• 제목/요약/키워드: Knowledge Domain

검색결과 998건 처리시간 0.028초

On the Analysis of Natural Language Processing Morphology for the Specialized Corpus in the Railway Domain

  • Won, Jong Un;Jeon, Hong Kyu;Kim, Min Joong;Kim, Beak Hyun;Kim, Young Min
    • International Journal of Internet, Broadcasting and Communication
    • /
    • 제14권4호
    • /
    • pp.189-197
    • /
    • 2022
  • Today, we are exposed to various text-based media such as newspapers, Internet articles, and SNS, and the amount of text data we encounter has increased exponentially due to the recent availability of Internet access using mobile devices such as smartphones. Collecting useful information from a lot of text information is called text analysis, and in order to extract information, it is performed using technologies such as Natural Language Processing (NLP) for processing natural language with the recent development of artificial intelligence. For this purpose, a morpheme analyzer based on everyday language has been disclosed and is being used. Pre-learning language models, which can acquire natural language knowledge through unsupervised learning based on large numbers of corpus, are a very common factor in natural language processing recently, but conventional morpheme analysts are limited in their use in specialized fields. In this paper, as a preliminary work to develop a natural language analysis language model specialized in the railway field, the procedure for construction a corpus specialized in the railway field is presented.

반도체 공정에서 가상계측 위한 XGBoost 기반 예측모델 (XGBoost Based Prediction Model for Virtual Metrology in Semiconductor Manufacturing Process)

  • 한정석;김형근
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2022년도 춘계학술발표대회
    • /
    • pp.477-480
    • /
    • 2022
  • 반도체 성능 향상으로 신호를 전달하는 회로의 단위가 마이크로 미터에서 나노미터로 미세화되어 선폭(linewidth)이 점점 좁아지고 있다. 이러한 변화는 검출해야 할 불량의 크기가 작아지고, 정상 공정상태와 비정상 공정상태의 차이도 상대적으로 감소되어, 공정오차 및 공정조건의 허용범위가 축소되었음을 의미한다. 따라서 검출해야 할 이상징후 탐지가 더욱 어렵게 되어, 높은 정밀도와 해상도를 갖는 검사공정이 요구되고 있다. 이러한 이유로, 미세 공정변화를 파악할 수 있는 신규 검사 및 계측 공정이 추가되어 TAT(Turn-around Time)가 증가하게 되었고, 웨이퍼가 가공되어 완제품까지 도달하는데 필요한 공정시간이 증가하여 제조원가 상승의 원인으로 작용한다. 본 논문에서는 웨이퍼의 검계측 데이터가 아닌, 제조공정 과정에서 발생하는 다양한 센서 및 장비 데이터를 기반으로 웨이퍼 제조 결과가 양품인지 그렇지 않으면 불량인지 구별할 수 있는 가상계측 모델을 제안한다. 기계학습의 여러 알고리즘 중에서 다양한 장점을 갖는 XGBoost 알고리즘을 이용하여 예측모델을 구축하였고, 데이터 전처리(data-preprocessing), 주요변수 추출(feature selection), 모델 구축(model design), 모델 평가(model evaluation)의 순서로 연구를 수행하였다. 결과적으로 약 94% 이상의 정확성을 갖는 모형을 구축하는데 성공하였으나 더욱 높은 정확성을 확보하기 위해서는 반도체 공정과 관련된 Domain Knowledge 를 반영한 모델구축과 같은 추가적인 연구가 필요하다.

Causality, causal discovery, causal inference and counterfactuals in Civil Engineering: Causal machine learning and case studies for knowledge discovery

  • M.Z. Naser;Arash Teymori Gharah Tapeh
    • Computers and Concrete
    • /
    • 제31권4호
    • /
    • pp.277-292
    • /
    • 2023
  • Much of our experiments are designed to uncover the cause(s) and effect(s) behind a phenomenon (i.e., data generating mechanism) we happen to be interested in. Uncovering such relationships allows us to identify the true workings of a phenomenon and, most importantly, to realize and articulate a model to explore the phenomenon on hand and/or allow us to predict it accurately. Fundamentally, such models are likely to be derived via a causal approach (as opposed to an observational or empirical mean). In this approach, causal discovery is required to create a causal model, which can then be applied to infer the influence of interventions, and answer any hypothetical questions (i.e., in the form of What ifs? Etc.) that commonly used prediction- and statistical-based models may not be able to address. From this lens, this paper builds a case for causal discovery and causal inference and contrasts that against common machine learning approaches - all from a civil and structural engineering perspective. More specifically, this paper outlines the key principles of causality and the most commonly used algorithms and packages for causal discovery and causal inference. Finally, this paper also presents a series of examples and case studies of how causal concepts can be adopted for our domain.

The Relationship between Management bonuses with Earnings stability in Information technology and Computer listed companies on the Tehran Stock Exchange

  • Moghani, Reza;Mohammadi, Shaban;Esmaeilioghaz, Hamed
    • 융합경영연구
    • /
    • 제4권4호
    • /
    • pp.17-24
    • /
    • 2016
  • The purpose of the present study is to investigate the relationship between Management bonuses and earnings stability of the listed companies on the Tehran Stock Exchange (TSE). The population includes 94 firms selected through systematic sampling. The data is collected from the audited financial statements of the firms provided by TSE's website from 2009 to 2016. The results of multiple linear regression analysis show that there is a significant relationship between Management bonuses and earnings stability. The aim of this study primarily investigating the relationship between earnings stability and management bonus. In the case of this target, the next goal of this research is to develop a proposal for legislation in the domain of capital market, students and faculty as well as accounting information users provide research interests. Observations show many companies despite the decline in profitability, bonus managers to continually pay. Increase in listed companies Stock Exchange as well as the importance of communication between earnings quality and bonus managers in Financial Accounting the authors created an incentive to research about this relationship do. The results of this research could be the development of literature done in the past. Thus, more knowledge about the issue of sustainability and its relation to bonus managers the users of accounting information, accounting courses provide students and faculty.

식품 수입 절차에서의 효율적 의사결정을 위한 데이터 전처리 기술에 관한 연구 (Research on Data Preprocessing Techniques for Efficient Decision-Making in Food Import Procedures)

  • 박재형;송용욱;강주영
    • 한국빅데이터학회지
    • /
    • 제8권1호
    • /
    • pp.61-71
    • /
    • 2023
  • 데이터 기반 의사결정 방법론, 고도화된 빅데이터 처리 기법의 발달로 데이터를 처리하는 방법에 대한 정보의 수요가 늘어나고 있다. 데이터를 활용하는 거의 모든 작업과 연구에서 데이터 전처리 과정이 포함되나, 이러한 과정은 주장하고자 하는 내용이나 결과물을 도출하기 위한 수단으로써 언급될 뿐 실질적인 과정에 대해서 자세하게 설명하고 있는 연구는 부족하였다. 실질적인 분석 기법을 활용하기 이전의 단계로 간단하게 언급되는 경우가 많아 데이터 처리에 대한 인사이트를 획득하기 어려운 경우가 많았다. 따라서 이 연구에서는, raw data에서부터 데이터를 처리하는 과정, 즉 데이터 처리 파이프라인에 대해서 자세하게 작성하고자 하였다. 특히 수입식품 수입 절차에 대한 설명을 구체화함으로써 해당 상황에서 데이터의 필드들이 어떻게 해석될 수 있고 어떠한 필드들을 왜 활용하게 되었는지에 대한 상황과 관련 도메인 지식을 공유하면서 흐름을 기술하고자 하였다.

이미지 분석을 위한 퓨샷 학습의 최신 연구동향 (Recent advances in few-shot learning for image domain: a survey)

  • 석호식
    • 전기전자학회논문지
    • /
    • 제27권4호
    • /
    • pp.537-547
    • /
    • 2023
  • 퓨삿학습(few-shot learning)은 사전에 확보한 관련 지식과 소규모의 학습데이터를 이용하여 학습데이터의 부족으로 인한 어려움을 해결할 수 있는 가능성을 제시해주어 최근 많은 주목을 받고 있다. 본 논문에서는 퓨삿학습의 개념과 주요 접근방법을 빠르게 파악할 수 있도록 데이터 증강, 임베딩과 측도학습, 메타학습의 세 관점에서 최신연구동향을 설명한다. 또한 퓨샷학습을 적용하려는 연구자들에게 도움을 제공할 수 있도록 주요 벤치마크 데이터셋에 대하여 간략하게 소개하였다. 퓨삿학습은 이미지 분석과 자연어 처리 등 다양한 분야에서 활용되고 있으나, 본 논문은 이미지 처리를 위한 퓨삿학습의 접근법에 집중하였다.

OK-KGD:오픈 도메인 한국어 지식 기반 대화 데이터셋 구축 (OK-KGD:Open-domain Korean Knowledge Grounded Dialogue Dataset)

  • 문선아;김산;장진예;정민영;신사임
    • 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
    • /
    • 한국정보과학회언어공학연구회 2023년도 제35회 한글 및 한국어 정보처리 학술대회
    • /
    • pp.342-345
    • /
    • 2023
  • 최근 자연어처리 연구 중 오픈 도메인 지식 기반 대화는 많은 관심을 받고 있다. 연구를 위해서는 오픈 도메인 환경을 갖추고 적절한 지식을 사용한 대화 데이터셋이 필요하다. 지금까지 오픈 도메인 환경을 갖춘 한국어 지식 기반 대화 데이터셋은 존재하지 않아 한국어가 아닌 데이터셋을 한국어로 기계번역하여 연구에 사용하였다. 이를 사용할 경우 두 가지 단점이 존재한다. 먼저 사용된 지식이 한국 문화에 익숙하지 않아 한국인이 쉽게 알 수 없는 대화 내용이 담겨있다. 그리고 번역체가 남아있어 대화가 자연스럽지 않다. 그래서 본 논문에서는 자연스러운 대화체와 대화 내용을 담기 위해 새로운 오픈 도메인 한국어 지식 기반 대화 데이터셋을 구축하였다. 오픈 도메인 환경 구축을 위해 위키백과와 나무위키의 지식을 사용하였고 사용자와 시스템의 발화로 이루어진 1,773개의 대화 세트를 구축하였다. 시스템 발화는 크게 지식을 사용한 발화, 사용자 질문에 대한 답을 주지 못한 발화, 그리고 지식이 포함되지 않은 발화 3가지로 구성된다. 이렇게 구축한 데이터셋을 통해 KE-T5와 Long-KE-T5를 사용하여 간단한 실험을 진행하였다.

  • PDF

건축공간 환경관리 지원을 위한 AI·IoT 기반 이상패턴 검출에 관한 연구 (A Study on Detection of Abnormal Patterns Based on AI·IoT to Support Environmental Management of Architectural Spaces)

  • 강태욱
    • 한국BIM학회 논문집
    • /
    • 제13권3호
    • /
    • pp.12-20
    • /
    • 2023
  • Deep learning-based anomaly detection technology is used in various fields such as computer vision, speech recognition, and natural language processing. In particular, this technology is applied in various fields such as monitoring manufacturing equipment abnormalities, detecting financial fraud, detecting network hacking, and detecting anomalies in medical images. However, in the field of construction and architecture, research on deep learning-based data anomaly detection technology is difficult due to the lack of digitization of domain knowledge due to late digital conversion, lack of learning data, and difficulties in collecting and processing field data in real time. This study acquires necessary data through IoT (Internet of Things) from the viewpoint of monitoring for environmental management of architectural spaces, converts them into a database, learns deep learning, and then supports anomaly patterns using AI (Artificial Infelligence) deep learning-based anomaly detection. We propose an implementation process. The results of this study suggest an effective environmental anomaly pattern detection solution architecture for environmental management of architectural spaces, proving its feasibility. The proposed method enables quick response through real-time data processing and analysis collected from IoT. In order to confirm the effectiveness of the proposed method, performance analysis is performed through prototype implementation to derive the results.

Integrating Perceived Enjoyment within the UTAUT Model for Enhanced Distribution Management Strategies

  • Putu Yudi SETIAWAN;Ni Putu Cempaka Dharmadewi ATMAJA;I Gusti Ayu TIRTAYANI
    • 유통과학연구
    • /
    • 제22권1호
    • /
    • pp.13-23
    • /
    • 2024
  • Purpose: Within the ever-changing realm of modern e-commerce, this study delves into the complex effects of factors like performance expectations, ease of use, social influence, favorable conditions, and enjoyment perception on users' intentions and usage patterns in online marketplace apps. The research centres on Tokopedia app users in Denpasar City, encompassing a wide and varied demographic. Methods: Utilizing a non-probability sampling method, 200 participants were selected for extensive data collection through surveys. Subsequent rigorous analysis of the gathered data was performed using Structural Equation Modeling-Partial Least Squares (SEM-PLS) techniques. Results: This study aims to contribute substantially to theoretical and practical knowledge regarding marketplace app usage. Theoretical contributions involve enhancing the marketing domain, especially in digital marketing, by revealing the intricate factors influencing user conduct in online marketplaces. From a practical standpoint, this research provides valuable insights for entrepreneurs aspiring to join or improve their positions in the Tokopedia app market. Conclusion: Based on the study, we suggest optimising online shopping apps for a more appealing and user-friendly interface. Enhancing the enjoyment and simplicity of finding desired products can prompt heightened usage of online shopping services, thereby reinforcing distribution management strategies and overall market presence.

Revolutionizing Brain Tumor Segmentation in MRI with Dynamic Fusion of Handcrafted Features and Global Pathway-based Deep Learning

  • Faizan Ullah;Muhammad Nadeem;Mohammad Abrar
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제18권1호
    • /
    • pp.105-125
    • /
    • 2024
  • Gliomas are the most common malignant brain tumor and cause the most deaths. Manual brain tumor segmentation is expensive, time-consuming, error-prone, and dependent on the radiologist's expertise and experience. Manual brain tumor segmentation outcomes by different radiologists for the same patient may differ. Thus, more robust, and dependable methods are needed. Medical imaging researchers produced numerous semi-automatic and fully automatic brain tumor segmentation algorithms using ML pipelines and accurate (handcrafted feature-based, etc.) or data-driven strategies. Current methods use CNN or handmade features such symmetry analysis, alignment-based features analysis, or textural qualities. CNN approaches provide unsupervised features, while manual features model domain knowledge. Cascaded algorithms may outperform feature-based or data-driven like CNN methods. A revolutionary cascaded strategy is presented that intelligently supplies CNN with past information from handmade feature-based ML algorithms. Each patient receives manual ground truth and four MRI modalities (T1, T1c, T2, and FLAIR). Handcrafted characteristics and deep learning are used to segment brain tumors in a Global Convolutional Neural Network (GCNN). The proposed GCNN architecture with two parallel CNNs, CSPathways CNN (CSPCNN) and MRI Pathways CNN (MRIPCNN), segmented BraTS brain tumors with high accuracy. The proposed model achieved a Dice score of 87% higher than the state of the art. This research could improve brain tumor segmentation, helping clinicians diagnose and treat patients.