• 한국항행학회논문지
• /
• 제28권4호
• /
• pp.466-471
• /
• 2024

항공 분야에도 머신러닝 (ML; machine learning) 기반의 인공지능(AI; artificial intelligence)를 활용하는 시스템 개발이 본격적으로 시작되었다. 항공용 소프트웨어는 항공무선기술위원회(RTCA; Radio Technical Commission for Aeronautics) DO-178C 또는 DO-278A 등의 표준을 통해 안전성 보증을 하고 있으며, 이 표준들은 결정론적 특성과 설명가능성을 내재한 소프트웨어를 대상으로 개발되었고 잘 적용된다. 반면 ML 기반 AI는 그 특성을 고려할 때, 이러한 기존 소프트웨어 인증 표준 적용만으로는 그 신뢰성을 제대로 보증하기 어렵다. 본 논문에서는 유럽항공안전청(EASA; european union aviation safety agency)이 이에 대응하기 위해 제시하는 새로운 인증 방법론에 대해 알아보고, AI가 적용된 항공 소프트웨어 인증을 위해 국내 규제당국과 산업계가 어떤 준비를 해야 하는지 논의한다.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.90-104
• /
• 2020

It is difficult for non-experts to build machine learning (ML) models at the level that satisfies their needs. Deep learning models are even more challenging because it is unclear how to improve the model, and a trial-and-error approach is not feasible since training these models are time-consuming. To assist these novice users, we examined how interactive and explainable feedback while training a deep learning network can contribute to model performance and users' satisfaction, focusing on the data preparation process. We conducted a user study with 31 participants without expertise, where they were asked to improve the accuracy of a deep learning model, varying feedback conditions. While no significant performance gain was observed, we identified potential barriers during the process and found that interactive and explainable feedback provide complementary benefits for improving users' understanding of ML. We conclude with implications for designing an interface for building ML models for novice users.

• 스마트미디어저널
• /
• 제11권2호
• /
• pp.31-38
• /
• 2022

하천의 염분 변화를 신속히 예측하는 것은 염분 침투로 인한 농업, 생태계의 피해를 예측하고 재해 방지 대책을 수립하기 위해서 중요한 작업이다. 머신러닝 기법은 물리 기반 수리 모델에 비해 계산량이 훨씬 적기 때문에, 비교적 짧은 시간에 염분농도를 예측 가능하여 물리 기반 수리 모델의 보완 기법으로 연구되고 있다. 해외에서는 머신러닝 기법 기반 염분 예측 연구들이 활발히 연구되고 있으나, 대한민국의 공공데이터에 머신러닝 기법을 적용한 연구는 충분치 않다. 낙동강 하구의 환경 정보에 관한 공공데이터와 함께, 본 연구는 여러 종류의 머신러닝 기법의 염분농도에 대한 예측 성능을 측정하였다. 실험 결과에서, 결정 트리 기반의 LightGBM 알고리즘은 평균 RMSE 0.37의 예측 정확도와 타 알고리즘 대비 2-20배 빠른 학습 속도를 보여주었다. 따라서 국내 하천의 염분농도 예측에도 머신러닝 기법을 적용할 수 있다고 판단된다.

• International Journal of Computer Science & Network Security
• /
• 제21권12spc호
• /
• pp.549-555
• /
• 2021

Machine Learning(ML) splits data into 3 parts, which are usually 60% for training, 20% for validation, and 20% for testing. It just splits quantitatively instead of selecting each set of data by a criterion, which is very important concept for the adequacy of test data. ML measures a model's accuracy by applying a set of validation data, and revises the model until the validation accuracy reaches on a certain level. After the validation process, the complete model is tested with the set of test data, which are not seen by the model yet. If the set of test data covers the model's attributes well, the test accuracy will be close to the validation accuracy of the model. To make sure that ML's set of test data works adequately, we design an experiment and see if the test accuracy of model is always close to its validation adequacy as expected. The experiment builds 100 different SVM models for each of six data sets published in UCI ML repository. From the test accuracy and its validation accuracy of 600 cases, we find some unexpected cases, where the test accuracy is very different from its validation accuracy. Consequently, it is not always true that ML's set of test data is adequate to assure a model's quality.

• 한국임상수의학회지
• /
• 제40권4호
• /
• pp.243-259
• /
• 2023

Machine learning and deep learning (ML/DL) algorithms have been successfully applied in medical practice. However, their application in veterinary medicine is relatively limited, possibly due to a lack in the quantity and quality of relevant research. Because the potential demands for ML/DL applications in veterinary clinics are significant, it is important to note the current gaps in the literature and explore the possible directions for advancement in this field. Thus, a scoping review was conducted as a situation analysis. We developed a search strategy following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. PubMed and Embase databases were used in the initial search. The identified items were screened based on predefined inclusion and exclusion criteria. Information regarding model development, quality of validation, and model performance was extracted from the included studies. The current review found 55 studies that passed the criteria. In terms of target animals, the number of studies on industrial animals was similar to that on companion animals. Quantitative scarcity of prediction studies (n = 11, including duplications) was revealed in both industrial and non-industrial animal studies compared to diagnostic studies (n = 45, including duplications). Qualitative limitations were also identified, especially regarding validation methodologies. Considering these gaps in the literature, future studies examining the prediction and validation processes, which employ a prospective and multi-center approach, are highly recommended. Veterinary practitioners should acknowledge the current limitations in this field and adopt a receptive and critical attitude towards these new technologies to avoid their abuse.

• 전기전자학회논문지
• /
• 제24권3호
• /
• pp.766-776
• /
• 2020

최근 기계학습에 대한 관심이 높아지고 연구가 활성화됨에 따라 다양한 기계학습 모델에서 최적의 하이퍼 파라미터 조합을 찾는 것이 중요해지고 있다. 본 논문에서는 다양한 하이퍼 파라미터 중에서 옵티마이저에 중점을 두고, 다양한 데이터에서 주요 옵티마이저들의 성능을 측정하고 비교하였다. 특히, 가장 기본이 되는 SGD부터 Momentum, NAG, AdaGrad, RMSProp, AdaDelta, Adam, AdaMax, Nadam까지 총 9개의 옵티마이저의 성능을 MNIST, CIFAR-10, IRIS, TITANIC, Boston Housing Price 데이터를 이용하여 비교하였다. 실험 결과, 전체적으로 Adam과 Nadam을 사용하였을 때 기계학습 모델의 손실 함숫값이 가장 빠르게 감소하는 것을 확인할 수 있었으며, F1 score 또한 높아짐을 확인할 수 있었다. 한편, AdaMax는 학습 중에 불안정한 모습을 많이 보여주었으며, AdaDelta는 다른 옵티마이저들에 비하여 수렴 속도가 느리며 성능이 낮은 것을 확인할 수 있었다.

• Asia pacific journal of information systems
• /
• 제33권4호
• /
• pp.1171-1187
• /
• 2023

This study explores how an organization has successfully implemented ML-supported HR services to resolve high employee turnover problems in the IT sector. The empirical setting of the research is where contradicting institutional logics exist among technical, HR, and business groups regarding the ML model development and use of the model predictions in HR services. Institutional framework is used to identify the roles of organizational actors and the legitimacy structures in the organizational environments that can shape or constrain the ML led organizational changes. In institutional theories, technology adoption and organizational change are not only constrained by organizational context, but also fostered through organizational actors' roles and efforts to increase the legitimacy for the change. This research found that when multiple contradicting institutional logics exist, legitimizing the establishment of an enabling environment for multiple logics to reconcile and for the project to move forward is critical. Industry-wide conditions, previous experiences with the pilot ML project, forming a TFT with clearly defined roles and responsibilities, and relevant KPIs are found to legitimize the HR team and the business division to collaborate with the technical personnel to launch ML-supported HR services.

• International Journal of Contents
• /
• 제15권4호
• /
• pp.1-7
• /
• 2019

As the recent developments of artificial intelligence, particularly machine-learning, impact every aspect of society, they are also increasingly influencing creative fields manifested as new artistic tools and inspirational sources. However, as more artists integrate the technology into their creative works, the issues of diversity and fairness are also emerging in the AI-based creative practice. The data dependency of machine-learning algorithms can amplify the social injustice existing in the real world. In this paper, we present an interactive visualization system for raising the awareness of the diversity and fairness issues. Rather than resorting to education, campaign, or laws on those issues, we have developed a web & ML-based interactive data visualization system. By providing the interactive visual experience on the issues in interesting ways as the form of web content which anyone can access from anywhere, we strive to raise the public awareness of the issues and alleviate the important ethical problems. In this paper, we present the process of developing the ML-based interactive visualization system and discuss the results of this project. The proposed approach can be applied to other areas requiring attention to the issues.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.203-208
• /
• 2022

The occurrence of Type 2 Diabetes Mellitus (T2DM) is hoarding globally. All kinds of Diabetes Mellitus is controlled to disrupt over 415 million grownups worldwide. It was the seventh prime cause of demise widespread with a measured 1.6 million deaths right prompted by diabetes during 2016. Over 90% of diabetes cases are T2DM, with the utmost persons having at smallest one other chronic condition in UK. In valuation of contemporary applications of Big Data (BD) to Diabetes Medicare by sighted its upcoming abilities, it is compulsory to transmit out a bottomless revision over foremost theoretical literatures. The long-term growth in medicine and, in explicit, in the field of "Diabetology", is powerfully encroached to a sequence of differences and inventions. The medical and healthcare data from varied bases like analysis and treatment tactics which assistances healthcare workers to guess the actual perceptions about the development of Diabetes Medicare measures accessible by them. Apache Spark extracts "Resilient Distributed Dataset (RDD)", a vital data structure distributed finished a cluster on machines. Machine Learning (ML) deals a note-worthy method for building elegant and automatic algorithms. ML library involving of communal ML algorithms like Support Vector Classification and Random Forest are investigated in this projected work by using Jupiter Notebook - Python code, where significant quantity of result (Accuracy) is carried out by the models.

• Tuberculosis and Respiratory Diseases
• /
• 제86권4호
• /
• pp.251-263
• /
• 2023

The stethoscope has long been used for the examination of patients, but the importance of auscultation has declined due to its several limitations and the development of other diagnostic tools. However, auscultation is still recognized as a primary diagnostic device because it is non-invasive and provides valuable information in real-time. To supplement the limitations of existing stethoscopes, digital stethoscopes with machine learning (ML) algorithms have been developed. Thus, now we can record and share respiratory sounds and artificial intelligence (AI)-assisted auscultation using ML algorithms distinguishes the type of sounds. Recently, the demands for remote care and non-face-to-face treatment diseases requiring isolation such as coronavirus disease 2019 (COVID-19) infection increased. To address these problems, wireless and wearable stethoscopes are being developed with the advances in battery technology and integrated sensors. This review provides the history of the stethoscope and classification of respiratory sounds, describes ML algorithms, and introduces new auscultation methods based on AI-assisted analysis and wireless or wearable stethoscopes.