• Experimental and Molecular Medicine
• /
• 제50권12호
• /
• pp.10.1-10.11
• /
• 2018

Cancer growth and progression are associated with immune suppression. Cancer cells have the ability to activate different immune checkpoint pathways that harbor immunosuppressive functions. Monoclonal antibodies that target immune checkpoints provided an immense breakthrough in cancer therapeutics. Among the immune checkpoint inhibitors, PD-1/PD-L1 and CTLA-4 inhibitors showed promising therapeutic outcomes, and some have been approved for certain cancer treatments, while others are under clinical trials. Recent reports have shown that patients with various malignancies benefit from immune checkpoint inhibitor treatment. However, mainstream initiation of immune checkpoint therapy to treat cancers is obstructed by the low response rate and immune-related adverse events in some cancer patients. This has given rise to the need for developing sets of biomarkers that predict the response to immune checkpoint blockade and immune-related adverse events. In this review, we discuss different predictive biomarkers for anti-PD-1/PD-L1 and anti-CTLA-4 inhibitors, including immune cells, PD-L1 overexpression, neoantigens, and genetic and epigenetic signatures. Potential approaches for further developing highly reliable predictive biomarkers should facilitate patient selection for and decision-making related to immune checkpoint inhibitor-based therapies.

• 대한의생명과학회지
• /
• 제25권3호
• /
• pp.256-266
• /
• 2019

In this study, obese adults were compared for their ability to predict obesity and lipid related variables and their optimal cutoff values to predict metabolic syndrome and insulin resistance. In this study, 9,256 adults aged 20 years or older and less than 80 years old, who were in the Gyeonggi region from January 2014 to December 2016 and who were examined at a general hospital, were enrolled. The diagnostic criteria for obesity were WHO (World Health Organization), and BMI $25kg/m^2$ or more presented in the Asia-Pacific region. Metabolic syndrome was diagnosed based on the criteria of American Heart Association / National Heart, Lung, and Blood Institute (AHA / NHLBI). According to the results of receiver operating characteristic curve (ROC) analysis, Triglyceride / HDL-cholesterol (TG / HDL-C), Triglyceride and Glucose (TyG) index, lipid accumulation product (LAP) and visceral adiposity index (VAI) showed high predictive power for diagnosing metabolic syndrome. The diagnostic accuracy of LAP (AUC: 0.854) for males and VAI (0.888) for females was the highest. The optimal cutoff value of LAP was 42.71 for male and 35.44 for female, and the cutoff value of VAI was 1.92 for male and 2.15 for female. In addition, WHtR (waist to height ratio), TyG index, and LAP were used as predictors of insulin resistance in obese adults. Therefore, LAP and VAI were superior to other indicators in predicting metabolic syndrome in obese adults.

• Safety and Health at Work
• /
• 제12권1호
• /
• pp.1-9
• /
• 2021

This review article addresses the role of safety professionals in the diffusion strategies for predictive analytics for safety performance. The article explores the models, definitions, roles, and relationships of safety professionals in knowledge application, access, management, and leadership in safety analytics. The article addresses challenges safety professionals face when integrating safety analytics in organizational settings in four operations areas: application, technology, management, and strategy. A review of existing conventional safety data sources (safety data, internal data, external data, and context data) is briefly summarized as a baseline. For each of these data sources, the article points out how emerging analytic data sources (such as Industry 4.0 and the Internet of Things) broaden and challenge the scope of work and operational roles throughout an organization. In doing so, the article defines four perspectives on the integration of predictive analytics into organizational safety practice: the programmatic perspective, the technological perspective, the sociocultural perspective, and knowledge-organization perspective. The article posits a four-level, organizational knowledge-skills-abilities matrix for analytics integration, indicating key organizational capacities needed for each area. The work shows the benefits of organizational alignment, clear stakeholder categorization, and the ability to predict future safety performance.

• 문화기술의 융합
• /
• 제10권3호
• /
• pp.145-154
• /
• 2024

행정 빅데이터를 활용하는 예측 모형을 운영하기 위해서는 정책의 변화 및 변동성 심한 데이터의 특성이 고려가 되어야만 한다. 이런 상황을 고려하여 본 연구에서는 Cut-off Voting Classifier(CVC) 알고리즘을 제안한다. 제안하는 알고리즘은 여러개의 약 분류기를 활용하여 적중률이 급격하게 하락하는 것을 방지하는 알고리즘이다. 본 연구에서는 제안하는 알고리즘을 실험을 통해 성능을 검증한다. 성능검증 결과 급격하게 예측모형 적중률이 하락하는 상황에서도 안정적으로 예측률을 유지한다는 것을 입증할 수 있었다.

• 전기학회논문지
• /
• 제63권4호
• /
• pp.526-533
• /
• 2014

In this study, we introduce design methodology to develop a guidance for issuing heavy rainfall warning by using both RBFNNs(Radial basis function neural networks) and SVR(Support vector regression) model, and then carry out the comparative studies between two pattern classifiers. Individual classifiers are designed as architecture realized with the aid of optimization and pre-processing algorithm. Because the predictive performance of the existing heavy rainfall forecast system is commonly affected from diverse processing techniques of meteorological data, under-sampling method as the pre-processing method of input data is used, and also data discretization and feature extraction method for SVR and FCM clustering and PSO method for RBFNNs are exploited respectively. The observed data, AWS(Automatic weather wtation), supplied from KMA(korea meteorological administration), is used for training and testing of the proposed classifiers. The proposed classifiers offer the related information to issue a heavy rain warning in advance before 1 to 3 hours by using the selected meteorological data and the cumulated precipitation amount accumulated for 1 to 12 hours from AWS data. For performance evaluation of each classifier, ETS(Equitable Threat Score) method is used as standard verification method for predictive ability. Through the comparative studies of two classifiers, neuro-fuzzy method is effectively used for improved performance and to show stable predictive result of guidance to issue heavy rainfall warning.

• 한국음향학회지
• /
• 제18권3호
• /
• pp.62-67
• /
• 1999

본 논문은 회귀신경망을 이용한 음성인식에 관한 연구이다. 예측형 신경망으로 음절단위로 모델링한 후 미지의 입력음성에 대하여 예측오차가 최소가 되는 모델을 인식결과로 한다. 이를 위해서 예측형으로 구성된 신경망에 음성의 시변성을 신경망 내부에 흡수시키기 위해서 회귀구조의 동적인 신경망인 회귀예측신경망을 구성하고 Elman과 Jordan이 제안한 회귀구조에 따라 인식성능을 서로 비교하였다. 음성DB는 ETRI의 샘돌이 음성 데이터를 사용하였다. 그리고, 신경망의 최적모델을 구하기 위하여 예측차수와 은닉층 유니트 수의 변화에 따른 인식률의 변화와 문맥층에서 자기회귀계수를 두어 이전의 값들이 문맥층에서 누적되도록 하였을 경우에 대한 인식률의 변화를 비교하였다. 실험결과, 최적의 예측차수, 은닉층 유니트수, 자기회귀계수는 신경망의 구조에 따라 차이가 나타났으며, 전반적으로 Jordan망이 Elman망보다 인식률이 높았으며, 자기회귀계수에 대한 영향은 신경망의 구조와 계수값에 따라 불규칙하게 나타났다.

• 인터넷정보학회논문지
• /
• 제12권6호
• /
• pp.83-94
• /
• 2011

감정 컴퓨팅의 대표적 연구 주제는 기계가 사람의 감정을 인식하여 이에 적절히 대응하는 것이다. 감정 인식 연구에서는 얼굴과 목소리 단서를 이용하여 감정을 포착하는데 집중했으며 최근에 와서 행동자세를 주요 수단으로 이용하고 있다. 본 연구의 목적은 감정 표현에서 중요한 역할을 담당하는 자세 특징을 포착하고 확인하여 감정을 판별하는 것이다. 이를 위해 먼저 자세포착시스템으로 다양한 감정 자세를 수집하여 감정별 특징을 공간적 특징으로 설명한다. 그리고 동작을 취하는 행위자가 의도하는 감정과 관찰자가 인지하는 감정 간에 통계적으로 의미 있는 상관관계가 있음을 표준통계기술을 통해 확인한다. 6가지 주요 감정을 판별하기 위해 판별 분석법을 이용하여 감정 자세 예측 모델을 구축하고 자세 특징을 측정한다. 제안 특징과 모델의 평가는 행위자-관찰자 감정 자세 집단의 상관관계를 이용하여 수행한다. 정량적 실험 결과는 제안된 자세 특징으로 감정을 잘 판별하며 감정 예측 모델이 잘 수행됨을 보여준다.

• Journal of Information Processing Systems
• /
• 제14권3호
• /
• pp.751-770
• /
• 2018

Web applications are indispensable in the software industry and continuously evolve either meeting a newer criteria and/or including new functionalities. However, despite assuring quality via testing, what hinders a straightforward development is the presence of defects. Several factors contribute to defects and are often minimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases of software development is important. Therefore, a fault prediction model for identifying fault-prone classes in a web application is highly desired. In this work, we compare 14 machine learning techniques to analyse the relationship between object oriented metrics and fault prediction in web applications. The study is carried out using various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, the input basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statistical analysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of these metrics in the defect prediction of web applications. The overall predictive ability of different fault prediction models is first ranked using Friedman technique and then statistically compared using Nemenyi post-hoc analysis. The results not only upholds the predictive capability of machine learning models for faulty classes using web applications, but also finds that ensemble algorithms are most appropriate for defect prediction in Apache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique and the statistical analysis of the datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권4호
• /
• pp.826-842
• /
• 2024

As 5G and AI continue to develop, there has been a significant surge in the healthcare industry. The COVID-19 pandemic has posed immense challenges to the global health system. This study proposes an FL-supported edge computing model based on federated learning (FL) for predicting clinical outcomes of COVID-19 patients during hospitalization. The model aims to address the challenges posed by the pandemic, such as the need for sophisticated predictive models, privacy concerns, and the non-IID nature of COVID-19 data. The model utilizes the FATE framework, known for its privacy-preserving technologies, to enhance predictive precision while ensuring data privacy and effectively managing data heterogeneity. The model's ability to generalize across diverse datasets and its adaptability in real-world clinical settings are highlighted by the use of SHAP values, which streamline the training process by identifying influential features, thus reducing computational overhead without compromising predictive precision. The study demonstrates that the proposed model achieves comparable precision to specific machine learning models when dataset sizes are identical and surpasses traditional models when larger training data volumes are employed. The model's performance is further improved when trained on datasets from diverse nodes, leading to superior generalization and overall performance, especially in scenarios with insufficient node features. The integration of FL with edge computing contributes significantly to the reliable prediction of COVID-19 patient outcomes with greater privacy. The research contributes to healthcare technology by providing a practical solution for early intervention and personalized treatment plans, leading to improved patient outcomes and efficient resource allocation during public health crises.

• 대한지역사회작업치료학회지
• /
• 제7권3호
• /
• pp.35-42
• /
• 2017

목적 : 본 연구는 일부지역 버스운전기사의 일반적 특성과 수면의 질 그리고 작업 능력 간의 상관성을 파악하고, 작업능력에 미치는 영향을 확인하고자 하였다. 연구방법 : 버스운전기사 120명을 대상으로 작업 능력의 측정을 위해 작업 능력 지수(Work Ability Index : WAI)를 사용하였고, 수면의 질은 수면의 질 평가(Pittsburgh Sleep Quality Index : PSQI)를 통해 평가하였다. 작업능력과 수면의 질과의 상관관계를 확인하기 위하여 피어슨 상관분석(Pearson's correlation coefficient)를 이용하였고, 수면의 질이 작업능력에 미치는 영향을 확인하기 위해 단계적 다중 회귀분석(Stepwise regression analysis)을 통해 분석하였다. 결과 : 작업능력에 영향을 미치는 변인들의 상관관계를 분석 한 결과 수면의 질(p<.001)과 근로시간(p<.001) 에서 부적인 상관관계가 나타났다. 최종적으로 수면의 질(p<.001)과 근로시간(p<.01)이 버스운전기사들의 작업능력에 통계적으로 유의한 영향을 미치는 변인으로 분석되었고, 수정된 결정계수 값($R^2$)이 0.482로 48.2%의 설명력을 보였다. 결론 : 버스운전기사들의 수면의 질과 근로시간이 작업능력에 영향을 미치는 주요 변인으로 파악되었다. 그러므로 버스운전기사의 작업능력을 향상시키기 위한 방안으로 수면의 질과 근로시간을 고려하여야 하겠다.