• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제12권2호
• /
• pp.69-76
• /
• 2023

매년 수십만 개의 암호를 분실하거나 잊어버리면서 합법적인 소유자나 권한을 부여받은 법 집행 담당자가 필요한 정보를 사용할 수 없게 된다. 이러한 암호를 되찾기 위해 암호 해독(Password Cracking)이 사용된다. 암호 해독에 CPU 대신 GPU를 사용하면 복구 과정에서 필요한 많은 양의 계산을 신속하게 처리할 수 있다. 본 논문은 현재 가장 많이 사용되는 PDF 1.4 -1.6 버전의 암호 해독에 중점을 두고 CUDA를 사용하여 GPU에서 최적화한다. MD5 알고리즘의 불필요 연산 제거, RC4 알고리즘의 32비트 워드 통합 구현, 공유메모리 사용의 기법을 사용하였다. 또한 성능향상에 영향을 미치는 블록, 스레드 수 탐색을 위해 오토튠 기법을 사용하였다. 결과적으로 RTX 3060, RTX 3090 환경에서 블록 크기 65,536, 스레드 크기 96에서 31,460 kp/s(kilo passwords per second), 66,351 kp/s의 처리량을 보였으며, 기존 최고 처리량을 보여주는 해시캣의 처리량보다 각각 22.5%, 15.2%를 향상시켰다.

• 한국엔터테인먼트산업학회논문지
• /
• 제15권7호
• /
• pp.215-223
• /
• 2021

본 연구의 목적은 지역사회에 거주하고 있는 경도인지장애를 보이는 노인을 대상으로 한 컴퓨터 기반의 인지재활프로그램의 적용이 인지기능과 도구적 일상생활수행능력에 미치는 영향을 알아보고는 것이다. MCI 노인 22명을 실험군 11명, 대조군 11명으로 무작위 할당하여 진행하였으며, 총 10주간, 주 3회, 회기당 30분씩 실험군은 CoTras, 대조군은 전통적 인지 재활을 받았다. 중재 전후로 인지기능과 수단적 일상생활활동의 수행 능력애 대한 변화를 알아보기 위해 NCSE와 K-IADL을 사용하였다. 연구 결과, 실험군은 집중력과 기억력을 포함한 전반적인 인지기능과 수단적 일상생활활동의 수행능력의 향상을 보였다. 지역사회 경도인지장애 노인들을 대상으로 인지기능과 수단적 일상생활활동의 수행능력 증진을 위해 CoTras의 적용을 고려해 볼 수 있을 것이다.

• 한국콘텐츠학회논문지
• /
• 제22권9호
• /
• pp.76-84
• /
• 2022

본 논문에서는 스마트폰의 사진과 영상을 활용하는 상호작용형 콘텐츠 디바이스인 아이퍼즐 이미지 블록과 연동 가능한 시지각 인지기능 훈련 콘텐츠를 구성하였다. 이를 위해 시각기억, 시각연속성, 공간관계, 시각구별의 4개 영역을 도출하고 콘텐츠 동작, 활용방법과 시나리오를 작성하였다. 콘텐츠 이미지를 디자인하고 기존 학습지형 시각 및 지각 인지기능 훈련 자료를 모바일 미니 게임형으로 개발하여 유아의 훈련참여 욕구를 지속부여, 유도하고자 하였다. 개발된 콘텐츠를 활용하여 일반 아동과 보호자를 대상으로 체험활동을 수행하였으며 기본 퍼즐 완구 대비 높은 집중도와 유익성, 효과성에서 의미있는 결과를 확인하였다. 본 논문을 통해 디지털 완구와 콘텐츠를 기반으로 하는 인지기능 개선활동 연구에 의미있는 자료가 되기를 기대한다.

• 한국ITS학회 논문지
• /
• 제21권3호
• /
• pp.42-52
• /
• 2022

BIS(Bus Information System) 서비스는 대도시를 포함하여 중소도시까지 전국적으로 확대운영되는 추세이며, 이용자의 만족도는 지속적으로 향상되고 있다. 이와 함께 버스도착시간 신뢰성 향상 관련 기술개발, 오차 최소화를 위한 개선 연구가 지속되고 있으며 무엇보다 정보 정확도의 중요성이 부각되고 있다. 본 연구에서는 기계학습 방법인 LSTM을 이용하여 정확도 성능을 평가하였으며 기존 칼만필터, 뉴럴 네트워크 등 방법론과 비교하였다. 실제 여행시간과 예측값에 대해 표준오차를 분석한 결과 LSTM 기계학습 방법이 기존 알고리즘에 비해 정확도는 약 1% 높고, 표준오차는 약 10초 낮은 것으로 분석되었다. 반면 총 162개 구간 중 109개 구간(67.3%) 우수한 것으로 분석되어 LSTM 방법이 전적으로 우수한 것은 아닌 것으로 나타났다. 구간 특성 분석을 통한 알고리즘 융합시 더욱 향상된 정확도 예측이 가능할 것으로 판단된다.

• 한국해양바이오학회지
• /
• 제14권1호
• /
• pp.9-24
• /
• 2022

Low-molecular weight peptides derived from fish collagen exhibit several bioactivities, including antioxidant, antiwrinkle, antimicrobial, antidiabetic, and antihypertension effects. These peptides are also involved in triglyceride suppression and memory improvement. This study aimed to investigate the optimal processing condition for preparing low-molecular weight peptides from flounder skin, and the properties of the hydrolysate. The optimal processing conditions for peptic hydrolysis were as follows: a ratio of pepsin to dried skin powder of 2% (w/w), pH of 2.0, and a temperature of 50℃. Peptic hydrolysate contains several low-molecular weight peptides below 300 Da. Gly-Pro-Hyp(GPHyp) peptide, a process control index, was detected only in peptic hydrolysate on matrix-assisted laser desorption/ionization-time-of-flight(MALDI-TOF) spectrum. 2,2'-azinobis-(3-3-ethylbenzothiazolline-6- sulfonic acid(ABTS) radical scavenging activity of the peptic hydrolysate was comparable to that of 1 mM ascorbic acid, which was used as a positive control at pH 5.5, whereas collagenase inhibition was five times higher with the peptic hydrolysate than with 1 mM ascorbic acid at pH 7.5. However, the tyrosinase inhibition ability of the peptic hydrolysate was lower than that of arbutin, which was used as a positive control. The antibacterial effect of the peptic hydrolysate against Propionibacterium acne was not observed. These results suggest that the peptic hydrolysate derived from a flounder skin is a promising antiwrinkle agent that can be used in various food and cosmetic products to prevent wrinkles caused by ultraviolet radiations.

• Biomolecules & Therapeutics
• /
• 제31권3호
• /
• pp.285-297
• /
• 2023

Alzheimer's disease (AD) is a neurodegenerative disease with progressive memory loss and the cognitive decline. AD is mainly caused by abnormal accumulation of misfolded amyloid β (Aβ), which leads to neurodegeneration via a number of possible mechanisms such as down-regulation of brain-derived neurotrophic factor-tropomyosin-related kinase B (BDNF-TRKB) signaling pathway. 7,8-Dihydroxyflavone (7,8-DHF), a TRKB agonist, has demonstrated potential to enhance BDNF-TRKB pathway in various neurodegenerative diseases. To expand the capacity of flavones as TRKB agonists, two natural flavones quercetin and apigenin, were evaluated. With tryptophan fluorescence quenching assay, we illustrated the direct interaction between quercetin/apigenin and TRKB extracellular domain. Employing Aβ folding reporter SH-SY5Y cells, we showed that quercetin and apigenin reduced Aβ-aggregation, oxidative stress, caspase-1 and acetylcholinesterase activities, as well as improved the neurite outgrowth. Treatments with quercetin and apigenin increased TRKB Tyr516 and Tyr817 and downstream cAMP-response-element binding protein (CREB) Ser133 to activate transcription of BDNF and BCL2 apoptosis regulator (BCL2), as well as reduced the expression of pro-apoptotic BCL2 associated X protein (BAX). Knockdown of TRKB counteracted the improvement of neurite outgrowth by quercetin and apigenin. Our results demonstrate that quercetin and apigenin are to work likely as a direct agonist on TRKB for their neuroprotective action, strengthening the therapeutic potential of quercetin and apigenin in treating AD.

• 대한조현병학회지
• /
• 제21권2호
• /
• pp.74-80
• /
• 2018

Objectives : This study investigated whether long-acting injectable (LAI) paliperidone is different from its oral form in terms of the effect on cognitive function in schizophrenia spectrum and other psychotic disorders. Methods : We reviewed the medical records of patients in Seoul National University Bundang Hospital who were diagnosed as having schizophrenia and/or other psychotic disorders based on DSM-5 from 2016 to 2017. Seven patients were treated with oral paliperidone and 11 were treated with paliperidone palmitate. All patients underwent clinical and neuropsychological assessment, including the Korean version of the MATRICS Consensus Cognitive Battery (MCCB) at their first visit or within one month of their initial treatment. MCCB was repeated within three to 12 months after the initial assessment. Results : There was no significant difference between the two groups in most cognitive domains including speed of processing, attention and vigilance, working memory, verbal learning, visual learning and reasoning and problem solving domain. However, patients treated with paliperidone palmitate showed better improvement in social cognition domain than those taking oral paliperidone. The standardized values of social cognition domain scores had significantly improved over time in patients under paliperidone palmitate, demonstrating a significant time-by-group interaction. Conclusion : Our results show that long-acting injectable paliperidone could be helpful in some aspects of improving cognitive function in schizophrenia spectrum and other psychotic disorders. Further studies with other antipsychotics are necessary to generalize the results.

• 정보보호학회논문지
• /
• 제33권6호
• /
• pp.1055-1065
• /
• 2023

최근 사물 인터넷을 활용한 산업 현장에서 수집되는 빅데이터를 활용해 복잡한 문제들을 해결하기 위하여 심층 강화학습 기술을 적용한 다양한 연구들이 이루어지고 있다. 심층 강화학습은 강화 학습의 시행 착오 알고리즘과 보상의 누적값을 이용해 자체 데이터를 생성하여 학습하고 신경망 구조와 파라미터 결정을 빠르게 탐색한다. 그러나 종래 방법은 학습 데이터의 크기가 커질수록 메모리 사용량과 탐색 시간이 기하급수적으로 높아지며 정확도가 떨어진다. 본 연구에서는 메타 학습을 적용한 연합학습 기반의 심층 강화학습 모델을 활용하여 55.9%만큼 보안성을 개선함으로써 프라이버시 침해 문제를 해결하고, 종래 최적화 기반 메타 학습 모델 대비 5.5% 향상된 97.8%의 분류 정확도를 달성하면서 평균 28.9%의 지연시간을 단축하였다.

• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.59-66
• /
• 2023

Text mining (TM) is most widely used to find patterns from various text documents. Cyber-bullying is the term that is used to abuse a person online or offline platform. Nowadays cyber-bullying becomes more dangerous to people who are using social networking sites (SNS). Cyber-bullying is of many types such as text messaging, morphed images, morphed videos, etc. It is a very difficult task to prevent this type of abuse of the person in online SNS. Finding accurate text mining patterns gives better results in detecting cyber-bullying on any platform. Cyber-bullying is developed with the online SNS to send defamatory statements or orally bully other persons or by using the online platform to abuse in front of SNS users. Deep Learning (DL) is one of the significant domains which are used to extract and learn the quality features dynamically from the low-level text inclusions. In this scenario, Convolutional neural networks (CNN) are used for training the text data, images, and videos. CNN is a very powerful approach to training on these types of data and achieved better text classification. In this paper, an Ensemble model is introduced with the integration of Term Frequency (TF)-Inverse document frequency (IDF) and Deep Neural Network (DNN) with advanced feature-extracting techniques to classify the bullying text, images, and videos. The proposed approach also focused on reducing the training time and memory usage which helps the classification improvement.

• Structural Engineering and Mechanics
• /
• 제91권1호
• /
• pp.39-47
• /
• 2024

Bridge deterioration shows the change of bridge condition during its operation, and predicting bridge deterioration is important for implementing predictive protection and planning future maintenance. However, in practical application, the raw inspection data of bridges are not continuous, which has a greater impact on the accuracy of the prediction results. Therefore, two kinds of bridge deterioration models are established in this paper: one is based on the traditional regression theory, combined with the distribution fitting theory to preprocess the data, which solves the problem of irregular distribution and incomplete quantity of raw data. Secondly, based on the theory of Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN), the network is trained using the raw inspection data, which can realize the prediction of the future deterioration of bridges through the historical data. And the inspection data of 60 prestressed concrete box girder bridges in Xiamen, China are used as an example for validation and comparative analysis, and the results show that both deterioration models can predict the deterioration of prestressed concrete box girder bridges. The regression model shows that the bridge deteriorates gradually, while the LSTM-RNN model shows that the bridge keeps great condition during the first 5 years and degrades rapidly from 5 years to 15 years. Based on the current inspection database, the LSTM-RNN model performs better than the regression model because it has smaller prediction error. With the continuous improvement of the database, the results of this study can be extended to other bridge types or other degradation factors can be introduced to improve the accuracy and usefulness of the deterioration model.