• Journal of the Optical Society of Korea
• /
• 제20권6호
• /
• pp.752-761
• /
• 2016

Hyperspectral images are often contaminated with stripe noise, which severely degrades the imaging quality and the precision of the subsequent processing. In this paper, a variational model is proposed by employing spectral-spatial adaptive unidirectional variation and a sparse representation. Unlike traditional methods, we exploit the spectral correction and remove stripes in different bands and different regions adaptively, instead of selecting parameters band by band. The regularization strength adapts to the spectrally varying stripe intensities and the spatially varying texture information. Spectral correlation is exploited via dictionary learning in the sparse representation framework to prevent spectral distortion. Moreover, the minimization problem, which contains two unsmooth and inseparable $l_1$-norm terms, is optimized by the split Bregman approach. Experimental results, on datasets from several imaging systems, demonstrate that the proposed method can remove stripe noise effectively and adaptively, as well as preserve original detail information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5978-5999
• /
• 2018

Pedestrian detection is a challenging area in the intelligent vehicles domain. During the last years, many works have been proposed to efficiently detect motion in images. However, the problem becomes more complex when it comes to detecting moving areas while the vehicle is also moving. This paper presents a variational optical flow-based method for motion estimation in vehicular traffic scenarios. We introduce a framework for detecting motion areas with small and large displacements by computing optical flow using a multilevel architecture. The flow field is estimated at the shortest level and then successively computed until the largest level. We include a filtering parameter and a warping process using bicubic interpolation to combine the intermediate flow fields computed at each level during optimization to gain better performance. Furthermore, we find that by including a penalization function, our system is able to effectively reduce the presence of outliers and deal with all expected circumstances in real scenes. Experimental results are performed on various image sequences from Daimler Pedestrian Dataset that includes urban traffic scenarios. Our evaluation demonstrates that despite the complexity of the evaluated scenes, the motion areas with both moving and static camera can be effectively identified.

• Ocean Systems Engineering
• /
• 제11권1호
• /
• pp.59-81
• /
• 2021

The nonlinear formulation using the principle of virtual work-energy for free vibration of a large-sag extensible catenary riser in two dimensions is presented in this paper. A support at one end is hinged and the other is a free-sliding roller in the horizontal direction. The catenary riser has a large-sag configuration in the static equilibrium state and is assumed to displace with large amplitude to the motion state. The total virtual work of the catenary riser system involves the virtual strain energy due to bending, the virtual strain energy due to axial deformation, the virtual work done by the effective weight, and the inertia forces. The nonlinear equations of motion for two-dimensional free vibration in the Cartesian coordinate system is developed based on the difference between the Euler's equations in the static state and the displaced state. The linear and nonlinear stiffness matrices of the catenary riser are obtained and the eigenvalue problem is solved using the Galerkin finite element procedure. The natural frequencies and mode shapes are obtained. The results are validated with regard to the reference research addressing the accuracy and efficiency of the proposed nonlinear formulation. The numerical results for free vibration and the effect of the nonlinear behavior for catenary riser are presented.

• Journal of Information Processing Systems
• /
• 제17권6호
• /
• pp.1057-1070
• /
• 2021

Case-related news filtering is crucial in legal text mining and divides news into case-related and case-unrelated categories. Because case-related news originates from various fields and has different writing styles, it is difficult to establish complete filtering rules or keywords for data collection. In addition, the labeled corpus for case-related news is sparse; therefore, to train a high-performance classification model, it is necessary to annotate the corpus. To address this challenge, we propose topic-enhanced positive-unlabeled learning, which selects positive and negative samples guided by topics. Specifically, a topic model based on a variational autoencoder (VAE) is trained to extract topics from unlabeled samples. By using these topics in the iterative process of positive-unlabeled (PU) learning, the accuracy of identifying case-related news can be improved. From the experimental results, it can be observed that the F1 value of our method on the test set is 1.8% higher than that of the PU learning baseline model. In addition, our method is more robust with low initial samples and high iterations, and compared with advanced PU learning baselines such as nnPU and I-PU, we obtain a 1.1% higher F1 value, which indicates that our method can effectively identify case-related news.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.713-725
• /
• 2022

Mostly, artificial intelligence does not show any definite change in emotions. For this reason, it is hard to demonstrate empathy in communication with humans. If frequency modification is applied to neutral emotions, or if a different emotional frequency is added to them, it is possible to develop artificial intelligence with emotions. This study proposes the emotion conversion using the Generative Adversarial Network (GAN) based voice frequency synthesis. The proposed method extracts a frequency from speech data of twenty-four actors and actresses. In other words, it extracts voice features of their different emotions, preserves linguistic features, and converts emotions only. After that, it generates a frequency in variational auto-encoding Wasserstein generative adversarial network (VAW-GAN) in order to make prosody and preserve linguistic information. That makes it possible to learn speech features in parallel. Finally, it corrects a frequency by employing Amplitude Scaling. With the use of the spectral conversion of logarithmic scale, it is converted into a frequency in consideration of human hearing features. Accordingly, the proposed technique provides the emotion conversion of speeches in order to express emotions in line with artificially generated voices or speeches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권1호
• /
• pp.81-98
• /
• 2013

Since Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA) were introduced, many revised or extended topic models have appeared. Due to the intractable likelihood of these models, training any topic model requires to use some approximation algorithm such as variational approximation, Laplace approximation, or Markov chain Monte Carlo (MCMC). Although these approximation algorithms perform well, training a topic model is still computationally expensive given the large amount of data it requires. In this paper, we propose a new method, called non-simultaneous sampling deactivation, for efficient approximation of parameters in a topic model. While each random variable is normally sampled or obtained by a single predefined burn-in period in the traditional approximation algorithms, our new method is based on the observation that the random variable nodes in one topic model have all different periods of convergence. During the iterative approximation process, the proposed method allows each random variable node to be terminated or deactivated when it is converged. Therefore, compared to the traditional approximation ways in which usually every node is deactivated concurrently, the proposed method achieves the inference efficiency in terms of time and memory. We do not propose a new approximation algorithm, but a new process applicable to the existing approximation algorithms. Through experiments, we show the time and memory efficiency of the method, and discuss about the tradeoff between the efficiency of the approximation process and the parameter consistency.

• Coupled systems mechanics
• /
• 제1권4호
• /
• pp.361-379
• /
• 2012

This paper presents a fully coupled three-dimensional solver for the analysis of interaction between pulsatile flow and large deformation structure. A partitioned time marching algorithm is employed for the solution of the time dependent coupled discretised problem, enabling the use of highly developed, robust and well-tested solvers for each field. Conservative transfer of information at the fluid-structure interface is combined with an effective multi-predict-correct iterative scheme to enable implicit coupling of the interacting fields at each time increment. The three-dimensional unsteady incompressible fluid is solved using a powerful implicit time stepping technique and an ALE formulation for moving boundaries with second-order time accurate is used. A full spectrum of total variational diminishing (TVD) schemes in unstructured grids is allowed implementation for the advection terms and finite element shape functions are used to evaluate the solution and its variation within mesh elements. A finite element dynamic analysis of the highly deformable structure is carried out with a numerical strategy combining the implicit Newmark time integration algorithm with a Newton-Raphson second-order optimisation method. The proposed model is used to predict the wave flow fields of a particular flow-induced vibrational phenomenon, and comparison of the numerical results with available experimental data validates the methodology and assesses its accuracy. Another test case about three-dimensional biomedical model with pulsatile inflow is presented to benchmark the algorithm and to demonstrate the potential applications of this method.

• Structural Engineering and Mechanics
• /
• 제42권5호
• /
• pp.715-728
• /
• 2012

This paper deals with determining the fundamental frequency of tall buildings that consist of framed tube, shear core, belt truss and outrigger systems in which the framed tube and shear core vary in size along the height of the structure. The effect of belt truss and outrigger system is modeled as a concentrated rotational linear spring at the belt truss and outrigger system location. Many cantilevered tall structures can be treated as cantilevered beams with variable cross-section in free vibration analysis. In this paper, the continuous approach, in which a tall building is replaced by an idealized cantilever continuum representing the structural characteristics, is employed and by using energy method and Hamilton's variational principle, the governing equation for free vibration of tall building with variable distributed mass and stiffness is obtained. The general solution of governing equation is obtained by making appropriate selection for mass and stiffness distribution functions. By applying the separation of variables method for time and space, the governing partial differential equation of motion is reduced to an ordinary differential equation with variable coefficients with the assumption that the transverse displacement is harmonic. A power-series solution representing the mode shape function of tall building is used. Applying boundary conditions yields the boundary value problem; the frequency equation is established and solved through a numerical process to determine the natural frequencies. Computer program has been developed in Matlab (R2009b, Version 7.9.0.529, Mathworks Inc., California, USA). A numerical example has been solved to demonstrate the reliability of this method. The results of the proposed mathematical model give a good understanding of the structure's dynamic characteristics; it is easy to use, yet reasonably accurate and suitable for quick evaluations during the preliminary design stages.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1164-1183
• /
• 2019

The rapid development of cloud computing and high requirements of operators requires strong support from the underlying Data Center Networks. Therefore, the effectiveness of using resources in the data center networks becomes a point of concern for operators and material for research. In this paper, we discuss the online virtual-cluster provision problem for multiple tenants with an aim to decide when and where the virtual cluster should be placed in a data center network. Our objective is maximizing the total revenue for the data center networks under the constraints. In order to solve this problem, this paper divides it into two parts: online multi-tenancy scheduling and virtual cluster placement. The first part aims to determine the scheduling orders for the multiple tenants, and the second part aims to determine the locations of virtual machines. We first approach the problem by using the variational inequality model and discuss the existence of the optimal solution. After that, we prove that provisioning virtual clusters for a multi-tenant data center network that maximizes revenue is NP-hard. Due to the complexity of this problem, an efficient heuristic algorithm OMS (Online Multi-tenancy Scheduling) is proposed to solve the online multi-tenancy scheduling problem. We further explore the virtual cluster placement problem based on the OMS and propose a novel algorithm during the virtual machine placement. We evaluate our algorithms through a series of simulations, and the simulations results demonstrate that OMS can significantly increase the efficiency and total revenue for the data centers.