• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.2
• /
• pp.69-76
• /
• 2023

Hundreds of thousands of passwords are lost or forgotten every year, making the necessary information unavailable to legitimate owners or authorized law enforcement personnel. In order to recover such a password, a tool for password cracking is required. Using GPUs instead of CPUs for password cracking can quickly process the large amount of computation required during the recovery process. This paper optimizes on GPUs using CUDA, with a focus on decryption of the currently most popular PDF 1.4-1.6 version. Techniques such as eliminating unnecessary operations of the MD5 algorithm, implementing 32-bit word integration of the RC4 algorithm, and using shared memory were used. In addition, autotune techniques were used to search for the number of blocks and threads that affect performance improvement. As a result, we showed throughput of 31,460 kp/s (kilo passwords per second) and 66,351 kp/s at block size 65,536, thread size 96 in RTX 3060, RTX 3090 environments, and improved throughput by 22.5% and 15.2%, respectively, compared to the cracking tool hashcat that achieves the highest throughput.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.7
• /
• pp.215-223
• /
• 2021

The purpose of this study is to investigate the effect of computerized cognitive therapy on cognitive function and Instrumental Activities of Daily Living for elderly people with mild cognitive impairment living in the community. 22 MCI elderly people were randomly assigned to 11 experimental group and 11 control group. For a total of 10 weeks, 3 times a week, 30 minutes per session, the experimental group received CoTras and the control group received traditional cognitive rehabilitation. Neurobehavioral Cognitive Status Examination(NCSE) and Korean Instrumental Activities of Daily Living(K-IADL) were used to investigate the changes in cognitive function and performance of instrumental activities of daily living before and after the intervention. As a result of the study, the experimental group showed improvement in overall cognitive function, including attention and memory, and performance in IADL. The use of CoTras may be considered to improve cognitive function and performance of instrumental activities of daily living for the elderly with mild cognitive impairment in the community.

• The Journal of the Korea Contents Association
• /
• v.22 no.9
• /
• pp.76-84
• /
• 2022

In this paper, in order to compose the visual perception cognitive function training content that can be linked with the IPUZZLE image block, an interactive content device that utilizes photos and videos of smartphones. Four areas of visual memory, visual continuity, spatial relationship, and visual discrimination were derived and the content operation, application method, and scenario were written. It was intended to continuously give and induce children's desire to participate in training by designing the content image and developing the existing learning terrain visual and perceptual cognitive function training materials in the form of mobile mini-games. Experiential activities were conducted for general children and their guardians using the developed contents, and the results were found to be significant in terms of concentration, effect, and effect compared to basic puzzle toys. It is expected that this thesis will be a meaningful data for the study of cognitive function improvement activities based on digital toys and contents.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.42-52
• /
• 2022

Bus Information System (BIS) services are expanding nationwide to small and medium-sized cities, including large cities, and user satisfaction is continuously improving. In addition, technology development related to improving reliability of bus arrival time and improvement research to minimize errors continue, and above all, the importance of information accuracy is emerging. In this study, accuracy performance was evaluated using LSTM, a machine learning method, and compared with existing methodologies such as Kalman filter and neural network. As a result of analyzing the standard error for the actual travel time and predicted values, it was analyzed that the LSTM machine learning method has about 1% higher accuracy and the standard error is about 10 seconds lower than the existing algorithm. On the other hand, 109 out of 162 sections (67.3%) were analyzed to be excellent, indicating that the LSTM method was not entirely excellent. It is judged that further improved accuracy prediction will be possible when algorithms are fused through section characteristic analysis.

• Journal of Marine Bioscience and Biotechnology
• /
• v.14 no.1
• /
• 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
• /
• v.31 no.3
• /
• 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.

• Korean Journal of Schizophrenia Research
• /
• v.21 no.2
• /
• 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.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1055-1065
• /
• 2023

Recently, various studies using deep reinforcement learning (deep RL) technology have been conducted to solve complex problems using big data collected at industrial internet of things. Deep RL uses reinforcement learning"s trial-and-error algorithms and cumulative compensation functions to generate and learn its own data and quickly explore neural network structures and parameter decisions. However, studies so far have shown that the larger the size of the learning data is, the higher are the memory usage and search time, and the lower is the accuracy. In this study, model-agnostic learning for efficient federated deep RL was utilized to solve privacy invasion by increasing robustness as 55.9% and achieve 97.8% accuracy, an improvement of 5.5% compared with the comparative optimization-based meta learning models, and to reduce the delay time by 28.9% on average.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• 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
• /
• v.91 no.1
• /
• 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.