• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.11-15
• /
• 2003

Amount of biological data information has been increasing exponentially. In order to cope with this bio-information explosion, it is necessary to construct a biological data information integration system. The integration system could provide useful services for bio-application developers by answering general complex queries that require accessing information from heterogeneous bio data sources, and easily accommodate a new database into the integrated systems. In this paper, we analyze architectures and mechanisms of existing integration systems with their advantages and disadvantages. Based on this analysis and user requirement studies, we propose an integration system framework that embraces advantages of the existing systems. More specifically, we propose an integration system architecture composed of a mediator and wrappers, which can offer a service interface layer for various other applications as well as independent biologists, thus playing the role of database management system for biology applications. In other words, the system can help abstract the heterogeneous information structures and formats from the application layer. In the system, the wrappers send database-specific queries and report the result to the mediator using XML. The proposed system could facilitate in silico knowledge discovery by allowing combination of numerous discrete biological information databases.

• Journal of information and communication convergence engineering
• /
• 제8권1호
• /
• pp.6-12
• /
• 2010

In this paper a cross layer protocol, referred to as an underwater ad-hoc communication (UAC) protocol, is proposed for underwater acoustic networks (UANets). An underwater node (UN), which tries to transfer data to another UN or a buoy in ad-hoc manner, can access channel as well as determine routing path by employing the UAC protocol. The channel access, route determination, and reliable data transfer are designed being adaptive to underwater environments. In addition, we propose both UN and packet architectures in order to efficiently implement the UAC protocol for UANets.

• Computers and Concrete
• /
• 제10권6호
• /
• pp.557-573
• /
• 2012

This paper discusses the combined application of two different techniques, Neural Networks (NN) and Principal Component Analysis (PCA), for improved prediction of concrete properties. The combination of these approaches allowed the development of six neural networks models for predicting slump and compressive strength of concrete with mineral additives such as blast furnace slag, fly ash and silica fume. The Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian regularization was used in all these models. They are produced to implement the complex nonlinear relationship between the inputs and the output of the network. They are also established through the incorporation of a huge experimental database on concrete organized in the form Mix-Property. Thus, the data comprising the concrete mixtures are much correlated to each others. The PCA is proposed for the compression and the elimination of the correlation between these data. After applying the PCA, the uncorrelated data were used to train the six models. The predictive results of these models were compared with the actual experimental trials. The results showed that the elimination of the correlation between the input parameters using PCA improved the predictive generalisation performance models with smaller architectures and dimensionality reduction. This study showed also that using the developed models for numerical investigations on the parameters affecting the properties of concrete is promising.

• 전자공학회논문지C
• /
• 제35C권2호
• /
• pp.29-35
• /
• 1998

This paper describes architectures and design of a SIMD type parallel image processing chip called SliM-II. The chiphas a linear array of 64 processing elements (PEs), operates at 30 MHz in the worst case simulation and gives at least 1.92 GIPS. In contrast to existing array processors, such as IMAP, MGAP-2, VIP, etc., each PE has a multiplier that is quite effective for convolution, template matching, etc. The instruction set can execute an ALU operation, data I/O, and inter-PE communication simulataneously in a single instruction cycle. In addition, during the ALU/multiplier operation, SliM-II provides parallel move between the register file and on-chip memory as in DSP chips, SliM-II can greatly reduce the inter-PE communication overhead, due to the idea a sliding, which is a technique of overlapping inter-PE communication with computation. Moreover, the bandwidth of data I/O and inter-PE communication increases due to bit-parallel data paths. We used the COMPASS$^{TM}$ 3.3 V 0.6.$\mu$m standrd cell library (v8r4.10). The total number of transistors is about 1.5 muillions, the core size is 13.2 * 13.0 mm$^{2}$ and the package type is 208 pin PQ2 (Power Quad 2). The performance evaluation shows that, compared to a existing array processors, a proposed architeture gives a significant improvement for algorithms requiring multiplications.s.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2735-2751
• /
• 2020

The emergence of Software Defined Networking (SDN) overcomes the limitations of traditional networking architectures. There are some advantages in SDN which are centralized global network view, programmability, and separation of the data plane and control plane. Due to the limitation of data plane storage capacity in SDN, it is necessary to process the redundancy rules of switch. In this paper, we propose a method for active detection and processing of redundant rules. We use the result generated by the customized probe package to detect redundant rules. And by checking the forwarding behavior of probe packets in the data plane, the redundancy rules are further processed. Furthermore, in order to quickly check the dynamic networks, we propose an incremental algorithms for rapidly evolve the network strategies. We conduct simulation experiments on Matlab to verify the feasibility of the algorithm. The influence of some parameters on the result are discussed.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제14권4호
• /
• pp.391-406
• /
• 2014

The performance of General-Purpose computation on Graphics Processing Units (GPGPU) is heavily dependent on the memory access behavior. This sensitivity is due to a combination of the underlying Massively Parallel Processing (MPP) execution model present on GPUs and the lack of architectural support to handle irregular memory access patterns. Application performance can be significantly improved by applying memory-access-pattern-aware optimizations that can exploit knowledge of the characteristics of each access pattern. In this paper, we present an algorithmic methodology to semi-automatically find the best mapping of memory accesses present in serial loop nest to underlying data-parallel architectures based on a comprehensive static memory access pattern analysis. To that end we present a simple, yet powerful, mathematical model that captures all memory access pattern information present in serial data-parallel loop nests. We then show how this model is used in practice to select the most appropriate memory space for data and to search for an appropriate thread mapping and work group size from a large design space. To evaluate the effectiveness of our methodology, we report on execution speedup using selected benchmark kernels that cover a wide range of memory access patterns commonly found in GPGPU workloads. Our experimental results are reported using the industry standard heterogeneous programming language, OpenCL, targeting the NVIDIA GT200 architecture.

• Nuclear Engineering and Technology
• /
• 제49권6호
• /
• pp.1165-1171
• /
• 2017

The traditional form of parallelism in Monte Carlo particle transport simulations, wherein each individual particle history is considered a unit of work, does not lend itself well to data-level parallelism. Event-based algorithms, which were originally used for simulations on vector processors, may offer a path toward better utilizing data-level parallelism in modern computer architectures. In this study, a simple model is developed for estimating the efficiency of the event-based particle transport algorithm under two sets of assumptions. Data collected from simulations of four reactor problems using OpenMC was then used in conjunction with the models to calculate the speedup due to vectorization as a function of the size of the particle bank and the vector width. When each event type is assumed to have constant execution time, the achievable speedup is directly related to the particle bank size. We observed that the bank size generally needs to be at least 20 times greater than vector size to achieve vector efficiency greater than 90%. When the execution times for events are allowed to vary, the vector speedup is also limited by differences in the execution time for events being carried out in a single event-iteration.

• International Journal of Computer Science & Network Security
• /
• 제21권5호
• /
• pp.256-266
• /
• 2021

The Convolutional Neural Network (CNN) has recently made potential improvements in face verification applications. In fact, different models based on the CNN have attained commendable progress in the classification rate using a massive amount of data in an uncontrolled environment. However, the enormous computation costs and the considerable use of storage causes a noticeable problem during training. To address these challenges, we focus on relevant data trained within the CNN model by integrating a lifting method for a better tradeoff between the data size and the computational efficiency. Our approach is characterized by the advantage that it does not need any additional space to store the features. Indeed, it makes the model much faster during the training and classification steps. The experimental results on Labeled Faces in the Wild and YouTube Faces datasets confirm that the proposed CNN framework improves performance in terms of precision. Obviously, our model deliberately designs to achieve significant speedup and reduce computational complexity in deep CNNs without any accuracy loss. Compared to the existing architectures, the proposed model achieves competitive results in face recognition tasks

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3275-3298
• /
• 2022

Cloud-based architectures for precision agriculture are domain-specific controlled and require remote access to process and analyze the collected data over third-party cloud computing platforms. Due to the dynamic changes in agricultural parameters and restrictions in terms of accessing cloud platforms, developing a locally controlled and real-time configured architecture is crucial for efficient water irrigation and farmers management in agricultural fields. Thus, we present a new implementation of an independent sensor-enabled architecture using variety of wireless-based sensors to capture soil moisture level, amount of supplied water, and compute the reference evapotranspiration (ETo). Both parameters of soil moisture content and ETo values was then used to manage the amount of irrigated water in a small-scale agriculture field for 356 days. We collected around 34,200 experimental data samples to evaluate the performance of the architecture under different agriculture parameters and conditions, which have significant influence on realizing real-time monitoring of agricultural fields. In a proof of concept, we provide empirical results that show that our architecture performs favorably against the cloud-based architecture, as evaluated on collected experimental data through different statistical performance models. Experimental results demonstrate that the architecture has potential practical application in a many of farming activities, including water irrigation management and agricultural condition control.

• 한국인터넷방송통신학회논문지
• /
• 제13권2호
• /
• pp.1-7
• /
• 2013

최근 빅 데이터 관리가 정보기술 분야의 학계와 업계에서 중요한 이슈로 떠오르고 있다. 빅 데이터 중 소프트웨어 시스템에서 필연적으로 생성되는 대표적인 유형 중 하나가 로그 데이터이다. 로그 데이터는 서비스 제공자가 더 나은 서비스를 제공하고 소프트웨어의 품질을 향상시키기 위해 필요하다. 따라서 적절한 방법으로 로그 데이터를 수집하고 이를 분석할 수 있는 인프라 환경을 구축하는 것은 매우 중요하다. 본 논문은 로그 데이터에 특화된 새로운 빅 데이터 관리 기법을 제안한다. 제안하는 기법은 다수의 클라이언트 어플리케이션에서 생성되는 로그 데이터를 네트워크를 통해 전송하고 이를 실시간으로 저장한 후 분석할 수 있는 아키텍처를 제공한다. 해당 아키텍처는 서버-클라이언트 환경에서 로그의 비동기적인 처리를 지원하여 원격 로깅임에도 불구하고 데이터 처리의 병목 현상이나 클라이언트의 성능 저하를 발생시키지 않는다. 제안하는 기법을 실제 시스템에 구현하고 실측한 결과 확장성 있는 로그 데이터 관리가 이루어짐을 확인하였다. 특히, 본 논문에서는 모든 구현을 오픈소스 소프트웨어에 기반하여 수행했으며, 개발 프로토타입 또한 오픈소스 소프트웨어 형태로 공개하여 누구나 사용할 수 있도록 하였다.