• Genomics & Informatics
• /
• 제2권3호
• /
• pp.121-125
• /
• 2004

The purpose of this study was to investigate the use of decision tree for the classification of antimicrobial peptides. The classification was based on the activities of known antimicrobial peptides against common microbes including Escherichia coli and Staphylococcus aureus. A feature selection was employed to select an effective subset of features from available attribute sets. Sequential applications of decision tree with 17 nodes with 9 leaves and 13 nodes with 7 leaves provided the classification rates of $76.74\%$ and $74.66\%$ against E. coli and S. aureus, respectively. Angle subtended by positively charged face and the positive charge commonly gave higher accuracies in both E. coli and S. aureusdatasets. In this study, we describe a successful application of decision tree that provides the understanding of the effects of physicochemical characteristics of peptides on bacterial membrane.

• 한국정보통신학회논문지
• /
• 제4권3호
• /
• pp.517-526
• /
• 2000

본 논문에서는 직접대역확산통신시스템에서 코딩 이득을 향상시키고자 다중 심벌 검파를 수행하는 트렐리스 부호화 변조를 적용하였다. $MDPSK(\pi/4 shift QPSK)$를 트렐리스 부호화된 직접대역확산시스템 적용하고 정보가 인접한 채널 신호의 위상차에 전송된다는 것을 이용하여 1차 위상차 뿐만 아니라 다중위상차를 추출한다. BER특성을 향상시키기 위해, 이러한 다중 위상차를 이용하여 $MDPSK(\pi/4 shift QPSK)$에서 다중 심벌 검파를 수행하는 트렐리스 부호화된 직접대역확산시스템의 비터비 디코더 알고리듬을 설계하여 향상된 코딩 이득을 얻고자 한다. 이러한 시스템을 직접대역확산통신시스템에 적용하였을 때 얻을 수 있는 코딩 이득은 시뮬레이션 결과, AWGN채널에서 TCM의 콘볼류션부호화기의 상태수 4, 8, 16에 따라 3-4dB 정도의 성능향상이 있으며, 레일레이 페이딩 채널에서는 4-5dB정도의 성능 향상이 있음을 알 수 있다. 일반적으로 상태수가 증가할수록 더 큰 코딩 이득을 얻을 수 있다.

• 한국농공학회논문집
• /
• 제57권2호
• /
• pp.1-13
• /
• 2015

The Coupled Model Intercomparison Project Phase 5 (CMIP5), coordinated by the World Climate Research Programme in support of the Intergovernmental Panel on Climate Change (IPCC) AR5, is the most recent, provides projections of future climate change using various global climate models under four major greenhouse gas emission scenarios. There is a wide selection of climate models available to provide projections of future climate change. These provide for a wide range of possible outcomes when trying to inform managers about possible climate changes. Hence, future agrometeorological indicators estimation will be much impacted by which global climate model and climate change scenarios are used. Decision makers are increasingly expected to use climate information, but the uncertainties associated with global climate models pose substantial hurdles for agricultural resources planning. Although it is the most reasonable that quantifying of the future uncertainty using climate change scenarios, preliminary analysis using reasonable factors for selecting a subset for decision making are needed. In order to narrow the projections to a handful of models that could be used in a climate change impact study, we could provide effective information for selecting climate model and scenarios for climate change impact assessment using maximum/minimum temperature, precipitation, reference evapotranspiration, and moisture index of nine Representative Concentration Pathways (RCP) scenarios.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 추계학술대회 학술발표 논문집 제14권 제2호
• /
• pp.433-436
• /
• 2004

In this paper, we introduce a new Fuzzy Polynomial Neural Networks (FPNNS)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNS based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNS-like structure named Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. The proposed design procedure for networks architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IC) based on HCM clustering algorithm and a standard least square method-based learning. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized FSPNN (gFSPNN), the model is experimented with using the time series dataset of gas furnace process.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권15호
• /
• pp.5983-5991
• /
• 2014

Introduction: Upper aero-digestive tract cancer is a multidimensional problem, international trends showing complex rises and falls in incidence and mortality across the globe, with variation across different cultural and socio-economic groups. This paper seeks some explanations and identifies some research and policy needs. Methodological Approach: The literature illustrates the multifactorial nature of carcinogenesis. At the cellular level, it is viewed as a multistep process involving multiple mutations and selection for cells with progressively increasing capacity for proliferation, survival, invasion, and metastasis. Established and emerging risk factors, in addition to changes in incidence and prevalence of cancers of the upper aero-digestive tract, were identified. Risk Factors: Exposure to tobacco and alcohol, as well as diets inadequate in fresh fruits and vegetables, remain the major risk factors, with persistent infection by particular so-called "high risk" genotypes of human papillomavirus increasingly recognised as also playing an important role in a subset of cases, particularly for the oropharynx. Chronic trauma to oral mucosa from poor restorations and prostheses, in addition to poor oral hygiene with a consequent heavy microbial load in the mouth, are also emerging as significant risk factors. Conclusions: Understanding and quantifying the impact of individual risk factors for these cancers is vital for health decision-making, planning and prevention. National policies and programmes should be designed and implemented to control exposure to environmental risks, by legislation if necessary, and to raise awareness so that people are provided with the information and support they need to adopt healthy lifestyles.

• 한국통신학회논문지
• /
• 제14권4호
• /
• pp.348-359
• /
• 1989

본 논문은 [1]와 [2]에 의해 제안된 multitree 형상 인식 기법의 성능 개선에 관한 논문이다. Multitree 형상 인식 기법의 기본적인 생각은, Classifier 설계과정에서 각 특징별로 Binary Decision Tree 를 구성하고, 이들의 탐색 순서를 결정하며, 인식 과정에서는 앞에서 정한 탐색 순서에 의거하여, BDT(Binary Decision Tree)를 탐색해 나간다는 것이다. 이때 BDT를 추가하여 탐색하기 전에 그때까지 얻은 정보를 이용하여 입력 물체를 인식할 수 있는지에 대한 여부를 결정하며, 인식이 가능한 경우 BDT의 탐색을 멈추고, 인식이 불가능한 경우 BDT의 탐색을 계속해 나간다. 이 방법은 BDT를 각 특징별로 만들기 때문에 새로운 특징의 삭제나 첨가가 상당히 용이하며 인식에 사용되는 특징의 갯수가 감소하게 된다. 따라서 이 알고리즘은 특징의 수가 많거나 class수가 많을 경우 쉽게 이용될 수 있다. 본 논문은 각 특징에서 구한 근사화된 확률 분포로부터 입력 특징값에 대한 확률값을 구해 인식에 이용하였으며, 이 값을 이용한ㄴ 여러가지 인식 방법을 제안하였다. 그리고 Branch and Bound 방법을 사용하여 특징의 선택 순서와 탐색 범위를 구하였다. 위에서 제안한 것들을 실험한 결과 기존의 multitree형상 인식 기법보다 본 논문에서 제안한 기법의 성능이 향상되었다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권2호
• /
• pp.45-51
• /
• 2006

In this paper, we propose a new architecture of Information Granulation based genetically optimized Self-Organizing Fuzzy Polynomial Neural Networks (IG_gSOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially information granulation and genetic algorithms. The proposed IG_gSOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. In addition, the fuzzy rules used in the networks exploit the notion of information granules defined over system's variables and formed through the process of information granulation. That is, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. This granulation is realized with the aid of the hard c-menas clustering method (HCM). To evaluate the performance of the IG_gSOFPNN, the model is experimented with using two time series data(gas furnace process and NOx process data).

• 디지털융복합연구
• /
• 제13권3호
• /
• pp.155-165
• /
• 2015

기업부도예측은 재무 분야에 있어 중요한 연구주제 중 하나로 1960년대 이후부터 꾸준히 연구되어져 왔다. 국내의 경우, IMF 사태 이후 기업부도예측에 관한 중요성이 강조되고 있다. 이에 본 연구에서는 보다 정확한 기업부도예측을 위해 높은 예측력과 동시에 과적합화의 문제를 해결한다고 알려진 SVM(Support Vector Machine)을 기반으로 퍼지이론(fuzzy theory)을 활용해 입력변수를 확장하고, 유전자 알고리즘(GA, Genetic Algorithm)을 이용해 유사 혹은 유사최적의 입력변수집합과 파라미터를 탐색하는 새로운 융합모형을 제시한다. 제안모형의 유용성을 검증하기 위하여 H은행의 비외감 중공업 기업 데이터를 이용하여 실험을 수행하였으며, 비교모형으로는 로짓분석, 판별분석, 의사결정나무, 사례기반추론, 인공신경망, SVM을 선정하였다. 실험결과, 제안모형이 모든 비교모형들에 비해 우수한 예측력을 보이는 것으로 나타났다. 본 연구는 우수한 예측 성능을 가진 다기법 융합 모형을 새롭게 제안하여, 부도예측 분야에 학술적, 실무적으로 기여할 수 있을 것으로 기대된다.

• Journal of Medicine and Life Science
• /
• 제16권3호
• /
• pp.96-100
• /
• 2019

Postural tachycardia syndrome (POTS) is common, although not so well-known variant of cardiovascular autonomic disorder characterized by an excessive heart rate increase on standing. POTS is probably underdiagnosed due to the heterogeneity in both presentation and etiology. This study aimed to evaluate the clinical and autonomic features in patients with POTS. We reviewed the medical records of patients with POTS. Medical records include onset age, sex, presenting symptoms, body mass index (BMI) and prognosis. All patients had an autonomic function and laboratory tests. Ninety-nine patients met the inclusion criteria for POTS (51.5% male; mean±SD age, 20.0±9.7 years; mean±SD, BMI 21.9±3.9). Common presenting symptoms were a brief loss of consciousness, dizziness, blurred vision and headache. Autonomic function tests showed abnormal quantitative sudomotor axon reflex testing in 20 patients of 99 POTS patients. The abnormal post-ganglionic sympathetic sudomotor function is generally considered to reflect a neuropathic form of POTS. In treatments, 83 patients were treated by non-pharmacological management including lifestyle changes and 16 patients required the initiation of pharmacological therapies. Most patients with POTS showed a relatively favorable prognosis. POTS is a chronic disease with a substantial subset of patients recovering within a few years after the initial presentation. Future efforts should focus on better understanding of POTS pathophysiology and designing randomized controlled trials for the selection of more effective therapy.

• Animal cells and systems
• /
• 제3권1호
• /
• pp.29-39
• /
• 1999

Current data on reproductive characters of endemic and native species are essential to provide a strategy for the conservation of these species. Red pine (Pinus densiflora Sieb. & Zucc.) is one of the dominant, native tree species in Korea, but its reproductive ecology is not well-known. In 1997, the pattern of variation in cone and seed yields contributing to the conservation of declining populations of red pines was examined. Plant height and dbh were measured, and several new cones were collected from each tagged tree after counting the number of cones on each tree. For a subset of cones sampled, the number of fertile scales, the number of seeds at three development stages (early/late aborted, and filled seed), seed wing size, wing color, and individual filled seed mass were measured. The three sites which differed significantly in mean plant size also differed in mean cone and seed production per plant. However further analyses showed that most variation in characters examined occurred among plants within sites, but not among sites. An average of 90% of the potential seeds on the cones aborted at an early developmental stage, demonstrating that early abortion is a major factor affecting the number of filled seeds per cone. Individual seed mass was the only character which exhibited significant variations among sites as well as among trees within sites. Individual seed mass was overall negatively correlated with both the percentage of late abortion and the number of old cones per plant, suggesting that both the past and current years' reproductive activities have caused variations in seed mass. The potential dispersal distance of red pine seeds is quite large. However, wing loading was correlated with seed mass and number in a complex pattern across the sites. Distribution of seeds with varied colored wings differed among sites and among trees within sites. These results suggest that red pines at different sites might possess different strategies to cope with selection pressures acting during the final phase of reproduction, from seed dispersal to establishment. Then the ‘fitted’ red pine trees at each site should be identified and managed to conserve or restore populations.