• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.62-67
• /
• 2023

This paper proposes an imputation method using a bidirectional k-nearest components search based local linear regression method. The bidirectional k-nearest-components search method selects components in the dynamic range from the missing points. Unlike the existing methods, which use a fixed-size window, the proposed method can flexibly select adjacent components in an imputation problem. The weight values assigned to the components around the missing points are calculated using local linear regression. The local linear regression method is free from the rank problem in a matrix of dependent variables. In addition, it can calculate the weight values that reflect the data flow in a specific environment, such as a blackout. The original missing values were estimated from a linear combination of the components and their weights. Finally, the estimated value imputes the missing values. In the experimental results, the proposed method outperformed the existing methods when the error between the original data and imputation data was measured using MAE and RMSE.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2913-2929
• /
• 2014

Traditional vector quantization (VQ) schemes encode image blocks as VQ indices, in which there is significant similarity between the image block and the codeword of the VQ index. Thus, the method can compress an image and maintain good image quality. This paper proposes a novel lossless VQ indices compression algorithm to further compress the VQ index table. Our scheme exploits the high correlation of adjacent image blocks to search for the same VQ index with the current encoding index from the neighboring indices. To increase compression efficiency, codewords in the codebook are sorted according to the degree of similarity of adjacent VQ indices to generate a state codebook to find the same index with the current encoding index. Note that the repetition indices both on the search path and in the state codebooks are excluded to increase the possibility for matching the current encoding index. Experimental results illustrated the superiority of our scheme over other compression schemes in the index domain.

• ETRI Journal
• /
• 제33권3호
• /
• pp.434-442
• /
• 2011

This paper presents a practical differential fault analysis method for the faulty Advanced Encryption Standard (AES) with a reduced round by means of a semi-invasive fault injection. To verify our proposal, we implement the AES software on the ATmega128 microcontroller as recommended in the standard document FIPS 197. We reduce the number of rounds using a laser beam injection in the experiment. To deduce the initial round key, we perform an exhaustive search for possible key bytes associated with faulty ciphertexts. Based on the simulation result, our proposal extracts the AES 128-bit secret key in less than 10 hours with 10 pairs of plaintext and faulty ciphertext.

• 한국컴퓨터정보학회논문지
• /
• 제24권9호
• /
• pp.83-95
• /
• 2019

Recently, a variety of IoT data is collected by attaching geosensors to many vehicles that are on the road. IoT data basically has time and space information and is composed of various data such as temperature, humidity, fine dust, Co2, etc. Although a certain sensor data can be retrieved using time, latitude and longitude, which are keys to the IoT data, advanced search engines for IoT data to handle high-level user queries are still limited. There is also a problem with searching large amounts of IoT data without generating indexes, which wastes a great deal of time through sequential scans. In this paper, we propose a unified spatial index model that handles both grid and trajectory queries using a cell-based space-filling curve method. also it presents a visualization method that helps user grasp intuitively. The Trajectory query is to aggregate the traffic of the trajectory cells passed by taxi on the road searched by the user. The grid query is to find the cells on the road searched by the user and to aggregate the fine dust. Based on the generated spatial index, the user interface quickly summarizes the trajectory and grid queries for specific road and all roads, and proposes a Web-based prototype system that can be analyzed intuitively through road and heat map visualization.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권3호
• /
• pp.77-90
• /
• 2018

소프트웨어 결함 예측(SDP)은 결함이 있는 모듈을 식별하기 위한 연구 분야이다. 충분한 로컬 데이터가 없으면 다른 회사에서 수집한 데이터를 사용하여 분류기를 구축하는 교차 프로젝트 결함 예측(CPDP)을 활용할 수 있다. SDP에 대한 대부분의 기계 학습 알고리즘은 서로 다른 값에 따라 예측 성능에 큰 영향을 미치는 하나 이상의 매개 변수를 사용한다. 본 연구의 목적은 CPDP의 예측 성능 향상을 위해 매개 변수 선택 기법을 제안하는 것이다. Harmony Search 알고리즘을 사용하여, 예측 어려움을 야기하는 클래스 불균형을 해결하는 방법인 비용에 민감한 부스팅의 매개 변수를 조정한다. 분포 특성에 따라 매개 변수 범위와 매개 변수 간의 제한 조건 규칙이 정의되어 하모니 검색 알고리즘에 적용된다. 제안된 접근법은 15개의 대상 프로젝트를 대상으로 3개의 CPDP 모델과 내부프로젝트 결함 예측(WPDP) 모델을 비교한다. 실험 결과는 제안된 방법이 클래스 불균형의 맥락에서 다른 CPDP 방법보다 성능이 우수하다는 것을 보여준다. 이전의 연구에서는 탐지 확률이 낮거나 오보 가능성이 높았으나 우리의 기법은 높은 PD와 낮은 PF를 제공하면서 높은 전체 성능을 보였다. 또한 WPDP와 비슷한 성능을 제공하였다.

• 한국정보통신학회논문지
• /
• 제19권9호
• /
• pp.2037-2043
• /
• 2015

본 논문에서는 제안한 알고리즘은 이전 유전 알고리즘의 분산처리를 위해 라우터 그룹 단위인 셀을 도입하였다. 셀 단위로 유전 알고리즘을 시행하여 전체 네트워크의 탐색 지연시간을 줄이는 방법을 제시하였다. 또한, 실험을 통하여 기존 최적경로 알고리즘인 Dijkstra 알고리즘에서 네트워크가 손상되었을 경우 제안한 알고리즘에는 대체 경로 설정의 연산시간이 단축되었으며 손상된 네트워크의 셀 안에서 2순위의 경로를 가지고 있으므로 Dijkstra 알고리즘보다 신속하게 대체경로를 설정하도록 설계되었다. 이는 제안한 알고리즘이 네트워크상에서 Dijkstra 알고리즘이 손상되었을 경우 대체 경로설정을 보완할 수 있음을 확인하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 추계학술대회
• /
• pp.599-602
• /
• 2014

본 논문에서는 제안한 알고리즘은 이전 유전 알고리즘의 분산처리를 위해 라우터 그룹 단위인 셀을 도입하였다. 셀 단위로 유전 알고리즘을 시행하여 전체 네트워크의 탐색 지연시간을 줄이는 방법을 제시하였다. 본 논문에서 제안한 알고리즘의 수행 절차를 살펴보면 첫 번째 셀을 만들고 그 위치에서 두 번째 셀과 세 번째 그리고 네 번째 셀을 차례로 만들며 그 포인트에 에이전트를 복제 이전시키고 에이전트로 하여금 각 셀마다 최단 경로를 구하도록 하고 그 후 경쟁하여 가장 나은 요소를 찾도록 하였다.

• 전기학회논문지P
• /
• 제64권4호
• /
• pp.315-320
• /
• 2015

Proposal algorithm in this paper introduced cells, units of router group, for distributed processing of previous genetic algorithm. This paper presented ways to reduce search delay time of overall network through cell-based genetic algorithm. As a result of performance analysis comparing with existing genetic algorithm through experiments, the proposal algorithm was verified superior in terms of costs and delay time. Furthermore, time for routing an alternative path was reduced in proposal algorithm, in case that a network was damaged in existing optimal path algorithm, Dijkstra algorithm, and the proposal algorithm was designed to route an alternative path faster than Dijkstra algorithm, as it has a 2nd shortest path in cells of the damaged network. The study showed that the proposal algorithm can support routing of alternative path, if Dijkstra algorithm is damaged in a network.

• 한국멀티미디어학회논문지
• /
• 제21권1호
• /
• pp.18-25
• /
• 2018

In High Efficiency Video Coding (HEVC), integer motion estimation (IME) requires a large amount of computational complexity because HEVC adopts the high flexible and hierarchical coding structures. In order to reduce the computational complexity of IME, this paper proposes the search range reduction algorithm, which takes advantage of motion vectors similarity between different layers. It needs only a few modification for HEVC reference software. Based on the experimental results, the proposed algorithm reduces the processing time of IME by 28.1% on average, whereas its the $Bj{\emptyset}ntegaard$ delta bitrate (BD-BR) increase is 0.15% which is negligible.

• Journal of Electrical Engineering and Technology
• /
• 제6권6호
• /
• pp.853-866
• /
• 2011

We propose a multi-objective space search algorithm (MSSA) and introduce the identification of fuzzy inference systems based on the MSSA and information granulation (IG). The MSSA is a multi-objective optimization algorithm whose search method is associated with the analysis of the solution space. The multi-objective mechanism of MSSA is realized using a non-dominated sorting-based multi-objective strategy. In the identification of the fuzzy inference system, the MSSA is exploited to carry out parametric optimization of the fuzzy model and to achieve its structural optimization. The granulation of information is attained using the C-Means clustering algorithm. The overall optimization of fuzzy inference systems comes in the form of two identification mechanisms: structure identification (such as the number of input variables to be used, a specific subset of input variables, the number of membership functions, and the polynomial type) and parameter identification (viz. the apexes of membership function). The structure identification is developed by the MSSA and C-Means, whereas the parameter identification is realized via the MSSA and least squares method. The evaluation of the performance of the proposed model was conducted using three representative numerical examples such as gas furnace, NOx emission process data, and Mackey-Glass time series. The proposed model was also compared with the quality of some "conventional" fuzzy models encountered in the literature.