• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.1-13
• /
• 2021

In this research, we study the problem of font image skeletonization using an end-to-end deep adversarial network, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies have been concerned with skeletonization, but a few have utilized deep learning. Further, no study has considered generative models based on deep neural networks for font character skeletonization, which are more delicate than natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of font characters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization, in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generator is proved superior to all well-known mathematical skeletonization methods in terms of character structure, including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominance of our method against the state-of-the-art supervised image-to-image translation method in font character skeletonization task.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.277-283
• /
• 2022

Email phishing has become very prevalent especially now that most of our dealings have become technical. The victim receives a message that looks as if it was sent from a known party and the attack is carried out through a fake cookie that includes a phishing program or through links connected to fake websites, in both cases the goal is to install malicious software on the user's device or direct him to a fake website. Today it is difficult to deploy robust cybersecurity solutions without relying heavily on machine learning algorithms. This research seeks to detect phishing emails using high-accuracy machine learning techniques. using the WEKA tool with data preprocessing we create a proposed methodology to detect emails phishing. outperformed random forest algorithm on Naïve Bayes algorithms by accuracy of 99.03 %.

• 반도체디스플레이기술학회지
• /
• 제21권1호
• /
• pp.75-78
• /
• 2022

Deep Neural Networks (DNN) has become an essential data processing architecture for the implementation of multiple computer vision tasks. Recently, DNN-based algorithms achieve much higher recognition accuracy than traditional algorithms based on shallow learning. However, training and inference DNNs require huge computational capabilities than daily usage purposes of computers. Moreover, with increased size and depth of DNNs, CPUs may be unsatisfactory since they use serial processing by default. GPUs are the solution that come up with greater speed compared to CPUs because of their Parallel Processing/Computation nature. In this paper, we analyze the inference time complexity of DNNs using well-known computer vision library, OpenCV. We measure and analyze inference time complexity for three cases, CPU, GPU-Float32, and GPU-Float16.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.297-299
• /
• 2021

Text classification is one of the popular tasks in Natural Language Processing (NLP) used to classify text or document applications such as sentiment analysis and email filtering. Nowadays, state-of-the-art (SOTA) Machine Learning (ML) and Deep Learning (DL) algorithms are the core engine used to perform these classification tasks with high accuracy, and they show satisfying results. This paper conducts a benchmarking performance's analysis of multiple SOTA algorithms on the first known labeled Korean voice phishing dataset called KorCCVi. Experimental results reveal performed on a test set of 366 samples reveal which algorithm performs the best considering the training time and metrics such as accuracy and F1 score.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.1067-1070
• /
• 2005

In this paper, we propose the address allocation algorithm in hybrid Mobile ad-hoc network (MANET). Most of proposed address autoconfiguration algorithms are node based. Node based address autoconfiguration algorithms are inefficient. Because the node based algorithms waste bandwidth and consume much battery in mobile ad-hoc networks. we present the address allocation algorithm using internet gateway based address autoconfiguration by modifing the IPv6 stateless address autoconfiguration protocol. We use the network simulator NS-2 in our experiments. The simulation result shows reducing network traffic and saving battery.

• 한국컴퓨터정보학회논문지
• /
• 제10권6호
• /
• pp.85-92
• /
• 2005

본 논문에서는 변형된 돌연변이 연산자를 적용한 대화형 유전자 알고리즘을 사용해서 웹-기반 학습 콘텐츠를 개발하였다. 대화형 유전자 알고리즘은 주로 상호 교환(reciprocal exchange) 돌연변이를 사용한다. 그러나 본 논문에서는 학습자의 학습 효과를 높이기 위해 돌연변이 연산자를 변형하였다. 그리고, 대화형 유전자 알고리즘을 이용한 웹 기반 학습 콘텐츠는 동적인 학습 내용과 실시간 테스트 시스템을 제공한다. 특히 학습자가 자신의 특성과 흥미에 따라 대화형 유전자 알고리즘을 수행하면서 효율적인 학습 환경과 콘텐츠 배열 순서를 선택할 수 있다.

• Journal of Information Processing Systems
• /
• 제2권2호
• /
• pp.67-75
• /
• 2006

In order to acquire a precise and quick response to an analytical query, proper selection of the views to materialize in the data warehouse is crucial. In traditional view selection algorithms, all relations are considered for selection as materialized views. However, materializing all relations rather than a part results in much worse performance in terms of time and space costs. Therefore, we present an improved algorithm for selection of views to materialize using the clustering method to overcome the problem resulting from conventional view selection algorithms. In the presented algorithm, ASVMRT (Algorithm for Selection of Views to Materialize using Reduced Table), we first generate reduced tables in the data warehouse using clustering based on attribute-values density, and then we consider the combination of reduced tables as materialized views instead of a combination of the original base relations. For the justification of the proposed algorithm, we reveal the experimental results in which both time and space costs are approximately 1.8 times better than conventional algorithms.

• 한국항공운항학회지
• /
• 제24권4호
• /
• pp.6-11
• /
• 2016

There has been an increase in the number of researches on the segment for commercialization after developing avionics systems. In this paper, we have applied a commercial off-the-shelf(COTS) operating systems in an aircraft mission computer. We used UAV collision avoidance algorithms to compare the performance of COTS operating systems. The UAV collision avoidance algorithms were tested on different operating systems to compare the performances of the operating systems. The measured parameters are memory usage and processing time. We have verified that the UAV collision avoidance algorithms worked successfully and compared the performance of each operating system.

• 한국컴퓨터산업학회논문지
• /
• 제5권7호
• /
• pp.711-720
• /
• 2004

프로그램을 계산적으로나 수명적으로 최적화하는 기법에는 수식 모션 변환과 수식 모션을 포함하는 배정문 모션 변환이 있다. 본 논문에서는 노드 단위 분석과 명령어 단위 분석의 혼용 때문에 발생하는 모호함을 가지는 Knoop의 알고리즘을 개선하는 불필요한 코드 모션 재구성 알고리즘을 제안하였다. 제안한 알고리즘은 수식이나 배정문의 불필요한 재계산이나 재수행을 피하게 함으로써 프로그램의 능률과 수행시간을 개선하였다.

• 한국지능시스템학회논문지
• /
• 제14권5호
• /
• pp.630-634
• /
• 2004

According to the progress of an information-oriented society, more human friendly systems are required. The systems can be implemented by a kind of intelligent algorithms. In this paper we propose the possibility of the implementation of an intelligent algorithm from gene, behavior of human beings, which has some properties such as self organization and self regulation. The regulation of gene behavior is widely analyzed by Boolean network. Also the SORE (Self Organizable and Regulating Engine) is one of those algorithms. This paper does not report detailed research results; rather, it studies the feasibility of gene behavior in biocontrol systems based upon computer simulations.