• Title/Summary/Keyword: Mean Absolute Difference

Search Result 203, Processing Time 0.027 seconds

Feature Extraction and Evaluation for Classification Models of Injurious Falls Based on Surface Electromyography

  • Lim, Kitaek;Choi, Woochol Joseph
    • 한국전문물리치료학회지
    • /
    • 제28권2호
    • /
    • pp.123-131
    • /
    • 2021
  • Background: Only 2% of falls in older adults result in serious injuries (i.e., hip fracture). Therefore, it is important to differentiate injurious versus non-injurious falls, which is critical to develop effective interventions for injury prevention. Objects: The purpose of this study was to a. extract the best features of surface electromyography (sEMG) for classification of injurious falls, and b. find a best model provided by data mining techniques using the extracted features. Methods: Twenty young adults self-initiated falls and landed sideways. Falling trials were consisted of three initial fall directions (forward, sideways, or backward) and three knee positions at the time of hip impact (the impacting-side knee contacted the other knee ("knee together") or the mat ("knee on mat"), or neither the other knee nor the mat was contacted by the impacting-side knee ("free knee"). Falls involved "backward initial fall direction" or "free knee" were defined as "injurious falls" as suggested from previous studies. Nine features were extracted from sEMG signals of four hip muscles during a fall, including integral of absolute value (IAV), Wilson amplitude (WAMP), zero crossing (ZC), number of turns (NT), mean of amplitude (MA), root mean square (RMS), average amplitude change (AAC), difference absolute standard deviation value (DASDV). The decision tree and support vector machine (SVM) were used to classify the injurious falls. Results: For the initial fall direction, accuracy of the best model (SVM with a DASDV) was 48%. For the knee position, accuracy of the best model (SVM with an AAC) was 49%. Furthermore, there was no model that has sensitivity and specificity of 80% or greater. Conclusion: Our results suggest that the classification model built upon the sEMG features of the four hip muscles are not effective to classify injurious falls. Future studies should consider other data mining techniques with different muscles.

GEMS 영상과 기계학습을 이용한 산불 연기 탐지 (Detection of Wildfire Smoke Plumes Using GEMS Images and Machine Learning)

  • 정예민;김서연;김승연;유정아;이동원;이양원
    • 대한원격탐사학회지
    • /
    • 제38권5_3호
    • /
    • pp.967-977
    • /
    • 2022
  • 산불의 발생과 강도는 기후 변화로 인하여 증가하고 있다. 산불 연기에 의한 배출가스 대기질과 온실 효과에 영향을 미치는 주요 원인 중 하나로 인식되고 있다. 산불 연기의 효과적인 탐지를 위해서는 위성 산출물과 기계학습의 활용이 필수적이다. 현재까지 산불 연기 탐지에 대한 연구는 구름 식별의 어려움 및 모호한 경계 기준 등으로 인한 어려움이 존재하였다. 본 연구는 우리나라 환경위성 센서인 Geostationary Environment Monitoring Spectrometer (GEMS)의 Level 1, Level 2 자료와 기계학습을 이용한 산불 연기 탐지를 목적으로 한다. 2022년 3월 강원도 산불을 사례로 선정하여 산불 연기 레이블 영상을 생성하고, 랜덤 포레스트 모델에 GEMS Level 1 및 Level 2 자료를 투입하여 연기 픽셀 분류 모델링을 수행하였다. 훈련된 모델에서 입력변수의 중요도는 Aerosol Optical Depth (AOD), 380 nm 및 340 nm의 복사휘도 차, Ultra-Violet Aerosol Index (UVAI), Visible Aerosol Index (VisAI), Single Scattering Albedo (SSA), 포름알데히드, 이산화질소, 380 nm 복사휘도, 340 nm 복사휘도의 순서로 나타났다. 또한 2,704개 픽셀에 대한 산불 연기 확률(0≤p≤1) 추정에서 Mean Bias Error (MBE)는 -0.002, Mean Absolute Error (MAE)는 0.026, Root Mean Square Error (RMSE)는 0.087, Correlation Coefficient (CC)는 0.981의 정확도를 보였다.

월경통 환자의 체열분포에 대한 연구 (소음인, 태음인을 대상으로) (Study on the Thermography of Dysmenorreic women)

  • 김미진;이인선;김종원
    • 대한한방체열의학회지
    • /
    • 제2권1호
    • /
    • pp.11-16
    • /
    • 2003
  • Purpose D.I.T.I. can be used to diagnose the dysmenorrhea and prove the Oriental Medical Theory and the Sasang Constitutional Medicine concerning Dysmenorrhea. According to the Sasang Constitutional Medicine, we chose 39 dysmenorrhea patients (Soeumin 26 Patients, Taeumin 13 Patients) and expremented D.I.T.I. to find difference of chilliness and fever in the upper part of body and the lower part of body. Methods We expremented 39 dysmenorrhea patients chosena expremental group from Apr 1. 2002 to May 30, 2002. We diagnosed the constitution by Q.S.C.C. and selected six acu-points CV-17, CV-12, CV-4, G-21, B-15 and B-23. To appraise difference of temperature according to constitution we compared skin temperature of front to back. Result Mean Absolute Value of ${\Delta}T$ in body (front and back) shows significant difference. Totally the temperature of front is higher than the temperature of back. the temperature of Soeumin is higher than the temperature of Taeumin in whole. Conciusion Especially the upper abdomen area(CV-17) shows high temperature in 39 dysmenorrhea patients, the lower abdomen area (CV-4) of Soeumin shows lower temperature relatively.

  • PDF

Comparison of three-dimensional digital technique with two-dimensional replica method for measuring marginal and internal fit of full coverage restorations

  • Hasanzade, Mahya;Koulivand, Soudabeh;Moslemian, Naeime;Alikhasi, Marzieh
    • The Journal of Advanced Prosthodontics
    • /
    • 제12권3호
    • /
    • pp.173-180
    • /
    • 2020
  • PURPOSE. This study compared digital (reference point matching) and replica methods for measuring marginal and internal fit of full coverage restorations. MATERIALS AND METHODS. A maxillary left first molar typodent was fixed on to an aluminum base and prepared to receive all-ceramic full coverage restoration. The model was scanned with an intraoral scanner (CEREC Omnicam, Sirona, York, PA, USA). Twelve crowns were fabricated from lithium disilicate blocks (IPS emax CAD, Ivoclar Vivadent) and then crystalized. Marginal and internal fit of each restoration was measured by two examiners using replica and a new digital three-dimensional technique. Reliability between the two methods and two examiners was assessed by correlation and Cronbach's Alpha coefficient (P<.05). A Bland-Altman assessment for agreement was used to compare the two methods. RESULTS. Bland-Altman assessment showed that the mean of difference for marginal, absolute marginal, and axial gap was respectively -1.04 ㎛, -41.9 ㎛, and -29.53 ㎛ with limit of agreement (LOA) between -37.26 to 35.18 ㎛ for marginal, -105.85 to 22.05 ㎛ for absolute marginal and -80.52 to 22.02 ㎛ for axial gap. Positive correlation for repeatability (P<.05) in determining marginal and internal gaps by the two examiners in both techniques was revealed. Reliability of both techniques in all sites of measurements was at least good (0.8 ≤ α < 0.9). CONCLUSION. Both measuring techniques appeared highly reliable for evaluating fit of fixed dental restorations, while reference point matching provided higher values in axial and absolute marginal gap assessment.

The combined effect of dismantling for steam sterilization and aging on the accuracy of spring-style mechanical torque devices

  • Mahshid, Minoo;Saboury, Aboulfazl;Sadr, Seyed Jalil;Fayyaz, Ali;Kadkhodazadeh, Mahdi
    • Journal of Periodontal and Implant Science
    • /
    • 제43권5호
    • /
    • pp.221-226
    • /
    • 2013
  • Purpose: This study aimed to assess the combined effect of dismantling before sterilization and aging on the accuracy (${\pm}10%$ of the target torque) of spring-style mechanical torque devices (S-S MTDs). Methods: Twenty new S-SMTDs from two different manufacturers (Nobel Biocare and Straumann: 10 of each type) were selected and divided into two groups, namely, case (group A) and control (group B). For sterilization, 100 cycles of autoclaving were performed in 100 sequences. In each sequence, 10 repetitions of peak torque values were registered for aging. To measure and assess the output of each device, a Tohnichi torque gauge was used (P<0.05). Results: Before steam sterilization, all of the tested devices stayed within 10% of their target values. After 100 cycles of steam sterilization and aging with or without dismantling of the devices, the Nobel Biocare devices stayed within 10% of their target torque. In the Straumann devices, despite the significant difference between the peak torque and target torque values, the absolute error values stayed within 10% of their target torque. Conclusion: Within the limitations of this study, there was no significant difference between the mean and absolute value of error between Nobel Biocare and Straumann S-S MTDs.

Use of an anatomical mid-sagittal plane for 3-dimensional cephalometry: A preliminary study

  • Vernucci, Roberto Antonio;Aghazada, Huseynagha;Gardini, Kelly;Fegatelli, Danilo Alunni;Barbato, Ersilia;Galluccio, Gabriella;Silvestri, Alessandro
    • Imaging Science in Dentistry
    • /
    • 제49권2호
    • /
    • pp.159-169
    • /
    • 2019
  • Purpose: Cone-beam computed tomography (CBCT) is widely used for 3-dimensional assessments of cranio-maxillo-facial relationships, especially in patients undergoing orthognathic surgery. We have introduced, for reference in CBCT cephalometry, an anatomical mid-sagittal plane (MSP) identified by the nasion, the midpoint between the posterior clinoid processes of the sella turcica, and the basion. The MSP is an updated version of the median plane previously used at our institution for 2D posterior-anterior cephalometry. This study was conducted to test the accuracy of the CBCT measures compared to those obtained using standard posterior-anterior cephalometry. Materials and Methods: Two operators measured the inter-zygomatic distance on 15 CBCT scans using the MSP as a reference plane, and the CBCT measurements were compared with measurements made on patients' posterior-anterior cephalograms. The statistical analysis evaluated the absolute and percentage differences between the 3D and 2D measurements. Results: As demonstrated by the absolute mean difference (roughly 1 mm) and the percentage difference (less than 3%), the MSP showed good accuracy on CBCT compared to the 2D plane, especially for measurements of the left side. However, the CBCT measurements showed a high standard deviation, indicating major variability and low precision. Conclusion: The anatomical MSP can be used as a reliable reference plane for transverse measurements in 3D cephalometry in cases of symmetrical or asymmetrical malocclusion. In patients who suffer from distortions of the skull base, the identification of landmarks might be difficult and the MSP could be unreliable. Becoming familiar with the relevant software could reduce errors and improve reliability.

2차원 비트율-왜곡 모델을 이용한 매크로블록 단위 비트율 제어 (A Macroblock-Layer Rate Control for H.264/AVC Using Quadratic Rate-Distortion Model)

  • 손남례;이귀상;임창훈
    • 한국통신학회논문지
    • /
    • 제32권9C호
    • /
    • pp.849-860
    • /
    • 2007
  • H.264/AVC부호화 방식이 압축성능이 뛰어나더라도 가변길이부호화방식을 따르기 때문에 동영상을 부호화할 때 발생하는 데이터량은 시간의 흐름에 따라 큰 폭으로 변할 수 밖에 없다. 따라서 부호화된 비디오 비트스트림을 고정된 저대역폭의 네트워크를 통해 실시간으로 전송하고자 할 경우에는 부호기로부터 출력되는 비트율을 반드시 제어할 필요가 있다. 기존의 비트율 제어 알고리즘은 각 프레임당 목표 비트를 결정하는 2차원 비트율-왜곡 모델을 채택하고 있다. 본 논문에서는 전송율이 고정된 비디오 채널에서 H.264/AVC 부호화 기법으로 압축된 동영상을 전송할 때 움직임이 많은 영상의 비트율을 보다 효율적으로 제어하는 알고리즘을 제시한다. 제안된 비트율 제어 알고리즘은 2차원 비트율-왜곡 모델식을 이용하여 이전 프레임의 매크로블록과 현재 프레임의 매크로블록간에 움직임 변화량을 예측함으로써 매크로블록 단위로 비트율을 제어한다. 움직임이 많고 장면전환이 빈번한 동영상 샘플을 대상으로 비교 실험한 결과, 비트율 제어의 경우 기존의 알고리즘은 채널전송 환경에 부적합하게 비트율을 초과하지만, 새롭게 제안한 알고리즘은 채널전송에 적합하게 부호화됨을 확인할 수 있었다. 화질 또한 제안한 방법이 기존의 비트율 제어 방법보다 평균적으로 $0.4{\sim}0.9\;dB$로 높게 나타남을 확인하였다.

한국 COVID-19 확진자 수에 대한 시계열 분석: HAR-TP-T 모형 접근법 (Time series analysis for Korean COVID-19 confirmed cases: HAR-TP-T model approach)

  • 유성민;황은주
    • 응용통계연구
    • /
    • 제34권2호
    • /
    • pp.239-254
    • /
    • 2021
  • 이 논문에서는, 2개의 혼합된 t-분포(TP-T)의 오차과정을 따르는 이질적 자기회귀 (HAR) 모형을 이용하여, 한국 코로나 (COVID-19) 확진자 수 데이터에 대한 시계열 분석, 즉 추정과 예측에 대하여 연구한다. HAR-TP-T 시계열 모형을 고려하여 HAR 모형의 계수 뿐 아니라 TP-T 오차과정의 모수를 추정하고자 단계별 추정법을 제안한다. 본 연구에서 제안하고 있는 단계별 추정법은, HAR 계수 추정을 위해서는 통상적 최소제곱추정법을 채택하고, TP-T 모수 추정을 위해서는 최대우도추정법을 이용한다. 단계별 추정법에 대한 모의실험을 수행하여, 성능이 우수함을 입증한다. 한국 코로나 확진자 수에 대한 실증적 데이터 분석에서, HAR 모형에서의 차수 p = 2, 3, 4에 대해, 모형의 평균제곱오차가 최소가 되도록 하는 최적화 시간간격(optimal lag)을 포함하여, 여러가지 시간간격을 고려한 HAR-TP-T 모형의 모수 추정값을 계산한다. 제안된 단계별 추정방법과 기존의 MLE만의 방법을, 추정 결과를 제시함으로 함께 비교한다. 본 연구에서 제안하고 있는 추정은 두 가지의 오차 측면, 즉 HAR 모형의 평균제곱오차와 잔차분포에 대한 밀도함수 추정의 평균제곱오차, 두 측면에서 모두 우수함을 입증하였다. 나아가, 추정 결과를 활용한 코로나 확진자 수 예측을 수행하였고, 예측정확도의 한 측도로서 mean absolute percentage error (MAPE)를 계산하여 0.0953%의 매우 작은 오차값을 얻었다. 본 연구에서 선택한 최적화 시간간격을 고려한 HAR-TP-T 시계열 모형 및 단계별 추정 방법은, 정확한 한국 코로나 확진자 수 예측 성능을 제공한다고 할 수 있다.

수중 환경에서 상호상관을 이용한 시간차이 추정 (Estimation of Time Difference Using Cross-Correlation in Underwater Environment)

  • 이영필;문용선;고낙용;최현택;이정구;배영철
    • 한국항행학회논문지
    • /
    • 제20권2호
    • /
    • pp.155-160
    • /
    • 2016
  • 최근에 수중 음향통신에 대한 연구가 많은 연구자들에 의해 연구되어왔다. 수중 환경 UWAC를 사용하기 위해서는 두 신호들 사이의 시간차이를 추정하는 것이 필요하다. 일반적으로 두 신호 시아의 시간차이를 추정하는 기법으로는 배경 영역이 없는 시간을 추정하여 시간 차이를 추정하는 기법, 시간을 추정하여 두 신호 사이의 상호 상관을 추정하는 기법, 시간 차이 추정을 위한 위상지연을 추정하는 기법이 주로 사용된다. 본 논문에서는 UWAC에 적용하기 위하여 시간 지연 추정에 의한 두 신호 사이의 상호상관을 계산하고 이 상호 상관을 이용한 도착 시간의 추정 결과를 0.003055 초가 됨을 보인다.

Progress Report of the Hubble Constant Determination based on the TRGB Method

  • Jang, In Sung;Lee, Myung Gyoon
    • 천문학회보
    • /
    • 제40권1호
    • /
    • pp.46.2-46.2
    • /
    • 2015
  • Modern methods in determining the value of the Hubble constant are divided into two main ways: the classical distance ladder method and the inverse distance ladder method. The classical distance ladder method is based on Cepheid calibrated Type Ia supernovae (SNe Ia), which are known as powerful distance indicator. The inverse distance ladder method uses cosmic microwave background radiation, which emitted from the high-z universe, and the cosmological model. Recent estimations of the Hubble constant based on these two methods show a $2{\sim}3{\sigma}$ difference, which called the "Hubble tension". It is currently an issue in the modern cosmology. We have been working on the luminosity calibration of SNe Ia based on the Tip of the Red Giant Branch (TRGB), which is a precise population I distance indicator. We present the TRGB distance estimates of 5 SNe Ia host galaxies with the archival Hubble Space Telescope image data. We derive the mean absolute maximum magnitude of 5 SNe Ia and the value of the Hubble constant. Cosmological implications of our estimate will be discussed.

  • PDF