• Journal of Information Processing Systems
• /
• 제17권5호
• /
• pp.892-904
• /
• 2021

An image semantic segmentation model is proposed based on improved ENet network in order to achieve the low accuracy of image semantic segmentation in complex environment. Firstly, this paper performs pruning and convolution optimization operations on the ENet network. That is, the network structure is reasonably adjusted for better results in image segmentation by reducing the convolution operation in the decoder and proposing the bottleneck convolution structure. Squeeze-and-excitation (SE) module is then integrated into the optimized ENet network. Small-scale targets see improvement in segmentation accuracy via automatic learning of the importance of each feature channel. Finally, the experiment was verified on the public dataset. This method outperforms the existing comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU) values. And in a short running time, the accuracy of the segmentation and the efficiency of the operation are guaranteed.

• Geomechanics and Engineering
• /
• 제35권1호
• /
• pp.67-80
• /
• 2023

Due to the nature of the conjunctive Cone Penetration Test(CPT), which does not verify the actual sample directly, geotechnical engineers commonly classify the underground geomaterials using CPT results with the classification diagrams proposed by various researchers. However, such classification diagrams may fail to reflect local geotechnical characteristics, potentially resulting in misclassification that does not align with the actual stratification in regions with strong local features. To address this, this paper presents an objective method for more accurate local CPT soil classification criteria, which utilizes C4.5 decision tree models trained with the CPT results from the clay-dominant southern coast of Korea and the sand-dominant region in South Carolina, USA. The results and analyses demonstrate that the C4.5 algorithm, in conjunction with oversampling, outlier removal, and pruning methods, can enhance and optimize the decision tree-based CPT soil classification model.

• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.406-420
• /
• 2020

In order to make up the deficiencies of the existing research results which cannot effectively deal with the nearest neighbor query based on the line segments in obstacle space, the k nearest neighbor query method of line segment in obstacle space is proposed and the STA_OLkNN algorithm under the circumstance of static obstacle data set is put forward. The query process is divided into two stages, including the filtering process and refining process. In the filtration process, according to the properties of the line segment Voronoi diagram, the corresponding pruning rules are proposed and the filtering algorithm is presented. In the refining process, according to the relationship of the position between the line segments, the corresponding distance expression method is put forward and the final result is obtained by comparing the distance. Theoretical research and experimental results show that the proposed algorithm can effectively deal with the problem of k nearest neighbor query of the line segment in the obstacle environment.

• 한국컴퓨터정보학회논문지
• /
• 제14권10호
• /
• pp.251-258
• /
• 2009

그래프마이닝에서 그래프패턴의 동형판단문제는 지수함수적 계산시간을 요구하기 때문에 그래프마이닝의 전체수행시간에서 동형판단 연산이 차지하는 비율이 매우 높다. 그러므로 그래프마이닝 알고리즘은 그래프동형판단을 최대한 효율적으로 할 필요가 있다. 본 논문은 그래프마이닝에서 빠른 수행시간을 보이는 gaston 알고리즘의 동형판단효율성을 증가시켜 수행시간을 평가해 보았으며, 제시한 방법으로 인해 더욱 향상된 성능을 보인다.

• 정보처리학회논문지D
• /
• 제10D권3호
• /
• pp.447-458
• /
• 2003

기존의 데이터 마이닝 방법들은 기본적으로 지식 발견의 대상이 되는 데이터 집합이 마이닝 작업 시작 이전에 명확히 정의되는 것으로 가정하며 이러한 가정은 고정적으로 정의된 특정 데이터 집합에 내재된 정보 추출이 데이터 마이닝의 목적이 될 때 유효하다. 또한, 기존의 데이터 마이닝 방법들은 대용량의 데이터 집합에 대한 마이닝 결과를 얻는데 있어서 상당한 처리 시간을 요구한다. 따라서, 새로운 트랜잭션 데이터가 지속적으로 추가되는 데이터 스트림에서 추가된 트랜잭션의 정보들을 포함하는 최신의 마이닝 결과를 최대한 빠른 시간 안에 얻기를 기대하는 실시간 처리 환경에서는 기존의 데이터 마이닝 방법을 적용하는 것이 거의 불가능하다. 이러한 목적에 부합하기 위해서 본 논문에서는 새로운 데이터 마이닝 개념인 개방 데이터 마이닝을 제안한다. 개방 데이터 마이닝에서는 새로운 트랜잭션이 발생함에 따라 이전에 발생한 트랜잭션들에 대한 마이닝 결과가 새롭게 갱신되며 따라서 확장된 전체 트랜잭션 집합에 대한 마이닝 결과를 빠르게 얻을 수 있다. 이러한 방법을 효과적으로 구현하기 위해서는 새롭게 출현한 항목에 대한 지연추가와 이전 데이터 집합에 출현한 항목들 중에서 중요하지 않는 항목에 대한 전지작업이 병행되어야 한다. 논문에서 제안하는 알고리즘은 알고리즘의 특성을 파악하기 위한 일련의 다양한 실험을 통해서 검증된다.

• 한국멀티미디어학회논문지
• /
• 제20권11호
• /
• pp.1759-1767
• /
• 2017

Although Open API has been invigorated by advancements in the software industry, diverse types of malicious code have also increased. Thus, many studies have been carried out to discriminate the behaviors of malicious code based on API data, and to determine whether malicious code is included in a specific executable file. Existing methods detect malicious code by analyzing signature data, which requires a long time to detect mutated malicious code and has a high false detection rate. Accordingly, in this paper, we propose a method that analyzes and detects malicious code using association rule mining and an Naive Bayes classification. The proposed method reduces the false detection rate by mining the rules of malicious and normal code APIs in the PE file and grouping patterns using the DHP(Direct Hashing and Pruning) algorithm, and classifies malicious and normal files using the Naive Bayes.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2012년도 하계학술대회
• /
• pp.298-301
• /
• 2012

This paper presents a graph-based method of detecting and tracking moving objects in H.264/SVC bitstreams for video surveillance applications that makes use the information from spatial base and enhancement layers of the bitstreams. In the base layer, segmentation of real moving objects are first performed using a spatio-temporal graph by removing false detected objects via graph pruning and graph projection, followed by graph matching to precisely identify the real moving objects over time even under occlusion. For the accurate detection and reliable tracking of moving objects in the enhancement layer, as well as saving computational complexity, the identified block groups of the real moving objects in the base layer are then mapped to the enhancement layer to provide accurate and efficient object detection and tracking in the bitstreams of higher resolution. Experimental results show the proposed method can produce reliable results with low computational complexity in both spatial layers of H.264/SVC test bitstreams.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권5호
• /
• pp.1825-1839
• /
• 2015

The final draft of the latest video coding standard, High Efficiency Video Coding (HEVC), was approved in January 2013. The coding efficiency of HEVC surpasses its predecessor, H.264/MPEG-4 Advanced Video Coding (AVC), by using only half of the bitrate to encode the same sequence with similar quality. However, the complexity of HEVC is sharply increased compared to H.264/AVC. In this paper, a method is proposed to decrease the complexity of intra coding in HEVC. Early pruning and an early splitting strategy are applied to the quadtree structure of coding tree units (CTU) and residual quadtree (RQT). According to our experiment, when our method is applied to sequences from Class A to Class E, the coding time is decreased by 44% at the cost of a 1.08% Bjontegaard delta rate (BD-rate) increase on average.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5782-5799
• /
• 2018

With the development of GPS and the popularity of mobile devices with positioning capability, collecting massive amounts of trajectory data is feasible and easy. The daily trajectories of moving objects convey a concise overview of their behaviors. Different social roles have different trajectory patterns. Therefore, we can identify users or groups based on similar trajectory patterns by mining implicit life patterns. However, most existing daily trajectories mining studies mainly focus on the spatial and temporal analysis of raw trajectory data but missing the essential semantic information or behaviors. In this paper, we propose a novel trajectory semantics calculation method to identify groups that have similar behaviors. In our model, we first propose a fast and efficient approach for stay regions extraction from daily trajectories, then generate semantic trajectories by enriching the stay regions with semantic labels. To measure the similarity between semantic trajectories, we design a semantic similarity measure model based on spatial and temporal similarity factor. Furthermore, a pruning strategy is proposed to lighten tedious calculations and comparisons. We have conducted extensive experiments on real trajectory dataset of Geolife project, and the experimental results show our proposed method is both effective and efficient.

• 한국인터넷방송통신학회논문지
• /
• 제19권2호
• /
• pp.127-133
• /
• 2019

지금까지의 빈발 항목 추출에서는 FP-Tree에 대한 순회와 패턴의 탐색이 필수적인 과정이기 때문에 마이닝 데이터를 트리에 저장하는데 공간이 필요하고 탐색하는데 CPU시간이 필요하기 마련이다. 이러한 단점을 극복하기 위하여 본 논문에서는 조건부 FP-Tree의 의존하지 않고 트랜잭션 데이터의 각 항목들의 위치 정보를 부여하여 트랜잭션 데이터를 2차원의 위치정보 Look-Up테이블로 변환하여 시간과 공간적인 접근성을 용이하게 한다. 또한 항목과 항목의 위치에 대한 매핑배열을 병행하여 시간 복잡도를 줄이는 방법을 고려하는 알고리즘을 제안한다. 실험 결과를 통하여 제안된 방법은 FIMI 저장소 웹 사이트에서 얻은 데이터 세트를 기반으로 많은 실행 시간과 메모리 사용을 줄일 수 있음을 보였다.