• Title/Summary/Keyword: maeA

Search Result 624, Processing Time 0.023 seconds

Fast Inter CU Partitioning Algorithm using MAE-based Prediction Accuracy Functions for VVC (MAE 기반 예측 정확도 함수를 이용한 VVC의 고속 화면간 CU 분할 알고리즘)

  • Won, Dong-Jae;Moon, Joo-Hee
    • Journal of Broadcast Engineering
    • /
    • v.27 no.3
    • /
    • pp.361-368
    • /
    • 2022
  • Quaternary tree plus multi-type tree (QT+MTT) structure was adopted in the Versatile Video Coding (VVC) standard as a block partitioning tool. QT+MTT provides excellent coding gain; however, it has huge encoding complexity due to the flexibility of the binary tree (BT) and ternary tree (TT) splits. This paper proposes a fast inter coding unit (CU) partitioning algorithm for BT and TT split types based on prediction accuracy functions using the mean of the absolute error (MAE). The MAE-based decision model was established to achieve a consistent time-saving encoding with stable coding loss for a practical low complexity VVC encoder. Experimental results under random access test configuration showed that the proposed algorithm achieved the encoding time saving from 24.0% to 31.7% with increasing luminance Bjontegaard delta (BD) rate from 1.0% to 2.1%.

A Study on Medical-criminal Problem of Withdrawing Life-Sustaining Treatment (치료중단행위에 대한 의료형법적 고찰 -의학적 충고에 반한 퇴원 사례를 중심으로-)

  • Cho, In-Ho
    • The Korean Society of Law and Medicine
    • /
    • v.9 no.1
    • /
    • pp.319-382
    • /
    • 2008
  • As a withdrawing care's study, the purpose of this study is searching about withdrawing care's acceptance and circumstances through Bora-mae hospital case(chapter 1). Withdrawing life-sustaining treatment has various forms. Though the meaning of euthanasia, death with dignity, natural death, physician assisted suicide are duplicated, the meaning of those are different slightly. Firstly, this study looks about the difference of the those meaning and acceptance range(condition) by withdrawing care's forms(chapter 2). Bora-mae hospital case sentenced guilty about physician who discharged incompetent patient who was after surgery by patient's wife determination. This Bora-mae case that sentenced guilty about discharge against medical advise(DAMA) that is regarded to custom has brought intensive confliction of legal, social, medical aspect, Bora-mae hospital case has many legal problems. First, as to criminal law rule 250(murder), the problem is whether discharge and withdrawing life-sustaining treatment is commission or omission. this study concluded omission(district court: omission, appeal, supreme court: commission). Because legal denounce point of discharge and medical treatment withdrawing is omission that physician who is obligatory on patient to cure. If physician's act is regarded omission, it is necessary to determine whether he has guardian status and obligation. Without guardian status and obligation, omission crime can't exist. This study decided that physician had guardian status and obligation and foundation of guardian status was pre-action or acceptance of emergency patient. Physician's medical treatment duty finished when patient(or patient's guardian) demands discharge. But when patient death is foreseen and other possible treatment does not exist, his duty of life prolonging treatment does not finish. This originate from physician's social responsibility and public status that limits patient's private liberty. This study regarded physician's action as accomplice about whether physician's discharging action is accomplice or the principal offender(district court: the principal offender, appeal, supreme court: accomplice). Though the principal offender needs criminal determination and action, there is no this common determination and functional action control of physician in Bora-mae case(chapter 3). Bora-mae hospital case partly originated from deficiency of legal, institutive system including medical security system shortage, the instruction is 1. medical security system strengthening, 2. hospital ethical committee's activity strengthening, 3. institutionalization of withdrawing life-sustaining treatment, 4. acceptance of pre-decision making system, 5. sufficient persuasion of physician for patient and faithful writing of medical paper, 6. respect for patients' self-determination and rights, 7. consciousness's changing for withdrawing life-sustaining treatment and persistent education about medical ethics(chapter 4). Considering Bora-mae case, medical sector is not the dead ground of a criminal punishment. Intervention of criminal law in medical sector give rise to ill effect, that is, excess medical examination and treatment, safeguard treatment, delay of discharge from a hospital. Because sufficient guarantee of life becomes mere empty slogan under situation that impose a burden of heavy cost to family or hospital, public and systematic solution should be given(chapter 5).

  • PDF

Predictive Analysis of Fire Risk Factors in Gyeonggi-do Using Machine Learning (머신러닝을 이용한 경기도 화재위험요인 예측분석)

  • Seo, Min Song;Castillo Osorio, Ever Enrique;Yoo, Hwan Hee
    • Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
    • /
    • v.39 no.6
    • /
    • pp.351-361
    • /
    • 2021
  • The seriousness of fire is rising because fire causes enormous damage to property and human life. Therefore, this study aims to predict various risk factors affecting fire by fire type. The predictive analysis of fire factors was carried out targeting Gyeonggi-do, which has the highest number of fires in the country. For the analysis, using machine learning methods SVM (Support Vector Machine), RF (Random Forest), GBRT (Gradient Boosted Regression Tree) the accuracy of each model was presented with a high fit model through MAE (Mean Absolute Error) and RMSE (Root Mean Squared Error), and based on this, predictive analysis of fire factors in Gyeonggi-do was conducted. In addition, using machine learning methods such as SVM (Support Vector Machine), RF (Random Forest), and GBRT (Gradient Boosted Regression Tree), the accuracy of each model was presented with a high-fit model through MAE and RMSE. Predictive analysis of occurrence factors was achieved. Based on this, as a result of comparative analysis of three machine learning methods, the RF method showed a MAE = 1.765 and RMSE = 1.876, as well as the MAE and RMSE verification and test data were very similar with a difference between MAE = 0.046 and RMSE = 0.04 showing the best predictive results. The results of this study are expected to be used as useful data for fire safety management allowing decision makers to identify the sequence of dangers related to the factors affecting the occurrence of fire.

Periodicity Dependence of Magnetic Anisotropy and Magnetization of FeCo Heterostructure

  • Kim, Miyoung
    • Journal of Magnetics
    • /
    • v.21 no.1
    • /
    • pp.6-11
    • /
    • 2016
  • The magnetic anisotropy energy (MAE) and the saturation magnetization $B_s$ of (110) $Fe_nCo_n$ heterostructures with n = 1, 2, and 3 are investigated in first-principles within the density functional theory by using the precise full-potential linearized augmented plane wave (FLAPW) method. We compare the results employing two different exchange correlation potentials, that is, the local density approximation (LDA) and the generalized gradient approximation (GGA), and include the spin-orbit coupling interaction of the valence states in the second variational way. The MAE is found to be enhanced significantly compared to those of bulk Fe and Co and the magnetic easy axis is in-plane in agreement with experiment. Also the MAE exhibits the in-plane angle dependence with a two-fold anisotropy showing that the $[1{\overline{I}}0]$ direction is the most favored spin direction. We found that as the periodicity increases, (i) the saturation magnetization $B_s$ decreases due to the reduced magnetic moment of Fe far from the interface, (ii) the strength of in-plane preference of spin direction increases yielding enhancement of MAE, and (iii) the volume anisotropy coefficient decreases because the volume increase outdo the MAE enhancement.

A Study on Sparsity Effect about MAE in Collaborative Filtering (협력적 필터링에서 희소성에 따른 MAE 향상에 관한 연구)

  • Kim, Sun-Ok;Lee, Seok-Jun;Lee, Hee-Choon
    • 한국IT서비스학회:학술대회논문집
    • /
    • 2007.11a
    • /
    • pp.616-620
    • /
    • 2007
  • 전자상거래에서 사용되고 있는 추천시스템은 사용자들의 프로파일과 이들의 정보를 바탕으로 사용자가 선호할 만한 아이템을 추천한다. 추천시스템에서 널리 사용되고 있는 협력적 필터링 방식은 사용자들 사이의 선호도 평가치를 비교하여 유사 사용자를 선택하고, 아이템에 대한 유사 사용자의 선호도 평가치를 기반으로 하여 추천하고자 하는 아이템에 대한 사용자의 선호도를 예측하는 것이다. 하지만 사용자의 선호도가 적은 데이터로 인한 희소성 문제는 추천시스템의 성능을 저해하는 요인으로 작용하고 있다. 이러한 희소성의 문제는 선호도 평가 자료에 나타난 아이템들의 총수에 비하여 사용자가 선호한 아이템의 수가 아주 적기 때문에 발생하며, 새로운 사용자의 경우에는 아이템에 대한 선호도 평가치가 없어 유사 사용자를 선택할 수가 없어 나타나며 심한 경우에는 아이템을 전혀 추천할 수 없게 된다. 이리할 추천 시스템의 희소성문제를 해결차기 위한 방법은 희소성이 높은 데이터들에 대한 희소성을 감소시키는 것이다. 따라서 본 논문에서는 아이템에 대한 희소성을 조사하여 협력적 필터링에서 희소성 아이템이 MAE에 미치는 영향을 분석하였다. 그리고 희소성 문제를 완화하여 예측 정확도를 높이기 위한 방법으로 선호도가 적은 아이템에 대해 희소성을 최소화하는 연구와 이에 따라 희소성과 MAE의 값을 개선하는 방법을 제안한다.

  • PDF

Polar-coordinates Linear Interpolation for Map Contour Reconstruction at Summit Area (정상 영역의 등고선 재구성을 위한 극좌표계 선형보간)

  • Hwang Dong-Kuk;Jun Byung-Min;Park Cheon-Joo
    • The Journal of the Korea Contents Association
    • /
    • v.5 no.1
    • /
    • pp.127-134
    • /
    • 2005
  • To connect the gap on the contours at the summit area, we propose the linear interpolation in the polar coordinates. Tn the experiments of applying both existing algorithms and a proposed method to some graphic images, the proposed method generated curves that average MAE was 1.940 pixels. In particular, our method with MAE of 1.240 on real map image was superior than the others. Also by generating new curves with neighbors-resembled appearance, the contours were reconstructed seamlessly.

  • PDF

Effects of Shoulder Taping on Discomfort and Electromyographic Responses of the Neck While Texting on a Touchscreen Smartphone

  • Areeudomwong, Pattanasin;Oapdunsalam, Konnika;Havicha, Yupadee;Tantai, Sawit;Buttagat, Vitsarut
    • Safety and Health at Work
    • /
    • v.9 no.3
    • /
    • pp.319-325
    • /
    • 2018
  • Background: Prolonged neck flexion during smartphone use is known as a factor of neck pain and alteration of neck muscle activity. Studies on the effects of shoulder taping on neck discomfort and neck muscle responses while texting on a smartphone are still lacking. The aim of this study was to examine the effects of shoulder taping on neck discomfort using a numerical rating scale, and neck muscle activity and fatigue using a surface electromyography during a texting task on a touchscreen smartphone. Methods: Twenty-five healthy adolescents used the dominant hand to perform a 30-minute texting task using a touchscreen smartphone at two separate times under one of the following two conditions: taping across the upper trapezius muscle and no taping. Neck discomfort, normalized root mean square, and normalized median frequency slopes for upper trapezius, cervical erector spinae, and sternocleidomastoid muscles were recorded. Results: The results revealed that shoulder taping provided significantly lower neck discomfort than no taping (p < 0.001). However, shoulder taping did not significantly alter normalized root mean square and normalized median frequency slope values of all muscles when compared with no taping controls. Conclusion: Shoulder taping reduces neck discomfort but does not affect neck muscle activity and fatigue while texting on a touchscreen smartphone.

Predictive Model of Optimal Continuous Positive Airway Pressure for Obstructive Sleep Apnea Patients with Obesity by Using Machine Learning (비만 폐쇄수면무호흡 환자에서 기계학습을 통한 적정양압 예측모형)

  • Kim, Seung Soo;Yang, Kwang Ik
    • Journal of Sleep Medicine
    • /
    • v.15 no.2
    • /
    • pp.48-54
    • /
    • 2018
  • Objectives: The aim of this study was to develop a predicting model for the optimal continuous positive airway pressure (CPAP) for obstructive sleep apnea (OSA) patient with obesity by using a machine learning. Methods: We retrospectively investigated the medical records of 162 OSA patients who had obesity [body mass index (BMI) ≥ 25] and undertaken successful CPAP titration study. We divided the data to a training set (90%) and a test set (10%), randomly. We made a random forest model and a least absolute shrinkage and selection operator (lasso) regression model to predict the optimal pressure by using the training set, and then applied our models and previous reported equations to the test set. To compare the fitness of each models, we used a correlation coefficient (CC) and a mean absolute error (MAE). Results: The random forest model showed the best performance {CC 0.78 [95% confidence interval (CI) 0.43-0.93], MAE 1.20}. The lasso regression model also showed the improved result [CC 0.78 (95% CI 0.42-0.93), MAE 1.26] compared to the Hoffstein equation [CC 0.68 (95% CI 0.23-0.89), MAE 1.34] and the Choi's equation [CC 0.72 (95% CI 0.30-0.90), MAE 1.40]. Conclusions: Our random forest model and lasso model ($26.213+0.084{\times}BMI+0.004{\times}$apnea-hypopnea index+$0.004{\times}oxygen$ desaturation index-$0.215{\times}mean$ oxygen saturation) showed the improved performance compared to the previous reported equations. The further study for other subgroup or phenotype of OSA is required.

A Study on Predictive Modeling of I-131 Radioactivity Based on Machine Learning (머신러닝 기반 고용량 I-131의 용량 예측 모델에 관한 연구)

  • Yeon-Wook You;Chung-Wun Lee;Jung-Soo Kim
    • Journal of radiological science and technology
    • /
    • v.46 no.2
    • /
    • pp.131-139
    • /
    • 2023
  • High-dose I-131 used for the treatment of thyroid cancer causes localized exposure among radiology technologists handling it. There is a delay between the calibration date and when the dose of I-131 is administered to a patient. Therefore, it is necessary to directly measure the radioactivity of the administered dose using a dose calibrator. In this study, we attempted to apply machine learning modeling to measured external dose rates from shielded I-131 in order to predict their radioactivity. External dose rates were measured at 1 m, 0.3 m, and 0.1 m distances from a shielded container with the I-131, with a total of 868 sets of measurements taken. For the modeling process, we utilized the hold-out method to partition the data with a 7:3 ratio (609 for the training set:259 for the test set). For the machine learning algorithms, we chose linear regression, decision tree, random forest and XGBoost. To evaluate the models, we calculated root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) to evaluate accuracy and R2 to evaluate explanatory power. Evaluation results are as follows. Linear regression (RMSE 268.15, MSE 71901.87, MAE 231.68, R2 0.92), decision tree (RMSE 108.89, MSE 11856.92, MAE 19.24, R2 0.99), random forest (RMSE 8.89, MSE 79.10, MAE 6.55, R2 0.99), XGBoost (RMSE 10.21, MSE 104.22, MAE 7.68, R2 0.99). The random forest model achieved the highest predictive ability. Improving the model's performance in the future is expected to contribute to lowering exposure among radiology technologists.

A Study on the Yi Mae-Bang's Salpurichum Costume (이매방 살풀이춤[중요무형문화재 제 97호] 복식 연구)

  • Jeong, Ye-Hee
    • Journal of the Korean Society of Costume
    • /
    • v.63 no.7
    • /
    • pp.31-48
    • /
    • 2013
  • It goes without saying that Yi Mae-Bang, as the sole owner of two of the intangible cultural assets including No. 27 Seungmu in 1987 and No. 97 Salpuri Chum, is a top-notch Korean traditional dancer. Moreover, in regards to traditional clothing, he is also known as the only traditional dancer who directly performs on stage as well as analyzes traditional clothing in order to apply them into his own dance performances by designing and producing them to meet his artistic spirit. In order to examine how Yi Mae-Bang's unique and creative stage clothing was developed, and what kind of process it went through to possess its unique style, which draws the attentions of people with its harmony of beauty and dance, this research first examined the change of the composition through the yearly picture data. Before 1984, the composition of the Salpuri Chum clothes changed by putting on 'Jeogori' on the 'Mudong-Bok' without the 'Kweia' (sleeveless), and in 1999 'Mudong-Bok' became widened with the decoration of embroidered hem making it more attractively colorful. after 2000 it became more splendidly adorned by embroidering hem on widened Mudong-Bok and tucking 'Kweja' in the layers which created silhouette like a dress that is seemingly wider and luxuriant than a skirt. One of notable features of Yi Mae-Bang's Salpuri is that its cloth and cuff ribbons are lightly colored in different colors enclosing the tip part. As for the ribbons, it was also changed as time went by from direct-cutting of the cloth just like the A-line of Mudong-Bok to drawing a diagonal line less than 5cm above the ribbon and 8cm below the ribbon so that it takes the form of getting widened as it gets to the lower part, and its length was also elongated in proportion to that of the bottom of Mudong-Bok.