• ETRI Journal
• /
• 제22권2호
• /
• pp.1-10
• /
• 2000

Pattern recognition is one of the most common problems encountered in engineering and scientific disciplines, which involves developing prediction or classification models from historic data or training samples. This paper introduces a new approach, called the Representational Capability (RC) algorithm, to handle pattern recognition problems using radial basis function (RBF) models. The RC algorithm has been developed based on the mathematical properties of the interpolation and design matrices of RBF models. The model development process based on this algorithm not only yields the best model in the sense of balancing its parsimony and generalization ability, but also provides insights into the design process by employing a design parameter (${\delta}$). We discuss the RC algorithm and its use at length via an illustrative example. In addition, RBF classification models are developed for heart disease diagnosis.

• Molecules and Cells
• /
• 제44권6호
• /
• pp.377-383
• /
• 2021

Severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) is a novel virus that causes coronavirus disease 2019 (COVID-19). To understand the identity, functional characteristics and therapeutic targets of the virus and the diseases, appropriate infection models that recapitulate the in vivo pathophysiology of the viral infection are necessary. This article reviews the various infection models, including Vero cells, human cell lines, organoids, and animal models, and discusses their advantages and disadvantages. This knowledge will be helpful for establishing an efficient system for defense against emerging infectious diseases.

• BMB Reports
• /
• 제55권5호
• /
• pp.213-219
• /
• 2022

The blood-brain barrier (BBB) is an interface between cerebral blood and the brain parenchyma. As a gate keeper, BBB regulates passage of nutrients and exogeneous compounds. Owing to this highly selective barrier, many drugs targeting brain diseases are not likely to pass through the BBB. Thus, a large amount of time and cost have been paid for the development of BBB targeted therapeutics. However, many drugs validated in in vitro models and animal models have failed in clinical trials primarily due to the lack of an appropriate BBB model. Human BBB has a unique cellular architecture. Different physiologies between human and animal BBB hinder the prediction of drug responses. Therefore, a more physiologically relevant alternative BBB model needs to be developed. In this review, we summarize major features of human BBB and current BBB models and describe organ-on-chip models for BBB modeling and their applications in neurological complications.

• 동의생리병리학회지
• /
• 제23권5호
• /
• pp.938-941
• /
• 2009

In spite of abundant clinical resources of stroke patients, the objective and logical data analyses or diagnostic systems were not established in oriental medicine. In the present study we tried to develop the statistical diagnostic tool discriminating the subtypes of oriental medicine diagnostic system, syndrome differentiation (SD). Discriminant analysis was carried out using clinical data collected from 1,478 stroke patients with the same subtypes diagnosed identically by two clinical experts with more than 3 year experiences. Numerical discriminant models were constructed using important 61 symptom and syndrome indices. Diagnostic accuracy and prediction rate of 5 SD subtypes: The overall diagnostic accuracy of 5 SD subtypes using 61 indices was 74.22%. According to subtypes, the diagnostic accuracy of "phlegm-dampness" was highest (82.84%), and followed by "qi-deficiency", "fire/heat", "static blood", and "yin-deficiency". On the other hand, the overall prediction rate was 67.12% and that of qi-deficiency was highest (73.75%). Diagnostic accuracy and prediction rate of 4 SD subtypes: The overall diagnostic accuracy and prediction rate of 4 SD subtypes except "static blood" were 75.06% and 71.63%, respectively. According to subtypes, the diagnostic accuracy and prediction rate was highest in the "phlegm-dampness" (82.84%) and qi-deficiency (81.69%), respectively. The statistical discriminant model of constructed using 4 SD subtypes, and 61 indices can be used in the field of oriental medicine contributing to the objectification of SD.

• Journal of the Korean Data and Information Science Society
• /
• 제25권2호
• /
• pp.271-280
• /
• 2014

구제역은 전염성이 높고 치명적 결과를 유발하는 우제류 전염병이며, 2010/2011년도에 국내에서 발생한 구제역 (2010/2011 구제역)은 사회 및 경제적으로 국가에 재난 수준의 손실을 끼쳤다. 따라서 국가적 차원에서 구제역의 예방과, 발병 시 피해를 줄이려는 많은 노력을 하고 있다. 이러한 노력의 하나로 구제역의 전염 현상을 확률적으로 모형화하고 이해하려는 노력이 필요하다. 영국에서 발생한 2001년 구제역은 그 규모와 피해가 막대하여, 영국에서는 다양한 확률적 모형으로 구제역 전파 현상에 대한 이해를 통하여 미래의 발생에 대비하려는 연구가 이루어져 왔다. 그러나 2010/2011 구제역에 대하여는 확률적 모형을 활용한 연구가 미미한 편이다. 따라서 본 연구에서는 2010/2011 구제역에 대하여 시간-공간 확률 SIR 확률모형을 가정하고 시간과 공간에 따르는 전파 현상에 대하여 고찰한다. 농림수산검역검사본부에서 발표한 구제역 감염데이터와 통계청의 전국농가센서스 자료의 일부인 전체 우제류 농가의 데이터가 본 연구의 분석에 필요한 정도로 상세하지 않으므로 추정 및 보정작업을 통하여 데이터를 보완하였다. 감염데이터를 이용하여 커널함수를 추정하고, 전국 우제류 농장데이터를 이용하여 시뮬레이션을 통하여 모형의 모수를 추정하였다.

• Journal of Ginseng Research
• /
• 제31권1호
• /
• pp.51-53
• /
• 2007

Ginseng shows protective and trophic effects in neurodegenerative diseases in experimental models, and showed cognitive improvement in normal population. To investigate the efficacy of ginseng in patients with Alzheimer's disease, patients, who met NINDS-ADRDA criteria for AD were studied Subjects were randomly assigned to ginseng group and control group, and ginseng group was treated with Korean white ginseng powder (4.5 g/day) for 12 weeks. Efficacy variables included changes in mini-mental status exam (MMSE) and cognitive subscales of Alzheimer's disease assessment scale (ADAS-cog) at 4 weeks and 12 weeks. Baseline MMSE and ADAS scores showed no difference between the two groups. Results showed that ginseng improved ADAS-cog compared to the control group at 12 weeks (p<0.05). MMSE was also increased by ginseng treatment compared to the control at 12 weeks (p<0.01). This study suggests the symptomatic efficacy of ginseng in patients with Alzheimer's disease.

• 스마트미디어저널
• /
• 제11권4호
• /
• pp.38-45
• /
• 2022

Object detection models have become the current tool of choice for plant disease detection in precision agriculture. Most existing research improves the performance by ameliorating networks and optimizing the loss function. However, the data-centric part of a whole project also needs more investigation. In this paper, we proposed a systematic strategy with three different annotation methods for plant disease detection: local, semi-global, and global label. Experimental results on our paprika disease dataset show that a single class annotation with semi-global boxes may improve accuracy. In addition, we also studied the noise factor during the labeling process. An ablation study shows that annotation noise within 10% is acceptable for keeping good performance. Overall, this data-centric numerical analysis helps us to understand the significance of annotation methods, which provides practitioners a way to obtain higher performance and reduce annotation costs on plant disease detection tasks. Our work encourages researchers to pay more attention to label quality and the essential issues of labeling methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.504-519
• /
• 2023

Heart disease is becoming the top reason of death all around the world. Diagnosing cardiac illness is a difficult endeavor that necessitates both expertise and extensive knowledge. Machine learning (ML) is becoming gradually more important in the medical field. Most of the works have concentrated on the prediction of cardiac disease, however the precision of the results is minimal, and data integrity is uncertain. To solve these difficulties, this research creates an Integrated Accurate-Secure Heart Disease Prediction (IAS) Model based on Deep Convolutional Neural Networks. Heart-related medical data is collected and pre-processed. Secondly, feature extraction is processed with two factors, from signals and acquired data, which are further trained for classification. The Deep Convolutional Neural Networks (DCNN) is used to categorize received sensor data as normal or abnormal. Furthermore, the results are safeguarded by implementing an integrity validation mechanism based on the hash algorithm. The system's performance is evaluated by comparing the proposed to existing models. The results explain that the proposed model-based cardiac disease diagnosis model surpasses previous techniques. The proposed method demonstrates that it attains accuracy of 98.5 % for the maximum amount of records, which is higher than available classifiers.

• Biomolecules & Therapeutics
• /
• 제16권4호
• /
• pp.312-319
• /
• 2008

Attention deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by hyperactivity, inattention, and impulsiveness. Current estimates suggest that 4-12% of school age children are affected by ADHD, which hampers proper social relationship and achievements in school. Even though the exact etiology of the disorder is still in the middle of active investigation, the availability of pharmacological treatments for the disorder suggest that at least the symptoms of ADHD are manageable. To develop drugs with higher efficacy and fewer side effects, it is essential to have appropriate animal models for in vivo drug screening processes. Good animal models can also provide the chances to improve our understanding of the disease processes as well as the underlying etiology of the disorder. In this review, we summarized current animal models used for ADHD research and discussed the point of concerns about using specific animal models.

• 식물병연구
• /
• 제22권3호
• /
• pp.168-177
• /
• 2016

한국에서 발생하는 참다래 잎에서의 궤양병의 감염위험도를 예측하는 모형을 Magarey 등(2005)의 일반 감염 모형식을 이용하여 개발하였다. 이 연구를 통해 개발한 모형과 뉴질랜드에서 개발된 KVH PSA-V 모형을 2015년 서귀포시 남원읍의 녹색참다래 헤이워드 품종 재배 과원과 표선면과 성산읍 신산리의 황색 참다래 Hort16A 품종 재배 과원들에서 수집된 기상 조사 자료와 병조사 자료를 사용하여 분할표 분석을 통해 평가하였다. 자체 개발한 모형과 뉴질랜드에서 개발한 KVH PSA-V 모형, 감염 판단기준을 31로 조정한 KVH PSA-V 모형들은 실제 병이 일어났을 경우에 감염이 일어났다고 경고하는 비율인 probability of detection값이 모두 80% 이상으로 한국의 참다래 궤양병 방제 의사 결정지원용으로 사용하기에는 충분하였다. 모형이 일어나는 현상을 정확히 예측하는 지표인 proportion of correct는 이 연구를 통해 개발된 감염 위험 예측 모형이 가장 높은 51.1%를 나타내고 실제병이 일어났을 경우에 감염이 일어났다고 경고하는 비율인 probability of detection과 모형의 경고에 따라 방제를 결정하였을 때에 효율성 지표인 critical success index도 각각 가장 높은 수치인 90.9%와 47.6%를 나타내어 한국에서 발생하는 참다래 궤양에 대해서는 KVH PSA-V 모형보다 더 우수한 모형으로 판단되었다. 이 연구를 통해 새로 개발된 모형은 한국의 참다래 재배자들의 궤양병 방제를 위한 의사결정에 도움을 주어 궤양병으로 인한 피해를 줄이는 데에 도움이 될 것이다.