• Title/Summary/Keyword: F1 score

Search Result 1,378, Processing Time 0.034 seconds

Effect of Moxibustion Therapy on Ryodoraku Score of the Patients with Degenerative Arthritis of Knee Joint (퇴행성 슬관절염 환자의 뜸 치료가 양도락 점수에 미치는 영향)

  • Oh, Myung Jin;Song, Ho Sueb
    • Journal of Acupuncture Research
    • /
    • v.30 no.2
    • /
    • pp.9-15
    • /
    • 2013
  • Objectives : This study was done for reporting the effect of moxibustion therapy on Ryodoraku score of the patients with degenerative arthritis of knee joint. Methods : We investigated 65 cases of patients with degenerative arthritis of knee joint, and devided patients into two groups : One group treated by moxibustion therapy, which was not applied to the other group we analyzed of each group the Ryodoraku score(F1, F6) of each group before and after moxibustion therapy and compared it. Results : 1. In moxibustion therapy group compared with baseline, at final, Ryodoraku score(F1, F6) was significantly increased. 2. At final, moxibustion therapy group showed significant increase on Ryodoraku score(F1, F6) score compared with non moxibustion therapy group. Conclusions : It is suggested that Ryodoraku score(F1, F6) should be available for diagnosing degenerative arthritis of knee joint.

Performance Comparison of Recurrent Neural Networks and Conditional Random Fields in Biomedical Named Entity Recognition (의생명 분야의 개체명 인식에서 순환형 신경망과 조건적 임의 필드의 성능 비교)

  • Jo, Byeong-Cheol;Kim, Yu-Seop
    • 한국어정보학회:학술대회논문집
    • /
    • 2016.10a
    • /
    • pp.321-323
    • /
    • 2016
  • 최근 연구에서 기계학습 중 지도학습 방법으로 개체명 인식을 하고 있다. 그러나 지도 학습 방법은 데이터를 만드는 비용과 시간이 많이 필요로 한다. 본 연구에서는 주석 된 말뭉치를 사용하여 지도 학습 방법을 사용 한다. 의생명 개체명 인식은 Protein, RNA, DNA, Cell type, Cell line 등을 포함한 텍스트 처리에 중요한 기초 작업입니다. 그리고 의생명 지식 검색에서 가장 기본과 핵심 작업 중 하나이다. 본 연구에서는 순환형 신경망과 워드 임베딩을 자질로 사용한 조건적 임의 필드에 대한 성능을 비교한다. 조건적 임의 필드에 N_Gram만을 자질로 사용한 것을 기준점으로 설정 하였고, 기준점의 결과는 70.09% F1 Score이다. RNN의 jordan type은 60.75% F1 Score, elman type은 58.80% F1 Score의 성능을 보여준다. 조건적 임의 필드에 CCA, GLOVE, WORD2VEC을 사용 한 결과는 각각 72.73% F1 Score, 72.74% F1 Score, 72.82% F1 Score의 성능을 얻을 수 있다.

  • PDF

The Study on the Characteristics of Ryodoraku Score in the Children with Allergic Rhinitis (알레르기성 비염환아들의 양도락 특성에 관한 연구)

  • An, Ju Hyeon;Lee, Jin Young
    • The Journal of Pediatrics of Korean Medicine
    • /
    • v.30 no.3
    • /
    • pp.31-41
    • /
    • 2016
  • Objectives The purpose of this study is to investigate the characteristics of Ryodoraku Score in the children who visited department of pediatrics, hospital of Korean medicine with allergic rhinitis as the chief complaint. Methods Subjects were 80 children with allergic rhinitis. We calculated the average Ryodoraku Score (RS, ${\mu}A$), and compared the average of each meridian system. And we classified the children by several groups (depending on age, additional allergic disease), and accomplished a comparative analysis. Results 1. The average of Ryodoraku Score in 80 children was $76.36{\pm}22.72$. 2. The figure of H3 (心), H5 (三焦), F1 (脾), F2 (肝), F3 (腎), F4 (膀胱), F5 (三焦), F6 (胃) had significant statistical differences compared to the total average. 3. Comparing the group having only allergic rhinitis to group having allergic rhinitis and other allergic disease, showed significant statistical difference in H2 (心包), H3 (心). 4. Analyzed by age, there's a significant statistical difference in F1 (脾), F4 (膀胱). Conclusion We found that H5 (三焦), F1 (脾), F4 (膀胱) showed significant statistical difference in Ryodoraku Score, and F1 (脾) had the highest relevance. The research indicate meaningful difference depending on age, additional allergic disease.

A Named Entity Recognition Model in Criminal Investigation Domain using Pretrained Language Model (사전학습 언어모델을 활용한 범죄수사 도메인 개체명 인식)

  • Kim, Hee-Dou;Lim, Heuiseok
    • Journal of the Korea Convergence Society
    • /
    • v.13 no.2
    • /
    • pp.13-20
    • /
    • 2022
  • This study is to develop a named entity recognition model specialized in criminal investigation domains using deep learning techniques. Through this study, we propose a system that can contribute to analysis of crime for prevention and investigation using data analysis techniques in the future by automatically extracting and categorizing crime-related information from text-based data such as criminal judgments and investigation documents. For this study, the criminal investigation domain text was collected and the required entity name was newly defined from the perspective of criminal analysis. In addition, the proposed model applying KoELECTRA, a pre-trained language model that has recently shown high performance in natural language processing, shows performance of micro average(referred to as micro avg) F1-score 98% and macro average(referred to as macro avg) F1-score 95% in 9 main categories of crime domain NER experiment data, and micro avg F1-score 98% and macro avg F1-score 62% in 56 sub categories. The proposed model is analyzed from the perspective of future improvement and utilization.

Reconsideration of F1 Score as a Performance Measure in Mass Spectrometry-based Metabolomics

  • Jeong, Jaesik;Kim, Han Sol;Kim, Shin June
    • Journal of Integrative Natural Science
    • /
    • v.11 no.3
    • /
    • pp.161-164
    • /
    • 2018
  • Over the past decade, mass spectrometry-based metabolomics, especially two dimensional gas chromatography mass spectrometry (GCxGC/TOF-MS), has become a key analytical tool for metabolomics data because of its sensitivity and ability to analyze complex biological or biochemical sample. However, the need to reduce variations within/between experiments has been reported and methodological developments to overcome such problem has long been a critical issue. Along with methodological developments, developing reasonable performance measure has also been studied. Following four numerical measures have been typically used for comparison: sensitivity, specificity, receiver operating characteristic (ROC) curves, and positive predictive value (PPV). However, more recently, such measures are replaced with F1 score in many fields including metabolomics area without any carefulness of its validity. Thus, we want to investigate the validity of F1 score on two examples, with the goal of raising the awareness in choosing appropriate performance comparison measure. We noticed that F1 score itself, as a performance measure, was not good enough. Accordingly, we suggest that F1 score be supplemented with other performance measure such as specificity to improve its validity.

Performance Comparison of Recurrent Neural Networks and Conditional Random Fields in Biomedical Named Entity Recognition (의생명 분야의 개체명 인식에서 순환형 신경망과 조건적 임의 필드의 성능 비교)

  • Jo, Byeong-Cheol;Kim, Yu-Seop
    • Annual Conference on Human and Language Technology
    • /
    • 2016.10a
    • /
    • pp.321-323
    • /
    • 2016
  • 최근 연구에서 기계학습 중 지도학습 방법으로 개체명 인식을 하고 있다. 그러나 지도 학습 방법은 데이터를 만드는 비용과 시간이 많이 필요로 한다. 본 연구에서는 주석 된 말뭉치를 사용하여 지도 학습 방법을 사용 한다. 의생명 개체명 인식은 Protein, RNA, DNA, Cell type, Cell line 등을 포함한 텍스트 처리에 중요한 기초 작업입니다. 그리고 의생명 지식 검색에서 가장 기본과 핵심 작업 중 하나이다. 본 연구에서는 순환형 신경망과 워드 임베딩을 자질로 사용한 조건적 임의 필드에 대한 성능을 비교한다. 조건적 임의 필드에 N_Gram만을 자질로 사용한 것을 기준점으로 설정 하였고, 기준점의 결과는 70.09% F1 Score이다. RNN의 jordan type은 60.75% F1 Score, elman type은 58.80% F1 Score의 성능을 보여준다. 조건적 임의 필드에 CCA, GLOVE, WORD2VEC을 사용 한 결과는 각각 72.73% F1 Score, 72.74% F1 Score, 72.82% F1 Score의 성능을 얻을 수 있다.

  • PDF

Decision Making Style and Learning Style according to Sasang Constitution (사상체질에 따른 의사결정 및 학습 유형)

  • Shin, Eun-Ju
    • Journal of Oriental Neuropsychiatry
    • /
    • v.20 no.4
    • /
    • pp.115-126
    • /
    • 2009
  • Objectives : This study was performed to investigate the relationship between decision making style and learning style according to Sasang constitution. Methods : The subjects were 213 nursing students of K college in Jeonbuk, and the period of data gathering was limited from 1 Sep. 2009 to 7 Sep. 2009. The instrument tools included QSCC II, decision making style, and learning style. The collected data were analyzed by SPSS-PC programme. Results : 1. Decision making style: Soeumin group had significantly high score in rational score compared with Soyangin(F=7.174 p=.001), and in dependent score compared with Taeumin and Soyangin (F=3.414, p=.035). 2. Learning style: Soyangin group had significantly high score in cooperation score compared with Taeumin(F=5.688 p=.004), and Taeumin group had significantly high score in emulous score compared with Soeumin and Soyangin (F=.148, p=.002). Conclusions : In conclusion, it was found that decision making style and learning style are significantly different according to Sasang constitution. Therefore, these results suggest that nursing educational program needs to be developed considering Sasang constitution.

  • PDF

Studies on Simplified Procedures for Freezing and Thawing of Bovine Embryos VI. Effects of freezing procedures in a liquid nitrogen container on the survival rate of mouse embryos (육우수정란 간역동결 및 융해방법에 관한 연구 제육보. 내동제에 Sucrose 첨가에 따른 액체질소에 미치는 영향)

  • 이중계;이규훈;강만종;김영훈;문성호;김승호
    • Korean Journal of Animal Reproduction
    • /
    • v.12 no.2
    • /
    • pp.77-83
    • /
    • 1988
  • This study was done with mouse embryo to assess effects of freezing media containing sucrose, freezing metods(1-F, 0.3$^{\circ}C$/min;2-F, 3-5$^{\circ}C$/min;3-F, 15$^{\circ}C$min;4-F, LN2 vapour) and cell freezers on the embryo survival determined using the FDA test. The results are summarized as follows. 1. The FDA score obtained with 1, 2, 3 and 4-F was 3.8, 3.6, 3.2 and 3.2, respectively. There was a significant difference(P<0.05) between 1-F, 3-F and 2-F, 4-F. 2. The score at the morular stage(3.8) higher(P<0.005) than the blastocyst stage of embryos(3.2). 3. No difference (P>0.05) was found between the score obtained with a automatic embryo freezer(4.0) and a liquid nitrogen container(3.7).

  • PDF

Relation ship between Health Perception and Health Status of Clinical Nurses (임상간호사의 건강지각과 건강상태의 관계)

  • Seo, Jeong-Seon
    • The Korean Journal of Rehabilitation Nursing
    • /
    • v.5 no.1
    • /
    • pp.71-85
    • /
    • 2002
  • The purpose of study was to find out the relation ship between health perception and health status of clinical nurses. It also identified factors that related to health perception and health status of clinical nurses. The research design was descriptive correlational study. The subjects were consisted of 289 clinical nurses at the university hospital in Pusan. The data were collected from Feb. 12th to Feb. 28th, 2001 by self reporting structured questionnaires. The instruments used for this study were health perception questionnaire developed by Ware and Cornell Medical Index modified by Nam Ho-Chang (1965) for measuring health status. The data were analyzed by SPSS/PC+ program using frequency, percentage, mean, mean mark, standard deviation, t-test, ANOVA, Scheffe test, and Pearson's correlation coefficient. The results of this study were as follows. 1. The mean score of the health perception was $94.70{\pm}8.93$(range : 29-145), which the item mean mark score was $3.27{\pm}$0.31(range 1-5). The score of subarea of the health perception was the highest score in health concern ($4.57{\pm}0.58$) and the lowest score in rejection of sick role($2.94{\pm}0.32$). 2. The mean score of the health status was $102.83{\pm}7.61$(range: 57-114), which the item mean mark score was $1.80{\pm}0.13$ (range : 1-2). The mean mark score of the physical health status was $62.55{\pm}5.35$($1.69{\pm}0.14$) and the mental health status was $40.28{\pm}3.51$($1.83{\pm}0.16$). 3. There were statistically significant difference in the score of health perception according to the presence of disease(F=4.607, P=.011), job satisfaction (F=12.242, P=.000), and job place(F=2.838, P=.038). 4. There were statistically significant difference in the score of health status according to the age(F=3.164, P=.007), presence of leisure time(F=4.308, P=.039), presence of diseases(F=3.215, P=.042), job experience(F=9.064, P=.000), job satisfaction(F=7.182, P=.001), job place (F=5.638, P=.001), job position (F=3.900, P=.021). 5. Health perception of clinical nurse was shown to be positively related to health status(r=.543, p=.000). In conclusion, health perception of clinical nurse working at the university hospital was relatively high, and health status was fine. And the more health perception was high, the more health status was high. Therefore, the health promotion program for clinical nurses, should included health perception.

  • PDF

Machine learning-based Predictive Model of Suicidal Thoughts among Korean Adolescents. (머신러닝 기반 한국 청소년의 자살 생각 예측 모델)

  • YeaJu JIN;HyunKi KIM
    • Journal of Korean Artificial Intelligence Association
    • /
    • v.1 no.1
    • /
    • pp.1-6
    • /
    • 2023
  • This study developed models using decision forest, support vector machine, and logistic regression methods to predict and prevent suicidal ideation among Korean adolescents. The study sample consisted of 51,407 individuals after removing missing data from the raw data of the 18th (2022) Youth Health Behavior Survey conducted by the Korea Centers for Disease Control and Prevention. Analysis was performed using the MS Azure program with Two-Class Decision Forest, Two-Class Support Vector Machine, and Two-Class Logistic Regression. The results of the study showed that the decision forest model achieved an accuracy of 84.8% and an F1-score of 36.7%. The support vector machine model achieved an accuracy of 86.3% and an F1-score of 24.5%. The logistic regression model achieved an accuracy of 87.2% and an F1-score of 40.1%. Applying the logistic regression model with SMOTE to address data imbalance resulted in an accuracy of 81.7% and an F1-score of 57.7%. Although the accuracy slightly decreased, the recall, precision, and F1-score improved, demonstrating excellent performance. These findings have significant implications for the development of prediction models for suicidal ideation among Korean adolescents and can contribute to the prevention and improvement of youth suicide.