• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5179-5196
• /
• 2019

To explore an effective non-invasion medical imaging diagnostics approach for hepatocellular carcinoma (HCC), we propose a method based on adopting the multiple technologies with the multi-parametric data fusion, transfer learning, and multi-scale deep feature extraction. Firstly, to make full use of complementary and enhancing the contribution of different modalities viz. multi-parametric MRI images in the lesion diagnosis, we propose a data-level fusion strategy. Secondly, based on the fusion data as the input, the multi-scale residual neural network with SPP (Spatial Pyramid Pooling) is utilized for the discriminative feature representation learning. Thirdly, to mitigate the impact of the lack of training samples, we do the pre-training of the proposed multi-scale residual neural network model on the natural image dataset and the fine-tuning with the chosen multi-parametric MRI images as complementary data. The comparative experiment results on the dataset from the clinical cases show that our proposed approach by employing the multiple strategies achieves the highest accuracy of 0.847±0.023 in the classification problem on the HCC differentiation. In the problem of discriminating the HCC lesion from the non-tumor area, we achieve a good performance with accuracy, sensitivity, specificity and AUC (area under the ROC curve) being 0.981±0.002, 0.981±0.002, 0.991±0.007 and 0.999±0.0008, respectively.

• 대한공간정보학회지
• /
• 제21권4호
• /
• pp.143-150
• /
• 2013

본 연구의 목적은 상세 레벨의 대규모 도로망 데이터를 대상으로 다양한 축척과 추상화 수준을 가진 상위 레벨의 소축척 도로 선형 사상을 유도하는 가변-축척 기반 네트워크 데이터의 생성 방안을 제시하는 것이다. 이를 위해 우선, 가변-축척 모델 구축을 위해 관련 용어의 정의와 모델 구축시의 이점과 구축 절차에 대해 살펴보았다. 둘째, 가변-축척 모델을 설계하기 위해 지도 표출을 위한 표현 레벨과 레이어 구성요소를 제시하였다. 또한 상위 LoD와 데이터 연계 방법과 인덱스 구조 생성을 위한 규칙을 정의 하였다. 마지막으로 설계된 모델의 구현과 검증을 위해 제시된 알고리즘을 실제적인 연구지역 도로망(제주도)에 적용하여 가변 축척 도로망을 유도하여 구축하고, 공간 데이터베이스(Oracle Spatial)에 저장한 후 성능 분석을 통해 모델의 효율성과 타당성을 검증하였다.

• Journal of Electrical Engineering and Technology
• /
• 제10권4호
• /
• pp.1851-1863
• /
• 2015

– In the paper, to handle the problem of traditional bag-of-features model ignoring the spatial relationship of local features in human action recognition, we proposed a Multiscale Spatial Position Coding under Locality Constraint method. Specifically, to describe this spatial relationship, we proposed a mixed feature combining motion feature and multi-spatial-scale configuration. To utilize temporal information between features, sub spatial-temporal-volumes are built. Next, the pooled features of sub-STVs are obtained via max-pooling method. In classification stage, the Locality-Constrained Group Sparse Representation is adopted to utilize the intrinsic group information of the sub-STV features. The experimental results on the KTH, Weizmann, and UCF sports datasets show that our action recognition system outperforms the classical local ST feature-based recognition systems published recently.

• Journal of applied mathematics & informatics
• /
• 제25권1_2호
• /
• pp.293-304
• /
• 2007

In this paper, we present a Krylov subspace based projection method for reduced-order modeling of large scale bilinear multi-input multi-output (MIMO) systems. The reduced-order bilinear system is constructed in such a way that it can match a desired number of moments of multi-variable transfer functions corresponding to the kernels of Volterra series representation of the original system. Numerical examples report the effectiveness of this method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3762-3781
• /
• 2020

Infrared pedestrian target recognition is a vital problem of significant interest in computer vision. In this work, a novel infrared pedestrian target recognition method that uses heterogeneous features with multi-kernel transfer learning is proposed. Firstly, to exploit the characteristics of infrared pedestrian targets fully, a novel multi-scale monogenic filtering-based completed local binary pattern descriptor, referred to as MSMF-CLBP, is designed to extract the texture information, and then an improved histogram of oriented gradient-fisher vector descriptor, referred to as HOG-FV, is proposed to extract the shape information. Second, to enrich the semantic content of feature expression, these two heterogeneous features are integrated to get more complete representation for infrared pedestrian targets. Third, to overcome the defects, such as poor generalization, scarcity of tagged infrared samples, distributional and semantic deviations between the training and testing samples, of the state-of-the-art classifiers, an effective multi-kernel transfer learning classifier called MK-TrAdaBoost is designed. Experimental results show that the proposed method outperforms many state-of-the-art recognition approaches for infrared pedestrian targets.

• Journal of Electrical Engineering and information Science
• /
• 제2권5호
• /
• pp.79-88
• /
• 1997

This paper introduces a new energy function, as maximum a posteriori(MAP) estimate of binocular disparity, that can deal with both random dot stereo-gram(RDS) and natural scenes. The energy function uses phase-magnitude as features to detect only the shift for a pair of corrupted conjugate images. Also we adopted Fleet singularity that effectively detects unstable areas of image plant and thus eliminates in advance error-prone stereo mathcing. The multi-scale concept is applied to the multi laser architecture that can search the solutions systematically from coarse to fine details and thereby avoids drastically the local minima. Using mean field approximation, we obtained a compact representation that is suitable for fast computation. In this manner, the energy function satisfies major natural constraints and requirements for implementing parallel relaxation. As an experiment, the proposed algorithm is applied to RDS and natural stereo images. As a result we will see that it reveals good performance in terms of recognition errors, parallel implementation, and noise characteristics.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권12호
• /
• pp.4513-4532
• /
• 2014

Motivated by the Weber's Law, this paper proposes an efficient and robust shape descriptor based on the perceptual stimulus model, called Weber's Law Shape Descriptor (WLSD). It is based on the theory that human perception of a pattern depends not only on the change of stimulus intensity, but also on the original stimulus intensity. Invariant to scale and rotation is the intrinsic properties of WLSD. As a global shape descriptor, WLSD has far lower computation complexity while is as discriminative as state-of-art shape descriptors. Experimental results demonstrate the strong capability of the proposed method in handling shape retrieval.

• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.37-50
• /
• 2021

Query applications based on nested data, the most commonly used form of data representation on the web, especially precise query, is becoming more extensively used. MapReduce, a distributed architecture with parallel computing power, provides a good solution for big data processing. However, in practical application, query requests are usually concurrent, which causes bottlenecks in server processing. To solve this problem, this paper first combines a column storage structure and an inverted index to build index for nested data on MapReduce. On this basis, this paper puts forward an optimization strategy which combines query execution service tree and frequent sub-query trajectory to reduce the response time of frequent queries and further improve the efficiency of multi-user concurrent queries on large scale nested data. Experiments show that this method greatly improves the efficiency of nested data query.

• Computers and Concrete
• /
• 제30권5호
• /
• pp.339-355
• /
• 2022

The high cost of ultra-high-performance engineered cementitious composite (UHP-ECC) is currently a crucial issue, especially in terms of the polyethylene (PE) fibers use. In this paper, cheap calcium carbonate whiskers (CW) were evaluated on the feasibility of hybrid with PE fibers. Diverse combinations of PE fibers and CW were employed to investigate the multi-scale enhancement on the UHP-ECC performance. A probabilistic-based UHP-ECC tensile strain reliability analysis approach was utilized, which was in general agreement with the experimental results. Furthermore, a multi-dimensional integrated representation was conducted for the comprehensive assessment of UHP-ECC. Results illustrated that CW improved the compressive strength and energy dissipation capacity of UHP-ECC owing to the microscopic strengthening mechanism. CW and PE fiber further promoted the saturated cracking of composite by multi-scale crack arresting effect. In particular, PE1.75-CW0.5 specimen possessed the best overall performance. The ultimate cracking width of PE1.75-CW0.5 group had 98 ㎛, which was 46.18% lower compared to PE2-CW0 group, the 28d compressive strength were slightly improved, the tensile strain capacity was comparable to that of PE2-CW0 group. The results above demonstrated that combinations of PE fiber and CW could significantly enhance the comprehensive performance of UHP-ECC, which was beneficial for large-scale engineering applications.

• Spatial Information Research
• /
• 제19권1호
• /
• pp.73-82
• /
• 2011

최근, 지적도 이용에 대한 요구사항이 공공기관과 민간부문에서 높아지고 있는 추세이다. 지적도를 웹 환경 또는 모바일 환경에서 활용하기 위해서는 원 지도자료를 임의 단계의 축척 별로 압축해 놓은 다축척 공간표현 데이터베이스로 구축되어야 할 필요가 있다. 본 연구에서는 기존의 연속지적도를 다축척 공간표현 데이터베이스로 구축하는데 있어서 지형도와의 중첩과 폴리곤 지도 일반화 기법을 적용하는 방안에 대해서 제안하였다. 이 과정은 크게 지형도 네트워크 데이터 재구조화, 네트워크 위계에 따른 필지경계선 병합, 선형 단순화 기법 적용의 세 단계로 이루어져 있다. 본 연구에서 제안된 일반화 기법을 수원지역의 연속지적도에 적용한 결과, 1:5,000, 1:20,000, 1:100,000 세 축척의 연속지적도로 각각 일반화 되었으며, 데이터 압축률은 각각 15%, 8%, 1% 수준으로 나타났다.