• Journal of Life Science
• /
• v.33 no.6
• /
• pp.490-497
• /
• 2023

Pregnant women may need to take medications to treat preexisting diseases or diseases that develop during pregnancy. However, some drugs may be fetotoxic and lead to, for example, teratogenicity and growth retardation. Predicting the fetotoxicity of drugs is thus important for the health of the mother and fetus. The fetotoxicity of many drugs has not been established because various challenges hinder the ability of researchers to determine their fetotoxicity. The need exists for in silico-based fetotoxicity assessment models, as they can modernize the testing paradigm, improve predictability, and reduce the use of animals and the costs of fetotoxicity testing. In this study, we collected data on the fetotoxicity of drugs and constructed fetotoxicity prediction models based on various machine learning algorithms. We optimized the models for more precise predictions by tuning the hyperparameters. We then performed quantitative performance evaluations. The results indicated that the constructed machine learning-based models had high performance (AUROC >0.85, AUPR >0.9) in fetotoxicity prediction. We also analyzed the feature importance of our model's predictions, which could be leveraged to identify the specific features of drugs that are strongly associated with fetotoxicity. The proposed model can be used to prescreen drugs and drug candidates at a lower cost and in less time. It provides a predictive score for fetotoxicity risk, which may be beneficial in the design of studies on fetotoxicity in human pregnancy.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.401-410
• /
• 2023

In this paper, we propose optimization methods for implementing SPARKLE, one of the NIST LWC finalists, on a 64-bit ARMv8 processor. The proposed methods consist of two approaches: an implementation using ARM A64 instructions and another using NEON ASIMD instructions. The A64-based implementation is optimized by performing register scheduling to efficiently utilize the available registers on the ARMv8 architecture. By utilizing the optimized A64-based implementation, we can achieve speeds that are 1.69 to 1.81 times faster than the C reference implementation on a Raspberry Pi 4B. The ASIMD-based implementation, on the other hand, optimizes data by parallelizing the ARX-boxes to perform more than three of them concurrently through a single vector instruction. While the general speed of the optimized ASIMD-based implementation is lower than that of the A64-based implementation, it only slows down by 1.2 times compared to the 2.1 times slowdown observed in the A64-based implementation as the block size increases from SPARKLE256 to SPARKLE512. This is an advantage of the ASIMD-based implementation. Therefore, the ASIMD-based implementation is more efficient for SPARKLE variant block cipher or permutation designs with larger block sizes than the original SPARKLE, making it a useful resource.

• Knowledge Management Research
• /
• v.24 no.2
• /
• pp.87-115
• /
• 2023

This study aims to examine the causal relationships between sales and employment for public technology-based startups. Although there is a limit to statistical generalization due to the poor understanding of the actual conditions of public technology start-up companies, these companies were analyzed by classifying them into high-growth companise, potential growth companies, and other companies. In order to understand the causal relationship, and to estimate the time required to be effective, panel vector autoregression was applied. As a result, the performance creation mechanism was identified as government supoort and private investment was mutually causal with employment, sales did not cause employment, and employment caused sales. In other words, it was found that employment plays an mediator role in public technology based startups' performance mechanism. In addition, private investment had the effect of improving employment and sales in the short time than governments support, and showed that firms with high employment can attract government support and private investment. This study are academically meaningful in that they empirically revealed the process of performance creation, whereas previous studies had only shown whether there was an effect on performance. It also has a policy contribution by suggesting the need for effective policy promotion by considering the 'employment' factor, such as human resource support, as more important.

• Communications of Mathematical Education
• /
• v.37 no.1
• /
• pp.65-84
• /
• 2023

The method of Lagrange multipliers, one of the most fundamental algorithms for solving equality constrained optimization problems, has been widely used in basic mathematics for artificial intelligence (AI), linear algebra, optimization theory, and control theory. This method is an important tool that connects calculus and linear algebra. It is actively used in artificial intelligence algorithms including principal component analysis (PCA). Therefore, it is desired that instructors motivate students who first encounter this method in college calculus. In this paper, we provide an integrated perspective for instructors to teach the method of Lagrange multipliers effectively. First, we provide visualization materials and Python-based code, helping to understand the principle of this method. Second, we give a full explanation on the relation between Lagrange multiplier and eigenvalues of a matrix. Third, we give the proof of the first-order optimality condition, which is a fundamental of the method of Lagrange multipliers, and briefly introduce the generalized version of it in optimization. Finally, we give an example of PCA analysis on a real data. These materials can be utilized in class for teaching of the method of Lagrange multipliers.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1A
• /
• pp.31-43
• /
• 2009

In this study, the numerical method is presented, which can consider the various train types and can solve the equations of motion for a vehicle-bridge interaction analysis by non-iteration procedure through formulating the coupled equations of motion. The coupled equations of motion for the vehicle-bridge interaction are solved by the Newmark ${\beta}$ of a direct integration method, and by composing the effective stiffness matrix and the effective force vector according to a analysis step, those can be solved with the same manner of the solving procedure of equilibrium equations in static analysis. Also, the effective stiffness matrix is reconstructed by the Skyline method for increasing the analysis effectiveness. The Cholesky's matrix decomposition scheme is applied to the analysis procedure for minimizing the numerical errors that can be generated in directly calculating the inverse matrix. The equations of motion for the conventional trains are derived, and the numerical models of the conventional trains are idealized by a set of linear springs and dashpots with 16 degrees of freedom. The bridge models are simplified by the 3 dimensional space frame element which is based on the Euler-Bernoulli theory. The rail irregularities of vertical and lateral directions are generated by the PSD functions of the Federal Railroad Administration (FRA). The results of the vehicle-bridge interaction analysis are verified by the experimental results for the railway plate girder bridges of a span length with 12 m, 18 m, and the experimental and analytical data are applied to the low pass filtering scheme, and the basis frequency of the filtering is a 2 times of the 1st fundamental frequency of a bridge bending.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.11 no.2
• /
• pp.175-188
• /
• 2009

When a new tunnel is excavated by the drill and blast method near pre-existing underground structures or tunnels due to the region restricted condition such as urban area, the ground will be relaxed by the excavation. In this case, issues can be created in terms of stability of pre-existing underground structures. One of major factors determining the stability of pre-existing underground structures can be a separation distance between pre-existing underground structures and a newly excavated tunnel. The region of ground relaxation defined by the plastic zone due to new excavation can be varied by separation distance. In this study, in other to estimate an influence of new tunnel excavation in terms of separation distance on the stability of pre-existing large pipelines, two-dimensional scaled model tests using plaster were performed for six models which have a different separation distance, The results show that based on the analysis of induced displacement during tunnel construction, the displacement decreases as the separation distance between large pipeline and new tunnel is increased until the distance is 2.5 times of pipeline diameter. Beyond this point, however, the displacement has become stabilized.

• Economic Analysis
• /
• v.25 no.2
• /
• pp.132-176
• /
• 2019

We use a time-varying parameter vector auto regression (TVP-VAR) model to understand the impact of U.S. monetary policy normalization on Korean financial markets and capital accounts. The U.S. monetary policy is represented by the federal funds rate, term premium and credit spread. During the U.S. monetary contraction period of 2004 to 2006, changes in the federal funds rate presented negative pressure on Korean financial markets. The changes in federal funds rate also led to a simultaneous contraction in inward and outward capital flows. However, the effects of a federal funds rate shock has been reduced since 2015. On the other hand, the effects of U.S. term premiums is getting stronger after the period of quantitative easing (QE). The influence of the U.S. credit spread also significantly increased after the global financial crisis. Simulation results show that a rise in the U.S. credit spread, which can be triggered by a contractionary monetary policy, can pose a larger adverse impact on the Korean economy than a rise in the federal funds rate itself. As for capital flows, a U.S. monetary policy contraction causes an outflow of foreign investment, but the repatriation of overseas investment by Korean residents can offset this outflow.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.28 no.4
• /
• pp.121-132
• /
• 2023

Marine heatwaves (MHWs), referring to anomalously high sea surface temperatures, have drawn significant attention from marine scientists due to their broad impacts on the surface marine ecosystem, fisheries, weather patterns, and various human activities. In this study, we examined the impact of the distribution of Changjiang diluted water (CDW), a significant factor causing oceanic property changes in the East China Sea (ECS) during the summer, on MHWs. The surface salinity distribution in the ECS indicates that from June to August, the eastern extension of the CDW influences areas as far as Jeju Island and the Korea Strait. In September, however, the CDW tends to reside in the Changjiang estuary. Through the Empirical Orthogonal Function analysis of the cumulative intensity of MHWs during the summer, we extracted the loading vector of the first mode and its principal component time series to conduct a correlation analysis with the distribution of the CDW. The results revealed a strong negative spatial correlation between areas of the CDW and regions with high cumulative intensity of MHWs, indicating that the reinforcement of stratification due to low-salinity water can increase the intensity and duration of MHWs. This study suggests that the CDW may still influence the spatial distribution of MHWs in the region, highlighting the importance of oceanic environmental factors in the occurrence of MHWs in the waters surrounding the Korean Peninsula.

• Journal of the Korean Society for information Management
• /
• v.40 no.4
• /
• pp.307-327
• /
• 2023

To analyze the impact of word embedding on book titles, this study utilized word embedding models (Word2vec, GloVe, fastText) to generate embedding vectors from book titles. These vectors were then used as classification features for automatic classification. The classifier utilized the k-nearest neighbors (kNN) algorithm, with the categories for automatic classification based on the DDC (Dewey Decimal Classification) main class 300 assigned by libraries to books. In the automatic classification experiment applying word embeddings to book titles, the Skip-gram architectures of Word2vec and fastText showed better results in the automatic classification performance of the kNN classifier compared to the TF-IDF features. In the optimization of various hyperparameters across the three models, the Skip-gram architecture of the fastText model demonstrated overall good performance. Specifically, better performance was observed when using hierarchical softmax and larger embedding dimensions as hyperparameters in this model. From a performance perspective, fastText can generate embeddings for substrings or subwords using the n-gram method, which has been shown to increase recall. The Skip-gram architecture of the Word2vec model generally showed good performance at low dimensions(size 300) and with small sizes of negative sampling (3 or 5).

• Journal of the Korean Society of Radiology
• /
• v.17 no.7
• /
• pp.1067-1073
• /
• 2023

Breast cancer is one of the top three most common cancers in modern women, and the incidence rate is increasing rapidly. Breast cancer has a high family history and a mortality rate of about 15%, making it a high-risk group. Therefore, breast cancer needs constant management after an early examination. Among the various equipment that can diagnose cancer, ultrasound has the advantage of low risk and being able to diagnose in real time. In addition, breast ultrasound will be more useful because Asian women's breasts are denser and less sensitive. However, the results of ultrasound examinations vary greatly depending on the technology of the examiner. To compensate for this, we intend to incorporate motion tracking technology. Motion tracking is a technology that specifies and analyzes a location according to the movement of an object in a three-dimensional space. Therefore, real-time control is possible, and complex and fast movements can be recorded in real time. We would like to present the production of an ultrasound examination guide using these advantages.