• Title/Summary/Keyword: 상태 분류

Search Result 2,299, Processing Time 0.03 seconds

A Study on The Improvement of Emotion Recognition by Gender Discrimination (성별 구분을 통한 음성 감성인식 성능 향상에 대한 연구)

  • Cho, Youn-Ho;Park, Kyu-Sik
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.45 no.4
    • /
    • pp.107-114
    • /
    • 2008
  • In this paper, we constructed a speech emotion recognition system that classifies four emotions - neutral, happy, sad, and anger from speech based on male/female gender discrimination. At first, the proposed system distinguish between male and female from a queried speech, then the system performance can be improved by using separate optimized feature vectors for each gender for the emotion classification. As a emotion feature vector, this paper adopts ZCPA(Zero Crossings with Peak Amplitudes) which is well known for its noise-robustic characteristic from the speech recognition area and the features are optimized using SFS method. For a pattern classification of emotion, k-NN and SVM classifiers are compared experimentally. From the computer simulation results, the proposed system was proven to be highly efficient for speech emotion classification about 85.3% regarding four emotion states. This might promise the use the proposed system in various applications such as call-center, humanoid robots, ubiquitous, and etc.

Suggestion of Regression Equations for Estimating RMR Factor Rating by Geological Condition (지질 조건을 고려한 RMR 인자값 추정을 위한 선형회귀식 제안)

  • Kim, Kwang-Yeom;Yim, Sung-Bin;Kim, Sung-Kwon;Kim, Chang-Yong;Seo, Yong-Seok
    • The Journal of Engineering Geology
    • /
    • v.17 no.4
    • /
    • pp.555-566
    • /
    • 2007
  • In general, RMR classification system is used for the support design of a tunnel. Face mapping during excavation and RMR-based rock classifications are conducted in order to provide information for complementary changes to preliminary survey plans and for continuous geological estimations in direction of tunnel route. Although they are ever so important, there are not enough time for survey in general and sometimes even face mapping is not available. Linear regression analysis for the estimation of mediating RQD and condition of discontinuities, which require longer time and more detailed observation in RMR, was performed and optimum regression equations are suggest as the result. The geological data collected from tunnels were analyzed in accordance with three rock types as sedimentary rock, phyllite and granite to see geological effects, generally not been considered in previous researches. Parameters for the regression analysis were set another RMR factor.

Combination and evaluation to multiplex-biomarkers for check of ovarian cancer (난소암 조기진단을 위한 다중 바이오마커 선택 알고리즘 성능 비교)

  • Choi, Kwang-Won;Kim, Seung-Il;Cho, Sang-Yeun;Song, Hae-Jung;Kim, Jong-Dae;Kim, Yu-Seop;Park, Chan-Young;Kim, Young-Mog;Park, Hyung-Ki;Lee, Eun-Young;Lee, Myung-Sun
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2011.06c
    • /
    • pp.176-179
    • /
    • 2011
  • 본 연구에서는 T-Test와 Genetic Algorithm을 사용해 Luminex 사용 환경에서 난소암을 진단할 수 있는 바이오마커의 조합을 찾고 Cancer와 Normal간의 분류 성능을 평가해 보았다. 바이오마커는 혈액, 체액 내의 특정 질환 여부나 상태를 나타내는 단백질, DNA들의 지표 물질이다. 정상인과는 다른 분포를 가진 성분이 환자의 혈액이나 체액에서 발견되면 이를 토대로 질병유무와 상태를 판단할 수 있다. 난소암을 진단할 수 있는 바이오마커 조합을 찾기 위해 T-Test와 Genetic Algorithm를 사용하여 분류성능이 좋은 바이오마커 조합을 각각 선별해 보았고, 선별된 각각의 마커조합을 선형분류기(LDA)를 사용해 평균 민감도, 특이도, 정확도를 비교해 보았다. 실험데이터는 두 곳의 병원에서 제공받은 총 58명(Cancer 27명, Normal 31명)의 혈청에서 21 종류의 바이오마커 데이터를 Luminex-PRA를 통해 얻었다. 본 연구에서는 T-Test로 만들어진 마커조합이 Genetic algorithm으로 만들어진 마커조합 보다 더 좋은 민감도, 특이도, 분류정확도를 보여주었다.

A Design of the Finite State Machine to Control User's Gaze on a Screen (화면 응시 제어를 위한 유한 상태 기계 설계)

  • Moon, Bong-Hee
    • Journal of the Korea Society of Computer and Information
    • /
    • v.16 no.5
    • /
    • pp.127-134
    • /
    • 2011
  • A finite state machine was designed to control user's gaze on the screen when the user is monitoring the. It consists of a set of situations where pupils are gazed and a set of states which decide the gaze on a screen or sleeping. The states were especially classified into main states, pre-states and potential states. The machine uses the situation history, which decide current state using continuous previous situation and current situation, and improves the accuracy to control the gaze on a screen. We implemented the machine with the data which were get using a pupil detection method, and tested the verification of the system with monitoring operations. The experimentation using the method which get date from real images shows advantage of decision whether it is temporary gaze or long-term gaze.

Comparison and Analysis of Subject Classification for Domestic Research Data (국내 학술논문 주제 분류 알고리즘 비교 및 분석)

  • Choi, Wonjun;Sul, Jaewook;Jeong, Heeseok;Yoon, Hwamook
    • The Journal of the Korea Contents Association
    • /
    • v.18 no.8
    • /
    • pp.178-186
    • /
    • 2018
  • Subject classification of thesis units is essential to serve scholarly information deliverables. However, to date, there is a journal-based topic classification, and there are not many article-level subject classification services. In the case of academic papers among domestic works, subject classification can be a more important information because it can cover a larger area of service and can provide service by setting a range. However, the problem of classifying themes by field requires the hands of experts in various fields, and various methods of verification are needed to increase accuracy. In this paper, we try to classify topics using the unsupervised learning algorithm to find the correct answer in the unknown state and compare the results of the subject classification algorithms using the coherence and perplexity. The unsupervised learning algorithms are a well-known Hierarchical Dirichlet Process (HDP), Latent Dirichlet Allocation (LDA) and Latent Semantic Indexing (LSI) algorithm.

Standard Classification System of Marine Research Facility and Equipment for an Integrated Management (통합관리를 위한 해양연구시설·장비 표준분류체계)

  • RHO, TAEKEUN
    • The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
    • /
    • v.25 no.4
    • /
    • pp.132-159
    • /
    • 2020
  • As multidisciplinary marine research is actively conducted, various types of marine research facilities and equipment are purchased every year. However, among marine research facilities and equipment, it is difficult to classify and manage various types of field observation equipment used for environmental data collection and sample collection under the current national research facility and equipment standard classification system. In the case of Korea Institute of Ocean Science and Technology, about 30% of research facilities and equipment are unclassified and not properly managed. In this study, marine research facilities and equipment are classified into 7 middle and 36 sub-classes according to their characteristics. It is proposed to add a large classification group called 'Environmental Observation/Analysis Equipment', to the national research facility equipment standard classification system. In addition, it is proposed to classify the equipment operated in the laboratory among marine research facilities and equipment according to the existing national research facility equipment standard classification system. Through this, it is expected that all of Korea's marine-related research facilities and equipment can be systematically classified and managed effectively.

Applying of SOM for Automatic Recognition of Tension and Relaxation (긴장과 이완상태의 자동인식을 위한 SOM의 적용)

  • Jeong, Chan-Soon;Ham, Jun-Seok;Ko, Il-Ju;Jang, Dae-Sik
    • Journal of the Korea Society of Computer and Information
    • /
    • v.15 no.2
    • /
    • pp.65-74
    • /
    • 2010
  • We propose a system that automatically recognizes the tense or relaxed condition of scrolling-shooting game subject that plays. Existing study compares the changed values of source of stimulation to the player by suggesting the source, and thus involves limitation in automatic classification. This study applies SOM of unsupervised learning for automatic classification and recognition of player's condition change. Application of SOM for automatic recognition of tense and relaxed condition is composed of two steps. First, ECG measurement and analysis, is to extract characteristic vector through HRV analysis by measuring ECG after having the player play the game. Secondly, SOM learning and recognition, is to classify and recognize the tense and relaxed conditions of player through SOM learning of the input vectors of heart beat signals that the characteristic extracted. Experiment results are divided into three groups. The first is HRV frequency change and the second the SOM learning results of heart beat signal. The third is the analysis of match rate to identify SOM learning performance. As a result of matching the LF/HF ratio of HRV frequency analysis to the distance of winner neuron of SOM based on 1.5, a match rate of 72% performance in average was shown.

Removable prosthetic rehabilitation in patient with maxillofacial defects caused by gunshot: A case report (총상으로 인한 악안면 결손을 가진 환자에 대한 가철성 보철물 수복증례)

  • Lee, Donggyu;Kang, Jeongkyung
    • The Journal of Korean Academy of Prosthodontics
    • /
    • v.55 no.2
    • /
    • pp.198-204
    • /
    • 2017
  • Maxillofacial defect comes from congenital defect, trauma and surgical resection. Patients with intraoral defect are commonly related to maxillary defect and they need prosthetic rehabilitation. Functional reconstruction of partially edentulous mandible has many limitations. However, if both condyles are intact, maxillofacial prosthesis using partial denture give competent results. In this case, a patient of 58 year-old male has a defect on palate and left mandibular posterior teeth from gunshot. The maxillary defect of this patient is Class IV according to Aramany classification and the mandibular one is Type V according to Cantor and Curtis classification. For retention of the obturator, remaining teeth are fully utilized and artificial teeth are arranged harmoniously to provide stable occlusion. Mandibular RPD covered limited range of deformed soft tissue derived from mandibular resection surgery. With these treatments, the patient in this case showed improvements in mastication, swallowing and speech.

A CAOPI System Based on APACHE II for Predicting the Degree of Severity of Emergency Patients (응급환자의 중증도 예측을 위한 APACHE II 기반 CAOPI 시스템)

  • Lee, Young-Ho;Kang, Un-Gu;Jung, Eun-Young;Yoon, Eun-Sil;Park, Dong-Kyun
    • Journal of the Korea Society of Computer and Information
    • /
    • v.16 no.1
    • /
    • pp.175-182
    • /
    • 2011
  • This study proposes CAOPI(Computer Aided Organ Prediction Index) system based on APACHE II(Acute Physiology And Chronic Health Evaluation) for classifying disease severity and predicting the conditions of patients' major organs. The existing ICU disease severity evaluation is mostly about calculating risk scores using patients' data at certain points, which has limitations on making precise treatments. CAOPI system is designed to provide personalized treatments by classifying accurate severity degrees of emergency patients, predicting patients' mortality rate and scoring the conditions of certain organs.

A Study on Performance-based Evaluation Method for Rock Slopes : Deduction of Evaluation Factors (암반비탈면의 성능기반 평가기법 연구 : 평가항목 도출)

  • Lee, Jong-Gun;Suk, Jae-Wook;Kim, Hong-Kyoon;Kim, Yong-Soo;Moon, Joon-Shik
    • Tunnel and Underground Space
    • /
    • v.25 no.1
    • /
    • pp.86-96
    • /
    • 2015
  • In this study, the performance-based evaluation factors for rock slopes have been deducted using Delphi-method. Validity of the result was verified through factor analysis. Performance of rock slope is classified as soundness, stability and durability. Through the Delphi survey, 17 factors including discontinuity orientation are deducted for soundness, 4 factors and 3 factors are selected for stability and durability, respectively. Validation is conducted using Exploratory Factor Analysis (EFA) for 24 factors, and all factors are found to be valid. As a result of Exploratory Factor Analysis (EFA), 3-types of performance were subdivided into internal soundness, external soundness, risk, damage and durability of slopes and protection (reinforcement) facilities.