• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.81-86
• /
• 2012

In this paper, we proposed a new design methodology of a pattern classification rule based on the local linear discriminant analysis expanded from the generic linear discriminant analysis which is used in the local area divided from the whole input space. There are two ways such as k-Means clustering method and the differential evolutionary algorithm to partition the whole input space into the several local areas. K-Means clustering method is the one of the unsupervised clustering methods and the differential evolutionary algorithm is the one of the optimization algorithms. In addition, the experimental application covers a comparative analysis including several previously commonly encountered methods.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.6
• /
• pp.496-504
• /
• 2003

In this paper, the error tolerance of each array element to ensure a given specified error level for the array pattern is analyzed using the Genetic Algorithm. In the conventional deterministic method for synthesis of sonar way problems the computational resource required in the simulation grows rapidly as the number of way elements increases. To alleviate this numerical inefficiency, the Monte-Carlo method may be considered as an alternative technique for array syntheses. However, it is difficult to apply the method to the synthesis of array patterns because of its relatively lower accuracy in spite of moderate computational complexity. A new analysis method for estimating error tolerances in sonar arrays is Proposed since the Genetic Algorithm has significant promise to efficiently solve way synthesis problems. Through several numerical tests in linear and planar arrays, it is demonstrated that the proposed method can provide accurate results for error tolerances of sonar arrays.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.3
• /
• pp.425-432
• /
• 1995

In this paper we propose a design and implementation technique of a universal automatic test pattern generator(UATPG) which is well suited for VLSI digital circuits. UATPG is designed to extend the capabilities of the existing APTG and to provide a convenient environment to computer-aided design(CAD) users. We employ heuristic techniques in line justification and fault propagation for functional gates during test pattern generation for a target fault. In addition, the flip-flops associated with design for testability (DFT) are exploited for pseudo PIs and pseudo POs to enhance the testabilities of VLSI circuits. As a result, UATPG shows a good enhancement in convenient usage and performance.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.39 no.11
• /
• pp.44-52
• /
• 2002

Since memory technology has been developed fast, test complexity and test time have been increased simultaneously. In practice, March algorithms are used widely for detecting various faults. However, March algorithms cannot detect NPSFs(Neighborhood Pattern Sensitive Faults) which must be considered for DRAMs. This paper proposes an effective algorithm for high fault coverage by modifying the conventional March algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2272-2279
• /
• 2014

Mobile applications are software systems running on handheld devices, such as smartphones, PDAs, tablets and so on. The market of mobile application has rapidly expanded in the past few years. In this paper, we present a novel approach to track smartphone application usage from a event logs on the mobile device and analyzed both on client system and usage analysis server. We implemented our client system on Android device based usage analytics platform. Based on the analysis server system, we obtained over 47,000 user base, and we get the user's app usage informations on realtime. In this paper, we describe a large scale deployment-based research for a smartphone usage patterns and usage information visualization techniques.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.8
• /
• pp.80-88
• /
• 2007

High adaptability and scalability are two critical issues in implementing a very complex system in a single chip. To obtain high adaptability and scalability, novel system design methodology known as communication-based system design has gained large attention from SoC designers. NoC (Network-on-Chip) is such an on-chip communication-based design approach for the next generation SoC design. To provide high adaptability and scalability, NoCs employ network interfaces and routers as their main communication structures and transmit and receive packetized data over such structures. However, data packetization, and routing overhead in terms of run time and area may cost too much compared with conventional SoC communication structure. Therefore, in this research, we propose a novel methodology which automatically generates a hybrid communication structure. In this work, we map traditional pin-to-pin wiring structure for frequent and timing critical communication, and map flexible and scalable structure for infrequent, or highly variable communication patterns. Even though, we simplify the communication structure significantly through our algorithm the connectivity or the scalability of the communication modules are almost maintained as the original NoC design. Using this method, we could improve the timing performance by 49.19%, and the area taken by the communication structure has been reduced by 24.03%.

• Journal of Advanced Navigation Technology
• /
• v.19 no.4
• /
• pp.330-337
• /
• 2015

A service in the environments of internet of things (IoT) exist various types with automation facilities and sensors. There can configure so many communication protocols to networking facilities and sensors. To provide efficient various kind of service, a middleware platform, is based on the internet protocol network, is needed a unified access with devices, controlling and monitoring huge kind of facilities and sensors, to provide a efficient IoT service and application configurations. In this paper, we propose a middleware that an application and service interact with automation facilities and monitor sensors. The proposed middleware is designed with adapter pattern that one of the software engineering design pattern. The adapter pattern is to ensure communication with each sensor and to make sure of service scalability. Finally, the proposed component middleware shows that variety sensors can be easily configure the service in the IoT environment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.3
• /
• pp.297-303
• /
• 2009

In this paper, we propose the biomedical spectral pattern classification techniques by the fusion scheme based on the SpPCA and MLP in extended feature space. A conventional PCA technique for the dimension reduction has the problem that it can't find an optimal transformation matrix if the property of input data is nonlinear. To overcome this drawback, we extract features by the SpPCA technique in extended space which use the local patterns rather than whole patterns. In the classification step, individual classifier based on MLP calculates the similarity of each class for local features. Finally, biomedical spectral patterns is classified by the fusion scheme to effectively combine the individual information. As the simulation results to verify the effectiveness, the proposed method showed more improved classification results than conventional methods.

• The Journal of the Korea Contents Association
• /
• v.12 no.2
• /
• pp.52-59
• /
• 2012

Recently, LEDs are used in various fields such as lightings, billboards, displays, and so on. In this paper, we tried to combine a costume with LEDs in a performance environment. To meet the environmental requirements, we propose a digital costume platform which consists of wireless network, an embedded system, a control jacket, a digital skin, and a pattern authoring tool. It is utilized for making a digital costume with LED lighting effects. The embedded system controls LED lighting according to the signals from a show control system through wireless networks. The control jacket can carry the embedded system and connect it with LEDs. The digital skin means a costume with LEDs. The LEDs were designed to fit in performance concept in point of aesthetic. The pattern authoring tool enables users to make timeline-based changing patterns of LED lighting. The proposed platform is a new lighting element in performances. It can expand stage representation techniques and be used as a special effect. It will play a role as a moving light in performances. We evaluated stable operations of our platform by employing it in live performances.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.58-67
• /
• 2009

A correspondence matching is one of the important tasks in computer vision, and it is not easy to find corresponding points in variable environment where a scale, rotation, view point and illumination are changed. A SURF(Speeded Up Robust Features) algorithm have been widely used to solve the problem of the correspondence matching because it is faster than SIFT(Scale Invariant Feature Transform) with closely maintaining the matching performance. However, because SURF considers only gray image and local geometric information, it is difficult to match corresponding points on the image where similar local patterns are scattered. In order to solve this problem, this paper proposes an extended SURF algorithm that uses the invariant color and global geometric information. The proposed algorithm can improves the matching performance since the color information and global geometric information is used to discriminate similar patterns. In this paper, the superiority of the proposed algorithm is proved by experiments that it is compared with conventional methods on the image where an illumination and a view point are changed and similar patterns exist.