• 제목/요약/키워드: condition index

검색결과 2,443건 처리시간 0.031초

EEG Feature Engineering for Machine Learning-Based CPAP Titration Optimization in Obstructive Sleep Apnea

  • Juhyeong Kang;Yeojin Kim;Jiseon Yang;Seungwon Chung;Sungeun Hwang;Uran Oh;Hyang Woon Lee
    • International journal of advanced smart convergence
    • /
    • 제12권3호
    • /
    • pp.89-103
    • /
    • 2023
  • Obstructive sleep apnea (OSA) is one of the most prevalent sleep disorders that can lead to serious consequences, including hypertension and/or cardiovascular diseases, if not treated promptly. Continuous positive airway pressure (CPAP) is widely recognized as the most effective treatment for OSA, which needs the proper titration of airway pressure to achieve the most effective treatment results. However, the process of CPAP titration can be time-consuming and cumbersome. There is a growing importance in predicting personalized CPAP pressure before CPAP treatment. The primary objective of this study was to optimize the CPAP titration process for obstructive sleep apnea patients through EEG feature engineering with machine learning techniques. We aimed to identify and utilize the most critical EEG features to forecast key OSA predictive indicators, ultimately facilitating more precise and personalized CPAP treatment strategies. Here, we analyzed 126 OSA patients' PSG datasets before and after the CPAP treatment. We extracted 29 EEG features to predict the features that have high importance on the OSA prediction index which are AHI and SpO2 by applying the Shapley Additive exPlanation (SHAP) method. Through extracted EEG features, we confirmed the six EEG features that had high importance in predicting AHI and SpO2 using XGBoost, Support Vector Machine regression, and Random Forest Regression. By utilizing the predictive capabilities of EEG-derived features for AHI and SpO2, we can better understand and evaluate the condition of patients undergoing CPAP treatment. The ability to predict these key indicators accurately provides more immediate insight into the patient's sleep quality and potential disturbances. This not only ensures the efficiency of the diagnostic process but also provides more tailored and effective treatment approach. Consequently, the integration of EEG analysis into the sleep study protocol has the potential to revolutionize sleep diagnostics, offering a time-saving, and ultimately more effective evaluation for patients with sleep-related disorders.

Determination of Resistance Factors of Load and Resistance Factor Design for Drilled Shaft Based on Load Test (LRFD 설계를 위한 현장타설말뚝의 주면지지력 저항계수 산정)

  • Kim, Seok-Jung;Kwon, Oh-Sung;Jung, Sung-Jun;Han, Jin-Tae;Kim, Myoung-Mo
    • Journal of the Korean Geotechnical Society
    • /
    • 제26권7호
    • /
    • pp.17-24
    • /
    • 2010
  • Load Resistance Factor Design method is used increasingly in geotechnical design world widely and resistance factors for drilled shafts are suggested by AASHTO. However, these resistance factors are determined for intact rock conditions; by comparison, most of bedrocks in Korea have weathered condition, so that applying the AASHTO resistance factors is not reasonable. Thus, this study suggests the proper resistance factors for design of drilled shaft in Korea. The 22 cases of pile load test data from 8 sites were chosen and reliability-based approach is used to analyze the data. Reliability analysis was performed by First Order Second Moment Method (FOSM) applying 4 bearing capacity equations. As a result, when the Factor of Safety (FOS) was selected as 3.0, the target reliability indexes (${\beta}_c$) were evaluated as 2.01~2.30. Resistance factors and load factors are determined from optimization based on above results. The resistance factors ranged between 0.48 and 0.56 and load factors for dead load and live load are evaluated as approximately 1.25 and 1.75 respectively. However, when the target reliabilities are considered as 3.0, the resistance factors are evaluated as approximately 50% of the results when the target reliability index was 2.0.

Evaluation of Undrained Shear Strength of Busan New-port Clay by DMT (DMT를 이용한 부산신항 점토의 비배수 전단강도 추정)

  • Hong, Sung-Jin;Shin, Dong-Hyun;Kim, Dong-Hee;Jung, Sang-Jin;Lee, Woo-Jin
    • Journal of the Korean Geotechnical Society
    • /
    • 제23권7호
    • /
    • pp.87-98
    • /
    • 2007
  • A series of dilatometer test, field vane test, and $CK_0U$ triaxial test were performed for clayey soils of Busan new port site to develop the relationships between undrained shear strength and the DMT results. Normalized undrained shear strength is turned out to be $S_{u(CKU)}/{\sigma}'_v=0.30{\sim}0.35\;for\;CK_0U$ triaxial test and ${\mu}S_{u(VST)}/{\sigma}'_v=0.20{\sim}0.22$ for vane shear test. By comparing the undrained shear strength estimated from DMT indices with the results measured by in-situ vane test or $CK_0U$ triaxial test, two methods to predict the undrained shear strength from DMT results are suggested. One is based on the relationship between $S_u/{\sigma}'_v$ and horizontal stress index (KD) while another method comes from $N_c-I_D$ and $N_c-E_D$ correlation. It was observed that the method based on $N_c-I_D\;or\;N_c-E_D$ relation shows slightly better accuracy than the one based on $K_D$ although all of the methods suggested in this study provided comparable values of predicted undrained shear strength. Since the definitions of $I_D\;and\;E_D$ contain $p_1-p_0$, in which soil condition is reflected, it is believed that the prediction method using $N_c$ is capable of taking a material type into consideration.

Study on the Diet Style According to the Sasang Constitution (사상체질(四象體質)에 따른 식이(食餌)습관에 관(關)한 연구(硏究))

  • Kim, Pan-jun;Lim, Hwa-jae;Kim, Jong-won
    • Journal of Sasang Constitutional Medicine
    • /
    • 제13권3호
    • /
    • pp.59-74
    • /
    • 2001
  • In oriental medicine, food are regarded as important one like medicine. Especially Sasang medicine put emphasis on diet, it regarded food as a important one by taking food according to their own constitution in the point of improving health condition and preventing diseases. In this report, the author try to find out the relationship between food preference and each suitable food according to Sasang constitution by using survey data. The results are like this. 1. In constitutional distribution patterns among 203 person(male : 118 person, female : 85 person) reveal Soyang Group 58person(28.6%), Taeum Group 61(30%) and Soeum Group 84(41.4%). And their were no significant difference in their height in all group according to gender. Compared with the other groups, When compared with the other groups on body weight and BMI, Taeum Group indicate significantly high body weight and BMI(Body Mass Index) in both gender. 2. Taeum Group show significantly high smoking rate. But alcohol drinking rates reveal no significant difference in all groups. 3. In the Survey about food preference according to the constitution, rice, Soju, watermelon show significantly high preference in case of suitable food to each group. But perilla seeds, coffee, ginger tea show insignificant results. 4. In the survey about food preference according to the constitution and sex, welsh onion, crab preserved with soysauce, beer show significantly high preference in case of suitable food to each group. But glutinous rice, cooked barley, water dropwort muchim, lettuce, dog meat, egg, yellow croaker, coffee, ginger tea, and Soju show insignificant results. 5. In the survey about food preference according to the constitution and age, rice, watermelon, onion, garlic, salt and Soju show significantly high preference in case of suitable food to each group. But sugar and perilla seeds show insignificant results. 6. In the survey about food preference according to constitution, sex and age, glutinous rice, soybean milk, banana, crab preserved with soysauce, sea cucumber, sea mustard, Soju, beer, onion, garlic, salt show high preference in case of suitable food to each group. But cooked barley, sugar, water dropwort muchim, dog meat, puffer soup and perilla seeds show insignificant results.

  • PDF

Numerical Investigations of Physical Habitat Changes for Fish induced by the Hydropeaking in the Downstream River of Dam (댐 하류 하천에서 발전방류로 인한 어류 물리서식처 변화 수치모의)

  • Kang, Hyeongsik;Im, Dongkyun;Kim, Kyu-Ho
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • 제30권2B호
    • /
    • pp.211-217
    • /
    • 2010
  • This paper presents numerical investigations of the physical habitat changes induced by the hydropeaking in the downstream river of dam. For the two-dimensional ecohydraulic simulations, River2D model is used. Pirami (Zacco platypus) is selected as the target fish for investigating the impact of the hydropeaking. For validation of the model, the water surface elevations are simulated with two different water discharges. The computed results are compared with field data in the literature, and the result shows that the model successfully simulates the water flows. The weight usable area (WUA) of Pirami with the life cycle and the composite suitability index with different water discharges are computed and discussed. The results show that habitat for Pirami appears to be best in the bend region downstream of the dam. The discharge of the maximum WUA for adult Pirami is computed to be about 9 $m^3/s$. Also, the WUA computed in a condition of hydropeaking during seven days are presented. The averaged discharge of the hydropeaking appears to be about 20% larger than the drought flow, but the WUA by the hydropeaking is computed to be 60-100% smaller. This result shows that the hydropeaking reduces quantity of habitat available to fish.

Effect of sweet pumpkin powder on lipid metabolism in leptin-deficient mice (Leptin 유전자 결핍 동물모델에서 단호박분말 투여가 지방대사변화에 미치는 영향)

  • Inae Jeong;Taesang Son;Sang-myeong Jun;Hyun-Jung Chung;Ok-Kyung Kim
    • Journal of Nutrition and Health
    • /
    • 제56권5호
    • /
    • pp.469-482
    • /
    • 2023
  • Purpose: Obesity has emerged as a critical global public health concern as it is associated with and increases susceptibility to various diseases. This condition is characterized by the excessive enlargement of adipose tissue, primarily stemming from an inequity between energy intake and expenditure. The purpose of this study was to investigate the potential of sweet pumpkin powder in mitigating obesity and metabolic disorders in leptin-deficient obese (ob/ob) mice and to compare the effects of raw sweet pumpkin powder (HNSP01) and heat-treated sweet pumpkin powder (HNSP02). Methods: Leptin-deficient obese mice were fed a diet containing 10% HNSP01 and another containing 10% HNSP02 for 6 weeks. Results: The supplementation of ob/ob mice with HNSP01 and HNSP02 resulted in decreased body weight gain, reduced adipose tissue weight, and a smaller size of lipid droplets in the adipose tissue and liver. Furthermore, the ob/ob-HNSP01 and ob/ob-HNSP02 supplemented groups exhibited lower levels of triglycerides, total cholesterol, low-density lipoprotein cholesterol, fasting blood glucose, and insulin, as well as a reduced atherogenic index in comparison with the control group. Molecular analysis also demonstrated that the intake of HNSP01 and HNSP02 resulted in a diminished activation of factors associated with fatty acid synthesis, including acetyl-CoA carboxylase and fatty acid synthase, while concurrently enhancing factors associated with lipolysis, including adipose triglyceride lipase and hormone-sensitive lipase, in the adipose tissue. Conclusion: Taken together, these findings collectively demonstrate the potential of sweet pumpkin powder as a functional food ingredient with therapeutic properties against obesity and its associated metabolic disorders, such as insulin resistance and dyslipidemia.

The Performance Improvement of PLC by Using RTP Extension Header Data for Consecutive Frame Loss Condition in CELP Type Vocoder (CELP Type Vocoder에서 RTP 확장 헤더 데이터를 이용한 연속적인 프레임 손실에 대한 PLC 성능개선)

  • Hong, Seong-Hoon;Bae, Myung-Jin
    • The Journal of the Acoustical Society of Korea
    • /
    • 제29권1호
    • /
    • pp.48-55
    • /
    • 2010
  • It has a falling off in speech quality, especially when consecutive packet loss occurs, even if a vocoder implemented in the packet network has its own packet loss concealment (PLC) algorithm. PLC algorithm is divided into transmitter and receiver algorithm. Algorithm in the transmitter gives superior quality by additional information. however it is impossible to provide mutual compatibility and it occurs extra delay and transmission rate. The method applied in the receiver does not require additional delay. However, it sets limits to improve the speech quality. In this paper, we propose a new method that puts extra information for PLC in a part of Extension Header Data which is not used in RTP Header. It can solve the problem and obtain enhanced speech quality. There is no extra delay occurred by the proposed algorithm because there is a jitter buffer to adjust network delay in a receiver. Extra information, 16 bits each frame for G.729 PLC, is allocated for MA filter index in LP synthesis, excitation signal, excitation signal gain and residual gain reconstruction. It is because a transmitter sends speech data each 20 ms when it transfers RTP payload. As a result, the proposed method shows superior performance about 13.5%.

Influence of Mixture Non-uniformity on Methane Explosion Characteristics in a Horizontal Duct (수평 배관의 메탄 폭발특성에 있어서 불균일성 혼합기의 영향)

  • Ou-Sup Han;Yi-Rac Choi;HyeongHk Kim;JinHo Lim
    • Korean Chemical Engineering Research
    • /
    • 제62권1호
    • /
    • pp.27-35
    • /
    • 2024
  • Fuel gases such as methane and propane are used in explosion hazardous area of domestic plants and can form non-uniform mixtures with the influence of process conditions due to leakage. The fire-explosion risk assessment using literature data measured under uniform mixtures, damage prediction can be obtained the different results from actual explosion accidents by gas leaks. An explosion characteristics such as explosion pressure and flame velocity of non-uniform gas mixtures with concentration change similar to that of facility leak were examined. The experiments were conducted in a closed 0.82 m long stainless steel duct with observation recorded by color high speed camera and piezo pressure sensor. Also we proposed the quantification method of non-uniform mixtures from a regression analysis model on the change of concentration difference with time in explosion duct. For the non-uniform condition of this study, the area of flame surface enlarged with increasing the concentration non-uniform in the flame propagation of methane and was similar to the wrinkled flame structure existing in a turbulent flame. The time to peak pressure of methane decreased as the non-uniform increased and the explosion pressure increased with increasing the non-uniform. The ranges of KG (Deflagration index) of methane with the concentration non-uniform were 1.30 to 1.58 [MPa·m/s] and the increase rate of KG was 17.7% in methane with changing from uniform to non-uniform.

Evaluation and Management of Frailty, and Its Association With Pain (노쇠의 평가와 관리, 그리고 통증과의 연관성)

  • Kang Joon Lee
    • Korean Journal of Psychosomatic Medicine
    • /
    • 제32권1호
    • /
    • pp.1-9
    • /
    • 2024
  • Frailty is a clinical syndrome as an increased vulnerability to stressors, leading to a decrease in physiologic reserves and a decline in the ability to maintain a good homeostasis. This condition leads to an increased risk of hospitalization, disability and mortality. Frailty occurs due to various causes and requires a multidimensional approach. It is also important to detect and manage it early. Frailty is also deeply related to neuropsychiatric problems such as pain and depression. In evaluating frailty, it is desirable to comprehensively consider not only physical areas such as disease, nutrition, movement, and sensory functions, but also psychosocial areas, and representative scales include Fried's physical frailty phenotype and Rockwood's frailty index. Physical activity and appropriate protein intake are important for frailty management, and inappropriate drug use should be reduced and oral care, cognitive function, and falls should also be noted. Frailty and pain can affect each other, and pain can promote frailty. Evidence has been published that hormone and protein abnormalities, immune system activity and inflammatory response, and epigenetic mechanisms work in common in the field of frailty and pain. More extensive and high-quality research should be conducted in the future, and the quality of life will be improved if the results are applied to the suppression and treatment of old age and pain.

Status Diagnosis Algorithm for Optimizing Power Generation of PV Power Generation System due to PV Module and Inverter Failure, Leakage and Arc Occurrence (태양광 모듈, 인버터 고장, 누설 및 아크 발생에 따른 태양광발전시스템의 발전량 최적화를 위한 상태진단 알고리즘)

  • Yongho Yoon
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • 제24권4호
    • /
    • pp.135-140
    • /
    • 2024
  • It is said that PV power generation systems have a long lifespan compared to other renewable energy sources and require little maintenance. However, there are cases where the performance expected during initial design is not achieved due to shading, temperature rise, mismatch, contamination/deterioration of PV modules, failure of inverter, leakage current, and arc generation. Therefore, in order to solve the problems of these systems, the power generation amount and operation status are investigated qualitatively, or the performance is comparatively analyzed based on the performance ratio (PR), which is the performance index of the solar power generation system. However, because it includes large losses, it is difficult to accurately determine whether there are any abnormalities such as performance degradation, failure, or defects in the PV power generation system using only the performance coefficient. In this paper, we studied a status diagnosis algorithm for shading, inverter failure, leakage, and arcing of PV modules to optimize the power generation of PV power generation systems according to changes in the surrounding environment. In addition, using the studied algorithm, we examined the results of an empirical test on condition diagnosis for each area and the resulting optimized operation of power generation.