• International Journal of Computer Science & Network Security
• /
• v.21 no.1
• /
• pp.220-225
• /
• 2021

Human population growth rate is an important parameter for real-world planning. Common approaches rely upon fixed parameters like human population, mortality rate, fertility rate, which is collected historically to determine the region's population growth rate. Literature does not provide a solution for areas with no historical knowledge. In such areas, machine learning can solve the problem, but a multitude of machine learning algorithm makes it difficult to determine the best approach. Further, the missing feature is a common real-world problem. Thus, it is essential to compare and select the machine learning techniques which provide the best and most robust in the presence of missing features. This study compares 17 machine learning techniques (base learners and ensemble learners) performance in predicting the human population growth rate of the country. Among the 17 machine learning techniques, random forest outperformed all the other techniques both in predictive performance and robustness towards missing features. Thus, the study successfully demonstrates and compares machine learning techniques to predict the human population growth rate in settings where historical data and feature information is not available. Further, the study provides the best machine learning algorithm for performing population growth rate prediction.

• Nutrition Research and Practice
• /
• v.15 no.1
• /
• pp.1-11
• /
• 2021

BACKGROUND/OBJECTIVES: It is difficult to consistently demonstrate the health effects of soy isoflavones owing to the multitude of factors contributing to their bioavailability. To accurately verify these health effects, dietary isoflavone intake should be measured using a biologically active dose rather than an intake dose. This concept has been expanded to the development of new exposure biomarkers in nutrition research. This review aims to provide an overview of the development of exposure biomarkers and suggest a novel research strategy for identifying the health effects of soy isoflavone intake. MATERIALS/METHODS: We cover recent studies on the health effects of soy isoflavones focusing on isoflavone metabolites as exposure biomarkers. RESULTS: Compared to non-fermented soy foods, fermented soy foods cause an increased concentration of isoflavones in the biofluid immediately following ingestion. The correlation between exposure biomarkers in blood and urine and the food frequency questionnaire was slightly lower than that of corresponding 24-h dietary recalls. Urinary and blood isoflavone levels did not show a consistent association with chronic disease and cancer risk. CONCLUSION: It is crucial to understand the variable bioavailabilities of soy isoflavones, which may affect evaluations of soy isoflavone intake in health and disease. Further studies on the development of valid exposure biomarkers are needed to thoroughly investigate the health effects of isoflavone.

• Korean Journal of Clinical Laboratory Science
• /
• v.54 no.1
• /
• pp.1-8
• /
• 2022

Erythrocyte sedimentation rate (ESR) evaluation is a useful tool for monitoring disease activity in various inflammatory and non-inflammatory conditions. ESR is known to be influenced by a multitude of confounding factors. The present study aimed to assess the possible determinants of the ESR and its relationship with various risk factors involved in ischemic stroke. ESR and other hematological and biochemical parameters were investigated in 163 ischemic stroke patients (107 males and 56 females) selected based on imaging techniques including magnetic resonance imaging (MRI) or computed tomography (CT) scans. Statistical analysis was performed using the SPSS 16.0 software. Linear regression analysis showed a significant inverse relationship of hemoglobin (Hb) and hematocrit or packed cell volume (PCV) (P<0.001 for females; P<0.01 for males) with the ESR. It was observed that the red blood cell (RBC) count was not strongly correlated with the ESR (P<0.05 for both males and females). It was also observed that sex significantly affected the variables determining the ESR levels, whereas age had no effect. Gender differences were also observed with respect to Hb, RBC, PCV, mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin concentration (MCHC), and ESR. The possible determinants of higher ESR levels in ischemic stroke may be sex, Hb, hematocrit, and RBC count, but the role of other clinical and laboratory parameters cannot be underestimated.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.133-141
• /
• 2001

Since the computing environment changes very rapidly, the estimation of software effort is very difficult because it is not easy to collect a sufficient number of relevant cases from the historical data. If we pinpoint the cases, the number of cases becomes too small. However is we adopt too many cases, the relevance declines. So in this paper we attempt to balance the number of cases and relevance. Since many researches on software effort estimation showed that the neural network models perform at least as well as the other approaches, so we selected the neural network model as the basic estimator. We propose a search method that finds the right level of relevant cases for the neural network model. For the selected case set. eliminating the qualitative input factors with the same values can reduce the scale of the neural network model. Since there exists a multitude of combinations of case sets, we need to search for the optimal reduced neural network model and corresponding case, set. To find the quasi-optimal model from the hierarchy of reduced neural network models, we adopted the beam search technique and devised the Case-Set Selection Algorithm. This algorithm can be adopted in the case-adaptive software effort estimation systems.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.82-87
• /
• 2023

<Deep Sea> is an 3D animated film that stands out for its exceptional special effects and distinctive artistic style. The film employs a multitude of dazzling and vibrant ink particles, creating a strong sense of three-dimensionality and weightlessness, while simultaneously portraying a dreamlike and elegant representation of a deep sea ink painting. Furthermore, through the utilization of fragmented stream of consciousness narrative technique, the film establishes a unique artistic effect infused with a Chinese atmosphere. This paper by analyzing the unique particle ink art style and color and stream of consciousness narrative methods in film, this paper discusses the innovative art style generated by traditional ink art style combined with three-dimensional technology, and the integration of traditional ink art ideas and artistic conception in animated films. The objective is to cultivate a new ink art style and prove the importance of traditional cultural expression in animated films, while providing new perspectives for the future application of traditional art in animation.

• Journal of the Daesoon Academy of Sciences
• /
• v.31
• /
• pp.1-45
• /
• 2018

Daesoon Jinrihoe is one of Korea's most influential religious organizations. Its doctrines and creeds include a rich variety of concepts, and among these, the philosophical notion of 'feminine virtue' holds tremendous value. This paper will explore the multitude meanings of feminine virtue, assume these as a foundation, and then examine the doctrines of Daesoon Jinrihoe to analyze the universality and uniqueness of the philosophical notion of feminine virtue. Additionally, background theoretical points of interest and distinctive features will likewise be analyzed to show the truly valuable lessons that this concept holds for today and why it is so worthy of research and promotion.

• Coupled systems mechanics
• /
• v.12 no.2
• /
• pp.167-181
• /
• 2023

The determination of the blast protection level and the corresponding minimum load-bearing capacity for a laminated glass (LG) window is of crucial importance for safety and security design purposes. In this paper, the focus is given to the window response under near-field blast loading, i.e., where relatively small explosives would be activated close to the target, representative of attack scenarios using small commercial drones. In general, the assessment of the load-bearing capacity of a window is based on complex and expensive experiments, which can be conducted for a small number of configurations. On the other hand, nowadays, validated numerical simulations tools based on the Finite Element Method (FEM) are available to partially substitute the physical tests for the assessment of the performance of various LG systems, especially for the far-field blast loading. However, very little literature is available on the LG window performance under near-field blast loads, which differs from far-field situations in two points: i) the duration of the load is very short, since the blast wavelength tends to increase with the distance and ii) the load distribution is not uniform over the window surface, as opposed to the almost plane wave configuration for far-field configurations. Therefore, the current study focuses on the performance assessment and structural behaviour of LG windows under near-field blasts. Typical behavioural trends are investigated, by taking into account possible relevant damage mechanisms in the LG window components, while size effects for target LG windows are also addressed under a multitude of blast loading configurations.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.686-693
• /
• 2022

Construction is a collaborative endeavor. The complexity in delivering construction projects successfully is impacted by the effective collaboration needs of a multitude of stakeholders throughout the project life-cycle. Technologies such as Building Information Modelling and relational project delivery approaches such as Alliancing and Integrated Project Delivery have developed to address this conundrum. However, with the onset of the pandemic, the digital economy has surged world-wide and advances in technology such as in the areas of machine learning (ML) and Artificial Intelligence (AI) have grown deep roots across specializations and domains to the point of matching its capabilities to the human mind. Several recent studies have both explored the role of AI in the construction process and highlighted its benefits. In contrast, literature in the organization studies field has highlighted the fear that tasks currently done by humans will be done by AI in future. Motivated by these insights and with the understanding that construction is a labour intensive sector where knowledge is both fragmented and predominantly tacit in nature, this paper explores the integration of AI in construction processes across project phases from planning, scheduling, execution and maintenance operations using literary evidence and experiential insights. The findings show that AI can complement human skills rather than provide a substitute for them. This preliminary study is expected to be a stepping stone for further research and implementation in practice.

• Steel and Composite Structures
• /
• v.49 no.1
• /
• pp.109-123
• /
• 2023

Headed studs welded to steel beams and embedded within the concrete of deck slabs are vital components of modern composite floor systems, where safety and economy depend on the accurate predictions of the stud shear resistance. The multitude of existing deck profiles and the complex behavior of studs in deck slab ribs makes developing accurate and reliable mechanical or empirical design models challenging. The paper addresses this issue by presenting a machine learning (ML) model developed from the natural gradient boosting (NGBoost) algorithm capable of producing probabilistic predictions and a database of 464 push-out tests, which is considerably larger than the databases used for developing existing design models. The proposed model outperforms models based on other ML algorithms and existing descriptive equations, including those in EC4 and AISC 360, while offering probabilistic predictions unavailable from other models and producing higher shear resistances for many cases. The present study also showed that the stud shear resistance is insensitive to the concrete elastic modulus, stud welding type, location of slab reinforcement, and other parameters considered important by existing models. The NGBoost model was interpreted by evaluating the feature importance and dependence determined with the SHapley Additive exPlanations (SHAP) method. The model was calibrated via reliability analyses in accordance with the Eurocodes to ensure that its predictions meet the required reliability level and facilitate its use in design. An interactive open-source web application was created and deployed to the cloud to allow for convenient and rapid stud shear resistance predictions with the developed model.

• Geomechanics and Engineering
• /
• v.35 no.5
• /
• pp.475-486
• /
• 2023

Ballast particles have an irregular shape and are discrete in nature. Due to the discrete nature of ballast, it exhibits complex mechanical behaviour under loading conditions. The discrete element method (DEM) can model the behaviour of discrete particles under a multitude of loading conditions. DEM is used in this paper to simulate a series of three-dimensional direct shear tests in order to investigate the shear behaviour of railway ballast and its interaction at the microscopic level. Particle flow code in three dimension (PFC3D) models the irregular shape of ballast particles as clump particles. To investigate the influence of particle size distribution (PSD), real PSD of Indian railway ballast specification IRS:GE:1:2004, China high-speed rail (HSR) and French rail specifications are generated. PFC3D built-in linear contact model is used to simulate the interaction of ballast particles under various normal stresses, shearing rate and shear box sizes. The results indicate how shear resistance and volumetric changes in ballast assembly are affected by normal stress, shearing rate, PSD and shear box size. In addition to macroscopic behaviour, DEM represents the microscopic behaviour of ballast particles in the form of particle displacement at different stages of the shearing process.