• 제목/요약/키워드: Memory Training Program

검색결과 57건 처리시간 0.025초

뇌졸중 환자의 인지기능, 질병의 심각도 및 장애 정도가 일상생활수행능력에 미치는 영향 (The Impacts of Cognitive Function, Disease Severity, and Disability on Ability to Perform Activities of Daily Living after Stroke)

  • 오은영;김민숙;소희영;정미숙
    • 재활간호학회지
    • /
    • 제16권2호
    • /
    • pp.90-99
    • /
    • 2013
  • Purpose: This study aimed to examine influence of cognitive function, disease severity and disability on ability to perform activity of daily living (ADL) after ischemic stroke. Methods: A total of 88 patients with ischemic stroke were recruited from January 1, 2008 to December 31, 2012 and assessed with the standardized cognitive test battery and self-reports about disease severity, disability, and ADL. To analyze the data, ANOVA, Pearson correlation coefficients and multiple regression were conducted using SPSS/WIN program. Results: Significant correlations were found between ADL and visuospatial function, visual memory, executive function, and disability (r=.29~.38). Executive function and disability explained 17.3% of total variability in ADL performance after ischemic stroke. Conclusion: Executive function may be a promising target for cognitive rehabilitation after ischemic stroke. Thus, effective therapeutic interventions such as cognitive training for stroke patients should be considered to improve their ability to perform ADL.

뇌졸중 환자의 주간 재활간호센터에 대한 요구 (The Needs for Rehabilitation Day Care Center in Stroke Patients)

  • 고선화;이명하
    • 가정간호학회지
    • /
    • 제9권2호
    • /
    • pp.114-128
    • /
    • 2002
  • In order to provide information for the establishment and maintenance of a rehabilitation day care center for stroke patients. this study is to assess needs for the rehabilitation day care center of the stroke patients and to identify the factors influencing the needs for the center. The data were collected face-to-face interview with 223 stroke patients. using a structured questionnaire. from September 24. 2001 to November 20. 2001. Major findings are as follows. 1. Most of the participants($94.6\%$) needed rehabilitation day care center for stroke patients. $95.5\%$ of participants were willing to use the rehabilitation day care center. 2. Also the score of the needs for the center's health services was $2.84\pm60$ out of 4.00. In regards to the sub-contents. while the physical exercise therapy showed the highest mark($3.54\pm71$) in the needs. the following marks showed physical therapy($3.48\pm79$), training for the memory. thinking and judgment($3.30\pm93$). training for ADL($3.09\pm99$). health education program($3.04\pm93$). In the meantime. the expected effects from the use of the center are $2.89\pm61$ out of 4 and its sub-contents showed that the center would promote their physical and mental well-being($3.30\pm74$) and the center would be more effective than in home care($3.12\pm70$). 3. Meanwhile. the desired frequency of use in the future and distance had significant interrelation with their families living together(p<.05). In addition those who paid to use it differentiated significantly according to their ages and the types of insurance they had(p<.05). 4. The needs in degrees of speech disorder therapy and hobbies & amusements. the patients with other disease had significantly higher degrees than those patients without it (p<.05). Also in regard to the need degrees for physical therapy. healthy education programs and individual counseling including their families. the degrees of the patients with speech disorders were significantly lower than those of the patients without the disorder (p<.05). On the other hand. the patients with speech disorders were significantly higher than those patients without it in the need degree of the speech disorder therapy (p=.000). And the needs in degree concerning about speech disorder therapy. physical exercise therapy. training for ADL. medicinal substances therapy and family education were negatively correlated with the ADL (r=-.236$\sim$.305, (p<.005). 5. Finally. the expected effect of using the rehabilitation day care center showed significant differences statistically according to whether or not they had other disease (p<.05). In conclusion. the study showed the stroke patients were willing to use the center and had a high requirements for it and they especially had relatively high need degrees for the physical exercise therapy. physical therapy. training for memory. thinking and judgment. and healthy education program. And significant factors for the use of the center were their ages. types of insurance. family cohabitation. complications and speech disorders. ADL and so forth. Accordingly. the rehabilitation day care center needs to be established for the stroke patients and the center should develop rehabilitation care programs. which are individual and special programs customized for each patient's characteristics and health conditions.

  • PDF

경계선지적기능 아동을 위한 언어기반 인지강화 기능성 게임 구현 (Implementation of Serious Games with Language-Based Cognitive Enhancement for BIF Children)

  • 류수린;박현주;정동규;백경선;윤홍옥
    • 디지털콘텐츠학회 논문지
    • /
    • 제19권6호
    • /
    • pp.1051-1060
    • /
    • 2018
  • 본 연구는 경계선지적기능 아동의 인지훈련 프로그램으로 '언어기반 인지강화 프로그램'을 제안하고, 해당 콘텐츠를 활용한 기능성 게임화의 타당성과 효과성을 보이고자 하였다. 콘텐츠는 4개 인지 영역(감각지각, 주의집중, 작업기억, 추론/지식)에 대해 4개 언어 차원(음소-단어-문장-담화)의 활동들로 구성되었으며, 그 중 16개의 언어활동 콘텐츠를 모바일 앱 게임으로 구현하여 일반아동과 BIF아동을 대상으로 시행하였다. 파일럿 테스트 결과, 두 집단의 게임 수행시간과 정확도 측정치는 지능 점수와 상관관계를 보였으며, 게임의 난이도에 따른 수행시간과 정확도의 차이를 확인함으로써 게임 구현의 타당성을 입증할 수 있었다. 또한 게임 시행 전 후 실시한 인지과제의 수행시간 변화를 통해 두 집단 모두에게서 인지강화 효과를 엿볼 수 있었다.

웨이블릿 변환의 특성을 이용한 얼굴 인식 성능 개선 (Performance Improvement of the Face Recognition Using the Properties of Wavelet Transform)

  • 박경준;서석용;고형화
    • 한국항행학회논문지
    • /
    • 제17권6호
    • /
    • pp.726-735
    • /
    • 2013
  • 본 논문에서는 웨이블릿 변환의 특성을 이용한 얼굴인식 방법을 제안하여 인식성능 향상에 관한 연구를 진행하였다. 사용한 이산 웨이블릿 변환은 모웨이블릿의 특징과 비슷한 Daubechies D4 필터이다. 웨이블릿 변환영역 중 LL 대역의 데이터만을 이용할 경우 원본 데이터에 비하여 크기가 줄어들게 되어 인식과정의 속도와 메모리 사용량을 줄일 수 있게 된다. 또한 2차원 데이터의 변형없이 손실을 줄여 인식률을 향상시키기 위하여 2차원 LDA 방법을 적용하였다. 그리고 여기서 얻은 특징벡터를 이용하여 SVM을 수행하도록 하였다. 실험은 Matlab 프로그램을 통하여 ORL 얼굴 데이터베이스와 Yale 얼굴 데이터베이스를 이용하여 실험을 하였고 기존의 방법들과 인식률과 수행시간을 비교를 함으로써 제안한 방법의 우수성을 입증하였다.

데이터의 불균형성을 제거한 네트워크 침입 탐지 모델 비교 분석 (Experimental Comparison of Network Intrusion Detection Models Solving Imbalanced Data Problem)

  • 이종화;방지원;김종욱;최미정
    • KNOM Review
    • /
    • 제23권2호
    • /
    • pp.18-28
    • /
    • 2020
  • 컴퓨팅 환경의 발전에 따라 IT 기술이 의료, 산업, 통신, 문화 등의 분야에서 사람들에게 제공해주는 혜택이 늘어나 삶의 질도 향상되고 있다. 그에 따라 발전된 네트워크 환경을 노리는 다양한 악의적인 공격이 존재한다. 이러한 공격들을 사전에 탐지하기 위해 방화벽, 침입 탐지 시스템 등이 존재하지만, 나날이 진화하는 악성 공격들을 탐지하는 데에는 한계가 있다. 이를 해결하기 위해 기계 학습을 이용한 침입 탐지 연구가 활발히 진행되고 있지만, 학습 데이터셋의 불균형으로 인한 오탐 및 미탐이 발생하고 있다. 본 논문에서는 네트워크 침입 탐지에 사용되는 UNSW-NB15 데이터셋의 불균형성 문제를 해결하기 위해 랜덤 오버샘플링 방법을 사용했다. 실험을 통해 모델들의 accuracy, precision, recall, F1-score, 학습 및 예측 시간, 하드웨어 자원 소모량을 비교 분석했다. 나아가 본 연구를 기반으로 랜덤 오버샘플링 방법 이외에 불균형한 데이터 문제를 해결할 수 있는 다른 방법들과 성능이 높은 모델들을 이용하여 좀 더 효율적인 네트워크 침입 탐지 모델 연구로 발전시키고자 한다.

"증언자료의 비판적 활용 - 6.25전쟁 시기 유격대의 경우" ("Critical Application of Witness Commentaries: The Case of Guerrilla Warfare in the Korean War")

  • 조성훈
    • 기록학연구
    • /
    • 제12호
    • /
    • pp.137-178
    • /
    • 2005
  • The anticommunist guerrillas' activities that aretheconcern of this article took place largely in North Korea or behind the enemy-held lines. Verifying their history is accordingly difficult and requires careful attention, but despite their active operations the military as well as the scholarly community have been lax in studying them. The Korean War came to be perceived as a traditional, limited war with regular battles, so that the studies addressed mostly the regular operations, and guerrilla warfare is remembered as an almost 'exclusive property' of the communist invaders; a small wonder that the anticommunist guerrillas have not been studied much and the collection of materials neglected. Therefore, in contrast with the witness accounts concerning regular battles, witness resources were of a small volume about these "patriots without the service numbers." For the above reasons the guerrilla participants and their later-organized fellowships took to the task of leaving records and compiling the histories of their units. They became active preservers of history in order to inform later generations of their works and also to secure deserved benefits from the government, in a world where none recognized their achievements. For instance, 4th Donkey Unit published witness accounts in addition to a unit history, and left video-recordings of guerrilla witnesses before any institute systematized the oral history of the guerrillas. In the case of Kyulsa ("Resolved to Die") Guerrilla Unit, the unit history was 10 times revised and expanded upon for publication, contributing substantially to the recovery of anticommunist guerrilla history which had almost totally lacked documented resources. Now because the guerrilla-related witness accounts were produced through fellowship societies and not individually, it often took the form of 'collective memory.' As a result, though thousands of former guerrillas remain surviving, the scarcity of numerous versions of, or perspectives upon, an event renders difficult an objective approach to the historical truth. Even requests to verify the service of a guerrilla member or to apply for decoration or government benefits for those killed in action, the process is taken care of not at the hands of the first party but the veteran society, so that a variety of opinions are not available for consideration. Moreover, some accounts were taken by American military personnel, and since some historians, unaware of official documents or evaluation of achievements, tended to center the records around their own units and especially to exaggerate the units' performances, they often featured factual errors. Thefollowing is the means to utilize positively the aforementioned type of witness accounts in military history research. It involves the active use of military historical detachments (MHD). As in the examples of those dispatched by the American forces during the Korean War, experts should be dispatched during, and not just after, wartimes. By considering and investigating the differences among various perspectives on the same historical event, even without extra documented resources it is possibleto arrive at theerrors or questionable points of the oral accounts, supplementing the additional accounts. Therefore any time lapses between witness accounts must be kept in consideration. Moreover when the oral accounts come from a group such as participants in the same guerrilla unit or operation, a standardized list of items ought to be put to use. Education in oral history is necessary not just for the training of experts. In America wherethefield sees much activity, it is used not only in college or graduate programs but also in elementary and lifetime educational processes. In comparison in our nation, and especially in historical disciplines, methodological insistence upon documented evidences prevails in the main, and in the fields of nationalist movement or modern history, oral accounts do not receive adequate attention. Like ancient documents and monuments, oral history also needs to be made a regular part of diverse resource materials at our academic institutes for history. Courses in memory and history, such as those in American colleges, are available possibilities.

이진 분류문제에서의 딥러닝 알고리즘의 활용 가능성 평가 (Feasibility of Deep Learning Algorithms for Binary Classification Problems)

  • 김기태;이보미;김종우
    • 지능정보연구
    • /
    • 제23권1호
    • /
    • pp.95-108
    • /
    • 2017
  • 최근 알파고의 등장으로 딥러닝 기술에 대한 관심이 고조되고 있다. 딥러닝은 향후 미래의 핵심 기술이 되어 일상생활의 많은 부분을 개선할 것이라는 기대를 받고 있지만, 주요한 성과들이 이미지 인식과 자연어처리 등에 국한되어 있고 전통적인 비즈니스 애널리틱스 문제에의 활용은 미비한 실정이다. 실제로 딥러닝 기술은 Convolutional Neural Network(CNN), Recurrent Neural Network(RNN), Deep Boltzmann Machine (DBM) 등 알고리즘들의 선택, Dropout 기법의 활용여부, 활성 함수의 선정 등 다양한 네트워크 설계 이슈들을 가지고 있다. 따라서 비즈니스 문제에서의 딥러닝 알고리즘 활용은 아직 탐구가 필요한 영역으로 남아있으며, 특히 딥러닝을 현실에 적용했을 때 발생할 수 있는 여러 가지 문제들은 미지수이다. 이에 따라 본 연구에서는 다이렉트 마케팅 응답모델, 고객이탈분석, 대출 위험 분석 등의 주요한 분류 문제인 이진분류에 딥러닝을 적용할 수 있을 것인지 그 가능성을 실험을 통해 확인하였다. 실험에는 어느 포르투갈 은행의 텔레마케팅 응답여부에 대한 데이터 집합을 사용하였으며, 전통적인 인공신경망인 Multi-Layer Perceptron, 딥러닝 알고리즘인 CNN과 RNN을 변형한 Long Short-Term Memory, 딥러닝 모형에 많이 활용되는 Dropout 기법 등을 이진 분류 문제에 활용했을 때의 성능을 비교하였다. 실험을 수행한 결과 CNN 알고리즘은 비즈니스 데이터의 이진분류 문제에서도 MLP 모형에 비해 향상된 성능을 보였다. 또한 MLP와 CNN 모두 Dropout을 적용한 모형이 적용하지 않은 모형보다 더 좋은 분류 성능을 보여줌에 따라, Dropout을 적용한 CNN 알고리즘이 이진분류 문제에도 활용될 수 있는 가능성을 확인하였다.