• The Korean Journal of Applied Statistics
• /
• v.35 no.3
• /
• pp.395-406
• /
• 2022

This paper studies the outlier detection method for multivariate long memory time series. The existing outlier detection methods are based on a short memory VARMA model, so they are not suitable for multivariate long memory time series. It is because higher order of autoregressive model is necessary to account for long memory, however, it can also induce estimation instability as the number of parameter increases. To resolve this issue, we propose outlier detection methods based on the VHAR structure. We also adapt the robust estimation method to estimate VHAR coefficients more efficiently. Our simulation results show that our proposed method performs well in detecting outliers in multivariate long memory time series. Empirical analysis with stock index shows RVHAR model finds additional outliers that existing model does not detect.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.246-256
• /
• 2022

Recently, parents and teachers consider physical education as a minor subject for students in elementary and secondary schools. Physical education performance has become increasingly significant as parents and schools pay more attention to physical schooling. The sports mining with distribution analysis model considers different factors, including the games, comments, conversations, and connection made on numerous sports interests. Using different machine learning/deep learning approach, children's athletic and academic interests can be tracked over the course of their academic lives. There have been a number of studies that have focused on predicting the success of students in higher education. Sports interest prediction research at the secondary level is uncommon, but the secondary level is often used as a benchmark to describe students' educational development at higher levels. An Automated Student Interest Prediction on Sports Mining using DL Based Bi-directional Long Short-Term Memory model (BiLSTM) is presented in this article. Pre-processing of data, interest classification, and parameter tweaking are all the essential operations of the proposed model. Initially, data augmentation is used to expand the dataset's size. Secondly, a BiLSTM model is used to predict and classify user interests. Adagrad optimizer is employed for hyperparameter optimization. In order to test the model's performance, a dataset is used and the results are analysed using precision, recall, accuracy and F-measure. The proposed model achieved 95% accuracy on 400^th instances, where the existing techniques achieved 93.20% accuracy for the same. The proposed model achieved 95% of accuracy and precision for 60%-40% data, where the existing models achieved 93% for accuracy and precision.

• Journal of Korea Trade
• /
• v.25 no.4
• /
• pp.17-36
• /
• 2021

Purpose - This study provides useful information to stakeholders by forecasting the tramp shipping market, which is a completely competitive market and has a huge fluctuation in freight rates due to low barriers to entry. Moreover, this study provides the most effective parameters for Baltic Dry Index (BDI) prediction and an optimal model by analyzing and comparing deep learning models such as the artificial neural network (ANN), recurrent neural network (RNN), and long short-term memory (LSTM). Design/methodology - This study uses various data models based on big data. The deep learning models considered are specialized for time series models. This study includes three perspectives to verify useful models in time series data by comparing prediction accuracy according to the selection of external variables and comparison between models. Findings - The BDI research reflecting the latest trends since 2015, using weekly data from 1995 to 2019 (25 years), is employed in this study. Additionally, we tried finding the best combination of BDI forecasts through the input of external factors such as supply, demand, raw materials, and economic aspects. Moreover, the combination of various unpredictable external variables and the fundamentals of supply and demand have sought to increase BDI prediction accuracy. Originality/value - Unlike previous studies, BDI forecasts reflect the latest stabilizing trends since 2015. Additionally, we look at the variation of the model's predictive accuracy according to the input of statistically validated variables. Moreover, we want to find the optimal model that minimizes the error value according to the parameter adjustment in the ANN model. Thus, this study helps future shipping stakeholders make decisions through BDI forecasts.

• Earthquakes and Structures
• /
• v.22 no.2
• /
• pp.185-201
• /
• 2022

Structural Health Monitoring (SHM) is used to provide reliable information about the structure's integrity in near realtime following extreme incidents such as earthquakes, considering the inevitable aging and degradation that occurs in operating environments. This paper experimentally investigates an integrated wireless sensor network (Wi-SN) based monitoring technique for damage detection in concrete structures. An effective SHM technique can be used to detect potential structural damage based on post-earthquake data. Two novel methods are proposed for damage detection in reinforced concrete (RC) building structures including: (i) Jerk Energy Method (JEM), which is based on time-domain analysis, and (ii) Modal Contributing Parameter (MCP), which is based on frequency-domain analysis. Wireless accelerometer sensors are installed at each story level to monitor the dynamic responses from the building structure. Prior knowledge of the initial state (immediately after construction) of the structure is not required in these methods. Proposed methods only use responses recorded during ambient vibration state (i.e., operational state) to estimate the damage index. Herein, the experimental studies serve as an illustration of the procedures. In particular, (i) a 3-story shear-type steel frame model is analyzed for several damage scenarios and (ii) 2-story RC scaled down (at 1/6th) building models, simulated and verified under experimental tests on a shaking table. As a result, in addition to the usual benefits like system adaptability, and cost-effectiveness, the proposed sensing system does not require a cluster of sensors. The spatial information in the real-time recorded data is used in global damage identification stage of SHM. Whereas in next stage of SHM, the damage is detected at the story level. Experimental results also show the efficiency and superior performance of the proposed measuring techniques.

• Advances in concrete construction
• /
• v.14 no.2
• /
• pp.103-113
• /
• 2022

On the basis of fabrication, the utilization of nano material in numerous industrial and technological system, obtained the utmost significance in current decade. Therefore, the current investigation presents a theoretical disposition regarding the flow of electric conducting Williamson nanoliquid over a stretchable surface in the presence of the motile microorganism. The impact of thermal radiation and magnetic parameter are incorporated in the energy equation. The concentration field is modified by adding the influence of chemical reaction. Moreover, the splendid features of nanofluid are displayed by utilizing the thermophoresis and Brownian motion aspects. Compatible similarity transformation is imposed on the equations governing the problem to derive the dimensionless ordinary differential equations. The Homotopy analysis method has been implemented to find the analytic solution of the obtained differential equations. The implications of specific parameters on profiles of velocity, temperature, concentration and motile microorganism density are investigated graphically. Moreover, coefficient of skin friction, Nusselt number, Sherwood number and density of motile number are clarified in tabular forms. It is revealed that thermal radiation, thermophoresis and Brownian motion parameters are very effective for improvement of heat transfer. The reported investigation can be used in improving the heat transfer appliances and systems of solar energy.

• Steel and Composite Structures
• /
• v.42 no.6
• /
• pp.805-826
• /
• 2022

The free and live load-forced vibration behaviour of porous functionally graded (PFG) higher order nanobeams in the thermal and magnetic fields is investigated comprehensively through this work in the framework of nonlocal strain gradient theory (NLSGT). The porosity effects on the dynamic behaviour of FG nanobeams is investigated using four different porosity distribution models. These models are exploited; uniform, symmetrical, condensed upward, and condensed downward distributions. The material characteristics gradation in the thickness direction is estimated using the power-law. The magnetic field effect is incorporated using Maxwell's equations. The third order shear deformation beam theory is adopted to incorporate the shear deformation effect. The Hamilton principle is adopted to derive the coupled thermomagnetic dynamic equations of motion of the whole system and the associated boundary conditions. Navier method is used to derive the analytical solution of the governing equations. The developed methodology is verified and compared with the available results in the literature and good agreement is observed. Parametric studies are conducted to show effects of porosity parameter; porosity distribution, temperature rise, magnetic field intensity, material gradation index, non-classical parameters, and the applied moving load velocity on the vibration behavior of nanobeams. It has been showed that all the analyzed conditions have significant effects on the dynamic behavior of the nanobeams. Additionally, it has been observed that the negative effects of moving load, porosity and thermal load on the nanobeam dynamics can be reduced by the effect of the force induced from the directed magnetic field or can be kept within certain desired design limits by controlling the intensity of the magnetic field.

• Geomechanics and Engineering
• /
• v.28 no.5
• /
• pp.531-546
• /
• 2022

Ground displacements caused by the construction of overlapping twin shield tunnels with small turning radius are complex, especially under special geological conditions of construction. To investigate the ground displacements caused due to shield machines in the unique calcareous sand layers in Israel for the first time and determine the main factors affecting the ground displacements, field monitoring, laboratory geological analysis, theoretical calculations, and parameter studies were adopted. By using rod extensometers, inclinometers, total stations, and automatic segment-displacement monitors, subsurface tunneling-induced displacement, surface settlement, and displacement of the down-track tunnel segments caused by the construction of an up-track tunnel were analyzed. The up-track tunnel and the down-track tunnel pass through different stratum, resulting in different construction parameters and ground displacements. The laws of variation of thrust and torque, soil pressure in the chamber, excavated soil quantity, synchronous grouting pressure, and grout volume of the two tunnels from parallel to fully overlapping orientations were compared. The thrust and torque of the shield in the fine sand are larger than those in the Kurkar layer, and the grouting amount in fine sand is unstable. According to fuzzy statistics and Gaussian curve fitting of the shield tunneling speed, the tunneling speed in the Kurkar stratum is twice that in the fine-sand stratum.

• Geomechanics and Engineering
• /
• v.33 no.1
• /
• pp.1-9
• /
• 2023

The unconfined compression strength (UCS) of soils is commonly used either before or during the construction of geo-structures. In the pre-design stage, UCS as a mechanical property is obtained through a laboratory test that requires cumbersome procedures and high costs from in-situ sampling and sample preparation. As an alternative way, the empirical model established from limited testing cases is used to economically estimate the UCS. However, many parameters affecting the 1D soil compression response hinder employing the traditional statistical analysis. In this study, gene expression programming (GEP) is adopted to develop a prediction model of UCS with common affecting soil properties. A total of 79 undisturbed soil samples are collected, of which 54 samples are utilized for the generation of a predictive model and 25 samples are used to validate the proposed model. Experimental studies are conducted to measure the unconfined compression strength and basic soil index properties. A performance assessment of the prediction model is carried out using statistical checks including the correlation coefficient (R), the root mean square error (RMSE), the mean absolute error (MAE), the relatively squared error (RSE), and external criteria checks. The prediction model has achieved excellent accuracy with values of R, RMSE, MAE, and RSE of 0.98, 10.01, 7.94, and 0.03, respectively for the training data and 0.92, 19.82, 14.56, and 0.15, respectively for the testing data. From the sensitivity analysis and parametric study, the liquid limit and fine content are found to be the most sensitive parameters whereas the sand content is the least critical parameter.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.56 no.4
• /
• pp.462-472
• /
• 2023

We investigated the physio-chemical and geochemical parameters in the spraying shellfish aquacultures (Yeoja and Gangjin Bay) to establish the systematic strategy for effective environmental management. Spatial variation of each parameter showed partially significant difference (P<0.05) between Yeoja and Ganjin Bay, inferring the discriminative progress (i.e., accumulation and degradation) of the autochthonous organic matter within the aquaculture environments. We additionally integrated various properties (e.g., water/sediment quality, natural hazard, and biological health) which may affect the biological growth within the aquaculture habitats based on the biogeochemical cycles related to environmental components and aquaculture species. We used a screening approach (i.e., one out-all out; OOAO) which can permit the assessment of the health levels of aquaculture species, the scoring for other parameters (seawater, sediment, and natural hazard) as three levels (excellent, moderate and poor) depending on the complex interactive properties occurring in the aquaculture environments. Actual, discriminative scores obtained via our case studies may confirm that these stepwise processes are effectively evaluated for optimal health conditions within the aquaculture habitats. Thus, this approach may provide valuable insights for effective environmental management and sustainable growth of aquaculture operation.

• Geomechanics and Engineering
• /
• v.34 no.6
• /
• pp.683-696
• /
• 2023

The destruction and fracture of rock masses are crucial components in engineering and there is an increasing demand for the study of the influence of rock mass heterogeneity on the safety of engineering projects. The numerical manifold method (NMM) has a unified solution format for continuous and discontinuous problems. In most NMM studies, material homogeneity has been assumed and despite this simplification, fracture mechanics remain complex and simulations are inefficient because of the complicated topology updating operations that are needed after crack propagation. These operations become computationally expensive especially in the cases of heterogeneous materials. In this study, a heterogeneous model algorithm based on stochastic theory was developed and introduced into the NMM. A new fracture algorithm was developed to simulate the rupture zone. The algorithm was validated for the examples of the four-point shear beam and semi-circular bend. Results show that the algorithm can efficiently simulate the rupture zone of heterogeneous rock masses. Heterogeneity has a powerful effect on the macroscopic failure characteristics and uniaxial compressive strength of rock masses. The peak strength of homogeneous material (with heterogeneity or standard deviation of 0) is 2.4 times that of heterogeneous material (with heterogeneity of 11.0). Moreover, the local distribution of parameter values can affect the configuration of rupture zones in rock masses. The local distribution also influences the peak value on the stress-strain curve and the residual strength. The post-peak stress-strain curve envelope from 60 random calculations can be used as an estimate of the strength of engineering rock masses.