• Smart Media Journal
• /
• v.5 no.1
• /
• pp.88-94
• /
• 2016

In this paper, we proposed a new object tracking algorithm based on sparse representation to handle the drifting problem. In APG-L1(accelerated proximal gradient) tracking, the sparse representation is applied to model the appearance of object using linear combination of target templates and trivial templates with proper coefficients. Also, the particle filter based on affine transformation matrix is applied to find the location of object and APG method is used to minimize the l1-norm of sparse representation. In this paper, we make use of the trivial template coefficients actively to block the drifting problem. We experiment the various videos with diverse challenges and the result shows better performance than others.

• Journal of Korea Multimedia Society
• /
• v.7 no.6
• /
• pp.841-850
• /
• 2004

This paper proposes a GA and GDM-based method for removing unnecessary rules and generating relevant rules from the fuzzy rules corresponding to several fuzzy partitions. The aim of proposed method is to find a minimum set of fuzzy rules that can correctly classify all the training patterns. When the fine fuzzy partition is used with conventional methods, the number of fuzzy rules has been enormous and the performance of fuzzy inference system became low. This paper presents the application of GA as a means of finding optimal solutions over fuzzy partitions. In each rule, the antecedent part is made up the membership functions of a fuzzy set, and the consequent part is made up of a real number. The membership functions and the number of fuzzy inference rules are tuned by means of the GA, while the real numbers in the consequent parts of the rules are tuned by means of the gradient descent method. It is shown that the proposed method has improved than the performance of conventional method in formulating and solving a combinatorial optimization problem that has two objectives: to maximize the number of correctly classified patterns and to minimize the number of fuzzy rules.

• Journal of Korea Game Society
• /
• v.19 no.3
• /
• pp.5-14
• /
• 2019

The gaming server is based on a distributed server. In order to distribute workloads of gaming servers, distributed gaming servers apply some algorithms which divide each of gaming server's workload into balanced workload among the gaming servers and as a result, efficiently manage response time and fusibility of server requested by the clients. In this paper, we propose a load balancing agent using PPO(Proximal Policy Optimization) which is one of the methods from a greedy algorithm and Policy Gradient which is from Reinforcement Learning. The proposed load balancing agent is compared with the previous researches based on the simulation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.5
• /
• pp.2529-2543
• /
• 2019

Scanning electron microscopy (SEM) image can link with the microscopic world through reflecting interaction between electrons and materials. The SEM images are easily subject to blurring distortions during the imaging process. Inspired by the fact that dark channel prior captures the changes to blurred SEM images caused by the blur process, we propose a method to evaluate the SEM images sharpness based on the dark channel prior. A SEM image database is first established with mean opinion score collected as ground truth. For the quality assessment of the SEM image, the dark channel map is generated. Since blurring is typically characterized by the spread of edge, edge of dark channel map is extracted. Then noise is removed by an edge-preserving filter. Finally, the maximum gradient and the average gradient of image are combined to generate the final sharpness score. The experimental results on the SEM blurred image database show that the proposed algorithm outperforms both the existing state-of-the-art image sharpness metrics and the general-purpose no-reference quality metrics.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.63-72
• /
• 2021

Mobile crowd-sensing (MCS) is a promising sensing paradigm that leverages mobile users with smart devices to perform large-scale sensing tasks in order to provide services to specific applications in various domains. However, MCS sensing tasks may not always be successfully completed or timely completed for various reasons, such as accidentally leaving the tasks incomplete by the users, asynchronous transmission, or connection errors. This results in missing sensing data at specific locations and times, which can degrade the performance of the applications and lead to serious casualties. Therefore, in this paper, we propose a missing data inference approach, called missing data approximation with probabilistic tensor factorization (MDI-PTF), to approximate the missing values as closely as possible to the actual values while taking asynchronous data transmission time and different sensing locations of the mobile users into account. The proposed method first normalizes the data to limit the range of the possible values. Next, a probabilistic model of tensor factorization is formulated, and finally, the data are approximated using the gradient descent method. The performance of the proposed algorithm is verified by conducting simulations under various situations using different datasets.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.7
• /
• pp.41-47
• /
• 2009

A solution to the problems of recognizing as one spot or detection failures for complex regions, in which many spots representing proteins are overlapped and saturated, is suggested. The accumulated gradients of each point in complex regions are calculated, and the resulting accumulated gradient image segmented using watershed technique. The suggested solution show better and efficient result than existing method for spot separation, detects more protein spots hidden in the image of 2-dimensional electrophoresis, and expands the scope of prediction.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• International Journal of Computer Science & Network Security
• /
• v.24 no.10
• /
• pp.154-158
• /
• 2024

Billions of the objects around us are transformed to the IoT device by connecting them with the internet and control in that way of collecting and sharing data. Privacy is required to keep the data save from the security attacks in internet of things. Computer vision is used for monitoring the people. Computer vision algorithms, application and tools are primarily used in IOT for human movement's analysis. Traditional system and algorithms are unable to detect the human in a perfect manner. Use of the thermal camera is degraded the movements of human detection. In this paper we propose a new IoT system that is combined with the latest feature of computer vision to detect the position using computer vision. It is a useful technology that helps to keep an eye on your house and office. It will alert you if anybody enters your home or office and do any harm at your place. For that purpose, the credit card size Raspberry PI card will be used. Histogram of oriented gradient (HOG) algorithm is used to detect the person in the image.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.12 no.1
• /
• pp.59-70
• /
• 1992

Quadratic programming problems(QP) have been widely used as a direction-finding subproblem in the engineering and structural design optimization. To develop an efficient solution algorithm for the QP subproblems, theoretical aspects and numerical behavior of mathematical programming methods that can be used as QP solver are studied and compared. For the solution of both primal and dual QP, Simplex, gradient projection(GRP), and augmented Lagrange multiplier algorithms are investigated and coded. From the numerical study, it is found that the primal GRP algorithm with potential constraint strategy and the dual Simplex algorithm are more attractive and effective than the others. They have theoretical robustness as well. Moreover, primal GRP algorithm is preferable in case the number of constraints is larger than the number of design variables. Favorable features of GRP and Simplex algorithm are merged into a combined algorithm, which is useful in the structural design optimization.

• Journal of KIISE:Software and Applications
• /
• v.32 no.10
• /
• pp.949-955
• /
• 2005

In this Paper, we propose fast block matching algorithm by dividing complex areas based on complexity order of reference block and square sub-block to reduce an amount of computation of full starch(FS) algorithm for fast motion estimation, while keeping the same prediction quality compared with the full search algorithm. By using the fact that matching error is proportional to the gradient of reference block, we reduced unnecessary computations with square sub-block adaptive matching scan based image complexity instead of conventional sequential matching scan and row/column based matching scan. Our algorithm reduces about $30\%$ of computations for block matching error compared with the conventional partial distortion elimination(PDE) algorithm without any prediction quality, and our algorithm will be useful in real-time video coding applications using MPEG-4 AVC or MPEG-2.