• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.785-804
• /
• 2017

Due to various factors such as postures, facial expressions and illuminations, face recognition by videos often suffer from poor recognition accuracy and generalization ability, since the within-class scatter might even be higher than the between-class one. Herein we address this problem by proposing a hierarchical cascaded classifier for video face recognition, which is a multi-layer algorithm and accounts for the misclassified samples plus their similar samples. Specifically, it can be decomposed into single classifier construction and multi-layer classifier design stages. In single classifier construction stage, classifier is created by clustering and the number of classes is computed by analyzing distance tree. In multi-layer classifier design stage, the next layer is created for the misclassified samples and similar ones, then cascaded to a hierarchical classifier. The experiments on the database collected by ourselves show that the recognition accuracy of the proposed classifier outperforms the compared recognition algorithms, such as neural network and sparse representation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.5
• /
• pp.1825-1839
• /
• 2015

The final draft of the latest video coding standard, High Efficiency Video Coding (HEVC), was approved in January 2013. The coding efficiency of HEVC surpasses its predecessor, H.264/MPEG-4 Advanced Video Coding (AVC), by using only half of the bitrate to encode the same sequence with similar quality. However, the complexity of HEVC is sharply increased compared to H.264/AVC. In this paper, a method is proposed to decrease the complexity of intra coding in HEVC. Early pruning and an early splitting strategy are applied to the quadtree structure of coding tree units (CTU) and residual quadtree (RQT). According to our experiment, when our method is applied to sequences from Class A to Class E, the coding time is decreased by 44% at the cost of a 1.08% Bjontegaard delta rate (BD-rate) increase on average.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.6
• /
• pp.1586-1605
• /
• 2012

With the prevalence of multimedia applications and the potential commercial usage of Mobile Ad hoc Networks (MANETs) in group communications, Quality of Service (QoS) support became a key requirement. Recently, some researchers studied QoS multicast issues in MANETs. Most of the existing QoS multicast routing protocols are designed with flat topology and small networks in mind. In this paper, we investigate the scalability problem of these routing protocols. In particular, a Position-Based QoS Multicast Routing Protocol (PBQMRP) has been developed. PBQMRP builds a source multicast tree guided by the geographic information of the mobile nodes, which helps in achieving more efficient multicast delivery. This protocol depends on the location information of the multicast members which is obtained using a location service algorithm. A virtual backbone structure has been proposed to perform this location service with minimum overhead and this structure is utilized to provide efficient packet transmissions in a dynamic mobile Ad hoc network environment. The performance of PBQMRP is evaluated by performing both quantitative analysis and extensive simulations. The results show that the used virtual clustering is very useful in improving scalability and outperforms other clustering schemes. Compared to On-Demand Multicast Routing Protocol (ODMRP), PBQMRP achieves competing packet delivery ratio and significantly lower control overhead.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3725-3748
• /
• 2018

Text data distribution is often imbalanced. Imbalanced data is one of the challenges in text classification, as it leads to the loss of performance of classifiers. Many studies have been conducted so far in this regard. The proposed solutions are divided into several general categories, include sampling-based and algorithm-based methods. In recent studies, feature selection has also been considered as one of the solutions for the imbalance problem. In this paper, a novel one-sided feature selection known as probabilistic feature selection (PFS) was presented for imbalanced text classification. The PFS is a probabilistic method that is calculated using feature distribution. Compared to the similar methods, the PFS has more parameters. In order to evaluate the performance of the proposed method, the feature selection methods including Gini, MI, FAST and DFS were implemented. To assess the proposed method, the decision tree classifications such as C4.5 and Naive Bayes were used. The results of tests on Reuters-21875 and WebKB figures per F-measure suggested that the proposed feature selection has significantly improved the performance of the classifiers.

• Korean Journal of Remote Sensing
• /
• v.34 no.1
• /
• pp.141-150
• /
• 2018

Crop type classification is essential for supporting agricultural decisions and resource monitoring. Remote sensing techniques, especially using hyperspectral imagery, have been effective in agricultural applications. Hyperspectral imagery acquires contiguous and narrow spectral bands in a wide range. However, large dimensionality results in unreliable estimates of classifiers and high computational burdens. Therefore, reducing the dimensionality of hyperspectral imagery is necessary. In this study, the Random Forest (RF) classifier was utilized for dimensionality reduction as well as classification purpose. RF is an ensemble-learning algorithm created based on the Classification and Regression Tree (CART), which has gained attention due to its high classification accuracy and fast processing speed. The RF performance for crop classification with airborne hyperspectral imagery was assessed. The study area was the cultivated area in Chogye-myeon, Habcheon-gun, Gyeongsangnam-do, South Korea, where the main crops are garlic, onion, and wheat. Parameter optimization was conducted to maximize the classification accuracy. Then, the dimensionality reduction was conducted based on RF variable importance. The result shows that using the selected bands presents an excellent classification accuracy without using whole datasets. Moreover, a majority of selected bands are concentrated on visible (VIS) region, especially region related to chlorophyll content. Therefore, it can be inferred that the phenological status after the mature stage influences red-edge spectral reflectance.

• ETRI Journal
• /
• v.37 no.3
• /
• pp.584-594
• /
• 2015

To date, many different kinds of logic styles for hardware countermeasures have been developed; for example, SABL, TDPL, and DyCML. Current mode-based logic styles are useful as they consume less power compared to voltage mode-based logic styles such as SABL and TDPL. Although we developed TPDyCML in 2012 and presented it at the WISA 2012 conference, we have further optimized it in this paper using a binary decision diagram algorithm and confirmed its properties through a practical implementation of the AES S-box. In this paper, we will explain the outcome of HSPICE simulations, which included correlation power attacks, on AES S-boxes configured using a compact NMOS tree constructed from either SABL, CMOS, TDPL, DyCML, or TPDyCML. In addition, to compare the performance of each logic style in greater detail, we will carry out a mutual information analysis (MIA). Our results confirm that our logic style has good properties as a hardware countermeasure and 15% less information leakage than those secure logic styles used in our MIA.

• Structural Engineering and Mechanics
• /
• v.23 no.5
• /
• pp.455-468
• /
• 2006

Smart structural systems are defined as ones that demonstrate the ability to modify their characteristics and/or properties in order to respond favorably to unexpected severe loading conditions. The performance of such a task requires a set of additional components to be integrated within such systems. These components belong to three major categories, sensors, processors and actuators. It is wellknown that all structural systems entail some level of uncertainty, because of their extremely complex nature, lack of complete information, simplifications and modeling. Similarly, sensors, processors and actuators are expected to reflect a similar uncertain behavior. As it is imperative to be able to evaluate the impact of such components on the behavior of the system, it is as important to ensure, or at least evaluate, the reliability of such components. In this paper, a system model for reliability assessment of smart structural systems is outlined. The presented model is considered a necessary first step in the development of a reliability assessment algorithm for smart structural systems. The system model outlines the basic components of the system, in addition to, performance functions and inter-relations among individual components. A fault tree model is developed in order to aggregate the individual underlying component reliabilities into an overall system reliability measure. Identification of appropriate limit states for all underlying components are beyond the scope of this paper. However, it is the objective of this paper to set up the necessary framework for identifying such limit states. A sample model for a three-story single bay smart rigid frame, is developed in order to demonstrate the proposed framework.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.4
• /
• pp.27-34
• /
• 1998

In this paper we present a method for automatic motion vector and brightness based video indexing and retrieval. We extract a representational frame from each shot and compute some motion vector and brightness based features. For each R-frame we compute the optical flow field; motion vector features are then derived from this flow field, BMA(block matching algorithm) is used to find motion vectors and Brightness features are related to the cut detection of method brightness histogram. A video database provided contents based access to video. This is achieved by organizing or indexing video data based on some set of features. In this paper the index of features is based on a B+ search tree. It consists of internal and leaf nodes stores in a direct access a storage device. This paper defines the problem of video indexing based on video data models.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.4
• /
• pp.341-352
• /
• 1990

In this paper, we introduce tree types of switching networks, I, e., a fully segregated type, a partially integrated type, and a fully integrated type switch, to accommodate nx 64Kb/s multi-slot connection traffic and analyze their blocking probabilites for the different traffic mixes by utilizing a computational algorithm of blocking probability, and finally determine the traffic handling capacity which satisfies the given grade of service. The fully integrated type switch can accommodate the ISDN traffic with relatively low wideband traffic. However, either the partially integrated type or the fully segregated type switch is needed to accommodate the ISDN traffic as the wideband traffic increases. This result can be usilized in the design of ISDN switching networks accommodating multi-slot connection traffic.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.3
• /
• pp.234-240
• /
• 1999

This paper presents a new approach for large-scale generator maintenance scheduling optimizations. The generator preventive maintenance scheduling problems are typical discrete dynamic n-dimensional vector optimization ones with several inequality constraints. The considered objective function to be minimized a subset of{{{{ { R}^{n } }}}} space is the variance (i.g., second-order momentum) of operating reserve margin to levelize risk or reliability during a year. By its nature of the objective function, the optimal solution can only be obtained by enumerating all combinatorial states of each variable, a task which leads to computational explosion in real-world maintenance scheduling problems. This paper proposes a new priority search mechanism based on each generator's discrete sensitivity value which was analytically developed in this study. Unlike the conventional capacity-based priority search, it can prevent the local optimal trap to some extents since it changes dynamically the search tree in each iteration. The proposed method have been applied to two test systems (i.g., one is a sample system with 10 generators and the other is a real-world lage scale power system with 280 generators), and the results anre compared with those of the conventional capacith-based search method and combinatorial optimization method to show the efficiency and effectiveness of the algorithm.