• Title/Summary/Keyword: Korean human dataset

Search Result 161, Processing Time 0.024 seconds

Improving Performance of Human Action Recognition on Accelerometer Data (가속도 센서 데이터 기반의 행동 인식 모델 성능 향상 기법)

  • Nam, Jung-Woo;Kim, Jin-Heon
    • Journal of IKEEE
    • /
    • v.24 no.2
    • /
    • pp.523-528
    • /
    • 2020
  • With a widespread of sensor-rich mobile devices, the analysis of human activities becomes more general and simpler than ever before. In this paper, we propose two deep neural networks that efficiently and accurately perform human activity recognition (HAR) using tri-axial accelerometers. In combination with powerful modern deep learning techniques like batch normalization and LSTM networks, our model outperforms baseline approaches and establishes state-of-the-art results on WISDM dataset.

Human Activity Recognition in Smart Homes Based on a Difference of Convex Programming Problem

  • Ghasemi, Vahid;Pouyan, Ali A.;Sharifi, Mohsen
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.11 no.1
    • /
    • pp.321-344
    • /
    • 2017
  • Smart homes are the new generation of homes where pervasive computing is employed to make the lives of the residents more convenient. Human activity recognition (HAR) is a fundamental task in these environments. Since critical decisions will be made based on HAR results, accurate recognition of human activities with low uncertainty is of crucial importance. In this paper, a novel HAR method based on a difference of convex programming (DCP) problem is represented, which manages to handle uncertainty. For this purpose, given an input sensor data stream, a primary belief in each activity is calculated for the sensor events. Since the primary beliefs are calculated based on some abstractions, they naturally bear an amount of uncertainty. To mitigate the effect of the uncertainty, a DCP problem is defined and solved to yield secondary beliefs. In this procedure, the uncertainty stemming from a sensor event is alleviated by its neighboring sensor events in the input stream. The final activity inference is based on the secondary beliefs. The proposed method is evaluated using a well-known and publicly available dataset. It is compared to four HAR schemes, which are based on temporal probabilistic graphical models, and a convex optimization-based HAR procedure, as benchmarks. The proposed method outperforms the benchmarks, having an acceptable accuracy of 82.61%, and an average F-measure of 82.3%.

The Influence of Human Rights Sensitivity and the Nursing Work Environment on Workplace Bullying Victimization among Nurses in Small- and Medium-Sized Hospitals (중소병원 간호사의 인권감수성과 간호근무환경이 직장 내 괴롭힘 피해에 미치는 영향)

  • Cho, Eun-Kyung;Kim, Moon-Jeong
    • The Korean Journal of Health Service Management
    • /
    • v.13 no.3
    • /
    • pp.27-38
    • /
    • 2019
  • Objectives: The purpose of this study was to examine the influence of human rights sensitivity and nursing work environment on workplace bullying victimization among nurses in small- and medium-sized hospitals. Methods: The participants were 255 nurses from 5 general hospitals in Busan. A dataset was collected using a structured self-reporting questionnaire during the month of July 2018. The data were analyzed with SPSS WIN 23.0 software (IBM Corp., Armonk, NY, USA) using independent t-test, one-way analysis of variance, Pearson's correlation coefficient, and multiple regression analysis. Results: Nursing work environment showed negative correlation with workplace bullying victimization. Being a witness to bullying, organizational support, head nurse's leadership, and relationships with peers were found to influence workplace bullying victimization, and these 4 variables explained 37% of workplace bullying victimization. Conclusions: Formal procedures for cases of bullying and improvements in the leadership of head nurses and peer relationships are crucial to reducing workplace bullying victimization among nurses in small- and medium-sized hospitals. Hospital executives' efforts to provide sufficient physical and human resources for nursing services and to improve the welfare of nurses are also needed.

A Synthetic Dataset for Korean Knowledge Graph-to-Text Generation (한국어 지식 그래프-투-텍스트 생성을 위한 데이터셋 자동 구축)

  • Dahyun Jung;Seungyoon Lee;SeungJun Lee;Jaehyung Seo;Sugyeong Eo;Chanjun Park;Yuna Hur;Heuiseok Lim
    • Annual Conference on Human and Language Technology
    • /
    • 2022.10a
    • /
    • pp.219-224
    • /
    • 2022
  • 최근 딥러닝이 상식 정보를 추론하지 못하거나, 해석 불가능하다는 한계점을 보완하기 위해 지식 그래프를 기반으로 자연어 텍스트를 생성하는 연구가 중요하게 수행되고 있다. 그러나 이를 위해서 대량의 지식 그래프와 이에 대응되는 문장쌍이 요구되는데, 이를 구축하는 데는 시간과 비용이 많이 소요되는 한계점이 존재한다. 또한 하나의 그래프에 다수의 문장을 생성할 수 있기에 구축자 별로 품질 차이가 발생하게 되고, 데이터 균등성에 문제가 발생하게 된다. 이에 본 논문은 공개된 지식 그래프인 디비피디아를 활용하여 전문가의 도움 없이 자동으로 데이터를 쉽고 빠르게 구축하는 방법론을 제안한다. 이를 기반으로 KoBART와 mBART, mT5와 같은 한국어를 포함한 대용량 언어모델을 활용하여 문장 생성 실험을 진행하였다. 실험 결과 mBART를 활용하여 미세 조정 학습을 진행한 모델이 좋은 성능을 보였고, 자연스러운 문장을 생성하는데 효과적임을 확인하였다.

  • PDF

KommonGen: A Dataset for Korean Generative Commonsense Reasoning Evaluation (KommonGen: 한국어 생성 모델의 상식 추론 평가 데이터셋)

  • Seo, Jaehyung;Park, Chanjun;Moon, Hyeonseok;Eo, Sugyeong;Kang, Myunghoon;Lee, Seounghoon;Lim, Heuiseok
    • Annual Conference on Human and Language Technology
    • /
    • 2021.10a
    • /
    • pp.55-60
    • /
    • 2021
  • 최근 한국어에 대한 자연어 처리 연구는 딥러닝 기반의 자연어 이해 모델을 중심으로 각 모델의 성능에 대한 비교 분석과 평가가 활발하게 이루어지고 있다. 그러나 한국어 생성 모델에 대해서도 자연어 이해 영역의 하위 과제(e.g. 감정 분류, 문장 유사도 측정 등)에 대한 수행 능력만을 정량적으로 평가하여, 생성 모델의 한국어 문장 구성 능력이나 상식 추론 과정을 충분히 평가하지 못하고 있다. 또한 대부분의 생성 모델은 여전히 간단하고 일반적인 상식에 부합하는 자연스러운 문장을 생성하는 것에도 큰 어려움을 겪고 있기에 이를 해결하기 위한 개선 연구가 필요한 상황이다. 따라서 본 논문은 이러한 문제를 해결하기 위해 한국어 생성 모델이 일반 상식 추론 능력을 바탕으로 문장을 생성하도록 KommonGen 데이터셋을 제안한다. 그리고 KommonGen을 통해 한국어 생성 모델의 성능을 정량적으로 비교 분석할 수 있도록 평가 기준을 구성하고, 한국어 기반 자연어 생성 모델의 개선 방향을 제시하고자 한다.

  • PDF

Arousal and Valence Classification Model Based on Long Short-Term Memory and DEAP Data for Mental Healthcare Management

  • Choi, Eun Jeong;Kim, Dong Keun
    • Healthcare Informatics Research
    • /
    • v.24 no.4
    • /
    • pp.309-316
    • /
    • 2018
  • Objectives: Both the valence and arousal components of affect are important considerations when managing mental healthcare because they are associated with affective and physiological responses. Research on arousal and valence analysis, which uses images, texts, and physiological signals that employ deep learning, is actively underway; research investigating how to improve the recognition rate is needed. The goal of this research was to design a deep learning framework and model to classify arousal and valence, indicating positive and negative degrees of emotion as high or low. Methods: The proposed arousal and valence classification model to analyze the affective state was tested using data from 40 channels provided by a dataset for emotion analysis using electrocardiography (EEG), physiological, and video signals (the DEAP dataset). Experiments were based on 10 selected featured central and peripheral nervous system data points, using long short-term memory (LSTM) as a deep learning method. Results: The arousal and valence were classified and visualized on a two-dimensional coordinate plane. Profiles were designed depending on the number of hidden layers, nodes, and hyperparameters according to the error rate. The experimental results show an arousal and valence classification model accuracy of 74.65 and 78%, respectively. The proposed model performed better than previous other models. Conclusions: The proposed model appears to be effective in analyzing arousal and valence; specifically, it is expected that affective analysis using physiological signals based on LSTM will be possible without manual feature extraction. In a future study, the classification model will be adopted in mental healthcare management systems.

TET2DICOM-GUI: Graphical User Interface Based TET2DICOM Program to Convert Tetrahedral-Mesh-Phantom to DICOM-RT Dataset

  • Se Hyung Lee;Bo-Wi Cheon;Chul Hee Min;Haegin Han;Chan Hyeong Kim;Min Cheol Han;Seonghoon Kim
    • Progress in Medical Physics
    • /
    • v.33 no.4
    • /
    • pp.172-179
    • /
    • 2022
  • Recently, tetrahedral phantoms have been newly adopted as international standard mesh-type reference computational phantoms (MRCPs) by the International Commission on Radiological Protection, and a program has been developed to convert them to computational tomography images and DICOM-RT structure files for application of radiotherapy. Through this program, the use of the tetrahedral standard phantom has become available in clinical practice, but utilization has been difficult due to various library dependencies requiring a lot of time and effort for installation. To overcome this limitation, in this study a newly developed TET2DICOM-GUI, a TET2DICOM program based on a graphical user interface (GUI), was programmed using only the MATLAB language so that it can be used without additional library installation and configuration. The program runs in the same order as TET2DICOM and has been optimized to run on a personal computer in a GUI environment. A tetrahedron-based male international standard human phantom, MRCP-AM, was used to evaluate TET2DICOM-GUI. Conversion into a DICOM-RT dataset applicable in clinical practice in about one hour with a personal computer as a basis was confirmed. Also, the generated DICOM-RT dataset was confirmed to be effectively implemented in the radiotherapy planning system. The program developed in this study is expected to replace actual patient data in future studies.

Optimised ML-based System Model for Adult-Child Actions Recognition

  • Alhammami, Muhammad;Hammami, Samir Marwan;Ooi, Chee-Pun;Tan, Wooi-Haw
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.13 no.2
    • /
    • pp.929-944
    • /
    • 2019
  • Many critical applications require accurate real-time human action recognition. However, there are many hurdles associated with capturing and pre-processing image data, calculating features, and classification because they consume significant resources for both storage and computation. To circumvent these hurdles, this paper presents a recognition machine learning (ML) based system model which uses reduced data structure features by projecting real 3D skeleton modality on virtual 2D space. The MMU VAAC dataset is used to test the proposed ML model. The results show a high accuracy rate of 97.88% which is only slightly lower than the accuracy when using the original 3D modality-based features but with a 75% reduction ratio from using RGB modality. These results motivate implementing the proposed recognition model on an embedded system platform in the future.

KMSS: Korean Media Script Dataset for Dialogue Summarization (대화 요약 생성을 위한 한국어 방송 대본 데이터셋 )

  • Bong-Su Kim;Hye-Jin Jun;Hyun-Kyu Jeon;Hye-in Jung;Jung-Hoon Jang
    • Annual Conference on Human and Language Technology
    • /
    • 2022.10a
    • /
    • pp.198-204
    • /
    • 2022
  • 대화 요약은 다중 발화자와 발화문으로 이루어진 멀티턴 형식의 문서에 대해 핵심내용을 추출하거나 생성하는 태스크이다. 대화 요약 모델은 추천, 대화 시스템 등에 콘텐츠, 서비스 기록에 대한 분석을 제공하는 데 유용하다. 하지만 모델 구축에 필요한 한국어 대화 요약 데이터셋에 대한 연구는 부족한 실정이다. 본 논문에서는 생성 기반 대화 요약을 위한 데이터셋을 제안한다. 이를 위해 국내 방송사의 대용량 콘텐츠로 부터 원천 데이터를 수집하고, 주석자가 수작업으로 레이블링 하였다. 구축된 데이터셋 규모는 6개 카테고리에 대해 약 100K이며, 요약문은 단문장, 세문장, 2할문장으로 구분되어 레이블링 되었다. 또한 본 논문에서는 데이터의 특성을 내재화하고 통제할 수 있도록 대화 요약 레이블링 가이드를 제안한다. 이를 기준으로 모델 적합성 검증에 사용될 디코딩 모델 구조를 선정한다. 실험을 통해 구축된 데이터의 몇가지 특성을 조명하고, 후속 연구를 위한 벤치마크 성능을 제시한다. 데이터와 모델은 aihub.or.kr에 배포 되었다.

  • PDF

Constructing Korean Named Recognition Dataset for Financial Domain Using Active Learning (능동 학습 기법을 활용한 한국어 금융 도메인 개체명 인식 데이터 구축)

  • Jeong, Dong-Ho;Heo, Min-Kang;Kim, Hyung-Chul;Park, Sang-Won
    • Annual Conference on Human and Language Technology
    • /
    • 2020.10a
    • /
    • pp.82-86
    • /
    • 2020
  • 딥러닝 모델의 성능은 데이터의 품질과 양에 의해 향상된다. 그러나 데이터 구축은 많은 비용과 시간을 요구한다. 특히 전문 도메인의 데이터를 구축할 경우 도메인 지식을 갖춘 작업자를 활용할 비용과 시간이 더욱 제약적이다. 능동 학습 기법은 최소한의 데이터 구축으로 모델의 성능을 효율적으로 상승시키기 위한 방법이다. 다양한 데이터셋이 능동 학습 기법으로 구축된 바 있으나, 아직 전문 도메인의 한국어 데이터를 구축하는 연구는 활발히 수행되지 못한 것이 현실이다. 본 논문에서는 능동학습기법을 통해 금융 도메인의 개체명 인식 코퍼스를 구축하였고, 이를 통해 다음의 기여가 있다: (1) 금융 도메인 개체명 인식 코퍼스 구축에 능동 학습 기법이 효과적임을 확인하였고, (2) 이를 통해 금융 도메인 개체명 인식기를 개발하였다. 본 논문이 제안하는 방법을 통해 8,043문장 데이터를 구축하였고, 개체명 인식기의 성능은 80.84%로 달성되었다. 또한 본 논문이 제안하는 방법을 통해 약 12~25%의 예산 절감 효과가 있음을 실험으로 보였다.

  • PDF