• 대한임베디드공학회논문지
• /
• 제18권3호
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권10호
• /
• pp.2692-2707
• /
• 2012

A separable identity-based ring signature scheme has been constructed as a fundamental cryptographic primitive for protecting user privacy. Using the separability property, ring members can be selected from arbitrary domains, thereby, giving a signer a wide range of ways to control privacy. In this paper we propose a generic method to construct efficient identity-based ring signature schemes with various levels of separability. We first describe a method to efficiently construct an identity-based ring signature scheme for a single domain, in which a signer can select ring identities by choosing from identities defined only for the domain. Next, we present a generic method for linking ring signatures constructed for a single domain. Using this method, an identity-based ring signature scheme with a compact structure, supporting multiple arbitrary domains can be designed. We show that our method outperforms the best known schemes in terms of signature size and computational costs, and that the security model based on the separability of identity-based ring signatures, presented in this paper, is highly refined and effective by demonstrating the security of all of the proposed schemes, using a model with random oracles.

• 가정과삶의질연구
• /
• 제15권1호
• /
• pp.41-52
• /
• 1997

This paper explored the public issue on housework analyzed the policy and the law associated housework and developed the theorical model for its political program. This idea is dependent that the policy has priority over change of the social ideology. That policy contains a campaign and a education to be aimed to share of housework in order to make responsibility of men as well as women on family and work. Also it contains economic value estimates to quantify and value the non-wage work(childcaring homemaking etc.) in order to confirm its productive activity. It would assume the lawful form as like a social security or a pension. For example the Family Rights Law Tax Law and Social Security Act have to be reflected on the value of housework and to be secured the social status of provider. After all this work was useful to improve a wage and a social status of all women. As consistent policy and operation associated housework are poor in Korea it is difficult to develop theoric l model on this theme. On the range a political proposal on housework would be bound by family policy(evaluation of housework) and women's labor policy(housework support). So the policy intend to secure a family life to improve welfare of women and to equilibrate the family and the work.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.400-407
• /
• 2022

Innovations significantly affect the efficiency of the socioeconomic systems of the regions, acting as a system-forming element of their development. Modern models of economic development also consider innovation activity, intellectual potential, knowledge as the basic factors for stimulating the economic growth of the region. The purpose of the study is to develop methodological foundations for evaluating the effectiveness of a regional innovation system based on a multidimensional analysis of its effects. To further study the effectiveness of RIS, we have used one of the methods of multidimensional statistical analysis - canonical analysis. The next approach allows adding another important requirement to the methodological provision of evaluation of the level of innovation development of industries and regions, namely - the time factor, the formalization of which is realized in autoregressive dynamic economic and mathematical models and can be used in our research. Multidimensional Statistical Analysis for RIS effectiveness estimation was used to model RIS by typological regression. Based on it, multiple regression models were built in groups of regions with low and relatively high innovation potential. To solve the methodological problem of RIS research, we can also use the approach to the system as a "box" with inputs and outputs.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.95-99
• /
• 2023

Recently Machine Learning has been considered as one of the active research areas of Computer Science. The various Artificial Intelligence techniques are used to solve the classification problems of environmental sciences, biological sciences, and medical sciences etc. Due to the heterogynous and malfunctioning weather sensors a considerable amount of noisy data with missing is generated, which is alarming situation for weather prediction stockholders. Filling of these missing values with proper method is really one of the significant problems. The data must be cleaned before applying prediction model to collect more precise & accurate results. In order to solve all above stated problems, this research proposes a novel weather forecasting system which consists upon two steps. The first step will prepare data by reducing the noise; whereas a decision model is constructed at second step using regression algorithm. The Confusion Matrix will be used to evaluation the proposed classifier.

• 한국재난관리표준학회지
• /
• 제3권1호
• /
• pp.33-42
• /
• 2010

본 논문에서는 전체해석과 국부해석 조합방법을 이용하여 국부손상 또는 균열의 영향을 반영한 트러스교의 전체지간에서의 응력거동을 예측하였다. 이를 위해서 전체 구조체는 프레임요소에 의한 해석을 수행하고 국부 상세부분은 쉘요소에 의한 해석을 수행하여 두 결과를 조합함으로써 교량의 연결부처럼 응력분포가 복잡한 부분에서 이동하중에 따른 응력이력을 손쉽게 산정하게 된다. 트러스 연결부의 실제 기하학적 형상 및 강성을 전체 프레임해석에 고려하기 위해 국부 쉘모델과 프레임모델의 변위 비교를 통해 프레임 모델의 단면수정계수를 산정하였으며, 실제 공용중인 트러스교의 실험값과 해석값을 비교하여 전체해석-국부해석 조합방법을 검증하였으며, 더 나아가 국부손상의 영향이 반영된 국부 쉘모델 해석결과를 전체해석에 반영시켰다.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.113-123
• /
• 2024

Stock market news sentiment analysis (SA) aims to identify the attitudes of the news of the stock on the official platforms toward companies' stocks. It supports making the right decision in investing or analysts' evaluation. However, the research on Arabic SA is limited compared to that on English SA due to the complexity and limited corpora of the Arabic language. This paper develops a model of sentiment classification to predict the polarity of Arabic stock news in microblogs. Also, it aims to extract the reasons which lead to polarity categorization as the main economic causes or aspects based on semantic unity. Therefore, this paper presents an Arabic SA approach based on the logistic regression model and the Bidirectional Encoder Representations from Transformers (BERT) model. The proposed model is used to classify articles as positive, negative, or neutral. It was trained on the basis of data collected from an official Saudi stock market article platform that was later preprocessed and labeled. Moreover, the economic reasons for the articles based on semantic unit, divided into seven economic aspects to highlight the polarity of the articles, were investigated. The supervised BERT model obtained 88% article classification accuracy based on SA, and the unsupervised mean Word2Vec encoder obtained 80% economic-aspect clustering accuracy. Predicting polarity classification on the Arabic stock market news and their economic reasons would provide valuable benefits to the stock SA field.

• 융합보안논문지
• /
• 제6권1호
• /
• pp.13-23
• /
• 2006

악성 코드로 인한 피해에 적극 대응하기 위해서는 클라이언트가 아닌 서버 측에서 실행되는 안티바이러스 소프트웨어가 필요하다. 그러나 서버용 안티바이러스 소프트웨어로 인하여 서버의 부하가 가중되는 것은 바람직하지 않다. 본 논문에서는 모니터/에이전트 구조로 멀티프로세서 환경의 서버 시스템에서 수행되는 안티바이러스 소프트웨어를 개발하였다. 이 소프트웨어는 안티바이러스 엔진의 주요 특징을 반영하여 서버에서 동적 부하 균형을 지원해줌으로써 효율적인 수행 환경을 제공한다. 악성코드 검색율과 검색 속도에 대한 성능 측정 결과는 서버용 안티바이러스 소프트웨어로서의 장점과 특징을 입증해준다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권12호
• /
• pp.1264-1268
• /
• 2010

본 논문에서는 정보보안 실습 훈련 과정 동안에 참여자들이 보이는 행동 패턴들을 관찰 분석하고 주어진 실습 미션의 성패를 결정짓는 행위 패턴을 추정하는 마코브체인 행위 모델링 기법과 알고리즘을 제안한다. 제안 알고리즘은 미션의 성공에 가장 큰 공헌을 하는 행위 패턴은 어떤 것이고 반대로 실패를 유도하는 행위 패턴용 어떤 것인가를 분석 평가하는데 활용된다. 제안 방법의 적용 및 실효성 검증을 위해 사례연구로서 "불필요한 네트워크 서비스 차단"에 관한 미션 수행 데이터를 분석하였다.

• 정보보호학회논문지
• /
• 제10권4호
• /
• pp.95-105
• /
• 2000

정보유출, 파괴, 위 변조, 바이러스와 같은 정보화 역 기능으로부터 정보시스템과 통신망을 보호하기 위하여 침입차단시스템에 대한 요구가 증대되고 있다. 실제로 침입차단시스템을 사용하기 위해서는 그것이 네트워크에 미치는 영향에 대해서 보안 관리자가 알고 분석할 수 있어야 한다. 그러나 현재 침입차단시스템의 성능에 대해서 의문을 갖게 될 때 이를 평가할 수 있는 마땅한 도구가 없기에 침입차단시스템이 네트워크에 미치는 영향에 대한 연구가 필요하다. 본 논문에서는 침입차단시스템이 네트워크에 미치는 영향을 파악하기 위하여 실제 네트워크에 다양한 트래픽을 적용해 봄으로써 분석하였다. 또한 COMNET-III를 이용하여 침입차단시스템이 없는 경우와 있는 경우의 네트워크를 모델링하여 다양한 침입차단시스템의 운영환경 및 네트워크 환경 변화에 따른 영향을 분석하였다.