• Journal of Platform Technology
• /
• 제11권5호
• /
• pp.110-125
• /
• 2023

본 논문에서는 2019년 국내 공항을 기준으로 측정된 시계열 항공기 위치 데이터를 활용하여 국내 공항에 이착륙 시 접근 단계에서의 항공 위험상황 중 Go-Around 및 UOC_D 를 분석하고, 다양한 클러스터링 기반 머신 러닝 기법을 적용하여 국내 항공 데이터에서 가장 알맞은 분석 기법이 무엇인지를 실험을 통해 제시한다. 항공기 위치를 측정하기 위한 센서는 ADS-B를 단일로 사용하였으며, 클러스터링 기법들 중 K-Means, GMM, DBSCAN 등의 알고리즘을 사용하여 이상상황을 분류하기 위한 모델을 설계하였다. 그 중 해외에서는 RF 모델이 가장 나은 성능을 보였으나, 국내 항공 데이터에 대해서는 국내 지형에 특화된 부분을 반영한 GMM이 가장 높은 분류 성능을 보이는 것으로 실험을 통해 확인하였다.

• 한국수정란이식학회지
• /
• 제25권3호
• /
• pp.133-139
• /
• 2010

The purpose of this study was to determine the relationship between conception rate and other parameters (body condition score; BCS, progesterone concentrations and follicle size) before estrus induction with $PGF_2{\alpha}$. The conception rate in cows with (2.75, 2.75 to 3.25 and 3.25), BCS regardless of AI (artificial insemination) time was 47.5, 67.5% and 48.5% at $PGF_2{\alpha}$ injection, respectively. The conception rate regardless of BCS was 59.0% in cows inseminated based on detected estrus, and 46.2% in cows inseminated at 72 to 80 hours (timed artificial insemination, TAI) after $PGF_2{\alpha}$ injection. The conception rate regardless of AI time was 43.0% in cows with low progesterone concentrations (less than 1.0 ng/ml), and 67.5% in cows with high progesterone concentrations (more than 1.0 ng/ml) at $PGF_2{\alpha}$ injection. The conception rate regardless of progesterone concentrations was 59.9% in cows inseminated based on detected estrus, and 48.1% in cows of TAI after $PGF_2{\alpha}$ injection. The conception rate regardless of AI time was 36.0% in cows with small dominant follicles (less than 5 mm), 56.0% in cows between 5 mm to 10 mm of follicle size, and 65.5% in cows with large dominant follicles (more than 10 mm) at $PGF_2{\alpha}$ injection, respectively. The conception rate regardless of follicle size was 57.3% in cows inseminated based on detected estrus, and 47.6% in cows of TAI after $PGF_2{\alpha}$ injection. These results indicated that if the cows with BCS 2.75 to 3.25, active corpus luteum, and/or large dominant follicle (more than 10 mm) are used for estrus induction, the conception rate will be greater.

• 한국수정란이식학회지
• /
• 제33권3호
• /
• pp.149-157
• /
• 2018

The objective of this study was to evaluate the effect of treating dairy cattle with exogenous human chorionic gonadotrophin (hCG), five (5) days post artificial insemination (AI) on serum progesterone (P4) concentration and pregnancy rate. In this experiment, five days after AI, cows were assigned randomly to two groups namely: a) treated group (67) which were administrered with 1500 IU hCG (Chorulon) and b) control group (61), which received no treatment. On day 5, 10, 15 and 20 after the artificial insemination, blood samples from a total of 8 cows (4 from each group) were collected and were analyzed for serum P4 concentration. Cows were detected for estrus according to standing heat by visual observation. Cows that were detected still in estrus after days 18-24 were re-inseminated and recorded as not pregnant (open). Pregnancy diagnosis was conducted by ultrasonographic examination and transrectal palpation of the uterus on approximately 60 days in cows that observed to be not in estrus. The conception rate in hCG treated and control groups were 52.5 and 36.1%, respectively. The results proved that there were no significant differences in conception rate between two groups (p=0.0568). However, pregnancy rates were reduced by hCG treatment. Average serum P4 concentrations did not differ between Hcg-treated and control groups on day 5 (0.377 versus 0.375 ng/ml). On day 20 serum P4 concentrations were greater in the treated group compared with the control group (3.085 versus 2.010 ng/ml). The treatment with hCG seemed to increase P4 level compared with the control. In conclusion, the results of this study showed that 1500 IU of hCG administered on 5 day post AI increased conception rate in dairy cows. This was supported by the results on serum P4 concentration which was greater in hCG treated group.

• 한국수정란이식학회지
• /
• 제25권4호
• /
• pp.237-245
• /
• 2010

Only an optimum number of viable spermatozoa in a frozen-thawed insemination dose can ensure conception at artificial insemination (AI). We report here the percentages of normal, abnormal and viable spermatozoa present in the frozen-thawed semen of 20 Black Bengal bucks used for commercial AI. Bucks in this experiment were of 19.3~46.1 months old and 25~42 kg body weight. Four semen straws (0.25 ml) from each buck were collected for evaluation of their kinetic parameters. Scrotal circumference was measured by using a scrotal tape, sperm motility was estimated on eye estimation and sperm concentration was determined by using a haemocytometer. Sperm morphology was studied in paraformaldehyde fixed spermatozoa under differential interference contrast (DIC) microscope. To determine the proportion of live (plasma membrane intact) spermatozoa, semen was stained with SYBR-14 and propidium iodide and examined under fluorescent microscope. Scrotal circumference, post-thaw sperm motility, sperm concentration per insemination dose and proportion of normal spermatozoa were $21.5{\pm}0.7\;cm$, $43.5 {\pm}5.4%$, $83.5{\pm}6.7$ million and $88.3{\pm}4.1%$, respectively. The percentages of spermatozoa with head shape and acrosome abnormalities were lower ($2.7{\pm}1.1$ and $1.4{\pm}1.3$, respectively), whereas higher percentages of abnormalities ($7.0{\pm}1.8$) were observed in mid piece and tail portion. The proportion of live spermatozoa was $28.5{\pm}5.4$. It is concluded that although a good number of morphologically normal spermatozoa are present in the insemination dose, the proportion of live spermatozoa is low, which warrants further improvements of buck semen freezing procedures to ensure good quality at AI.

• 한국임상수의학회지
• /
• 제24권3호
• /
• pp.337-341
• /
• 2007

This study determined the effect of postpartum intrauterine infusion of povidone-iodine solution on the subsequent reproductive performance in dairy cows. Six hundred and fifty-eight dairy cows that were around week 4 postpartum were randomly divided into two groups: (1) Cows in treated group received an intrauterine infusion of 100 to 150 ml 2% povidone-iodine solution (treated group, n=269), or (2) Cows that received no treatment were served as the controls (control group, n=389). The cows were bred at observed estrus more than 50 days after calving. Artificial insemination (AI) was done according to the a.m.-p.m. rule. The conception to AI was determined per rectum 60 days after AI by both ultrasonographical observation and manual palpation. The intervals from calving to first service and conception ($94.2{\pm}2.7$ and $144.1{\pm}4.1$ days vs. $88.0{\pm,}2.1$ and $143.5{\pm}4.6$ days, respectively), number of services per conception ($2.0{\pm}0.1$ vs. $2.1{\pm}0.1$), and cumulative pregnancy rates within 90 and 150 days postpartum (31.9 and 61.7% vs. 29.7 and 62.1%) did not differ between the control and treated groups (P>0.05), while conception rate at first service was lower (P<0.05) in the treated group (40.5%) than in the control group (49.4%). Additionally, we could not find any effect of intrauterine infusion of povidone-iodine solution according to cow parity or calving season on the reproductive performance. These results indicate that intrauterine infusion of povidone-iodine solution at week 4 postpartum does not affect the subsequent reproductive performance in dairy cows.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권7호
• /
• pp.2668-2717
• /
• 2021

Demands for high-speed wireless data services grow rapidly. It is a big challenge to increasing the network capacity operating on licensed spectrum resources. Unlicensed spectrum cellular networks have been proposed as a solution in response to severe spectrum shortage. Licensed Assisted Access (LAA) was standardized by 3GPP, aiming to deliver data services through unlicensed 5 GHz spectrum. Furthermore, the 3GPP proposed 5G New Radio-Unlicensed (NR-U) study item. On the other hand, artificial intelligence (AI) has attracted enormous attention to implement 5G and beyond systems, which is known as Intelligent Radio (IR). To tackle the challenges of unlicensed spectrum networks in 4G/5G/B5G systems, a lot of works have been done, focusing on using Machine Learning (ML) to support resource allocation in LTE-LAA/NR-U and Wi-Fi coexistence environments. Generally speaking, ML techniques are used in IR based on statistical models established for solving specific optimization problems. In this paper, we aim to conduct a comprehensive survey on the recent research efforts related to unlicensed cellular networks and IR technologies, which work jointly to implement 5G and beyond wireless networks. Furthermore, we introduce a positioning assisted LTE-LAA system based on the difference in received signal strength (DRSS) to allocate resources among UEs. We will also discuss some open issues and challenges for future research on the IR applications in unlicensed cellular networks.

• 한국분말재료학회지
• /
• 제31권2호
• /
• pp.137-145
• /
• 2024

In order to predict the process window of laser powder bed fusion (LPBF) for printing metallic components, the calculation of volumetric energy density (VED) has been widely calculated for controlling process parameters. However, because it is assumed that the process parameters contribute equally to heat input, the VED still has limitation for predicting the process window of LPBF-processed materials. In this study, an explainable machine learning (xML) approach was adopted to predict and understand the contribution of each process parameter to defect evolution in Ti alloys in the LPBF process. Various ML models were trained, and the Shapley additive explanation method was adopted to quantify the importance of each process parameter. This study can offer effective guidelines for fine-tuning process parameters to fabricate high-quality products using LPBF.

• The Korean Journal of Pain
• /
• 제11권1호
• /
• pp.81-85
• /
• 1998

Background: Continuous caudal epidural block is a useful method in postoperative pain control after perianal surgery. But caudal epidural block has the potential of developing adverse effects such as urinary retention. The goal of this study is to evaluate the analgesic and adverse effect of bupivacaine with fentanyl through continuous caudal epidural block in relation to the concentration of bupivacaine. Methods: We divided the patients randomly into two groups. For group I(n=25) postoperative pain was controlled by continuous caudal epidural infusion at the rate of 4 ml/hr of 0.0625% bupivacaine with 3 ${\mu}g$/ml fentanyl: group II(n=14), 0.125% bupivacaine with 3 ${\mu}g$/ml fentanyl, respectively, for duration of 48 hours via epidural catheter. We evaluated pain scores with visual analogue scales at 30 mins, 6 hrs, 12 hrs, 24 hrs and 48 hrs after the operation and the incidence of adverse effect, especially urinary retention, for each group. Results: There were no significant differences in the pain score between group I and II. Urinary retention developed in 9 patients(36%) of group I, and 11 patients (78.6%) of group II. Other adverse effects such as pruritus, nausea, vomiting and respiratory depression developed in few patients. Conclusions: While performing continuous caudal epidural block with mixture of bupivacaine and fentanyl after the perianal surgery, we conclude 0.0625% bupivacaine solution is preferable to 0.125% bupivacaine solution because 0.0625% solution resulted in satisfactory analgesia with minimal incidence of adverse effect.

• 융합정보논문지
• /
• 제11권3호
• /
• pp.1-6
• /
• 2021

매치 3 퍼즐 게임들은 주로 MCTS(Monte Carlo Tree Search) 알고리즘을 사용하여 자동 플레이를 구현하였지만 MCTS의 느린 탐색 속도로 인해 MCTS와 DNN(Deep Neural Network)을 함께 적용하거나 강화학습으로 인공지능을 구현하는 것이 일반적인 경향이다. 본 연구에서는 매치 3 게임 개발에 주로 사용되는 유니티3D 엔진과 유니티 개발사에서 제공해주는 머신러닝 SDK를 이용하여 PPO(Proximal Policy Optimization) 알고리즘을 적용한 강화학습 에이전트를 설계 및 구현하여, 그 성능을 확인해본 결과, 44% 정도 성능이 향상되었음을 확인하였다. 실험 결과 에이전트가 게임 규칙을 배우고 실험이 진행됨에 따라 더 나은 전략적 결정을 도출 해 낼 수 있는 것을 확인할 수 있었으며 보통 사람들보다 퍼즐 게임을 더 잘 수행하는 결과를 확인하였다. 본 연구에서 설계 및 구현한 에이전트가 일반 사람들보다 더 잘 플레이하는 만큼, 기계와 인간 플레이 수준 사이의 간극을 조절하여 게임의 레벨 디지인에 적용된다면 향후 빠른 스테이지 개발에 도움이 될 것으로 기대된다.

• Journal of Platform Technology
• /
• 제11권3호
• /
• pp.45-55
• /
• 2023

본 논문은 한국 영화 산업의 의사 결정자들이 온라인상에서의 영화의 흥행을 극대화할 수 있도록 지원하는 데 도움을 주고자 역대 박스오피스 영화를 수집하여 영화를 유형별로 군집화하고, 유형별 온라인 박스오피스를 예측하는 모델을 제시한다. 이를 위해 먼저 다양한 특성을 고려하여 영화의 흥행 요인을 식별하고, 계산 효율성을 고려하여 특성 차원을 줄인다. 다음으로 영화의 유형을 체계적으로 분류하고, 유형별 온라인 박스오피스를 예측하며 흥행에 이바지한 요소를 분석한다. 이때, AutoML (Automated Machine Learning) 기법을 활용함으로써 다양한 기계학습 알고리즘을 자동으로 구성하고, 문제에 최적화된 알고리즘을 선택함으로써 여러 알고리즘을 쉽게 시도 및 선택한다. 이를 통해 정보화된 판단을 내릴 수 있는 기반을 제공하고, 영화 산업의 더 나은 성과를 도모하는 데 이바지할 것으로 기대할 수 있다.