Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 김종현 | - |
dc.contributor.author | Seunghee Lee | - |
dc.date.accessioned | 2020-06-22T16:01:41Z | - |
dc.date.available | 2020-06-22T16:01:41Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://dgist.dcollection.net/common/orgView/200000284095 | en_US |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/11980 | - |
dc.description | Neurorehabilitation, Fugl-Meyer Assessment, Automatic assessment, Artificial intelligence | - |
dc.description.abstract | Assessment and evaluation of motor function in stroke patients is important in the neurorehabilitation interventions. In this paper, I proposed a system for automatically evaluating the motor function of stroke patients through the sensor fusion (depth camera sensor and force sensing resistor) and algorithm implementation. This research aims to overcome the limitations of conventional FMA and existing previous automated FMA related studies. In particular, two different algorithms (rule-based binary logic algorithm and fuzzy logic algorithm) were proposed to verify the feasibility and applicability of the proposed automated FMA system. Clinical trials with 51 stroke patients were performed for the system validation. The proposed system shows high FMA score classification accuracy (more than 90% agreement) through rule-based binary logic algorithm. The calculated continuous FMA also showed a high correlation (Pearson's correlation r = 0.923). The proposed automated FMA system can be applied to robot-aided therapy and remote / home rehabilitation in near future. | - |
dc.description.statementofresponsibility | prohibition | - |
dc.description.tableofcontents | I. Introduction 1.1 Limitations of FMA 1.2 Related Works on automated FMA 1.3 Underlying philosophy of FMA 1.4 Considerations for implementing automated FMA II. Proposed automated FMA system 2.1 Target FMA tests and sensor selection 2.2 Feature selection based on FMA guideline 2.3 Feature extraction 2.4 Rule-based binary logic classification 2.5 Fuzzy logic FMA score calculation 2.5.1 Fuzzy variables 2.5.2 Fuzzy rules 2.5.3 Fuzzy inference system 2.6 System configurations III. Clinical experiment 3.1 Experimental setup 3.2 Participant 3.3 Protocol 3.4 Data analysis IV. Result 4.1 Time efficiency 4.2 Evaluation of rule-based binary logic algorithm 4.2.1 Classification accuracy 4.2.2 Total FM score accuracy 4.2.3 Clinical outcome comparison 4.3 Evaluation of fuzzy logic algorithm 4.3.1 Continuous FM scale score comparison 4.3.2 Total score comparison 4.3.3 7-point scaled FM score comparison 4.3.4 Clinical outcome comparison V. Discussion VI. Conclusion |
- |
dc.format.extent | 56 | - |
dc.language | eng | - |
dc.publisher | DGIST | - |
dc.title | Clinically Relevant Automatic Assessment of Upper-limb Motor Function Impairment | - |
dc.type | Thesis | - |
dc.identifier.doi | 10.22677/Theses.200000284095 | - |
dc.description.alternativeAbstract | 뇌졸중 환자의 운동기능의 평가는 뇌신경계 재활 중재에서 매우 중요하다. 이 논문에서는, 센서 융합 기술(깊이 카메라 센서, 압력 저항 센서)과 알고리즘 설계를 통하여 뇌졸중 환자의 운동기능을 자동으로 평가하는 시스템을 제안하였다. 이를 통해 기존 푸글-마이어 평가와 푸글-마이어 평가의 자동화를 위한 이전 연구들의 한계를 극복하고자 한다. 특히 두 종류의 서로 다른 알고리즘(규칙기반 이산 논리 알고리즘, 퍼지 논리 알고리즘)을 설계하여 제안하는 푸글-마이어 평가 자동화 시스템의 임상 적용 가능성과 적용성에 대하여 검증하였다. 이를 위하여 51명의 뇌졸중 환자를 통한 임상시험이 수행되었다. 제안하는 시스템은 규칙기반 이산 논리 알고리즘을 통해 높은 푸글-마이어 점수 분류 정확도(90%이상의 일치율)를 보였다. 퍼지 논리 알고리즘을 통해 산출된 연속 스케일의 푸글-마이어 점수 또한 의료진이 평가한 점수와 높은 상관관계(피어슨 상관계수 r = 0.923)를 보였다. 제안하는 푸글-마이어 평가 자동화 시스템은 추후 로봇 재활과 원격/재택 재활 분야에 적용할 수 있다. | - |
dc.description.degree | Doctor | - |
dc.contributor.department | Robotics Engineering | - |
dc.contributor.coadvisor | Yang-soo Lee | - |
dc.date.awarded | 2020-02 | - |
dc.publisher.location | Daegu | - |
dc.description.database | dCollection | - |
dc.citation | XT.RD 이57C 202002 | - |
dc.date.accepted | 2020-01-20 | - |
dc.contributor.alternativeDepartment | 로봇공학전공 | - |
dc.embargo.liftdate | 2021-02-28 | - |
dc.contributor.affiliatedAuthor | Lee, Seunghee | - |
dc.contributor.affiliatedAuthor | Lee, Yang-soo | - |
dc.contributor.affiliatedAuthor | Kim, Jonghyun | - |
dc.contributor.alternativeName | 이승희 | - |
dc.contributor.alternativeName | Jonghyun Kim | - |
dc.contributor.alternativeName | 이양수 | - |
There are no files associated with this item.