• Journal of KIISE
• /
• v.44 no.7
• /
• pp.680-685
• /
• 2017

The emergence of online media and their data has enabled data-driven methods to solve challenging and complex tasks such as rumor classification problems. Recently, deep learning based models have been shown as one of the fastest and the most accurate algorithms to solve such problems. These new models, however, either rely on complete data or several days-worth of data, limiting their applicability in real time. In this study, we go beyond this limit and test the possibility of super early rumor detection via recurrent neural networks (RNNs). Our model takes in social media streams as time series input, along with basic meta-information about the rumongers including the follower count and the psycholinguistic traits of rumor content itself. Based on analyzing millions of social media posts on 498 real rumors and 494 non-rumor events, our RNN-based model detected rumors with only 30 initial posts (i.e., within a few hours of rumor circulation) with remarkable F1 score of 0.74. This finding widens the scope of new possibilities for building a fast and efficient rumor detection system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.687-690
• /
• 2015

Forward collision warning systems(FCWS) and lane change assist systems(LCAS) need regions of interest for detecting lanes and objects as road regions. Watershed segmentation is effective algorithm that classify the road. That algorithm is split results appear differently depending on Watershed line with local minimum in the early part of the seed. If not road regions or vehicles combined the road's seed, It segment road with the others. For compensate the that defect, It has to adaptive change by road environment. The method is that image segmentate the several of regions of interest. Then It is set in a straight line that is detected in regions of interest. If It was detected cars on seed, seed is adjusted the location. And If It wasn't include the line, seed is adjusted the length for final decision the seed. We can detect the road region using the final seed that selected according to the road environment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1089-1098
• /
• 2020

In this study, we propose a method to detect red tide Cochlodinium Polykrikoide using by machine learning and geostationary marine satellite images. To learn the machine learning model, GOCI Level 2 data were used, and the red tide location data of the National Fisheries Research and Development Institute was used. The machine learning model used logistic regression model, decision tree model, and random forest model. As a result of the performance evaluation, compared to the traditional GOCI image-based red tide detection algorithm without machine learning (Son et al., 2012) (75%), it was confirmed that the accuracy was improved by about 13~22%p (88~98%). In addition, as a result of comparing and analyzing the detection performance between machine learning models, the random forest model (98%) showed the highest detection accuracy.It is believed that this machine learning-based red tide detection algorithm can be used to detect red tide early in the future and track and monitor its movement and spread.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.69-74
• /
• 2021

Internet access is also increasing as online activities increase due to the influence of Corona 19. However, network attacks are also diversifying by malicious users, and DDoS among the attacks are increasing year by year. These attacks are detected by intrusion detection systems and can be prevented at an early stage. Various data sets are used to verify intrusion detection algorithms, but in this paper, CICIDS2017, the latest traffic, is used. DDoS attack traffic was analyzed using the decision tree. In this paper, we analyzed the traffic by using the decision tree. Through the analysis, a decisive feature was found, and the accuracy of the decisive feature was confirmed by proceeding the decision tree to prove the accuracy of detection. And the contents of false positive and false negative traffic were analyzed. As a result, learning the feature and the two features showed that the accuracy was 98% and 99.8% respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.6A
• /
• pp.1060-1066
• /
• 2001

레이어2 스위칭과 레이어3 라우팅의 통합 모델로써 MPLS(Multi-Protocol Label Switching) 환경에서 ATM LSR(Label-Switching Routers)은 백본망에서의 고속 전송이 가능하여 현재의 라우터 구조로써 제안되어지고 있다. MPLS가 코어 라이터로써 적용이 될 경우 확장성을 위해 label merging이라는 기술이 필요하다. VC(Virtual Circuit) merging은 ATM LSR에서 많은 IP 라우터를 하나의 라벨로 매핑을 시키며 수천 개의 목적지에 전송할 수 있는 확장성 있는 매핑 기술이다. VC merging은 같은 목적지인 다른 패킷들 간의 셀들의 섞임을 방지하기 위해 재 조합 버퍼가 요구된다. 재 조합 버퍼 사용시 일시적인 체증 현상이 발생하며 Non-VC merging과 비교시 많은 셀 손실과 많은 버퍼를 요구하게 된다. 본 논문에서는 RED(Random Early Detection) 알고리즘을 적용하여 VC merging이 필요한 버퍼의 요구량과 셀 손실을 줄였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.6A
• /
• pp.910-917
• /
• 2000

Because the random early detection(RED) algorithm deals all flows with the same best-effort traffic characteristic, it can not correctly control the output link bandwidth for the flows with different traffic characteristics. To remedy this problem, several per-flow algorithms have been proposed. In this paper, we propose a new per-flow type Fair Droptail algorithm which can fairly allocate bandwidth among flows over a shared output link. By evenly allocating buffers per flow, the Fair Droptail can restrict a flow not to use more bandwidth than others. In addition, it can be simply implemented even if it employs the per-flow state mechanism, because the Fair Droptail only keeps each information of flow in active state.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.354-357
• /
• 2020

DDoS(Distributed Denial of Service) 공격은 현재의 인터넷 환경뿐만 아니라 NDN에서도 정상적인 서비스를 저해시키는 주요 문제이며 이에 관련된 다양한 연구들이 진행되고 있다. 본 논문에서는 DDoS 공격이 가해질 때 NDN 라우터의 PIT(Pending Interest Table) 가용성 저해로 인해 발생하는 문제 해결에 중점을 둔다. 이를 위한 방안으로 RED(Random Early Detection) 알고리즘을 기반으로 하는 기법을 적용하고, 시뮬레이션을 통한 측정 결과를 보여준다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.660-661
• /
• 2020

본 논문에서는 기존 인공 신경망 기반 시계열 학습 기법인 Recurrent Neural Network (RNN)의 많은 연산량 및 고 사양 시스템 요구를 개선하기 위해 랜덤 포레스트 (Random Forest)기반의 새로운 시계열 학습 기법을 제안한다. 기존의 RNN 기반 방법들은 복잡한 연산을 통해 높은 성능을 달성하는 데 집중하고 있다. 이러한 방법들은 학습에 많은 파라미터가 필요할 뿐만 아니라 대규모의 연산을 요구하므로 실시간 시스템에 적용하는데 어려움이 있다. 따라서 본 논문에서는, 효율적이면서 빠르게 동작할 수 있는 시계열 다층 랜덤 포레스트(Time series Multilayered Random Forest)를 제안하고 산불 조기 탐지에 적용해 기존 RNN 계열의 방법들과 성능을 비교하였다. 다양한 산불화재 실험데이터에 알고리즘을 적용해본 결과 GPU 상에서 방대한 연산을 수행하는 RNN 기반 방법들과 비교해 성능적인 한계가 존재했지만 CPU 에서도 빠르게 동작 가능하므로 성능의 개선을 통해 다양한 임베디드 시스템에 적용 가능하다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.2
• /
• pp.119-129
• /
• 2023

Sleep apnea causes various secondary disease such as hypertension, stroke, myocardial infarction, depression and cognitive impairment. Early detection and continuous management of sleep apnea are urgently needed since it causes cardio-cerebrovascular diseases. In this study, wearable device for monitoring respiration during sleep using PVDF film was developed to detect vibration through trachea caused by breathing, which determines normal breathing and sleep apnea. Variables such as respiration rate and apnea were extracted based on the detected breathing sound data, and a noise reduction algorithm was established to minimize the effect even when there is a noise signal. In addition, it was confirmed that irregular breathing patterns can be analyzed by establishing a moving threshold algorithm. The results show that the accuracy of the respiratory rate from the developed device was 98.7% comparing with the polysomnogrphy result. Accuracy of detection for sleep apnea event was 92.6% and that of the sleep apnea duration was 94.0%. The results of this study will be of great help to the management of sleep disorders and confirmation of treatment by commercialization of wearable devices that can monitor sleep information easily and accurately at home during daily life and confirm the progress of treatment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.7A
• /
• pp.586-599
• /
• 2012

This paper proposes a fast face detection and tracking method which uses depth images as well as RGB images. It consists of the face detection procedure and the face tracking procedure. The face detection method basically uses an existing method, Adaboost, but it reduces the size of the search area by using the depth image. The proposed face tracking method uses a template matching technique and incorporates an early-termination scheme to reduce the execution time further. The results from implementing and experimenting the proposed methods showed that the proposed face detection method takes only about 39% of the execution time of the existing method. The proposed tracking method takes only 2.48ms per frame with $640{\times}480$ resolution. For the exactness, the proposed detection method showed a little lower in detection ratio but in the error ratio, which is for the cases when a detected one as a face is not really a face, the proposed method showed only about 38% of that of the previous method. The proposed face tracking method turned out to have a trade-off relationship between the execution time and the exactness. In all the cases except a special one, the tracking error ratio is as low as about 1%. Therefore, we expect the proposed face detection and tracking methods can be used individually or in combined for many applications that need fast execution and exact detection or tracking.