- Log In/Sign Up
- P-ISSN1738-6764
- E-ISSN2093-7504
- KCI
ISSN : 1738-6764
Vol.10 No.1
Abstract
In the current generation of smart mobile devices, object tracking is one of the most important research topics for computer vision. Because human face tracking can be widely used for many applications, collecting a dataset of face videos is necessary for evaluating the performance of a tracker and for comparing different approaches. Unfortunately, the well-known benchmark datasets of face videos are not sufficiently diverse. As a result, it is difficult to compare the accuracy between different tracking algorithms in various conditions, namely illumination, background complexity, and subject movement. In this paper, we propose a new dataset that includes 91 face video clips that were recorded in different conditions. We also provide a semi-automatic ground-truth generation tool that can easily be used to evaluate the performance of face tracking systems. This tool helps to maintain the consistency of the definitions for the ground-truth in each frame. The resulting video data set is used to evaluate well-known approaches and test their efficiency.
Abstract
This paper will explore the problem of domestic violence in the UK. It will begin by defining the problem and then set out estimates of the extent of the problem, while also examining the problems that are involved in measurement . It will then examine the policing strategies that have been put in place to tackle this problem, such as intelligence gathering, effective investigations, and risk management techniques. The paper will also highlight the importance of multi-agency involvement when dealing with domestic violence and the wide range of orders that have been created in order to help deal with this problem.
Abstract
Hidden nodes have a key role in the information processing of feed-forward neural networks in which inputs are processed through a series of weighted sums and nonlinear activation functions. In order to understand the role of hidden nodes, we must analyze the effect of the nonlinear activation functions on the weighted sums to hidden nodes. In this paper, we focus on the effect of nonlinear functions in a viewpoint of information theory. Under the assumption that the nonlinear activation function can be approximated piece-wise linearly, we prove that the entropy of weighted sums to hidden nodes decreases after piece-wise linear functions. Therefore, we argue that the nonlinear activation function decreases the uncertainty among hidden nodes. Furthermore, the more the hidden nodes are saturated, the more the entropy of hidden nodes decreases. Based on this result, we can say that, after successful training of feed-forward neural networks, hidden nodes tend not to be in linear regions but to be in saturated regions of activation function with the effect of uncertainty reduction.
Abstract
When developing a classifier using various objective functions, it is important to compare the performances of the classifiers. Although there are statistical analyses of objective functions for classifiers, simulation results can provide us with direct comparison results and in this case, a comparison criterion is considerably critical. A Receiver Operating Characteristics (ROC) graph is a simulation technique for comparing classifiers and selecting a better one based on a performance. In this paper, we adopt the ROC graph to compare classifiers trained by mean-squared error, cross-entropy error, classification figure of merit, and the n-th order extension of cross-entropy error functions. After the training of feed-forward neural networks using the CEDAR database, the ROC graphs are plotted to help us identify which objective function is better.
Abstract
This paper proposes an approach for visualizing research trends using theme maps and extra information. The proposed algorithm includes the following steps. First, text mining is used to construct a vector space of keywords. Second, correspondence analysis is employed to reduce high-dimensionality and to express relationships between documents and keywords. Third, kernel density estimation is applied in order to generate three-dimensional data that can show the concentration of the set of documents. Fourth, a cartographical concept is adapted for visualizing research trends. Finally, relative vitalization information is provided for more accurate research trend analysis. The algorithm of the proposed approach is tested using papers about Traditional Korean Medicine.
Abstract
Previous studies of the Korean wave have focused mainly on fan clubs by taking an ethnographic approach in the context of countries in Southeast Asia and, in a minor extension, Europe. This study fills the gap in the literature by providing a social network analysis of Tweets in the context of Mexico. We used the Twitter API in order to collect Twitter comments with the hashtag #kpop from March to August 2012, analyzing them with a set of webometric methodologies. The results indicate that #kpop power Twitterians in Mexico were more likely to be related to the public television broadcast. The sent Tweets were usually related to their programs and promotion for Kpop artists. These Tweets tended to be positive, and according to URLs, not only Kpop but also Korean dramas had considerable influence on the Korean wave in Mexico.
Abstract
Subject classification of journals is important because it can be utilized for the improvement of scholarly information services and analysis by research area. The classification by experts in a subject area wastes a lot of time and expense. On the other hand, the simple classification with basic information, such as the journal title has limitations. To solve this problem, this paper suggests the automatic classification of Korean journals using the SCI journals information cited by Korean journals, and an analysis of the classification result. In particular, this study adopted the WoS subject categories for classification to support the base for comparison between the Korean citation database and the global citation database (KSCI vs. SCI).
Abstract
The paper considers the challenges involved in measuring the similarities between time series, such as time shifts and the mixture of frequencies. To improve recognition accuracy, we investigate an improved linear dynamical system for discovering prominent features by exploiting the evolving dynamics and correlations in a time series, as the quality of unsupervised pattern recognition relies strongly on the extracted features. The proposed approach yields a set of compact extracted features that boosts the accuracy and reliability of clustering for time series data. Experimental evaluations are carried out on time series applications from the scientific, socio-economic, and business domains. The results show that our method exhibits improved clustering performance compared to conventional methods. In addition, the computation time of the proposed approach increases linearly with the length of the time series.
Abstract
In this paper, we propose a pioneering concept of DPD(Disaster Prevention Design) to realize a securable society in the future. Features of danger in the future society are expected to be diverse, abrupt occurring, large scale, and complicated ways. Due to increment of dangers with their features of uncertainty, interactivity, complexity, and accumulation, human-oriented design concept naturally participates in activities to prevent our society against disasters effectively. We presented DPD is an essential design activity in order to cope with dangers expected in the future societies as well as realize securable environments. DPD is also an integrated design aids including preemptive protections, rapid preparing, recovery, and interactive cooperation. We also expect these activities of DPD is effective for generation of new values in the market, satisfaction of social needs, expansion of design industry, and a novel chance for development in the future society. Throughout this paper, we submit various aspects of DPD concepts including definition, classification, scope, necessity, strategy, influencing elements, process, and its principle. We expect these concepts will be the seed and/or basement of DPD research for the future works. For the direction of study for DPD in the future, we emphasize alarm system for preemptive protection rather than recovery strategy for the damage occurred. We also need to research about progressive prevention techniques and convergence with other areas of design. In order to transfer the concept of product design from facility-oriented mechanism to human-oriented one, we should develop new kinds of city basis facilities, public-sense design concepts referred to social weak-party, e-Learning content design preparing disasters, and virtual simulation design etc. On the other hand, we have to establish laws and regulations to force central and/or provincial governments to have these DPD strategies applying their regional properties. Modern design activities are expanding to UI(user interface) content design area overcoming the conventional design concept of product and/or service. In addition, designers are recognized as art directors or life stylists who will change the human life and create the social value. DPD can be divided into prevention design, preparedness design, response design, and recovery design. Five strategies for successful DPD are Precaution-oriented, Human-oriented, Sense-oriented, Legislation, and Environment Friendly Strategies.
Abstract
Usually, cloud storage systems are developed based on DFS (Distributed File System) for scalability and reliability reasons. DFSs are designed to improve throughput than IO response time, and therefore, they are appropriate for batch processing jobs. Recently, cloud storage systems have been used for update intensive applications such as OLTP and so on. However, in DFSs, in-place update operations are not carefully considered. Therefore, when updates are frequent, I/O performance of DFSs are degraded significantly. DFSs with RAID techniques have been proposed to improve their performance and reliability. Their performance degradation caused by frequent update operations can be more significant. In this paper, we propose an in-place update method for DFS RAID exploiting a differential logging technique. The proposed method reduces the I/O costs, network traffic and XOR operation costs for RAID. We demonstrate the efficiency of our proposed in-place update method through various experiments.