Abstract Models predicting the occurrence of specific types of behavioral and psychological symptoms of dementia (BPSD) can be highly beneficial for its early intervention and individualized care planning. Using a machine learning approach, this study developed and validated predictive models of the occurrence of BPSD, categorized into seven subsyndromes, among community-dwelling older adults with dementia in South Korea. BPSD dairy was used to measure BPSD and the state of unmet needs daily. We measured sleep and activity levels using actigraphy, and stress and fatigue using a portable heart rate variability analyzer. We developed predictive models and conducted cross-validation using training data that consisted of the first two wave dataset, and then validated the models using wave 3 test data. To deal with imbalanced datasets, we used Synthetic Minority Oversampling Technique (SMOTE), an over-sampling method. Categorical variables were pre-processed using target encoding. We then compared the machine-learning models with logistic regression. The area under the receiver operating characteristic curve (AUC) scores of the support vector machine (SVM) models for the wave 3 test data showed a similar or greater value than logistic regression models across all BPSD subsyndromes. The SVM model (AUC = 0.899) had an AUC value greater than that of the logistic regression model (AUC = 0.717), particularly for hyperactivity symptoms. Machine learning algorithms, especially SVM models, can be used to develop BPSD prediction models to help identify at-risk individuals and implement symptom-targeted individualized interventions.
The escalating volume of construction activities and resultant waste generation underscores the imperative for developing sophisticated segmentation models to facilitate efficient sorting and recycling processes. This study introduces WasteSAM, an enhanced iteration of the segment anything model (SAM), specifically tailored to address the intricate complexities inherent in construction waste imagery. Drawing upon a comprehensive dataset comprising over 15,000 masks representing five distinct categories of construction materials, WasteSAM exhibits notably superior segmentation capabilities. Quantitative analysis demonstrates significant performance improvements, with WasteSAM outperforming the original SAM model by an average of 23.9% in dice similarity coefficient and 30.0% in normalized surface distance metrics. The integration of stereo-image techniques in refining the training dataset has facilitated WasteSAM in more accurately discerning the three-dimensional structure of waste materials, thereby augmenting the precision of waste classification. Noteworthy is the model’s adeptness in handling intricate textures and patterns across diverse imaging modalities, including varying lighting conditions and complex object interactions. While showing promising results, this study also highlights the need for high-quality, diverse datasets that reflect real-world construction site complexities, rather than merely larger datasets.
Abstract Social isolation in older adults, which encompasses limited social interaction and loneliness, is a significant risk factor for dementia. Subjective cognitive decline (SCD) and mild cognitive impairment (MCI) stages are considered focal points of preventive interventions, at which cognitive and physical functions can be restored. Thus, preventing social isolation via prompt identification of high-risk individuals is crucial. This study aimed to develop and validate machine learning models to predict social interaction and loneliness levels among older adults with SCD and MCI. This study included 99 community-dwelling older adults (n=67 SCD and 32 MCI). While demographic and health-related data were collected via survey, we applied a mobile Ecological Momentary Assessment approach for real-time measurement of social interaction and loneliness levels and wrist-worn actigraphy for sleep and activity data. While the Random Forest model was the most suitable for predicting social interaction level (area under the receiver operating characteristic curve [AUC]: 0.935), the Gradient Boosting Machine model was the most suitable for predicting high levels of loneliness (AUC: 0.887). Time-specific analyses demonstrated the association between a low frequency of physical movement in the morning and a low level of social interaction, and decreased sleep quality during night time and high levels of loneliness. This study showed the potential of machine learning models to predict the social interaction and loneliness of older adults at risk for dementia. The algorithms can be applied to develop mobile preventive interventions that utilize real-time sleep and behavioral data to prevent social isolation in these at-risk individuals.
Sodium-glucose cotransporter 2 inhibitors (SGLT2i), have shown benefits in patient with heart failure (HF), however, adherence remains a significant issue: with only 60% of patients continuing usage beyond a year. This study aims to identify patients at risk of discontinuing SGLT2i and promote its judicious use to reduce hospitalizations and improve cardiovascular outcomes. Using the Korean National Health Insurance Service database, patients diagnosed with HF and diabetes mellitus (n = 1,665,565) between 2013 and 2018 were identified. Among them, 55,694 participants prescribed SGLT2i were enrolled. The primary endpoint included 1) all-cause mortality and 2) SGLT2i-related hospitalization, encompassing incidents such as ketoacidosis, acute kidney injury, urinary tract infections, fall-related fractures, and other unplanned hospitalizations. During the follow-up period (median: 2.3 years; range: 1.2-3.6 years), 8,463 participants reached the primary endpoint (25.5 for all-cause death and 39.4 for SGLT2i-related hospitalizations per 1,000 person-years). Independent risk factors for the primary endpoint in multivariate Cox regression and propensity-score matching analyses included age of ≥ 70 years, body mass index (BMI) <18.5 kg/m2, body weight <60 kg, anemia, chronic kidney disease, and the use of diuretics. Age (hazard ratio [HR] 1.45, 95% confidence interval [CI]: 1.36-1.54), BMI (HR 1.78, 95% CI: 1.29-2.45), body weight (HR 1.17, 95% CI: 1.09-1.26) and the use of furosemide (HR 1.45, 95% CI: 1.22-1.74) (all p<0.001) were consistent independent risk factors in the propensity score-matched cohort. Having three or more risk factors was associated with an adjusted HR that was 3.04 times higher than cases with no risk factor (95% CI: 2.83-3.28, p<0.001). Old age, low weight or BMI, and the use of diuretics are risk factors that hinder the continuous use of SGLT2i in diabetic patients with HF. Close monitoring for side effects is essential when prescribing SGLT2i, particularly for those with multiple risk factors.
This study evaluates the vibration data of high-rise buildings during a typhoon by measuring the vibration data and using international serviceability standards. In order to do this, the horizontal vibration serviceability evaluation standards of each country were surveyed, but the standards that could be applied were limited to ISO10137 and ISO 6897. Despite the trend that the discomfort of residents increases as the number of high-rise buildings increases, the current standards are for high-frequency vibrations, such as machine vibrations or vertical floor vibrations, so there is an urgent need for research on new evaluation methods for low-frequency horizontal vibrations. As a result of analyzing the effects of typhoons on buildings, the study’s target building had low natural frequencies of less than 1 Hz, and the highest acceleration was observed to be amplified up to about 160 times due to the effects of Typhoon Danas and Chaba, but there was no change in the natural frequency. When this result was applied to the horizontal vibration serviceability evaluation, it was found that the likelihood of residents perceiving vibration was low during constant vibration, but during strong winds, the size of the top-floor horizontal vibration exceeded the average level of vibration perception proposed by ISO standards, so most residents of high-rise buildings would be likely to perceive the vibration as uncomfortable.
본 연구는 인공지능 연구개발과정에 많은 인적자원이 필요함을 인지하고 현 개발방식 고려할 사항에 대해 논의한다. 결론적으로 인공지능 개발의 효율성 향상을 위해서는 소수의 관리자와 많은 일반작업자들의 분업화가 이루어져야 가능하며, 이는 마치 일종의 경공업의 형태와 유사하다고 생각된다. 따라서 본 연구진은 컴퓨터라는 기계장치로 데이터라는 디지털 자원을 다루어 생산의 효율성을 높이는 인공지능 개발과정을 4차산업시대의 디지털 경공업이라고 명명한다. 이전 산업혁명시대에서 경험한 것과 마찬가지로 인적자원을 효율적으로 배분화하고 활용한다면 디지털 경공업은 2차산업혁명 못 지 않는 발전을 기대할 수 있을 것이며, 이를 위한 인력양성이 시급하다고 판단된다.
The demand for categorising technology that requires minimum manpower and equipment is increasing because a large amount of waste is produced during the demolition and remodelling of a structure. Considering the latest trend, applying an artificial intelligence (AI) model for automatic categorisation is the most efficient method. However, it is difficult to apply this technology because research has only focused on general domestic waste. Thus, in this study, we delineate the process for developing an AI model that differentiates between various types of construction waste. Particularly, solutions for solving difficulties in collecting learning data, which is common in AI research in special fields, were also considered. To quantitatively increase the amount of learning data, the Fréchet Inception Distance method was used to increase the amount of learning data by two to three times through augmentation to an appropriate level, thus checking the improvement in the performance of the AI model.
Abstract Recent studies have suggested an increased incidence of myocarditis and pericarditis following mRNA vaccination or COVID-19. However, the potential interaction effect between vaccine type and COVID-19 on heart disease risk remains uncertain. Our study aimed to examine the impact of COVID-19 status and vaccine type following the first dose on acute heart disease in the Korean population, using data from the National Health Insurance Service COVID-19 database (October 2018–March 2022). We sought to provide insights for public health policies and clinical decisions pertaining to COVID-19 vaccination strategies. We analysed heart disease risk, including acute cardiac injury, acute myocarditis, acute pericarditis, cardiac arrest, and cardiac arrhythmia, in relation to vaccine type and COVID-19 within 21 days after the first vaccination date, employing Cox proportional hazards models with time-varying covariates. This study included 3,350,855 participants. The results revealed higher heart disease risk in individuals receiving mRNA vaccines than other types (adjusted HR, 1.48; 95% CI, 1.35–1.62). Individuals infected by SARS-CoV-2 also exhibited significantly higher heart disease risk than those uninfected (adjusted HR, 3.56; 95% CI, 1.15–11.04). We found no significant interaction effect between vaccine type and COVID-19 status on the risk of acute heart disease. Notably, however, younger individuals who received mRNA vaccines had a higher heart disease risk compared to older individuals. These results may suggest the need to consider alternative vaccine options for the younger population. Further research is needed to understand underlying mechanisms and guide vaccination strategies effectively.
In the rapidly advancing field of construction, digital site management and Building Information Modeling (BIM) are pivotal. This study explores the integration of drone imagery into the digital construction site management process, aiming to create BIM models with enhanced object recognition capabilities. Initially, the research sought to achieve photorealistic rendering of point cloud models (PCMs) using blur/sharpen filters and generative adversarial network (GAN) models. However, these techniques did not fully meet the desired outcomes for photorealistic rendering. The research then shifted to investigating additional methods, such as fine-tuning object recognition algorithms with real-world datasets, to improve object recognition accuracy. The study’s findings present a nuanced understanding of the limitations and potential pathways for achieving photorealistic rendering in PCM, underscoring the complexity of the task and laying the groundwork for future innovations in this area. Although the study faced challenges in attaining the original goal of photorealistic rendering for object detection, it contributes valuable insights that may inform future research and technological development in digital construction site management.
'%3e%3cg id='b'%3e%3cpath id='a' stroke='%23000' stroke-width='2' d='M-6-25H6m-12 3H6m-12 3H6'/%3e%3cuse xlink:href='%23a' y='44'/%3e%3c/g%3e%3cpath stroke='%23fff' d='M0 17v10'/%3e%3ccircle r='12' fill='%23cd2e3a'/%3e%3cpath fill='%230047a0' d='M0-12A6 6 0 0 0 0 0a6 6 0 0 1 0 12 12 12 0 0 1 0-24z'/%3e%3c/g%3e%3cg transform='rotate(-123.69)'%3e%3cuse xlink:href='%23b'/%3e%3cpath stroke='%23fff' d='M0-23.5v3M0 17v3.5m0 3v3'/%3e%3c/g%3e%3c/svg%3e)
