• 제목/요약/키워드: Accuracy Rate

검색결과 3,386건 처리시간 0.029초

초음파를 이용한 다양한 고체추진제의 고압범위까지의 연소속도 측정 정밀도 분석 (Analysis of measurement Accuracy up to High Pressure for Various Solid Propellants using Ultrasound)

  • 오현택;송성진;김학준;고선필;김인철;유지창;정정용
    • 한국추진공학회:학술대회논문집
    • /
    • 한국추진공학회 2008년도 제31회 추계학술대회논문집
    • /
    • pp.265-268
    • /
    • 2008
  • 본 연구에서는 서로 다른 연소속도 범위를 갖는 다양한 고체추진제의 연소속도를 고압($\sim$5,000 psia)까지 측정하였고, 측정된 연소속도의 자체적인 편차를 추진제 종류별, 압력별로 분석하여 초음파법의 측정 정밀도를 평가하였다. 또한 스트랜드 버너법을 이용한 연소속도 측정값과 상호 비교하여 두 측정 기법의 특성을 비교해보았다.

  • PDF

Data Correction For Enhancing Classification Accuracy By Unknown Deep Neural Network Classifiers

  • Kwon, Hyun;Yoon, Hyunsoo;Choi, Daeseon
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제15권9호
    • /
    • pp.3243-3257
    • /
    • 2021
  • Deep neural networks provide excellent performance in pattern recognition, audio classification, and image recognition. It is important that they accurately recognize input data, particularly when they are used in autonomous vehicles or for medical services. In this study, we propose a data correction method for increasing the accuracy of an unknown classifier by modifying the input data without changing the classifier. This method modifies the input data slightly so that the unknown classifier will correctly recognize the input data. It is an ensemble method that has the characteristic of transferability to an unknown classifier by generating corrected data that are correctly recognized by several classifiers that are known in advance. We tested our method using MNIST and CIFAR-10 as experimental data. The experimental results exhibit that the accuracy of the unknown classifier is a 100% correct recognition rate owing to the data correction generated by the proposed method, which minimizes data distortion to maintain the data's recognizability by humans.

Evaluating Corrective Feedback Generated by an AI-Powered Online Grammar Checker

  • Moon, Dosik
    • International Journal of Internet, Broadcasting and Communication
    • /
    • 제13권4호
    • /
    • pp.22-29
    • /
    • 2021
  • This study evaluates the accuracy of corrective feedback from Grammarly, an online grammar checker, on essays written by cyber university learners in terms of detected errors, suggested replacement forms, and false alarms.The results indicate that Grammarly has a high overall error detection rate of over 65%, being particularly strong at catching errors related to articles and prepositions. In addition, on the detected errors, Grammarly mostly provide accurate replacement forms and very rarely make false alarms. These findings suggest that Grammarly has high potential as a useful educational tool to complement the drawbacks of teacher feedback and to help learnersimprove grammatical accuracy in their written work. However, it is still premature to conclude that Grammarly can completely replace teacher feedback because it has the possibility (approximately 35%) of failing to detect errors and the limitationsin detecting errors in certain categories. Since the feedback from Grammarly is not entirely reliable, caution should be taken for successful integration of Grammarly in English writing classes. Teachers should make judicious decisions on when and how to use Grammarly, based on a keen awareness of Grammarly's strengths and limitations.

SVM과 인공 신경망을 이용한 침입탐지 효과 비교 연구 (A Comparative Study on the Performance of SVM and an Artificial Neural Network in Intrusion Detection)

  • 조성래;성행남;안병혁
    • 한국산학기술학회논문지
    • /
    • 제17권2호
    • /
    • pp.703-711
    • /
    • 2016
  • 침입탐지시스템은 네트워크 데이터 분석을 통해 네트워크 침입을 탐지하는 역할을 수행하고 침입탐지를 위해 높은 수치의 정확도와 탐지율, 그리고 낮은 수치의 오경보율이 요구된다. 또한 네트워크 데이터 분석을 위해서는 전문가 시스템, 데이터 마이닝, 상태전이 분석(state transition analysis) 등 다양한 기법이 이용된다. 본 연구의 목적은 데이터 마이닝을 이용한 네트워크 침입탐지기법인 두 기법의 탐지효과를 비교하는데 있다. 첫번째 기법은 기계학습 알고리즘인 SVM이고 두번째 알고리즘은 인공 신경망 모형 중의 하나인 FANN이다. 두 기법의 탐지효과를 비교하기 위해 침입 탐지에 많이 쓰이는 KDD Cup 99 훈련 및 테스트 데이터를 이용하여 탐지의 정확도, 탐지율, 오경보율을 계산하고 비교하였다. 정상적인 데이터를 침입으로 간주하는 오경보율의 경우 SVM보다 FANN이 약간 많은 오경보율을 보이나, 탐지의 정확도 및 침입을 찾아내는 탐지율에서 FANN은 SVM보다 월등한 탐지효과를 보여준다. 정상적인 데이터를 침입으로 간주했을 때의 위험보다는 실제 침입을 정상적인 데이터로 인식할 때의 위험도가 훨씬 큰 것을 감안하면 FANN이 SVM보다 침입탐지에 훨씬 효과적임을 보이고 있다.

인상채득방법이 임플란트 주모형의 정확성에 미치는 영향 (EFFECT OF IMPRESSION TECHNIQUE ON THE ACCURACY OF MASTER CAST FOR IMPLANT PROSTHESIS)

  • 김영오;양홍서
    • 대한치과보철학회지
    • /
    • 제42권2호
    • /
    • pp.238-247
    • /
    • 2004
  • Statement of problem: Major objective in making on implant-supported prosthesis is the production of superstructure that exhibits a passive fit when connected to multiple abutments. One requirement to ensure passive fit is to make an accurate impression. Purpose : The purpose of this study was to compare the accuracy of master cast fabricated by using different impression methods at the different impression levels. Material and method: The master model used in this study was resin block having low implant analogs. Impression method studied were 1) direct method on fxiture level (Group FIX-D), 2) indirect method on fixture level(Group FIX-I), 3) modified indirect method on fixture level(Group FIX-M), 4) direct method on abutment level(Group AB-D) and 5) indirect method on abutment level(Group AB-I). Each of the five groups took 10 impressions. Fifty impressions were made for master cast by using Impregum $F^{(R)}$ impression material loaded on individual tray. Three dimensional measuring microscope was used to measure the inter-implant distance. Error rate of each inter-implant distance were calculated and evaluated. Results : The results were as follows. 1. Group FIX exhibited higher accuracy than group AB. 2. In group FIX, modified indirect method showed the highest accuracy, while indirect method showed the lowest accuracy. In group Ab, indirect method showed the higher accuracy than direct method. 3. Group FIX showed larger horizontal error than group AB. But, group AB showed the larger vertical error than group FIX. 4. Group Fix-M showed smallest vertical and horizontal error. Conclusion: An impression method have more effect on accuracy of master model than an impression level. A modified indirect method showed smallest vertical and horizontal error.

인상채득법이 임플랜트 주모형의 정확성에 미치는 영향 (EFFECT OF IMPRESS10N TECHNIQUE ON THE ACCURACY OF MASTER CAST FOR IMPLANT PROSTHESIS)

  • 김영오;양홍서;방몽숙;박상원;박하옥;이재봉
    • 대한치과보철학회지
    • /
    • 제44권1호
    • /
    • pp.63-72
    • /
    • 2006
  • Purpose: The purpose of this study was to compare the accuracy of master cast fabricated by using different impression methods at the different impression levels. Material and Method: The master model used in this study was resin block having low implant analogs. Impression method studied were 1) direct method on future level (Group FIX-D), 2) Indirect method on fixture level(Group FIX-I), 3) Modified indirect method on fixture level(Group FD(-M), 4) Direct method on abutment level(Group AB-D) and 5) Indirect method on abutment level(Group AB-I). Each of the five groups took 10 impressions. Fifty impressions were made for master cast by using Impregum $F^(R)$ impression material loaded on individual tray. Three dimensional measuring microscope was used to measure the inter-implant distance. Error rate of each inter-implant distance were calculated and evaluated. Results: The results were as follows. 1. Group FIX exhibited higher accuracy than group AB. 2 In group FIX, modified indirect method showed the highest accuracy, while indirect method showed the lowest accuracy. In group Ab, indirect method showed the higher accuracy than direct method. 3. Group FIX showed larger horizontal error than group AB. But, group AB showed the larger vertical error than group FIX. 4. Group Fix-M showed smallest vertical and horizontal error.

인삼, 산양삼 및 산삼의 부위별 Proteome분석 (Proteome Analysis of various types of Panax ginseng using 2-Dimensional Electrophoresis)

  • 위종성;박희수;권기록
    • 대한약침학회지
    • /
    • 제10권2호통권23호
    • /
    • pp.5-18
    • /
    • 2007
  • Objectives : The purpose of this study was to obtain an objective differentiating method for various types of Panax ginseng: ginseng, cultivated wild ginseng, and natural wild ginseng which are distinctive according to their growing environment. Methods : The roots, stem, and leaves of several types of ginseng were collected and comparative analysis of proteome was conducted on each part using 2-DE and the results examined. Results : 1. Proteome images of the respective parts within the samples showed spot-matching in most cases, suggesting that they are genetically identical panax ginseng. 2. Similar distribution patters were seen within the different parts of the Panax ginseng: ginseng, Chinese cultivated wild ginseng, and the 5 and 10 years old Korean cultivated wild ginseng. 3. For a quantitative evaluation of spots showing differences among the samples, 102 spots from the roots, 109 spots from the stems, and 132 spots form the leaves which showed a difference were selected and centrifugal identification was conducted. 4. Peculiar proteins from each respective part of the Panax ginseng were identified and the top 20 spots with significant differences were selected and analyzed in order to provide a differentiation rate among the samples. The accuracy rate ranged between 23.0-38.8%. 5. Differentiation rate of the top 10 spots with significant differences showed a 50-85% accuracy rate, and the differentiation rate was especially high for the stem of Chinese cultivated wild ginseng and Korean cultivated wild ginseng.

무인 원격 방사선 검출 모듈 개발 (Development of Unmanned Remote Radiation Detection Module)

  • 장보석
    • 한국방사선학회논문지
    • /
    • 제15권6호
    • /
    • pp.795-801
    • /
    • 2021
  • 원전 해체 작업장의 요구에 따라 드론 기반 무인 원격 방사선 검출 모듈을 개발하였다. 사람이 접근해서 방사선을 측정할 수 없는 원자력 발전소 격납용기 내부 상공 및 외부로 누설되는 방사선 측정을 위한 목적으로 저준위에 민감한 GM-tube를 사용하여 제작하였다. 드론 기반 방사선 검출 모듈의 무게는 200g 미만으로 원자력 발전소 격납용기 내부의 상공과 외부 공중에서도 운용이 가능하다. 설계된 장비의 성능 확인을 위해 국제 기준 (IEC60864)을 참고하여 성능평가 실험을 시행하였다. 현장의 요구에 맞게 설계된 방사선 검출 모듈의 안정성은 측정 정확도를 평가하기 위한 변동률 실험에서 반복 측정에 의한 통계적 변동률은 ±4.6%. 선량률 의존성을 평가하기 위한 선형성 실험에서 정확도 ± 7.3%, 전체 선형도는 ± 3.5%이며 성능평가를 위한 국제기준을 만족하였다. 본 연구에서 개발한 무인 원격 방사선 검출 모듈은 원전 해체 작업장 맞춤형 장비로, 방사선 분진이 많은 현장에서 정확한 공간선량률의 측정과 방사선 작업장 안전관리에 도움을 줄 수 있을 것으로 확신한다.

Clinical expression of programmed maxillary buccal expansion and buccolingual crown inclination with Invisalign EX30 and SmartTrack aligners and the effect of 1-week vs. 2-week aligner change regimes: A retrospective cohort study

  • Joseph O'Connor;Tony Weir;Elissa Freer;Brett Kerr
    • 대한치과교정학회지
    • /
    • 제54권3호
    • /
    • pp.142-152
    • /
    • 2024
  • Objective: This retrospective cohort study aimed to assess and compare the accuracy of 3 different Invisalign® treatment regimens in terms of variations of aligner change frequency and type of aligner material in achieving maxillary dental buccal expansion. Methods: Altogether, 120 adult patients whose treatment involved maxillary dental expansion with Invisalign® were included. The patients were divided into 3 groups, with each group comprising 40 patients as follows: SmartTrack® 1-week changes (ST1), SmartTrack® 2-week changes (ST2), and EX30® 2-week changes (EX2). The groups were assessed by comparing actual changes achieved with those prescribed by ClinCheck®. The rates of clinically significant inaccuracies (CSI) observed for buccal expansion (≥ 0.5 mm) and buccolingual inclination (≥ 2°) during expansion were then determined. Results: In terms of expansion, the ST1 group demonstrated the highest CSI rate at all tooth levels, whereas the ST2 group had the lowest rate of CSI and the lowest mean inaccuracy for each tooth level. In terms of buccolingual inclination, the ST1 group had the highest CSI rate across all tooth levels, whereas the EX2 group had the lowest CSI rate at all tooth levels except for the canine level where the ST2 group had the lowest CSI rate. A tendency toward overexpression of buccal crown inclination, and underexpression of buccal expansion was observed at all tooth levels. Conclusions: Two-week aligner change regimens offer improved accuracy compared with 1-week aligner changes. SmartTrack® 2-week changes were the most accurate for buccal expansion, whereas EX30® 2-week changes were the most accurate for buccolingual inclination.

A Study on Measuring the Speaking Rate of Speaking Signal by Using Line Spectrum Pair Coefficients

  • Jang, Kyung-A;Bae, Myung-Jin
    • The Journal of the Acoustical Society of Korea
    • /
    • 제20권3E호
    • /
    • pp.18-24
    • /
    • 2001
  • Speaking rate represents how many phonemes in speech signal have in limited time. It is various and changeable depending on the speakers and the characters of each phoneme. The preprocessing to remove the effect of variety of speaking rate is necessary before recognizing the speech in the present speech recognition systems. So if it is possible to estimate the speaking rate in advance, the performance of speech recognition can be higher. However, the conventional speech vocoder decides the transmission rate for analyzing the fixed period no regardless of the variety rate of phoneme but if the speaking rate can be estimated in advance, it is very important information of speech to use in speech coding part as well. It increases the quality of sound in vocoder as well as applies the variable transmission rate. In this paper, we propose the method for presenting the speaking rate as parameter in speech vocoder. To estimate the speaking rate, the variety of phoneme is estimated and the Line Spectrum Pairs is used to estimate it. As a result of comparing the speaking rate performance with the proposed algorithm and passivity method worked by eye, error between two methods is 5.38% about fast utterance and 1.78% about slow utterance and the accuracy between two methods is 98% about slow utterance and 94% about fast utterances in 30 dB SNR and 10 dB SNR respectively.

  • PDF