• Journal of Wetlands Research
• /
• v.21 no.2
• /
• pp.173-180
• /
• 2019

This study was conducted to understand factors affecting TSS and heavy metals transport on the road, parking lot and roof. During storm events, heavy metals, which were mostly attached to TSS, were also transported when TSS was washed off in the road, parking lot and roof. This finding may be supported by the significant correlations between TSS load and total and soluble heavy metals load including Cr, Fe, Cu, and Pb (Pearson r value: 0.52 to 0.73; probability p value<0.01). Generation and transport of TSS and heavy metals were greater in the road and parking lot compared to the roof due to vehicular activities, slope and greater catchment areas of these sites. It was found that TSS transport during peak flows of storm events ranges from 65% to 75% implying that by controlling peak flows, TSS transportation to nearby water bodies may be decreased. Depending on the target TSS and heavy metal reduction, sizing of low impact development (LID) technologies and green infrastructures (GI) such as infiltration trench, tree box filter, and rain garden may be calculated. Future researchers were recommended to assess the limitations of the systems and determine the design considerations for these types of facilities.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.6
• /
• pp.481-495
• /
• 2020

After the resonator on the basis of the wave-filter theory was designed to control the waves with a specific frequency range surging into the harbor, the several case with the use of resonator have been reported in some part of sea, including the port of Long Beach, USA, and yacht harbor at Rome, Italy in order to control the long-period wave motion from the vessels. Recently, the utility and applicability of the resonator has been sufficiently verified in respect of the control of tsunami approximated as the solitary wave and/or the super long-period waves. However, the case with the application of tsunami in the real sea have not been reported yet. In this research, the respective case with the use of existing resonator at the port of Mukho and Imwon located in the eastern coast of South Korea were studied by using the numerical analysis through the COMCOT model adapting the reduction rate of 1983 Central East Sea tsunami and 1993 Hokkaido Southwest off tsunami. Consequently, the effectiveness of resonator against tsunami in the real sea was confirmed through the reduction rate of maximum 40~50% at the port of Mukho, and maximum 21% at the port of Imwom, respectively. In addition, it was concluded that it is necessary to study about the various case with application of different shape, arrangement, and size of resonator in order to design the optimal resonator considering the site condition.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.801-806
• /
• 2022

In the modern era, the necessity of color capability in the digital era is the demand of the era, and research on improving color practice on the subdivided digital four areas that are not in the existing practice is needed. For digital majors who are difficult to solve in existing paint color practice, classes in digital color practice in four more specialized areas are needed, and the use of efficient artificial intelligence was studied for classes in digitized color and color sense. In this paper, we tried to show the expansion of the color practice area by suggesting digital color practice and color matching method based on Photoshop artificial intelligence and big data technology that existing color and color matching were practice that only CMYK could do. In addition, based on the color quantification data of individual users provided by the latest Adobe Sceney program artificial intelligence, the purpose of the practice was to improve learners' predictions of actual color combinations and random colors using filter effects. In conclusion, it is a study on the use of programs that eliminate ambiguity in the mixing process of existing paint practice, secure digital color details, and propose a practical method that can provide effective learning methods for beginners and intermediates to develop their senses through artificial intelligence support. The Adobe program practice method necessary for coloration and main color through theoretical consideration and improvement of teaching skills that are better than existing paint practice were presented.

• Imaging Science in Dentistry
• /
• v.53 no.3
• /
• pp.193-198
• /
• 2023

Purpose: Artificial intelligence (AI) is poised to play a major role in medical diagnostics. Periodontal disease is one of the most common oral diseases. The early diagnosis of periodontal disease is essential for effective treatment and a favorable prognosis. This study aimed to assess the effectiveness of AI in diagnosing periodontal bone loss through radiographic analysis. Materials and Methods: A literature search involving 5 databases (PubMed, ScienceDirect, Scopus, Health and Medical Collection, Dentistry and Oral Sciences) was carried out. A specific combination of keywords was used to obtain the articles. The PRISMA guidelines were used to filter eligible articles. The study design, sample size, type of AI software, and the results of each eligible study were analyzed. The CASP diagnostic study checklist was used to evaluate the evidence strength score. Results: Seven articles were eligible for review according to the PRISMA guidelines. Out of the 7 eligible studies, 4 had strong CASP evidence strength scores (7-8/9). The remaining studies had intermediate CASP evidence strength scores (3.5-6.5/9). The highest area under the curve among the reported studies was 94%, the highest F1 score was 91%, and the highest specificity and sensitivity were 98.1% and 94%, respectively. Conclusion: AI-based detection of periodontal bone loss using radiographs is an efficient method. However, more clinical studies need to be conducted before this method is introduced into routine dental practice.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.8
• /
• pp.189-199
• /
• 2017

The purpose of this study is to compare the grid usage that is common to Leonardo da Vinci and J.N.L. Durand in the process of designing the architectural plan. In the days when there was no proper measurement tool, auxiliary lines relied entirely on the architect's personal mindset and design convenience. Therefore, it is considered that studying the auxiliary lines drawn by the architects will be useful for studying the human perception system. Among auxiliary lines, the grid has been used by many architects. Leonardo da Vinci and J.N.L. Durand are famous. However, these two show a significant different grid usage. As auxiliary grid and space ares added the center of the Leonardo da Vinci grid continues to move, and the grid in his sketch is becoming a building space itself. So I call it 'conceptual grid'. In the case of J.N.L. Durand, the one center of the grid is always at the center of the drawing. That is, all the positions of the grid can be determined in phase around a common point, and all of the same specifications are assumed. The grid is a kind of filter. That's why his grid is a visual abstraction of the process of thinking. In this paper, I will call the grid of J.N.L. Durand as 'abstract grid'.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.552-558
• /
• 2014

This paper suggests how to design a ZigBee-chip-based communication module to remotely measure radiation level. The suggested communication module consists of two control processors for the chip as generally required to configure a ZigBee system, and one chip module to configure a ZigBee RF device. The ZigBee-chip-based communication module for remote radiation measurement consists of a wireless communication controller; sensor and high-voltage generator; charger and power supply circuit; wired communication part; and RF circuit and antenna. The wireless communication controller is to control wireless communication for ZigBee and to measure radiation level remotely. The sensor and high-voltage generator generates 500 V in two consecutive series to amplify and filter pulses of radiation detected by G-M Tube. The charger and power supply circuit part is to charge lithium-ion battery and supply power to one-chip processors. The wired communication part serves as a RS-485/422 interface to enable USB interface and wired remote communication for interfacing with PC and debugging. RF circuit and antenna applies an RLC passive component for chip antenna to configure BALUN and antenna impedance matching circuit, allowing wireless communication. After configuring the ZigBee-chip-based communication module, tests were conducted to measure radiation level remotely: data were successfully transmitted in 10-meter and 100-meter distances, measuring radiation level in a remote condition. The communication module allows an environment where radiation level can be remotely measured in an economically beneficial way as it not only consumes less electricity but also costs less. By securing linearity of a radiation measuring device and by minimizing the device itself, it is possible to set up an environment where radiation can be measured in a reliable manner, and radiation level is monitored real-time.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.9
• /
• pp.595-602
• /
• 2013

WiFi fingerprinting is well known as an effective localization technique used for indoor environments. However, this technique requires a large amount of pre-built fingerprint maps over the entire space. Moreover, due to environmental changes, these maps have to be newly built or updated periodically by experts. As a way to avoid this problem, crowd-sourced fingerprint mapping attracts many interests from researchers. This approach supports many volunteer users to share their WiFi fingerprints collected at a specific environment. Therefore, crowd-sourced fingerprinting can automatically update fingerprint maps up-to-date. In most previous systems, however, individual users were asked to enter their positions manually to build their local fingerprint maps. Moreover, the systems do not have any principled mechanism to keep fingerprint maps clean by detecting and filtering out erroneous fingerprints collected from multiple users. In this paper, we present the design of a crowd-sourced fingerprint mapping and localization(CMAL) system. The proposed system can not only automatically build and/or update WiFi fingerprint maps from fingerprint collections provided by multiple smartphone users, but also simultaneously track their positions using the up-to-date maps. The CMAL system consists of multiple clients to work on individual smartphones to collect fingerprints and a central server to maintain a database of fingerprint maps. Each client contains a particle filter-based WiFi SLAM engine, tracking the smartphone user's position and building each local fingerprint map. The server of our system adopts a Gaussian interpolation-based error filtering algorithm to maintain the integrity of fingerprint maps. Through various experiments, we show the high performance of our system.

• Clinical and Experimental Reproductive Medicine
• /
• v.26 no.3
• /
• pp.407-417
• /
• 1999

Objective: Mammalian follicle cells are the most important somatic cells which help oocytes grow, mature and ovulate and thus are believed to provide oocytes with various functional and structural components. In the present study we have examined whether cumulus or granulosa cells might playa role in establishing the plasma membrane structure of mouse oocytes during meiotic maturation. Design: In particular the differential resistances of mouse oocytes against chymotrypsin treatment were examined following culture with or without cumulus or granulosa cells, or in these cell-conditioned media. Results: When mouse denuded oocytes, freed from their surrounding cumulus cells, were cultured in vitro for $17{\sim}18hr$ and then treated with 1% chymotrypsin, half of the oocytes underwent degeneration within 37.5 min ($t_{50}=37.5{\pm}7.5min$) after the treatment. In contrast cumulus-enclosed oocytes showed $t_{50}=207.0$. Similarly, when oocytes were co-cultured with cumulus cells which were not associated with the oocytes but present in the same medium, the $t_{50}$ of co-cultured oocytes was $177.5{\pm}13.1min$. Furthermore, when oocytes were cultured in the cumulus cell-conditioned medium, $t_{50}$ of these oocytes was $190.0{\pm}10.8min$ whereas $t_{50}$ of the oocytes cultured in M16 alone was $25.5{\pm}2.9min$. Granulosa cell-conditioned medium also increased the resistance of oocytes against chymotrypsin treatment such that $t_{50}$ of oocytes cultured in granulosa cell-conditioned medium was $152.5{\pm}19.0min$ while that of oocytes cultured in M16 alone was $70.0{\pm}8.2min$. To see what molecular components of follicle cell-conditioned medium are involved in the above effects, the granulosa cell-conditioned medium was separated into two fractions by using Microcon-10 membrane filter having a 10 kDa cut-off range. When denuded oocytes were cultured in medium containing the retentate, $t_{50}$ of the oocytes was $70.0{\pm}10.5min$. In contrast, $t_{50}$ of the denuded oocytes cultured in medium containing the filtrate was $142.0{\pm}26.5min$. $T_{50}$ of denuded oocytes cultured in medium containing both retentate and filtrate was $188.0{\pm}13.6min$. However, $t_{50}$ of denuded oocytes cultured in M16 alone was $70.0{\pm}11.0min$ and that of oocytes cultured in whole granulosa cell-conditioned medium was $156.0{\pm}27.9min$. When surface membrane proteins of oocytes were electrophoretically analyzed, no difference was found between the protein profiles of oocytes cultured in M16 alone and of those cultured in the filtrate. Conclusions: Based upon these results, it is concluded that mouse follicle cells secrete a factor(s) which enhance the resistance of mouse oocytes against a proteolytic enzyme treatment. The factor appears to be a small molecules having a molecular weight less than 10 kDa.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.