• Smart Structures and Systems
• /
• 제29권4호
• /
• pp.523-533
• /
• 2022

A novel metaheuristic search method, namely black widow optimization (BWO) is employed to increase the accuracy of slope stability analysis. The BWO is a recently-developed optimizer that supervises the training of an artificial neural network (ANN) for predicting the factor of safety (FOS) of a single-layer cohesive soil slope. The designed slope bears a loaded foundation in different distances from the crest. A sensitivity analysis is conducted based on the number of active individuals in the BWO algorithm, and it was shown that the best performance is acquired for the population size of 40. Evaluation of the results revealed that the capability of the ANN was significantly enhanced by applying the BWO. In this sense, the learning root mean square error fell down by 23.34%. Also, the correlation between the testing data rose from 0.9573 to 0.9737. Therefore, the postposed BWO-ANN can be promisingly used for the early prediction of FOS in real-world projects.

• 융합경영연구
• /
• 제11권6호
• /
• pp.1-8
• /
• 2023

Purpose: In the era of the Fourth Industrial Revolution, individuals equipped with fundamental understanding and practical skills in artificial intelligence (AI) are essential. This study aimed to validate the effectiveness of AI education for enhancing AI literacy among business major student. Research design, data and methodology: Data for analyzing the effectiveness of the AI Fundamental Education Program for business major students were collected through surveys conducted at the beginning and end of the semester. Structural equation modeling was employed to perform basic statistical analyses regarding gender, grade, and prior software (SW) education duration. To validate the effectiveness of AI education, seven variables - AI interest, AI perception, data analysis/utilization, AI projects, AI literacy, AI self-efficacy, and AI learning persistence - were defined and derived. Results: All seven operationally defined variables showed statistically significant positive changes. The average differences were observed as follows: 0.47 for AI interest, 0.32 for AI perception, 0.37 for data analysis/utilization, 0.27 for AI projects, 0.25 for AI literacy, 0.39 for AI self-efficacy, and 0.41 for AI learning persistence. Statistically, AI interest exhibited the most substantial average difference. Conclusions: Through this study, the applied AI education was confirmed to enhance learners' overall competencies in AI, proving its utility and effectiveness in AI literacy education for business major students. Future research endeavors should build upon these results, focusing on ongoing studies related to AI education programs tailored to learners from diverse academic backgrounds and conducting continuous efficacy evaluations.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.277-283
• /
• 2023

Vital signals provide essential information regarding the health status of individuals, thereby contributing to health management and medical research. Present monitoring methods, such as ECGs (Electrocardiograms) and smartwatches, demand proximity and fixed postures, which limit their applicability. To address this, Non-contact vital signal measurement methods, such as CW (Continuous-Wave) radar, have emerged as a solution. However, unwanted signal components and a stepwise processing approach lead to errors and limitations in heart rate detection. To overcome these issues, this study introduces an integrated neural network approach that combines noise removal, demodulation, and dominant-frequency detection into a unified process. The neural network employed for signal processing in this research adopts a MLP (Multi-Layer Perceptron) architecture, which analyzes the in-phase and quadrature signals collected within a specified time window, using two distinct input layers. The training of the neural network utilizes CW radar signals and reference heart rates obtained from the ECG. In the experimental evaluation, networks trained on different datasets were compared, and their performance was assessed based on loss and frequency accuracy. The proposed methodology exhibits substantial potential for achieving precise vital signals through non-contact measurements, effectively mitigating the limitations of existing methodologies.

• 보건행정학회지
• /
• 제34권1호
• /
• pp.4-16
• /
• 2024

Smart hospitals involve the use of recent ICT (information and communications technology) technologies to improve healthcare access, efficiency, and effectiveness. Standardization in smart hospital technologies is crucial for interoperability, scalability, policy formulation, quality control, and maintenance. This study reviewed relevant international standards for smart hospitals and the organizations that develop them. Specific attention was paid to robotics in smart hospitals and the potential for standardization in this area. The study used online resources and existing standards to analyze technologies, standards, and practices in smart hospitals. Key technologies of smart hospitals were identified. Relevant standards from ISO (International Organization for Standardization) and IEC (International Electrotechnical Commission) were mapped to each core technology. Korea's leadership in smart hospital technology were highlighted. Approaches for standardizing smart hospitals were proposed. Finally, potential new international standard items for robotics in smart hospitals were identified and categorized by function: sampling, remote operation, delivery, disinfection, and movement tracking/contact tracing. Standardization in smart hospital technologies is crucial for ensuring interoperability, scalability, ethical use of artificial intelligence, and quality control. Implementing international standards in smart hospitals is expected to benefit individuals, healthcare institutions, nations, and industry by improving healthcare access, quality, and competitiveness.

• 한국인공지능학회지
• /
• 제12권2호
• /
• pp.9-16
• /
• 2024

In this study, we delve into the effects of personalization algorithms on the creation of "filter bubbles," which can isolate individuals intellectually by reinforcing their pre-existing biases, particularly through personalized Google searches. By setting up accounts with distinct ideological learnings-progressive and conservative-and employing deep neural networks to simulate user interactions, we quantitatively confirmed the existence of filter bubbles. Our investigation extends to the deployment of an LSTM model designed to assess political orientation in text, enabling us to bias accounts deliberately and monitor their increasing ideological inclinations. We observed politically biased search results appearing over time in searches through biased accounts. Additionally, the political bias of the accounts continued to increase. These results provide numerical evidence for the existence of filter bubbles and demonstrate that these bubbles exert a greater influence on search results over time. Moreover, we explored potential solutions to mitigate the influence of filter bubbles, proposing methods to promote a more diverse and inclusive information ecosystem. Our findings underscore the significance of filter bubbles in shaping users' access to information and highlight the urgency of addressing this issue to prevent further political polarization and media habit entrenchment. Through this research, we contribute to a broader understanding of the challenges posed by personalized digital environments and offer insights into strategies that can help alleviate the risks of intellectual isolation caused by filter bubbles.

• International Journal of Advanced Culture Technology
• /
• 제12권1호
• /
• pp.242-248
• /
• 2024

Contemporary societal and environmental transformations coincide with the emergence of novel mental health challenges. anxiety disorder, a chronic and highly debilitating illness, presents with diverse clinical manifestations. Epidemiological investigations indicate a global prevalence of 5%, with an additional 10% exhibiting subclinical symptoms. Notably, 9% of adolescents demonstrate clinical features. Untreated, anxiety disorder exerts profound detrimental effects on individuals, families, and the broader community. Therefore, it is very meaningful to predict anxiety disorder through machine learning algorithm analysis model. The main research content of this paper is the analysis of the prediction model of anxiety disorder by machine learning algorithms. The research purpose of machine learning algorithms is to use computers to simulate human learning activities. It is a method to locate existing knowledge, acquire new knowledge, continuously improve performance, and achieve self-improvement by learning computers. This article analyzes the relevant theories and characteristics of machine learning algorithms and integrates them into anxiety disorder prediction analysis. The final results of the study show that the AUC of the artificial neural network model is the largest, reaching 0.8255, indicating that it is better than the other two models in prediction accuracy. In terms of running time, the time of the three models is less than 1 second, which is within the acceptable range.

• 농촌계획
• /
• 제24권4호
• /
• pp.57-67
• /
• 2018

We examined the impact of paddy wetland's avian-diversity on the development of the protected horticulture complex. The results of this study were made to propose ecological protected horticulture complex and development direction suitable for avian habitat. The total number of species surveyed was analyzed as 1168 individuals in 11 orders 26 families and 36 generic 48 species. Type average was analyzed as paddy $17.25{\pm}4.83$ species and $74.50{\pm}38.08$ individuals, glass $10.00{\pm}0.82$ species and $46.75{\pm}2.06$ individuals, single $13.75{\pm}7.27$ species and $59.50{\pm}35.34$ individuals, multi $8.75{\pm}0.96$ species and $36.75{\pm}9.29$ individuals. Paddy showed higher species diversity than protected horticulture complex. The average number of species surveyed for one year was glass $14{\pm}2.83$, multi $12{\pm}1.41$, single $18{\pm}11.31$, and paddy $26{\pm}11.31$. The diversity difference was identified as paddy> single> glass and multi. Statistical analysis showed statistical difference of Ciconiiformes. Development of protected horticulture complex causes loss of avian habitat. The diversity index was glass $1.73{\pm}0.07$, multi $1.68{\pm}0.14$, single $1.91{\pm}0.47$, and paddy $2.29{\pm}0.17$. Paddy has a higher species diversity than the protected horticulture complex. For the purpose of ecological protected horticulture complex, detention ponds, artificial wetlands and habitats should be reflected in the design. This should be applied to reclamation areas or large-scale protected horticulture complexes.

• 한국패류학회지
• /
• 제17권1호
• /
• pp.35-44
• /
• 2001

벗굴의 종묘확보 방안을 모색하기 위하여 유생의 대량사육에 의한 인공채묘와 자연채묘율을 조사한 결과는 다음과 같다. 모패에서 방출된 D형 유생 (각장 153.4 $\mu\textrm{m}$, 각고 137.2 $\mu\textrm{m}$)을 3 톤짜리 F.R.R 수조에 5.8 개체/ml의 밀도로 대량 사육한 결과 유생사육 16일 째에 벗굴 유생의 성장률은 각장과 각고가 202.6%, 212.9%로 성장하여 310.9 $\pm$ 9.8 $\mu\textrm{m}$ ,292.2 $\pm$ 9.1 $\mu\textrm{m}$이었으며, 부착시기인 사육 20일 째는227.1%, 241.8%가 성장하여 348.4 $\pm$ 9.1 $\mu\textrm{m}$, 331.7 $\pm$ 9.4 $\mu\textrm{m}$였다. 그리고 16일 째에는 사육 기간 중 일간 사망률이 가장 높은 0.160, 일간생존율은 0.840을 보이면서 생존율은 54.8%였으며, 사육 20일 째의 최종 생존율은 43.2%였다. 굴 패각, 가리비 패각, 피조개 패각 그리고 PVC 조각을 이용한 부착기질별의 인공 채묘율은 32.9%, 24.1%, 16.8%,10.0%로 굴 패각이 32.9% (131.9 개체/패각) 로 가장 높았으며, 단위면적당 부착율도 굴 패각이 2.69 $\pm$ 0.31 개체/$\textrm{cm}^2$로 가장 높게 나타났다. 채묘방법에 따른 치패 부착율은 채묘기질을 수중에 시설한 수하식방법에서 54.2 개체/패각 (1.00 개체/$\textrm{cm}^2$) 보다 패각을 수조저면에 배열하는 바닥식이 83.8 개체/패각 (평균 1.69 개체/$\textrm{cm}^2$) 으로 높은 부착율을 보였다. 자연채묘는 노출보다는 비노출이, 채묘기질은 그물 등 부드러운 기질보다는 견고한 조개 패각을 이용하여 채묘 하는 경우가 높게 나타났으며, 수층별의 자연채묘는 표층보다는 저층에서 부착율이 높게 나타났다. 벗굴의 인공치 패는 부착 후 26일경에 각장 2.38 $\pm$ 0.97 mm, 각고 2.16 $\pm$ 0.86 mm로 성장하였고, 일간 성장률은 각장 3.75-7.69%, 각고 3.23-7.97%로 나타났으며 3개월 후 각각 28.58 $\pm$ 2.39 mm, 31.65 $\pm$ 2.03 mm로 성장하였다. 채표기질에 따른 부착율은 굴 패각, 가리비패각, 피조개패각 그리고 PVC조각에서 각각 10.3, 5.8, 4.0, 1.5개체로 굴 패각에서 가장 높게 나타났다.

• 수산해양교육연구
• /
• 제13권1호
• /
• pp.87-98
• /
• 2001

1. The bottom mean size of the research area had been showed 86.8% in, 13.2% in mud artificial sector, but and 82.4% in mud at comparative sector. 2. The water temperature had been showed $11.2{\sim}12^{\circ}C$ in surface, $10.9^{\circ}C$ in mid layer, $10.6{\sim}10.8^{\circ}C$ in lower layer. also, The salinity had been showed $31.85{\sim}31.95_{psu}$ in surface, $31.82{\sim}31.97_{psu}$ in mid layer, $31.85{\sim}31.97_{psu}$ at lower layer. The transparency was showed 3.6~5.6m. 3. The conservation condition of reefs was partially grooved and buried the lower part of reefs established '95~'96years but was good condition generaly. 4. The attached fauna has been appeared fisheres botanical specise 6, fisheries animate species 5. 5. The lure of fisheres has been appeared 17 species in reefs sector, 10 species in comparative sector(natural fishing ground). 6. The catchs of C.P.U.E by fishery was catched 2.2~3.3 times in reefs sector than the natural fishing ground. but the individuals was much catched in traps. The jumbo type reefs gill netter were much catched in square artificial reefs. The weight of fishery was much captured in jumbo type reefs.

• Fisheries and Aquatic Sciences
• /
• 제15권2호
• /
• pp.117-123
• /
• 2012

The starry flounder Platichthys stellatus, like all flatfish, exhibits conspicuous lateral asymmetry in numerous traits, most obvious of which is the migration of one eye to the other side of the head during metamorphosis. Additional changes related to eye migration include asymmetrical pigmentation, and a behavioral shift from larvae that exhibit upright, open-water swimming to juveniles and adults that lie on the ocean floor, eye side up. However, the morphology of these juveniles has been quite plastic in recent years, a phenomenon which is thought to be related to a diverse suite of semi-intensive and intensive larviculture methods. The cause of morphological abnormalities in the farmed flatfish is poorly understood. In the present study, we observe the features of morphological specificity and abnormality of immature fish (mean total length 23 cm) and survey the occurrence frequency of the specificity and abnormality of juvenile (mean total length 6.70 cm) in artificial culture facility. We find 2 types of abnormality (e.g., albino in ocular side and hypermelanosis in blind side) and 1 type of specificity (e.g., lateral polymorphism). These considerably differ from normal individuals (has sinistral eye and pigmented on only one side) by several characteristics (dextral eye, ocular side albinism, blind side hypermelanosis). The incidences of albinism, hypermelanosis, and body reversal are $10.1{\pm}2.56%$, $91.7{\pm}1.7%$, and $13.1{\pm}1.1%$, respectively. These suggest that these morphometric and morphological differences occur more in artificial environment during and just after metamorphosis.