• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.722-729
• /
• 2010

Prediction problems are widely used in medical domains. For example, computer aided diagnosis or prognosis is a key component in a CDSS (Clinical Decision Support System). SVMs with nonlinear kernels like RBF kernels, have shown superior accuracy in prediction problems. However, they are not preferred by physicians for medical prediction problems because nonlinear SVMs are difficult to visualize, thus it is hard to provide intuitive interpretation of prediction results to physicians. Nomogram was proposed to visualize SVM classification models. However, it cannot visualize nonlinear SVM models. Localized Radial Basis Function (LRBF) was proposed which shows comparable accuracy as the RBF kernel while the LRBF kernel is easier to interpret since it can be linearly decomposed. This paper presents a new tool named VRIFA, which integrates the nomogram and LRBF kernel to provide users with an interactive visualization of nonlinear SVM models, VRIFA visualizes the internal structure of nonlinear SVM models showing the effect of each feature, the magnitude of the effect, and the change at the prediction output. VRIFA also performs nomogram-based feature selection while training a model in order to remove noise or redundant features and improve the prediction accuracy. The area under the ROC curve (AUC) can be used to evaluate the prediction result when the data set is highly imbalanced. The tool can be used by biomedical researchers for computer-aided diagnosis and risk factor analysis for diseases.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.75-84
• /
• 2012

HMM-based Text-to-Speech systems generally utilize context dependent tri-phone units from a large corpus speech DB to enhance the synthetic speech. To downsize a large corpus speech DB, acoustically similar tri-phone units are clustered based on the decision tree using context dependent information. Context dependent information includes phoneme sequence as well as prosodic information because the naturalness of synthetic speech highly depends on the prosody such as pause, intonation pattern, and segmental duration. However, if the prosodic information was complicated, many context dependent phonemes would have no examples in the training data, and clustering would provide a smoothed feature which will generate unnatural synthetic speech. In this paper, instead of complicate prosodic information we propose a simple three prosodic boundary types and decision tree questions that use rising tone, falling tone, and monotonic tone to improve naturalness. Experimental results show that our proposed method can improve naturalness of a HMM-based Korean TTS and get high MOS in the perception test.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.10
• /
• pp.357-364
• /
• 2014

The first mission for the IoT based hyper-connectivity communication is developing a device-to-device communication technique in infra-less low-power and lossy networks. In a low-power and lossy wireless network, IoT devices and routers cannot keep the original path toward the destination since they have the limited memory. Different from the previous light-weight routing protocols focusing on the reduction of the control messages, the proposed scheme provides the light-weight IPv6 address auto-configuration, IPv6 neighbor discovery and routing protocol in a IoT capable infra-less wireless networks with the bloom filer and enhanced rank concepts. And for the first time we evaluate our proposed scheme based on the modeling of various probability distributions in the IoT environments with the lossy wireless link. Specifically, the proposed enhanced RPL based light-weight routing protocol improves the robustness with the multi-paths locally established based on the enhanced rank concepts even though lossy wireless links are existed. We showed the improvements of the proposed scheme up to 40% than the RPL based protocol.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.1-10
• /
• 2012

Improving operating frequency of processors is no longer today's issues; a multiprocessor technique which integrates many processors has received increasing attention. Currently, high-performance processors that integrate 64 or 128 cores are developing for large data processing over 2, 4, or 8 processor cores. This paper proposes an optimal many-core processor for synthesizing guitar sounds. Unlike the previous research in which a processing element (PE) was assigned to support one of guitar strings, this paper evaluates the impacts of mapping different numbers of PEs to one guitar string in terms of performance and both area and energy efficiencies using architectural and workload simulations. Experimental results show that the maximum area energy efficiencies were achieved at PEs=24 and 96, respectively, for synthesizing guitar sounds with sampling rate of 44.1kHz and 16-bit quantization. The synthesized sounds were very similar to original guitar sounds in their spectra. In addition, the proposed many-core processor was 1,235 and 22 times better than TI TMS320C6416 in area and energy efficiencies, respectively.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.12 no.3
• /
• pp.64-129
• /
• 1992

최근 초지중심 사양형태의 증가와 초지면적의 확대에 따라 단순한 사료로서가 아니라 영양가치가 높고 기호성이 높은 목초생산이 요구되고 있다. 그러나, 고위생산을 위해 다량으로 사용된 질소질비료에 의하여 질산태 중독 등의 문제가 야기되고 있어 목초의 생리 및 영양에 관한 연구가 필요하게 되었다. 사료성분 혹은 영양가치에 대한 연구는 이미 일찍부터 다루어져 왔으나, 주로 야초류, 청예작물 및 농가부산물 등의 일반성분 특히, 조단백질과 조섬유함량의 연구가 주가 되었고 다년생 목초류에 대한 연구는 1975년경부터 본격화 되기 시작하였다. 그동안 한국초지학회지와 축산학회지($1972\sim1991$)에 게재된 총 151편의 생리 및 영양에 관한 연구 중에서 다년생 목초류를 취급한 것은 불과 63편에 머물고 있다. 이 분야의 연구는 각종 목초 사료작물에 대한 재배조건과 생육단계에 따른 생리생태학적 연구와 사료성분, 소화율 및 가소화양분 함량의 일반적인 변화, 경향을 검토하여 사료 가치 평가를 위한 기준으로 삼았다. 그러나 다년생 목초류는 물론 사료 작물에 있어서 육종 생리분야의 연구는 매우 미흡한 상태로써 단지 발아, 생육, 저장탄수화물 및 유독성분 등 단편적인 연구만이 행해지고 있을 뿐이다. 또한 사료 성분이 가축의 기호성에 미치는 영향을 구명하기 위한 연구는 거의 이루어지고 있지 않으므로 금후 탄수화물과 미량 요소에 대한 자세한 연구 검토가 필요하다고 생각된다. 특히 목초와 사료작물의 화학적인 조성과 가축의 생리에 관련한 여러가지 문제들도 앞으로 보다 깊이 연구되어야 할 과제라고 생각된다.권을 잡기 위해 10년지기였던 IBM과 MS사는 각각 OS/2와 윈도즈를 내세우고 양보할 수 없는 힘겨루기에 들어갔다. 또 이들 양사는 펜컴퓨터,멀티미디어등 차세대제품의 운영체제 시장을 둘러싸고 일찍부터 격전에 들어갔으며 IBM과 MS사의 혼전을 틈타 썬마이크로시스템을 필두로한 워크스테이션 업체 및 유닉스진영까지 고성능 PC시장을 겨냥한 OS를 속속 개발, 90년대의 OS 전쟁은 한치 앞을 내다볼 수 없는 안개국면으로 접어들고 있다. DOS에서 32비트시대,펜컴퓨터, 멀티미디어에 이르는 차세대제품을 둘러싼 업계의 OS 쟁탈전을 통해 OS의 발전동향과 미래를 전망해 본다. results in the large change of the objective function, the sum of squares of deviations of the observed and computed groundwater levels. 본 논문에서는 가파른 산사면에서 산사태의 발생을 예측하기 위한 수문학적 인 지하수 흐름 모델을 개발하였다. 이 모델은 물리적인 개념에 기본하였으며, Lumped-parameter를 이용하였다. 개발된 지하수 흐름 모델은 두 모델을 조합하여 구성되어 있으며, 비포화대 흐름을 위해서는 수정된 abcd 모델을, 포화대 흐름에 대해서는 시간 지체 효과를 고려할 수 있는 선형 저수지 모델을 이용하였다. 지하수 흐름 모델은 토층의 두께, 산사면의 경사각, 포화투수계수, 잠재 증발산 량과 같은 불확실한 상수들과 a, b, c, 그리고 K와 같은 자유모델변수들을 가진다. 자유모델변수들은 유입-유출 자료들로부터 평가할 수

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.9
• /
• pp.2311-2319
• /
• 1999

We present two heuristic algorithms for the task allocation problem (NP-complete problem) in parallel computing. The problem is to find an optimal mapping of multiple communicating tasks of a parallel program onto the multiple processing nodes of a distributed-memory multicomputer. The purpose of mapping these tasks into the nodes of the target architecture is the minimization of parallel execution time without sacrificing solution quality. Many heuristic approaches have been employed to obtain satisfactory mapping. Our heuristics are based on genetic algorithms and simulated annealing. We formulate an objective function as a total computational cost for a mapping configuration, and evaluate the performance of our heuristic algorithms. We compare the quality of solutions and times derived by the random, greedy, genetic, and annealing algorithms. Our experimental findings from a simulation study of the allocation algorithms are presented.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.552-555
• /
• 2019

디지털 트윈이란 현실 세계의 물리적인 사물을 컴퓨터 상에 동일하게 가상화 시키는 기술을 의미하는 것으로, 물리적 사물이나 시스템을 모델링하거나 IoT 기술에 접목되어 활용되고 있는 기술이다. 디지털 트윈 기술은 가상의 모델을 무한정 시뮬레이션을 통해 동작을 튜닝하고 환경변화에 대한 대응을 미리 실험하여 리스크를 최소화할 수 있는 장점을 지닌다. 최근 인공지능이나 기계학습에 관련된 기술들이 주목받기 시작하면서, 이와 같은 물리적인 사물의 모델링 작업을 데이터 기반으로 수행하려는 시도가 증가하고 있다. 특히, 산업현장에서 많이 활용되는 인더스트리 4.0 공장 자동화의 핵심인 협력 로봇의 디지털 트윈을 구축하기 위해서는 로봇의 동작을 인지하는 과정이 필수적으로 요구된다. 그러나 현재 협력 로봇의 동작을 인지하기 위한 시도는 미비하며, 센서 데이터를 기반으로 동작을 역으로 예측하는 기술은 더욱 그렇다. 따라서 본 논문에서는 로봇의 동작을 인지하기 위해 가정용 협력 로봇에서 전류 및 관성 데이터를 수집하기 위한 실험 환경을 구축하고, 수집한 센서 데이터를 기반으로 한 동작 예측 모델을 제안하고자 한다. 제안하는 방식은 로봇의 동작 명령어를 조인트 위치 기반으로 분류하고 전류와 위치 센서 값을 사용하여 학습을 통해 예측하는 방식이다. SVM 을 이용하여 학습한 결과, 모델의 성능은 평균적으로 정확도, 정밀도, 및 재현율이 모두 96%로 평가되었다.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.31-40
• /
• 2012

u-GIS DSMSs have been researched to deal with various sensor data from GeoSensors in ubiquitous environment. Also, they has been more important for high availability. The data from GeoSensors have some characteristics that increase explosively. This characteristic could lead memory overflow and data loss. To solve the problem, various load shedding methods have been researched. Traditional methods drop the overloaded tuples according to a particular criteria in a single server. Tuple deletion sensitive queries such as aggregation is hard to satisfy accuracy. In this paper a dual processing load shedding method is suggested to improve the accuracy of aggregation in clustering environment. In this method two nodes use replicated stream data for high availability. They process a stream in two nodes by using a characteristic they share stream data. Stream data are synchronized between them with a window as a unit. Then, processed results are merged. We gain improved query accuracy without data loss.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.69-78
• /
• 2005

As the study and use of P2P systems are diversified, the effect of excessive amount of traffic, which occurs in searching peers' resource and is considered as a network bandwidth Problem, cannot let the matter Pass without making a protest. In case P2P application doesn't reduce network traffic, it can be much effected to use bandwidth smoothly in the internet environment where various network applications lie scattered and there will be inconvenience when many network users makes use of related applications . In this Paper, we propose a pure P2P model based-broadcasting technique for producing successful hit ratio and traffic amount in the weakly connected environment based-P2P system where situation of peers' connection and exit is ambiguous . The proposed searching technique is designed/implemented to improve a resident problem in the related system and we have estimated the performance of the proposed searching technique comparing our technique with the existing broadcasting based-searching technique .

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.1
• /
• pp.1-8
• /
• 2009

Learning user's preference is a key issue in intelligent system such as personalized service. The study on user preference model has adapted simple user preference model, which determines a set of preferred keywords or topic, and weights to each target. In this paper, we recommend multi-perspective user preference model that factors sentiment information in the model. Based on the topicality and sentimental information processed using natural language processing techniques, it learns a user's preference. To handle timc-variant nature of user preference, user preference is calculated by session, short-term and long term. User evaluation is used to validate the effect of user preference teaming and it shows 86.52%, 86.28%, 87.22% of accuracy for topic interest, keyword interest, and keyword favorableness.