• Journal of Information Processing Systems
• /
• v.10 no.4
• /
• pp.555-567
• /
• 2014

Biometric performance improvement is a challenging task. In this paper, a hierarchical strategy fusion based on multimodal biometric system is presented. This strategy relies on a combination of several biometric traits using a multi-level biometric fusion hierarchy. The multi-level biometric fusion includes a pre-classification fusion with optimal feature selection and a post-classification fusion that is based on the similarity of the maximum of matching scores. The proposed solution enhances biometric recognition performances based on suitable feature selection and reduction, such as principal component analysis (PCA) and linear discriminant analysis (LDA), as much as not all of the feature vectors components support the performance improvement degree.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.4
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.4
• /
• pp.1201-1208
• /
• 2006

Data fusion is generally defined as the use of techniques that combine data from multiple sources and gather that information in order to achieve inferences. Data fusion is also called data combination or data matching. Data fusion is divided in five branch types which are exact matching, judgemental matching, probability matching, statistical matching, and data linking. Currently, Gyeongnam province is executing the social survey every year with the provincials. But, they have the limit of the analysis as execute the different survey to 3 year cycles. In this paper, we study to data fusion of environmental survey data using sas macro. We can use data fusion outputs in environmental preservation and environmental improvement.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2007.04a
• /
• pp.193-196
• /
• 2007

Technology fusion has been recognized as one of the new emerging R&D areas in the construction industry. Therefore it is mandatory to identify important research streams of fusion R&D at the construction R&D planning phase, especially to technology follower. In order to generate innovative and promising fusion R&D programs effectively, this study analyzed research streams of fusion R&D for construction industry with the patent analysis by analyzing 352 patents. As a results, we suggest some important fusion R&D trends.

• 한국데이터정보과학회:학술대회논문집
• /
• 2006.11a
• /
• pp.21-27
• /
• 2006

Data fusion is generally defined as the use of techniques that combine data from multiple sources and gather that information in order to achieve inferences. Data fusion is also called data combination or data matching. Data fusion is divided in five branch types which are exact matching, judgemental matching, probability matching, statistical matching, and data linking. Currently, Gyeongnam province is executing the social survey every year with the provincials. But, they have the limit of the analysis as execute the different survey to 3 year cycles. In this paper, we study to data fusion of environmental survey data using sas macro. We can use data fusion outputs in environmental preservation and environmental improvement.

• Journal of Information Technology Services
• /
• v.11 no.sup
• /
• pp.27-39
• /
• 2012

As many applications are possible now in mobile environment with the trend of mobile convergence, diverse applications in healthcare industry are also possible in mobile devices. Though lots of researches on mobile and health services are introduced, they are limited to specific area or techniques. This study shows possible directions of fusion between mobile technologies and health services in the future using a data mining technique called association rule analysis. The data used in this study is collected from web pages containing key words related to mobile technologies and health services. The analysis shows that current cases of fusion between monitoring based telemedicine and patients. It also shows another case of fusion between mobile hospital and medical screen charts. These show that fusion between mobile technologies and health services already began in industry. Association rules are found between well-being, city, diet, and sleep. The association rules containing security and privacy, though their associations are not so strong, also show that security and privacy of patient information should be protected in the future. The results show that the fusion of mobile technologies and health services is expected to provide health services to more users and larger areas. It is also expected to create new diverse business models in the future.

• Korean Journal of Microbiology
• /
• v.26 no.2
• /
• pp.82-87
• /
• 1988

The genetic analysis and characterization of protoplast fusion hybrids between complementary auxotrophic mutants of Candida pseudotropicalis were carried out. Nuclear fusion appeared to occur in fusion hybrids (e.g., F15 and F33), as strongly suggested by isolation of recombinants after mitotic segregation of parental genetic markers. This was confirmed by KNA content, nuclear staining and comparison of survival rate to UV light. After keeping fusion hybrids for approximately one year, the frequency of spontaneous mitotic segregation was $3.0\times 10^{-4}$ - $8.1\times 10^{-4}$ while that of induced mitotic segregation was $1.4\times 10^{-3}$- $1.7\times 10^{-3}$. These results suggested that they maintained stable karyogamy state. It was also found that the production of $\beta$-D-galactosidase from F15, F33 and F158 was somewhat increased when compared with that from either auxotrophic parents or wild type.

• 한국데이터정보과학회:학술대회논문집
• /
• 2005.10a
• /
• pp.35-45
• /
• 2005

Data fusion is method to combination data. The purpose of this study is to design and implementation for street fashion information analysis system using data fusion. It can offer variety and actually information because it can fuse image data and survey data for street fashion. Data fusion method exists exact matching method, judgemental matching method, probability matching method, statistical matching method, data linking method, etc. In this study, we use exact matching method. Our system can be visual information analysis of customer's viewpoint because it can analyze both each data and fused data for image data and survey data.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.1
• /
• pp.77-85
• /
• 2008

The objective of the study is to construct a sensor fusion system for tool-condition monitoring (TCM) that will lead to a more efficient and economical drill usage. Drill-wear monitoring has an important attribute in the automatic machining processes as it can help preventing the damage of tools and workpieces, and optimizing the drill usage. In this study, we present the architectures of a multi-layer feed-forward neural network with Levenberg-Marquardt training algorithm based on sensor fusion for the monitoring of drill-wear condition. The input features to the neural networks were extracted from AE, vibration and current signals using the wavelet packet transform (WPT) analysis. Training and testing were performed at a moderate range of cutting conditions in the dry drilling of steel plates. The results show good performance in drill- wear monitoring by the proposed method of sensor fusion and neural network analysis.

• BMB Reports
• /
• v.31 no.5
• /
• pp.427-431
• /
• 1998

In the previous report (Choi et al., 1997), the angiogenin binding peptides identified from a phage-peptide library were analyzed by using the fusion proteins composed of the Escherichia coli maltose binding protein and its corresponding peptides. However, it was difficult to obtain a sufficient amount of the fusion proteins required for further analysis because of the low expression level. We now report a high level expression of the fusion protein and analysis of its anti-angiogenin activity. The use of strong T7 promoter and removal of signal sequence allowed about a 20-fold increase in the expression efficiency of the fusion protein. We were able to obtain about 10 mg of purified fusion protein from one liter of culture. The purified fusion protein showed angiogenin-specific affinity and inhibited the binding of biotinylated actin to human angiogenin at $IC_{50}$ of 0.6 mM. Its anti-angiogenin activity was also revealed by the chorioallantoic membrane assay.