfare service, develop tree burial methods capable of many burials, and improve professionalism to manage tree burial system. In addition, this study proposed related choice conditions to tree burial sites as follows: establish natural forest scenery, convert existing graveyards into tree burial sites, select easily accessible places for tree burial sites, form tree burial sites as places for both rest and memory, and reduce using fee of tree burial site.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.4
• /
• pp.351-360
• /
• 2016

The purpose of this study is to predict visual-spatial working memory performance through the characteristics of an electroencephalogram (EEG) in the resting state. The 31 study participants, middle school students with various to academic performance, were underwent visual-spatial working memory test in the Comprehensive Attention Test (CAT) on December in 2014. Each 7 and 6 participants were divided into an Excellent Working Memory (EWM) group and Poor Working Memory (PWM) group depending on the forward/backward working memory scores. The EEG measurements and analysis of the data from a Brain Function Tester were performed by the two groups. A Mann-Whitney Test was used to examine the statistical differences between them. The activation of high beta (${\beta}H$) at the Fp1 and Fp2 sites in the left and right hemisphere, and that of the low beta (${\beta}L$) in the right hemisphere in the EWM group was significantly higher than that in the PWM group. In conclusion, there is a correlation between the visual-spatial working memory performance and the activation of ${\beta}H$ and ${\beta}L$ in the resting state and a close correlation that of ${\beta}L$ in the right hemisphere in terms of mental activity and faculty. Therefore, the visual-spatial working memory performance can be predicted by the activation of ${\beta}H$ and ${\beta}L$ in the resting state. The activation of EEG can be applied as an assessment tool and provide basis data for visual-spatial working memory performance.