• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.305-326
• /
• 2019

Discriminative correlation filter (DCF) based tracking algorithms have recently shown impressive performance on benchmark datasets. However, amount of recent researches are vulnerable to heavy occlusions, irregular deformations and so on. In this paper, we intend to solve these problems and handle the contradiction between accuracy and real-time in the framework of tracking-by-detection. Firstly, we propose an innovative strategy to combine the template and color-based models instead of a simple linear superposition and rely on the strengths of both to promote the accuracy. Secondly, to enhance the discriminative power of the learned template model, the spatial regularization is introduced in the learning stage to penalize the objective boundary information corresponding to features in the background. Thirdly, we utilize a discriminative multi-scale estimate method to solve the problem of scale variations. Finally, we research strategies to limit the computational complexity of our tracker. Abundant experiments demonstrate that our tracker performs superiorly against several advanced algorithms on both the OTB2013 and OTB2015 datasets while maintaining the high frame rates.

• International Journal of Automotive Technology
• /
• v.8 no.3
• /
• pp.351-359
• /
• 2007

In this study, a hierarchical switching control scheme based on robust control theory is proposed for tracking control of vehicle longitudinal acceleration in the presence of large uncertainties. A model set consisting of four multiplicative-uncertainty models is set up, and its corresponding controller set is designed by the LMI approach, which can ensures the robust performance of the closed loop system under arbitray switching. Based on the model set and the controller set, a switching index function by estimating the system gain of the uncertainties between the plant and the nominal model is designed to determine when and which controller should be switched into the closed loop. After theoretical analyses, experiments have also been carried out to validate the proposed control algorithm. The results show that the control system has good performance of robust stability and tracking ability in the presence of large uncertainties. The response time is smaller than 1.5s and the max tracking error is about $0.05\;m/S^2$ with the step input.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.2 no.2
• /
• pp.57-67
• /
• 2010

Experimental investigations were carried out on an Axi-symmetric Body Model fitted with Pump-jet Propulsor (PJP) in the Cavitation Tunnel at Naval Science and Technological Laboratory (NSTL). The tests were intended for evaluating the propulsion characteristics of the body and propulsor. The self propulsion point of the model for two configurations was determined after finding the corrections for tunnel blockage effects and differences in model length at zero trim. The results were found to match closely with the towing tank results. The rotor and stator torques also matched closely over full range of experiment. Further experiments were carried out on the body at $4.5^{\circ}$ angle of trim to investigate the propulsive performance and assess the operational difficulties in the sea. The results indicated an increase in resistance and decrease in rotor thrust; but the balance of torques between the rotor and stator was undisturbed, causing no concern to vehicle roll.

• Journal of Microbiology and Biotechnology
• /
• v.18 no.5
• /
• pp.889-896
• /
• 2008

A suitable simple model tested by experiments is required to address complex biological reactions like esterase synthesis by Saccharomyces cerevisiae. Such an approach might be the answer to a proper bioprocessing strategy. In this regard, a logistic model for esterase production from Saccharomyces cerevisiae has been developed, which predicts well the cell mass, the carbon source (glucose) consumption, and the esterase activity. The accuracy of the model has been statistically examined by using the Student's t-test. The parameter sensitivity analysis showed that all five parameters (${\mu}_m$, $K_a$, $X_m$, $Y_{x/s}$, and $Y_{p/x}$) have significant influence on the predicted values of esterase activity.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.2
• /
• pp.699-707
• /
• 2015

Although digit character recognition has got a significant improvement in recent years, it is still challenging to achieve satisfied result if the data contains an amount of distracting factors. This paper proposes a novel digit character recognition approach using a multi-layer hierarchical model, Hybrid Restricted Boltzmann Machines (HRBMs), which allows the learning architecture to be robust to background distracting factors. The insight behind the proposed model is that useful high-level features appear more frequently than distracting factors during learning, thus the high-level features can be decompose into hybrid hierarchical structures by using only small label information. In order to extract robust and compact features, a stochastic 0-1 layer is employed, which enables the model's hidden nodes to independently capture the useful character features during training. Experiments on the variations of Mixed National Institute of Standards and Technology (MNIST) dataset show that improvements of the multi-layer hierarchical model can be achieved by the proposed method. Finally, the paper shows the proposed technique which is used in a real-world application, where it is able to identify digit characters under various complex background images.

• Computers and Concrete
• /
• v.7 no.5
• /
• pp.403-419
• /
• 2010

The bond mechanism for reinforcing bars in concrete is equivalent to the normal contact and friction between the inclined ribs and the surrounding concrete. Based on the contact density model for the computation of shear transfer across cracks, an open-slip coupled model was developed for simulating three-dimensional bond behavior for reinforcing bars in concrete. A parameter study was performed and verified by simulating pull-out experiments of extremely different boundary conditions: short bar embedment with a huge concrete cover, extremely long bar embedment with a huge concrete cover, embedded aluminum bar and short bar embedded length with an insufficient concrete cover. The bar strain effect and splitting of the concrete cover on a local bond can be explained by finite element (FE) analysis. The analysis shows that the strain effect results from a large local slip and the splitting effect of a large opening of the interface. Finally, the sensitivity of rebar geometry was also checked by FE analysis and implies that the open-slip coupled model can be extended to the case of plain bar.

• Computers and Concrete
• /
• v.7 no.5
• /
• pp.421-435
• /
• 2010

This paper utilizes the modified Davis model and the mode coupling theory, as parts of the electrolyte solution theory, to investigate the diffusivity of the ion in concrete. Firstly, a computational model of the ion diffusion coefficient, which is associated with ion species, pore solution concentration, concrete mix parameters including water-cement ratio and cement volume fraction, and microstructure parameters such as the porosity and tortuosity, is proposed in the saturated concrete. Secondly, the experiments, on which the chloride diffusion coefficient is measured by the rapid chloride penetration test, have been carried out to investigate the validity of the proposed model. The results indicate that the chloride diffusion coefficient obtained by the proposed model is in agreement with the experimental result. Finally, numerical simulation has been completed to investigate the effects of the porosity, tortuosity, water-cement ratio, cement volume fraction and ion concentration in the pore solution on the ion diffusion coefficients. The results show that the ion diffusion coefficient in concrete increases with the porosity, water-cement ratio and cement volume fraction, while we see a decrease with the increasing of tortuosity. Meanwhile, the ion concentration produces more obvious effects on the diffusivity itself, but has almost no effects on the other ions.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.11 no.1
• /
• pp.285-293
• /
• 2019

In the present paper, model tests of suppressing sloshing fitted with two perforated floating plates are carried out. The study involves identification of system performance such as the suppression and the solidity ratio. Three different solidity ratios of perforated plates have been tried out as potential positive slosh damping devices. A series of painstaking experiments have been conducted in a rigid rectangular tank on six degrees of freedom motion platform under roll harmonic excitation. Comparison of the clean tank shows that the three types of perforated plates are all effective on damping the run-up and impact pressure along the bulkhead. The parametric study indicates that the perforated plate with the median solidity ratio is the most optimal one in suppressing sloshing among three configurations.

• Journal of Coastal Disaster Prevention
• /
• v.4 no.1
• /
• pp.1-6
• /
• 2017

Most of the short period waves are blocked by the breakwaters when the short period irregular waves propagate into the ports. However, nonlinear irregular wave numerical experiments show that the long waves generated by the nonlinear interaction is predominant in the port. Seiches phenomenon in Geumjin Fishing Port is very similar to 60 and 300 second harbor oscillations. By arranging the inner breakwater of the proper length in the inside of the port, it is possible to effectively reduce seiches, as well as the short-period wave, and significantly improve the harbor tranquility. In the case of rectangular basin type such as the Geumjin Fishing Port, the multi-directional irregular wave numerical model should be used for the investigation and countermeasures for the harbor tranquility.

• Nuclear Engineering and Technology
• /
• v.56 no.1
• /
• pp.100-105
• /
• 2024

In this study, we propose an alternative approach using Artificial Neural Networks (ANN) for determining Mass Attenuation Coefficients (MAC) in various glass systems. This method takes into account the weights of glass compositions, density, and photon energy as input features. The ANN model was trained and tested on a dataset consisting of 650 data points and subsequently validated through a K-fold cross-validation procedure. Our findings demonstrate a high level of accuracy, with R² values ranging from 0.90 to 0.99. Additionally, the model exhibits robust extrapolation capabilities with an R² score of 0.87 for predicting MAC values in a new glass system. Furthermore, this approach significantly reduces the need for costly and time-consuming computations and experiments, making it a potential tool for selecting materials for effective radiation protection.