• Title/Summary/Keyword: regression function

Search Result 2,161, Processing Time 0.034 seconds

Analysis of on the Effect of Share-House Service Quality on Trust, Commitment, and Reuse Intention - The Case of University Town in East North Area of Seoul - (쉐어하우스 품질이 사용자의 신뢰와 몰입 및 재이용의사에 미치는 영향 분석 -서울 동북지역 대학가 사례-)

  • Choi, Eui-Ran;Oh, Dong-Hoon
    • The Journal of the Korea Contents Association
    • /
    • v.22 no.6
    • /
    • pp.329-341
    • /
    • 2022
  • The purpose of this study is to examine the influence of Share house quality, trust and commitment to reuse intention of share houses, which are used residences of the college students of South Korea, with a view to confirming whether such share houses can function as an alternative form of residence for college students and young generation. With this, it is intended to enhance the understanding of the current share house market and find implications in the reasonable supply of share houses in the near future and the improvement of the living environment. Literature reviews and empirical studies were conducted in this paper. The findings of this study can be summarized as follows; Regression analysis was conducted to see how tangibility, safety, empathy, reliability, and responsiveness of Share house quality affect trust, commitment, and reuse intension.

Unsupervised feature selection using orthogonal decomposition and low-rank approximation

  • Lim, Hyunki
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.5
    • /
    • pp.77-84
    • /
    • 2022
  • In this paper, we propose a novel unsupervised feature selection method. Conventional unsupervised feature selection method defines virtual label and uses a regression analysis that projects the given data to this label. However, since virtual labels are generated from data, they can be formed similarly in the space. Thus, in the conventional method, the features can be selected in only restricted space. To solve this problem, in this paper, features are selected using orthogonal projections and low-rank approximations. To solve this problem, in this paper, a virtual label is projected to orthogonal space and the given data set is also projected to this space. Through this process, effective features can be selected. In addition, projection matrix is restricted low-rank to allow more effective features to be selected in low-dimensional space. To achieve these objectives, a cost function is designed and an efficient optimization method is proposed. Experimental results for six data sets demonstrate that the proposed method outperforms existing conventional unsupervised feature selection methods in most cases.

Prognostic Impact of Postoperative Complications in High-Risk Operable Non-small Cell Lung Cancer

  • Lee, Seungwook;Roknuggaman, Md;Son, Jung A;Hyun, Seungji;Jung, Joonho;Haam, Seokjin;Yu, Woo Sik
    • Journal of Chest Surgery
    • /
    • v.55 no.1
    • /
    • pp.20-29
    • /
    • 2022
  • Background: Patients with high-risk (HR) operable non-small cell lung cancer (NSCLC) may have unique prognostic factors. This study aimed to evaluate surgical outcomes in HR patients and to investigate prognostic factors in HR patients versus standard-risk (SR) patients. Methods: In total, 471 consecutive patients who underwent curative lung resection for NSCLC between January 2012 and December 2017 were identified and reviewed retrospectively. Patients were classified into HR (n=77) and SR (n=394) groups according to the American College of Surgeons Oncology Group criteria (Z4099 trial). Postoperative complications were defined as those of grade 2 or higher by the Clavien-Dindo classification. Results: The HR group comprised more men and older patients, had poorer lung function, and had more comorbidities than the SR group. The patients in the HR group also experienced more postoperative complications (p≤0.001). More HR patients died without disease recurrence. The postoperative complication rate was the only significant prognostic factor in multivariable Cox regression analysis for HR patients but not SR patients. HR patients without postoperative complications had a survival rate similar to that of SR patients. Conclusion: The overall postoperative survival of HR patients with NSCLC was more strongly affected by postoperative complications than by any other prognostic factor. Care should be taken to minimize postoperative complications, especially in HR patients.

Correlation analysis between radiation exposure and the image quality of cone-beam computed tomography in the dental clinical environment

  • Song, Chang-Ho;Yeom, Han-Gyeol;Kim, Jo-Eun;Huh, Kyung-Hoe;Yi, Won-Jin;Heo, Min-Suk;Lee, Sam-Sun
    • Imaging Science in Dentistry
    • /
    • v.52 no.3
    • /
    • pp.283-288
    • /
    • 2022
  • Purpose: This study was conducted to measure the radiation exposure and image quality of various cone-beam computed tomography (CBCT) machines under common clinical conditions and to analyze the correlation between them. Materials and Methods: Seven CBCT machines used frequently in clinical practice were selected. Because each machine has various sizes of fields of view (FOVs), 1 large FOV and 1 small FOV were selected for each machine. Radiation exposure was measured using a dose-area product (DAP) meter. The quality of the CBCT images was analyzed using 8 image quality parameters obtained using a dental volume tomography phantom. For statistical analysis, regression analysis using a generalized linear model was used. Results: Polymethyl-methacrylate (PMMA) noise and modulation transfer function (MTF) 10% showed statistically significant correlations with DAP values, presenting positive and negative correlations, respectively (P<0.05). Image quality parameters other than PMMA noise and MTF 10% did not demonstrate statistically significant correlations with DAP values. Conclusion: As radiation exposure and image quality are not proportionally related in clinically used equipment, it is necessary to evaluate and monitor radiation exposure and image quality separately.

The Difference in the Quality of Life of Korean Children With Attention-Deficit/Hyperactivity Disorder Between Before and After COVID-19

  • Lee, Jung-Hoon;Maeng, Seri;Lee, Jeong-Seop;Bae, Jae-Nam;Kim, Won-Hyoung;Kim, Hyeyoung
    • Journal of the Korean Academy of Child and Adolescent Psychiatry
    • /
    • v.33 no.4
    • /
    • pp.113-121
    • /
    • 2022
  • Objectives: This study aimed to compare the quality of life (QoL) of children with attention-deficit/hyperactivity disorder (ADHD) before and during coronavirus disease-2019 (COVID-19) and to examine how their QoL is affected by emotional and environmental factors during COVID-19. Methods: Participants in the pre-COVID-19 (n=43) and COVID-19 (n=36) groups were recruited from the same university hospital. The Pediatric Quality of Life Inventory (PedsQL) 4.0 Child Self-report, the Children's Depression Inventory (CDI), the Revised Children's Manifest Anxiety Scale (RCMAS), the PedsQL 4.0 Parent Proxy Report, and the Conners' Parent Rating Scale (CPRS) were employed. Independent t-tests, Pearson's correlation analysis, and multiple regression analysis were conducted. Results: Caregivers assessed the children's QoL more negatively than the children themselves in both groups. Children with ADHD evaluated their physical function more negatively and anxiety was significantly higher in the COVID-19 group. In the COVID-19 group, the PedsQL child self-report was significantly predicted by the CPRS, the CDI, and environmental factors (i.e., relation to child and monthly household income). Conclusion: Children with ADHD in the COVID-19 group had a numerically lower QoL and significantly higher anxiety. To improve QoL, it is important to deal with not only depression but also ADHD symptoms and environmental factors.

Association of diet quality score with the risk of mild cognitive impairment in the elderly

  • Kim, Eunbin;Choi, Bo Youl;Kim, Mi Kyung;Yang, Yoon Jung
    • Nutrition Research and Practice
    • /
    • v.16 no.5
    • /
    • pp.673-684
    • /
    • 2022
  • BACKGROUND/OBJECTIVES: Although adherence to a higher diet quality may help prevent cognitive decline in older adults, literature for this in a Korean population is limited. Thus, the aim of this study was to examine the association between diet quality indices and the risk of mild cognitive impairment (MCI) in Korean older adults. SUBJECTS/METHODS: This cross-sectional study included 806 community-dwelling people aged 60 yrs and over in Korea. Diet quality was assessed via the revised Recommended Food Score (RFS) and alternate Mediterranean Diet Score (aMDS). Cognitive function was measured using a Korean version of the Mini-Mental State Examination (MMSE-KC). Associations between diet quality indices and MMSE-KC score were assessed with a general linear model after adjusting for covariates. Logistic regression was used to determine the association between diet quality indices and the risk of MCI. RESULTS: The prevalence of MCI was 35.3%. There were no significant trends between MMSE-KC scores and RFS and aMDS after adjusting for age, gender, education, exercise, living status, social activity, and alcohol drinking. Among total subjects, RFS was inversely associated with the risk of MCI after adjusting for covariates (Q5 vs. Q1; odds ratio [OR], 0.49; 95% confidence interval [CI], 0.28-0.83). Among total subjects and men, aMDS was inversely related to the risk of MCI after adjusting for covariates (Q5 vs. Q1; OR, 0.51; 95% CI, 0.29-0.89 for total subjects; Q5 vs. Q1; OR, 0.36; 95% CI, 0.15-0.83 for men). CONCLUSIONS: Our results demonstrate that high diet quality evaluated by RFS and aMDS is inversely associated with the risk of MCI. Thus, high quality diet may reduce or retard cognitive decline in the old population. Longitudinal studies are needed to determine the causal relationship between diet quality and the risk of MCI in the elderly.

Factors Affecting Readmission After Discharge in Stroke Patients: A Retrospective Study (뇌졸중 환자의 퇴원 후 재입원에 영향을 미치는 요인: 후향적 연구)

  • Kang, Ae Jeong;Lee, Song Hee;Kim, Rock Beum;Jeon, Mi Yang
    • Journal of Korean Biological Nursing Science
    • /
    • v.24 no.4
    • /
    • pp.262-271
    • /
    • 2022
  • Purpose: The purpose of this study was to identify the factors affecting readmission in stroke patients. Methods: A retrospective study design was used. Participants were 3,675 adult cerebral stroke patients in the inpatient wards of the Department of Neurology and Neurosurgery of G University Hospital located in C city. Data were collected from January 1, 2016 to December 31, 2021 and data were analyzed using χ2 test, independent t-test, and multivariate logistic regression with SPSS/WIN 24.0. Results: After discharge for stroke, the readmission rate was 23.7%, and the mortality rate was 0.3%. The variables with significant differences between the readmission group and non-readmission group were age, type of stroke, surgery, ICU treatment, mRS score, blood pressure, diabetes, and heart disease. Factors influencing an readmission in stroke patients were Age 65-74 (OR 1.30, 95% CI=1.03-1.64), ≥ 75 (OR 1.28, 95% CI=1.02-1.62), mRS score 2points (OR 2.50, 95% CI=1.99-3.13), HTN status (OR 1.26, 95% CI=1.07-1.50), CVD status (OR 1.38, 95% CI=1.01-1.90), TC (OR 1.60, 95% CI=1.05-2.44). Conclusion: To lower the readmission rate of stroke patients, it is essential to control lifestyle, including whether or not to take treatment drugs, after diagnosing risk factors such as high blood pressure, diabetes, and heart disease, hyperlipidemia. Nursing interventions that can provide information on risk factor management and coping strategies are urgently needed as symptoms change. In addition, research is needed to develop and implement an intervention strategy that can improve the function of stroke patients as much as possible at home or in society so that they can lead an independent life without the help of others, and verify their effectiveness.

Incidence of congenital hypothyroidism by gestational age: a retrospective observational study

  • Ha Young Jo;Eun Hye Yang;Young Mi Kim;Soo-Han Choi;Kyung Hee Park;Hye Won Yoo;Su Jeong Park;Min Jung Kwak
    • Journal of Yeungnam Medical Science
    • /
    • v.40 no.1
    • /
    • pp.30-36
    • /
    • 2023
  • Background: Congenital hypothyroidism (CH) is the leading cause of preventable physical and intellectual disabilities. This study aimed to assess the incidence and clinical characteristics of CH in newborns. Methods: We retrospectively reviewed the medical records of all newborns delivered at the Pusan National University Hospital between January 2011 and March 2021. The incidence of CH was compared according to gestational age, birth weight, and small for gestational age (SGA). The patients aged ≥3 years who could not maintain normal thyroid function and required levothyroxine treatment were diagnosed with permanent CH. Logistic regression analysis was performed to compare CH risks. Results: Of 3,722 newborns, 40 were diagnosed with CH (1.07%). Gestational age and birth weight were significantly associated with CH incidence. The odds ratios (ORs) of CH in infants delivered at 32-37, 28-31, and <28 weeks were 2.568 (95% confidence interval [CI], 1.141-5.778), 5.917 (95% CI, 2.264-15.464), and 7.441 (95% CI, 2.617-21.159) times higher, respectively, than those delivered at term. The ORs of CH in infants weighing 1,500-2,499 g, 1,000-1,499 g, and <1,000 g were 4.664 (95% CI, 1.928-11.279), 11.076 (95% CI, 4.089-29.999), and 12.544 (95% CI, 4.350-36.176) times greater, respectively, than those in infants weighing ≥2,500 g. The OR of CH was 6.795 (95% CI, 3.553-13.692) times greater in SGA than in non-SGA infants. Conclusion: The CH incidence in South Korea has increased significantly compared with that in the past. Gestational age, birth weight, and SGA were significantly associated with CH incidence.

Analysis on Water Retention Rate according to Water Cycle Characteristics in Jeju Gotjawal Forest (제주 곶자왈 산림의 물순환 특성에 따른 수원함양률 분석)

  • Jaehoon Kim;Honggeun Lim;Hyung Tae Choi;Qiwen Li;Haewon Moon;Hyungsoon Choi
    • Journal of Environmental Science International
    • /
    • v.31 no.12
    • /
    • pp.1013-1025
    • /
    • 2022
  • This study was carried out to analyze water cycle characteristics and evaluate water retention function in Jeju Gotjawal forest from 2013 to 2017. The average ratio of throughfall, stemflow, interception loss in Seonhul Gotjawal (SH) and Cheongsu Gotjawal (CS) was 43.1%, 15.8%, and 41.1%, respectively. Rainfall-throughfall, rainfall-stemflow, and rainfall-interception loss were expressed as linear regression equation (p<0.001). The comparison results showed that SH was higher than CS (p<0.05), indicating that the canopy area had an important effect on the difference in stand structure. The average water resources retention rate of the Gotjawal region was 41.9%, which is similar to the total water resources retention rate (40.6%) of Jeju Special Self-Governing Province (JSSGP). Currently, the development of Gotjawal is in progress in JSSGP. The development of Gotjawal will lead to a decrease in the water resources retention rate due to changes in the surface environment such as an increase in impervious areas, which will affect the total groundwater content of JSSGP. Therefore, the conservation of the Gotjawal area is judged to be very important from the point of view of water conservation.

A Study on the Response Plan by Station Area Cluster through Time Series Analysis of Urban Rail Riders Before and After COVID-19 (COVID-19 전후 도시철도 승차인원 시계열 군집분석을 통한 역세권 군집별 대응방안 고찰)

  • Li, Cheng Xi;Jung, Hun Young
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.43 no.3
    • /
    • pp.363-370
    • /
    • 2023
  • Due to the spread of COVID-19, the use of public transportation such as urban railroads has changed significantly since the beginning of 2020. Therefore, in this study, daily time series data for each urban railway station were collected for three years before COVID-19 and after the spread of COVID-19, and the similarity of time series analysis was evaluated through DTW (Dynamic Time Warping) distance method to derive regression centers for each cluster, and the effect of various external events such as COVID-19 on changes in the number of users was diagnosed as a time series impact detection function. In addition, the characteristics of use by cluster of urban railway stations were analyzed, and the change in passenger volume due to external shocks was identified. The purpose was to review measures for the maintenance and recovery of usage in the event of re-proliferation of COVID-19.