• The Korean Journal of Physiology and Pharmacology
• /
• 제23권2호
• /
• pp.131-139
• /
• 2019

Manually reviewing electroencephalograms (EEGs) is labor-intensive and demands automated seizure detection systems. To construct an efficient and robust event detector for experimental seizures from continuous EEG monitoring, we combined spectral analysis and deep neural networks. A deep neural network was trained to discriminate periodograms of 5-sec EEG segments from annotated convulsive seizures and the pre- and post-EEG segments. To use the entire EEG for training, a second network was trained with non-seizure EEGs that were misclassified as seizures by the first network. By sequentially applying the dual deep neural networks and simple pre- and post-processing, our autodetector identified all seizure events in 4,272 h of test EEG traces, with only 6 false positive events, corresponding to 100% sensitivity and 98% positive predictive value. Moreover, with pre-processing to reduce the computational burden, scanning and classifying 8,977 h of training and test EEG datasets took only 2.28 h with a personal computer. These results demonstrate that combining a basic feature extractor with dual deep neural networks and rule-based pre- and post-processing can detect convulsive seizures with great accuracy and low computational burden, highlighting the feasibility of our automated seizure detection algorithm.

• 한국멀티미디어학회논문지
• /
• 제24권2호
• /
• pp.233-244
• /
• 2021

Recently, several ICT-based cat studies have produced some successful results, according to academic and industry sources. However, research on the level of simply identifying the cat's condition, such as the behavior and sound classification of cats based on images and sound signals, has yet to be found. In this paper, based on the veterinary scientific knowledge of cats, a practical and academic cat monitoring and disease diagnosis system is proposed to monitor the health status of the cat 24 hours a day by automatically categorizing and analyzing the behavior of the cat with location information using LSTM with a beacon sensor and a raspberry pie that can be built at low cost. Validity of the proposed system is verified through experimentation with cats in actual custody (the accuracy of the cat behavior classification and location identification was 96.3% and 92.7% on average, respectively). Furthermore, a rule-based disease analysis system based on the veterinary knowledge was designed and implemented so that owners can check whether or not the cats have diseases at home (or can be used as an auxiliary tool for diagnosis by a pet veterinarian).

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.97-106
• /
• 2021

Social networking platforms have become a smart way for people to interact and meet on internet. It provides a way to keep in touch with friends, families, colleagues, business partners, and many more. Among the various social networking sites, Twitter is one of the fastest-growing sites where users can read the news, share ideas, discuss issues etc. Due to its vast popularity, the accounts of legitimate users are vulnerable to the large number of threats. Spam and Malware are some of the most affecting threats found on Twitter. Therefore, in order to enjoy seamless services it is required to secure Twitter against malicious users by fixing them in advance. Various researches have used many Machine Learning (ML) based approaches to detect spammers on Twitter. This research aims to devise a secure system based on Hybrid Similarity Cosine and Soft Cosine measured in combination with Genetic Algorithm (GA) and Artificial Neural Network (ANN) to secure Twitter network against spammers. The similarity among tweets is determined using Cosine with Soft Cosine which has been applied on the Twitter dataset. GA has been utilized to enhance training with minimum training error by selecting the best suitable features according to the designed fitness function. The tweets have been classified as spammer and non-spammer based on ANN structure along with the voting rule. The True Positive Rate (TPR), False Positive Rate (FPR) and Classification Accuracy are considered as the evaluation parameter to evaluate the performance of system designed in this research. The simulation results reveals that our proposed model outperform the existing state-of-arts.

• Educational Technology International
• /
• 제22권2호
• /
• pp.139-167
• /
• 2021

After experiencing school closures and online learning caused by COVID-19, the important role of school education was reinforced. Elementary school is the foundation of life and allows students to develop both social and academic skills. The purpose of this study was to examine the mediational role of Self-Regulatory Skills (SRS) on the relationship between Maternal Parenting Attitude (MPA) and School Adjustment (SA) of elementary school students. A total of 99 students enrolled in an international school in Seoul, Korea from grades 3 to 6 participated in this study. Data were analyzed through Independent Sample T-Test, one way ANOVA, Multiple Regression Analysis, and Hierarchical Regression Analysis using the SPSS 23.0. The findings of the study were as follows. First, there is a difference between genders and among grades. Second, only acceptance was significantly related to school adjustment. Third, acceptance, strict control, and accepted control are significantly related to SRS. Fourth, Self-Regulatory Skills (Sustained Attention) fully mediate the relationship between Maternal Parenting Attitude (Acceptance) and School Adjustment (Academic Attitude/ Rule compliance). Educational implications for understanding the role of parenting attitude and future directions are discussed.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.53-64
• /
• 2021

Depression is one of the most important psychiatric disorders worldwide. Most depression-related data mining and machine learning studies have been conducted to predict the presence of depression or to derive individual risk factors. However, since depression is caused by a combination of various factors, it is necessary to identify the complex relationship between the factors in order to establish effective anti-depression and management measures. In this study, we propose a methodology for identifying and interpreting patterns of depression expressions using the method of deriving random forest rules, where the random forest rule consists of the condition for the manifestation of the depressive pattern and the prediction result of depression when the condition is met. The analysis was carried out by subdividing into 4 groups in consideration of the different depressive patterns according to gender and age. Depression rules derived by the proposed methodology were validated by comparing them with the results of previous studies. Also, through the AUC comparison test, the depression diagnosis performance of the derived rules was evaluated, and it was not different from the performance of the existing PHQ-9 summing method. The significance of this study can be found in that it enabled the interpretation of the complex relationship between depressive factors beyond the existing studies that focused on prediction and deduction of major factors.

• 전자통신동향분석
• /
• 제36권3호
• /
• pp.106-118
• /
• 2021

The field of brain science (or neuroscience in a broader sense) has inspired researchers in artificial intelligence (AI) for a long time. The outcomes of neuroscience such as Hebb's rule had profound effects on the early AI models, and the models have developed to become the current state-of-the-art artificial neural networks. However, the recent progress in AI led by deep learning architectures is mainly due to elaborate mathematical methods and the rapid growth of computing power rather than neuroscientific inspiration. Meanwhile, major limitations such as opacity, lack of common sense, narrowness, and brittleness have not been thoroughly resolved. To address those problems, many AI researchers turn their attention to neuroscience to get insights and inspirations again. Biologically plausible neural networks, spiking neural networks, and connectome-based networks exemplify such neuroscience-inspired approaches. In addition, the more recent field of brain network analysis is unveiling complex brain mechanisms by handling the brain as dynamic graph models. We argue that the progress toward the human-level AI, which is the goal of AI, can be accelerated by leveraging the novel findings of the human brain network.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2022년도 제34회 한글 및 한국어 정보처리 학술대회
• /
• pp.289-294
• /
• 2022

의존구문분석은 문장을 의존관계(의존소-지배소)로 분석하는 구문분석 방법론이다. 현재 사전학습모델을 사용한 전이 학습의 딥러닝이 좋은 성능을 보이며 많이 연구되지만, 데이터셋에 의존적이며 그로 인한 자료부족 문제와 과적합의 문제가 발생한다는 단점이 있다. 본 논문에서는 언어학적 지식에 기반한 강화된 지배소-의존소 제약규칙 에지 알고리즘을 심층학습과 결합한 모델을 제안한다. TTAS 표준 가이드라인 기반 모두의 말뭉치로 평가한 결과, 최대 UAS 96.28, LAS 93.19의 성능을 보였으며, 선행연구 대비 UAS 2.21%, LAS 1.84%의 향상된 결과를 보였다. 또한 적은 데이터셋으로 학습했음에도 8배 많은 데이터셋 학습모델 대비 UAS 0.95%의 향상과 11배 빠른 학습 시간을 보였다. 이를 통해 심층학습과 언어지식의 결합이 딥러닝의 문제점을 해결할 수 있음을 확인하였다.

• 산업경영시스템학회지
• /
• 제45권1호
• /
• pp.1-9
• /
• 2022

The PoN (Proof of Nonce) distributed consensus algorithm basically uses a non-competitive consensus method that can guarantee an equal opportunity for all nodes to participate in the block generation process, and this method was expected to resolve the first trilemma of the blockchain, called the decentralization problem. However, the decentralization performance of the PoN distributed consensus algorithm can be greatly affected by the network transaction transmission delay characteristics of the nodes composing the block chain system. In particular, in the consensus process, differences in network node performance may significantly affect the composition of the congress and committee on a first-come, first-served basis. Therefore, in this paper, we presented a problem by analyzing the decentralization performance of the PoN distributed consensus algorithm, and suggested a fairness control algorithm using a learning-based probabilistic acceptance rule to improve it. In addition, we verified the superiority of the proposed algorithm by conducting a numerical experiment, while considering the block chain systems composed of various heterogeneous characteristic systems with different network transmission delay.

• 한국건설관리학회논문집
• /
• 제24권4호
• /
• pp.60-73
• /
• 2023

The need for adopting automation technologies to improve inefficiencies in interior finishing modeling work is increasing during the Building Information Modeling (BIM) design stage. As a result, the use of visual programming languages (VPL) for practical applications is growing. However, undefined or incorrect space designations in BIM models can hinder the development of automated finishing modeling processes, resulting in erroneous corrections and rework. To address this challenge, this study first developed a rule-based automated interior finishing detailing module for floors, walls, and ceilings. In addition, an automated space integrity checking module with 86.69% ACC using the Multi-Layer Perceptron (MLP) model was developed. These modules were integrated into a design automation module for interior finishing, which was then verified for practical utility. The results showed that the automation module reduced the time required for modeling and integrity checking by 97.6% compared to manual work, confirming its utility in assisting BIM model development for interior finishing works.

• 한국과학교육학회지
• /
• 제40권4호
• /
• pp.385-398
• /
• 2020

본 연구에서는 서로 다른 학습접근방식의 학생이 유전 가계도 문제 해결 과정상에서 어떠한 차이를 보여주는지 심층적으로 들여다보고자 하였다. 연구 대상은 고등학교 2학년 학생으로 생명과학I을 이수한 학생으로 학업성취수준은 비슷하였으나 학습접근방식이 각각 심층적 접근방식과 피상적 접근방식을 나타내었다. 각 학생의 문제 해결 사례를 심층적으로 분석하기 위해 문제 해결 과정은 비디오 녹화되었고, 문제 해결이 종료된 후에 학생들의 문제 해결 과정에 대한 사고 구술 인터뷰를 실시하였다. 연구 결과, 학생들은 2가지 형질의 유전 원리가 불확실한 문제 상황을 해결하는 과정에서 유사한 오류를 보여주었다. 하지만 심층적 학습접근방식의 학생 A는 자발적으로 2번 반복하여 문제를 해결하면서 3가지 제한 요인에 대해 원리 기반추론을 하며 옳은 개념적 프레이밍을 나타내었다. 검토 단계에서 자료와 본인이 그린 가계도 사이의 일치도를 점검하고, 문제 해결 이후에도 끊임없이 본인의 문제 해결 과정을 점검하였다. 마지막의 문제 해결 과정에서는 성공적인 문제 해결 알고리즘에 근접한 문제 해결 과정을 나타내었다. 하지만 피상적 학습접근방식의 학생 B는 연구자의 권유로 비자발적으로 문제 해결 과정을 반복하였고, 답을 구하려는 목적 지향적인 문제 해결 태도로 인해 문제에서 제시한 일부 정보만을 검토하였다. 문제의 제한 요인에 대해 기억 장치 추론이나 임의적 추론을 통해서 옳지 않은 개념적 프레이밍을 하였고, 이를 수정하지 않고 유지하는 모습을 나타내었다. 본 연구 결과를 통해 심층적 접근방식과 피상적 접근방식의 학생이 문제 해결 과정에서 추론 방식과 개념적 프레이밍의 변화가 어떻게 일어나는지 구체적으로 살펴봄으로써 유전 문제의 접근을 어려워하는 학생들이나 이들을 지도하는 교사들에게 도움을 줄 수 있을 것이다.