• Journal of KIISE
• /
• v.41 no.11
• /
• pp.927-934
• /
• 2014

In this paper, we propose an effective method for recognizing daily human activities from a stream of three dimensional body poses, which can be obtained by using Kinect-like RGB-D sensors. The body pose data provided by Kinect SDK or OpenNI may suffer from both the view variance problem and the scale variance problem, since they are represented in the 3D Cartesian coordinate system, the origin of which is located on the center of Kinect. In order to resolve the problem and get the view-invariant and scale-invariant features, we transform the pose data into the spherical coordinate system of which the origin is placed on the center of the subject's hip, and then perform on them the scale normalization using the length of the subject's arm. In order to represent effectively complex internal structures of high-level daily activities, we utilize Hidden state Conditional Random Field (HCRF), which is one of probabilistic graphical models. Through various experiments using two different datasets, KAD-70 and CAD-60, we showed the high performance of our method and the implementation system.

• Journal of Animal Reproduction and Biotechnology
• /
• v.34 no.4
• /
• pp.280-291
• /
• 2019

Potential utility of 14 candidate housekeeping genes as normalization reference for RT-qPCR analysis with developmental samples (fertilized eggs to late veliger larvae) in Pacific abalone Haliotis discus hannai was evaluated using four different statistical algorithms (geNorm, NormFinder, BestKeeper and comparative ΔCT method). Different algorithms identified different genes as the best candidates, and geometric mean-based final ranking from the most to the least stable expression was as follow: RPL5, RPL4, RPS18, RPL8, RPL7, UBE2, RPL7A, GAPDH, RPL36, PPIB, EF1A, ACTB and B-TU. The findings were further validated via relative quantification of metallothionein (MT) transcripts using the stable and unstable reference genes, and expression levels of MT were greatly influenced according to the choice of reference genes. In overall, our data suggest that RPL5 and RPS18, either singly or in combination, are appropriate for normalizing gene expression in developmental samples of this abalone species, whereas ACTB, B-TU and EF1A are less stable and not recommended. In addition, our findings propose that standard deviations in geometric ranking as well as geometric mean itself should also be taken into account for the final selection of reference gene(s). This study could be a useful basis to facilitate the generation of accurate and reliable RT-qPCR data with developmental samples in this abalone species.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.28 no.4
• /
• pp.301-319
• /
• 2017

The task of author name disambiguation involves identifying an author with different names or different authors with the same name. The author name disambiguation is important for correctly assessing authors' research achievements and finding experts in given areas as well as for the effective operation of scholarly information services such as citation indexes. In the study, we performed error correction and normalization of data and applied rules-based author name disambiguation to compare with baseline machine learning disambiguation in order to see if human intervention could improve the machine learning performance. The improvement of over 0.1 in F-measure by the corrected and normalized email-based author name disambiguation over machine learning demonstrates the potential of human pattern identification and inference, which enabled data correction and normalization process as well as the formation of the rule-based diambiguation, to complement the machine learning's weaknesses to improve the author name disambiguation results.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.17-23
• /
• 2018

We proposed a LSTM-based RNN model that can effectively perform the automatic spacing characteristics. For those long or noisy sentences which are known to be difficult to handle within Neural Network Learning, we defined a proper input data format and decoding data format, and added dropout, bidirectional multi-layer LSTM, layer normalization, and attention mechanism to improve the performance. Despite of the fact that Sejong corpus contains some spacing errors, a noise-robust learning model developed in this study with no overfitting through a dropout method helped training and returned meaningful results of Korean word spacing and its patterns. The experimental results showed that the performance of LSTM sequence-to-sequence model is 0.94 in F1-measure, which is better than the rule-based deep-learning method of GRU-CRF.

• Journal of Navigation and Port Research
• /
• v.28 no.7
• /
• pp.629-634
• /
• 2004

Continuous depth data are often required in applications of both onboard systems and maritime simulation. But data available are usually discrete and irregularly distributed. Based on the neuron network technique, methods of interpolation to the charted depth are suggested in this paper. Two algorithms based on Levenberg-Marquardt back-propaganda and radial-basis function networks are investigated respectively. A dynamic neuron network system is developed which satisfies both real time and mass processing applications. Using hyperbolic paraboloid and typical chart area, effectiveness of the algorithms is tested and error analysis presented. Special process in practical applications such as partition of lager areas, normalization and selection of depth contour data are also illustrated.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.08a
• /
• pp.37-44
• /
• 2004

Continuous depth data are often required in applications of both onboard systems and maritime simulation. But data available are usually discrete and irregularly distributed. Based on the neuron network technique, methods of interpolation to the charted depth are suggested in this paper. Two algorithms based on Levenberg-Marquardt back-propaganda and radial-basis function networks are investigated respectively. A dynamic neuron network system is developed which satisfies both real time and mass processing applications. Using hyperbolic paraboloid and typical chart area, effectiveness of the algorithms is tested and error analysis presented. Special process in practical applications such as partition of lager areas, normalization and selection of depth contour data are also illustrated.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2001.10a
• /
• pp.1-9
• /
• 2001

scale genomic and postgenomic data means that many of the challenges in biomedical research are now challenges in computational sciences and information technology. The informatics revolutions both in clinical informatics and bioinformatics will change the current paradigm of biomedical sciences and practice of clinical medicine, including diagnostics, therapeutics, and prognostics. Postgenome informatics, powered by high throughput technologies and genomic-scale databases, is likely to transform our biomedical understanding forever much the same way that biochemistry did a generation ago. In this talk, 1 will describe how these technologies will in pact biomedical research and clinical care, emphasizing recent advances in biochip-based functional genomics. Basic data preprocessing with normalization and filtering, primary pattern analysis, and machine teaming algorithms will be presented. Issues of integrated biochip informatics technologies including multivariate data projection, gene-metabolic pathway mapping, automated biomolecular annotation, text mining of factual and literature databases, and integrated management of biomolecular databases will be discussed. Each step will be given with real examples from ongoing research activities in the context of clinical relevance. Issues of linking molecular genotype and clinical phenotype information will be discussed.

• Journal of KSNVE
• /
• v.6 no.1
• /
• pp.97-106
• /
• 1996

This paper presents systematic study of the experimental application of a free-interfaced component mode synthesis method. In the free-interfaced component mode synthesis method, an error the to truncated higher modes and neglected ineria loadings on a component from the connected component is inherent. Also, it is difficult to directly use experimental modal data in a modal synthesis method which links experimental model to finite-element model because of many inconsistencies between experimentally obtained and analytically obtained modal vectors and missing degrees-of-freedom (DOFs) such as rotational DOFs. In order to solve these problems, three methods, the first one based on attaching auxiliary weights to the connection points, the second one utillizing the normalization of experimental modal vector, and the third one generating smoothed and expanded experimental mode shapes, are studied in this paper. Finally, the study is illustrated for a flat-plate structure by using simulated and measured experimental data.

• IE interfaces
• /
• v.11 no.2
• /
• pp.119-124
• /
• 1998

This paper proposes a new part family classification system (IPFACS: Image Processing and Fuzzy ART based Clustering System), which incorporates image processing techniques and a modified fuzzy ART neural network algorithm. IPFACS can classify parts based on geometrical shape and manufacturing attributes, simultaneously. With a proper reduction and normalization of an image data through the image processing methods and adding method in the modified Fuzzy ART, different types of geometrical shape data and manufacturing attribute data can be simultaneously classified in the same system. IPFACS has been tested for an example set of hypothetical parts. The results show that IPFACS provides a good feasible approach to form families based on both geometrical shape and manufacturing attributes.

• Journal of Information Management
• /
• v.21 no.1
• /
• pp.76-92
• /
• 1990

This paper discusses automatic spelling correction in a point of view bibliographic Data Base production and information retrieval. Types of commonly detected spelling errors and impact of spelling errors in bibliographic data bases are described here. Document normalization, spelling verification, spelling correction and user interface for general construction of automatic spelling correction systems are described.