• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.381-391
• /
• 2016

The Joint Bayesian (JB) method has been used in most state-of-the-art methods for face verification. However, since the publication of the original JB method in 2012, no improved verification method has been proposed. A lot of studies on face verification have been focused on extracting good features to improve the performance in the challenging Labeled Faces in the Wild (LFW) database. In this paper, we propose an improved version of the JB method, called the two-dimensional Joint Bayesian (2D-JB) method. It is very simple but effective in both the training and test phases. We separated two symmetric terms from the three terms of the JB log likelihood ratio function. Using the two terms as a two-dimensional vector, we learned a decision line to classify same and not-same cases. Our experimental results show that the proposed 2D-JB method significantly outperforms the original JB method by more than 1% in the LFW database.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.3 no.1
• /
• pp.65-75
• /
• 1993

Fuzzy data is a phenomenon often occurring in real life. There is the inherent vagueness of classification terms referring to a continuous scale, the uncertainty of linguistic terms such as "I almost agree" or the vagueness of terms and concepts due to the statistical variability in communication [20] and many more. Previously, such fuzzy data was approximated by non-fuzzy (crisp) data, which obviously did not lead to a correct and precise representation of the real world. Fuzzy set theory has been developed to represent and manipulate fuzzy data [18]. Explicitly managing the degree of fuzziness in databases allows the system to distinguish between what is known, what is not known and what is partially known. Systems in the literature whose specific objective is to handle imprecision in databases present various approaches. This paper is concerned with the different ways uncertainty and imprecision are handled in database design. It outlines the major areas of fuzzification in (relational) database systems.

• Journal of applied mathematics & informatics
• /
• v.41 no.3
• /
• pp.647-656
• /
• 2023

In this work, we are concerned by the problem of identification of noisy terms which arise in singular problem as for remote sensing problems, and which are modeled by a linear singular parabolic equation. For the reason of missing some data that could be arisen when using the traditional sentinel method, the later will be changed by a new sentinel method for attaining the same purpose. Such new method is a particular least square-like method which permits one to distinguish between the missing terms and the pollution terms. In particular, a sentinel method will be given here in its more realistic setting for singular parabolic problems, where in this case, the observation and the control have their support in different open sets. The problem of finding a new sentinel is equivalent to finding singular optimality system of the least square control for the parabolic equation that we solve.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.1
• /
• pp.15-22
• /
• 2004

Some recent advances in stability and optimality for the nonlinear receding horizon control (NRHC) or the nonlinear model predictive control (NMPC) are assessed. The NRHCs with terminal conditions are surveyed in terms of a terminal state equality constraint, a terminal cost, and a terminal constraint set. Other NRHCs without terminal conditions are surveyed in terms of a control Lyapunov function (CLF) and cost monotonicity. Additional approaches such as output feedback, fuzzy, and neural network are introduced. This paper excludes the results for linear receding horizon controls and concentrates only on the analytical results of NRHCs, not including applications of NRHCs. Stability and optimality are focused on rather than robustness.

• Journal of Korea Multimedia Society
• /
• v.10 no.12
• /
• pp.1733-1740
• /
• 2007

In this paper, we propose a wireless location-based routing algorithm which uses the location information of its neighbor nodes and a destination node. At first, the proposed routing algorithm forwards a packet to the X direction by selecting a closest node to its destination as a next hop in terms of the X coordinate until the packet reaches closely to the packet's destination. Then the packet is forwarded to the Y direction by selecting a closest node to its destination in terms of the Y coordinate. We use a back off mechanism in case that a next hop cannot be found using the proposed routing algorithm, which resolves loops while forwarding. The experimental results show that the proposed routing algorithm performs well like the existing routing algorithms Ad hoc On-demand Distance Vector and Greedy Perimeter Stateless Routing. It is expected to use the proposed routing algorithm in the digital battlefield of military environments and survival games of commercial environments.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.168-176
• /
• 2023

The use of sensors and actuators as a form of controlling cyber-physical systems in resource networks has been integrated and referred to as the Internet of Things (IoT). However, the connectivity of many stand-alone IoT systems through the Internet introduces numerous security challenges as sensitive information is prone to be exposed to malicious users. In this paper, IoT based-security issues ontology is proposed to collect, examine, analyze, prepare, acquire and preserve evidence of IoT security issues challenges. Ontology development has consists three main steps, 1) domain, purpose and scope setting, 2) important terms acquisition, classes and class hierarchy conceptualization and 3) instances creation. Ontology congruent to this paper is method that will help to better understanding and defining terms of IoT based-security issue ontology. Our proposed IoT based-security issue ontology resulting from the protégé has a total of 44 classes and 43 subclasses.

• Journal of Information Processing Systems
• /
• v.3 no.1
• /
• pp.38-42
• /
• 2007

Microarray data includes tens of thousands of gene expressions simultaneously, so it can be effectively used in identifying the phenotypes of diseases. However, the retrieval of functional information from a large corpus of gene expression data is still a time-consuming task. In this paper, we propose an efficient method for identifying functional categories of differentially expressed genes from a micro-array experiment by using Gene Ontology (GO). Our method is as follows: (1) The expression data set is first filtered to include only genes with mean expression values that differ by at least 3-fold between the two groups. (2) The genes are then ranked based on the t-statistics. The 100 most highly ranked genes are selected as informative genes. (3) The t-value of each informative gene is imposed as a score on the associated GO terms. High-scoring GO terms are then listed with their associated genes and represent the functional category information of the micro-array experiment. A system called HMDA (Hallym Micro-array Data analysis) is implemented on publicly available micro-array data sets and validated. Our results were also compared with the original analysis.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.9-13
• /
• 2014

The performance of large scale software applications has been automatically increasing for last few decades under the influence of Moore's law - the number of transistors on a microprocessor roughly doubled every eighteen months. However, on-chip transistors limitations and heating issues led to the emergence of multicore processors. The energy efficient ARM based System-on-Chip (SoC) processors are being considered for future high performance computing systems. In this paper, we present a case study of two widely used parallel programming models i.e. MPI and MapReduce on distributed memory cluster of ARM SoC development boards. The case study application, Black-Scholes option pricing equation, was parallelized and evaluated in terms of power consumption and throughput. The results show that the Hadoop implementation has low instantaneous power consumption that of MPI, but MPI outperforms Hadoop implementation by a factor of 1.46 in terms of total power consumption to execution time ratio.

• Journal of applied mathematics & informatics
• /
• v.28 no.1_2
• /
• pp.295-309
• /
• 2010

In this paper, we study delayed high-order Cohen-Grossberg neural networks with reaction-diffusion terms and Neumann boundary conditions. By using inequality techniques and constructing Lyapunov functional method, some sufficient conditions are given to ensure the existence and convergence of the periodic oscillatory solution. Finally, an example is given to verify the theoretical analysis.

• Genomics & Informatics
• /
• v.19 no.3
• /
• pp.26.1-26.3
• /
• 2021

Previous approaches to create a controlled vocabulary for Japanese have resorted to existing bilingual dictionary and transformation rules to allow such mappings. However, given the possible new terms introduced due to coronavirus disease 2019 (COVID-19) and the emphasis on respiratory and infection-related terms, coverage might not be guaranteed. We propose creating a Japanese bilingual controlled vocabulary based on MeSH terms assigned to COVID-19 related publications in this work. For such, we resorted to manual curation of several bilingual dictionaries and a computational approach based on machine translation of sentences containing such terms and the ranking of possible translations for the individual terms by mutual information. Our results show that we achieved nearly 99% occurrence coverage in LitCovid, while our computational approach presented average accuracy of 63.33% for all terms, and 84.51% for drugs and chemicals.