• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.5
• /
• pp.2590-2606
• /
• 2017

Generally, research of classical image classification algorithms assume that training data and testing data are derived from the same domain with the same distribution. Unfortunately, in practical applications, this assumption is rarely met. Aiming at the problem, a domain adaption image classification approach based on multi-sparse representation is proposed in this paper. The existences of intermediate domains are hypothesized between the source and target domains. And each intermediate subspace is modeled through online dictionary learning with target data updating. On the one hand, the reconstruction error of the target data is guaranteed, on the other, the transition from the source domain to the target domain is as smooth as possible. An augmented feature representation produced by invariant sparse codes across the source, intermediate and target domain dictionaries is employed for across domain recognition. Experimental results verify the effectiveness of the proposed algorithm.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.127-136
• /
• 2020

This paper presents an environment for rule-based English-Korean machine translation system, which supports the translation domain adaptation and the continuous translation quality improvement. For the purposes, corpus is essential, from which necessary information for translation will be acquired. The environment consists of a corpus construction part and a translation knowledge extraction part. The corpus construction part crawls news articles from some newspaper sites. The extraction part builds the translation knowledge such as newly-created words, compound words, collocation information, distributional word representations, and so on. For the translation domain adaption, the corpus for the domain should be built and the translation knowledge should be constructed from the corpus. For the continuous improvement, corpus needs to be continuously expanded and the translation knowledge should be enhanced from the expanded corpus. The proposed web-based environment is expected to facilitate the tasks of domain adaptation and translation system improvement.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.2
• /
• pp.519-528
• /
• 2016

In order to achieve fast computational speed with good visual quality of output video, we propose a frequency domain based new fractal video compression scheme. Normalized cross correlation is used to find the structural self similar domain block for the input range block. To increase the searching speed, cross correlation is implemented in the frequency domain using FFT with one computational operation for all the domain blocks instead of individual block wise calculations. The encoding time is further minimized by applying rotation and reflection DFT properties to the IFFT of zero padded range blocks. The energy of overlap small size domain blocks is pre-computed for the entire reference frame and retaining the energies of the overlapped search window portion of previous adjacent block. Quadtree decompositions are obtained by using domain block motion compensated prediction error as a threshold to control the further partitions of the block. It provides a better level of adaption to the scene contents than fixed block size approach. The result shows that, on average, the proposed method can raise the encoding speed by 48.8 % and 90 % higher than NHEXS and CPM/NCIM algorithms respectively. The compression ratio and PSNR of the proposed method is increased by 15.41 and 0.89 dB higher than that of NHEXS on average. For low bit rate videos, the proposed algorithm achieve the high compression ratio above 120 with more than 31 dB PSNR.

• Asian-Australasian Journal of Animal Sciences
• /
• v.26 no.8
• /
• pp.1144-1151
• /
• 2013

In this study, protein domains with cellulase activity in goat rumen microbes were investigated using metagenomic and bioinformatic analyses. After the complete genome of goat rumen microbes was obtained using a shotgun sequencing method, 217,892,109 pair reads were filtered, including only those with 70% identity, 100-bp matches, and thresholds below $E^{-10}$ using METAIDBA. These filtered contigs were assembled and annotated using blastN against the NCBI nucleotide database. As a result, a microbial community structure with 1431 species was analyzed, among which Prevotella ruminicola 23 bacteria and Butyrivibrio proteoclasticus B316 were the dominant groups. In parallel, 201 sequences related with cellulase activities (EC.3.2.1.4) were obtained through blast searches using the enzyme.dat file provided by the NCBI database. After translating the nucleotide sequence into a protein sequence using Interproscan, 28 protein domains with cellulase activity were identified using the HMMER package with threshold E values below $10^{-5}$. Cellulase activity protein domain profiling showed that the major protein domains such as lipase GDSL, cellulase, and Glyco hydro 10 were present in bacterial species with strong cellulase activities. Furthermore, correlation plots clearly displayed the strong positive correlation between some protein domain groups, which was indicative of microbial adaption in the goat rumen based on feeding habits. This is the first metagenomic analysis of cellulase activity protein domains using bioinformatics from the goat rumen.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.709-712
• /
• 1996

Generating a project network of a specific construction project is very time consuming and difficult task in the field. To effectiviely automate and support the planning process, we design a case-based project planning expert system inspired by the fact a human expert project planner uses previous cases for planning a new project. A construction project case consist of its specific characteristics and the corresponding project network (i.e. project plan). Using frame based representation. we represent the project features affecting the progress network and the entities composing the project plan such as the buildings, construction methods, WBS (work breakdown structure), activities, and resources. The project planning process runs through most similar case retrieval, case adaptation, and user requirement satisfaction. We represent the construction domain knowledge for each procedure using constraints and rules. We develop the methodology for constraint-based case adaption. Case adaptation process mainly consist of activity generation/deletion and predecence constraint satisfaction, for which we develop the dynamic constraint generation method and connect user-level requirement representation the system-level network modification knowledge. The methodology is being applied to the prototype for apartment construction project planning.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.65-72
• /
• 2007

In this study, we used nondestructive test based on ultrasonic test as inspection method and compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as pattern recognition algorithm of weld flaws. For this purpose, variables are applied the same to two algorithms. Where, feature variables are zooming flaw signals of reflected whole signals from weld flaws in time domain. Through this process, we compared advantages/ disadvantages of two algorithms and confirmed application methods of two algorithms.

• Journal of The Korean Association of Information Education
• /
• v.16 no.2
• /
• pp.173-180
• /
• 2012

This study looks for the requirements for adaptive courseware and provides background for developing effective adaptive courseware. Most adaptive courseware does not adequately reflect the requirements of learners. If it properly reflected learners' requirements well, it could be used more effectively. therefore, this study analyzes and suggests the requirements of an adaptive courseware for pre-service teachers who are majoring in computer education. The study methods were factor analysis and frequency analysis through survey. The results show that the important elements of an adaptive courseware are a learning style designed according to individual differences as well as an instruction model appropriate to the subject domain. The study examined adaption by learner level, by learning objective, by learning style, by method of learning content, and by learning history in that order. Therefore while the most of adaptive courseware support learning style; we propose that the adaptive courseware will support learning objects and instruction model as well.

• Molecules and Cells
• /
• v.42 no.2
• /
• pp.135-142
• /
• 2019

OCT4, also known as POU5F1 (POU domain class 5 transcription factor 1), is a transcription factor that acts as a master regulator of pluripotency in embryonic stem cells and is one of the reprogramming factors required for generating induced pluripotent stem cells. The human OCT4 encodes three isoforms, OCT4A, OCT4B, and OCT4B1, which are generated by alternative splicing. Currently, the functions and expression patterns of OCT4B remain largely unknown in malignancies, especially in human glioblastomas. Here, we demonstrated the function of OCT4B in human glioblastomas. Among the isoform of OCT4B, OCT4B-190 ($OCT4B^{19kDa}$) was highly expressed in human glioblastoma stem cells and glioblastoma cells and was mainly detected in the cytoplasm rather than the nucleus. Overexpression of $OCT4B^{19kDa}$ promoted colony formation of glioblastoma cells when grown in soft agar culture conditions. Clinical data analysis revealed that patients with gliomas that expressed OCT4B at high levels had a poorer prognosis than patients with gliomas that expressed OCT4B at low levels. Thus, $OCT4B^{19kDa}$ may play a crucial role in regulating cancer cell survival and adaption in a rigid environment.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.79-104
• /
• 2020

Recently, as deep learning has attracted attention, the use of deep learning is being considered as a method for solving problems in various fields. In particular, deep learning is known to have excellent performance when applied to applying unstructured data such as text, sound and images, and many studies have proven its effectiveness. Owing to the remarkable development of text and image deep learning technology, interests in image captioning technology and its application is rapidly increasing. Image captioning is a technique that automatically generates relevant captions for a given image by handling both image comprehension and text generation simultaneously. In spite of the high entry barrier of image captioning that analysts should be able to process both image and text data, image captioning has established itself as one of the key fields in the A.I. research owing to its various applicability. In addition, many researches have been conducted to improve the performance of image captioning in various aspects. Recent researches attempt to create advanced captions that can not only describe an image accurately, but also convey the information contained in the image more sophisticatedly. Despite many recent efforts to improve the performance of image captioning, it is difficult to find any researches to interpret images from the perspective of domain experts in each field not from the perspective of the general public. Even for the same image, the part of interests may differ according to the professional field of the person who has encountered the image. Moreover, the way of interpreting and expressing the image also differs according to the level of expertise. The public tends to recognize the image from a holistic and general perspective, that is, from the perspective of identifying the image's constituent objects and their relationships. On the contrary, the domain experts tend to recognize the image by focusing on some specific elements necessary to interpret the given image based on their expertise. It implies that meaningful parts of an image are mutually different depending on viewers' perspective even for the same image. So, image captioning needs to implement this phenomenon. Therefore, in this study, we propose a method to generate captions specialized in each domain for the image by utilizing the expertise of experts in the corresponding domain. Specifically, after performing pre-training on a large amount of general data, the expertise in the field is transplanted through transfer-learning with a small amount of expertise data. However, simple adaption of transfer learning using expertise data may invoke another type of problems. Simultaneous learning with captions of various characteristics may invoke so-called 'inter-observation interference' problem, which make it difficult to perform pure learning of each characteristic point of view. For learning with vast amount of data, most of this interference is self-purified and has little impact on learning results. On the contrary, in the case of fine-tuning where learning is performed on a small amount of data, the impact of such interference on learning can be relatively large. To solve this problem, therefore, we propose a novel 'Character-Independent Transfer-learning' that performs transfer learning independently for each character. In order to confirm the feasibility of the proposed methodology, we performed experiments utilizing the results of pre-training on MSCOCO dataset which is comprised of 120,000 images and about 600,000 general captions. Additionally, according to the advice of an art therapist, about 300 pairs of 'image / expertise captions' were created, and the data was used for the experiments of expertise transplantation. As a result of the experiment, it was confirmed that the caption generated according to the proposed methodology generates captions from the perspective of implanted expertise whereas the caption generated through learning on general data contains a number of contents irrelevant to expertise interpretation. In this paper, we propose a novel approach of specialized image interpretation. To achieve this goal, we present a method to use transfer learning and generate captions specialized in the specific domain. In the future, by applying the proposed methodology to expertise transplant in various fields, we expected that many researches will be actively conducted to solve the problem of lack of expertise data and to improve performance of image captioning.

• Child Health Nursing Research
• /
• v.2 no.1
• /
• pp.69-92
• /
• 1996

The purpose of study was : 1) to analyze the trend of research on the family with chronically ill children in Korea, 2) to suggest direction for future study on the family with chronically ill children, and contributing to the use of intervention in family nursing practice. Research studies on the family with chronically ill children were selected from the Korean Nusre, the Korean Nurses' Academic Society Journal, and from dissertations, which were conducted between 1975 and 1995. The total numbers of the studies were 35. These studies were analyzed for 1)time of publication or presentation, 2)research design, 3)characteristics of subjects, 4) type of chronic disease, 5)main concepts, 6)measurement tool, 7) the sis for a degree or nondegree, 8) result of correlational studies. The findings of the analysis were as follows : 1) The numbers of studies on the family with chronically ill children have increas rapidly the early 1990's. In research design, the numbers of survey research studies were the highest. Especially, the most frequently research design was the correlational survey. There were 19 correlational studies(25.7%) during the early 1990's. 2) The subjects in 16 studies(45.7%) were mother of chronically ill children and, in 8 studies (22.9% ) were their parents. 3) In most types of chronic diseases, there were 14 hematooncologic disease(32.6%) and 14 hadicapped children (32.6% ). 4) Frequently used research concepts were stress, degree of coping or way of coping, social support, parents' support, family functioning, intensity of family and family adaptation. 5) Acceding to the results of correlational studies, the more family stress was higher the more degree of coping, family functioning, intensity of family and degree of family adaption was lower. The more degree of social support was higher the more stress was lower and degree of coping, family functioning and intensity of family was higher. The more family functioning was higher the more intensity of family and family adaptation was higher. 6) 24 researches on the family with chronically ill children were done for a thesis for a degree and 11 were nondegree research studies. The following suggestions are made based on the above findings : 1) The pattern of these studies related to the family with chronically ill children in domain of Nursing need to be compared with trend in other domains. 2) More replicated research on the family with chronically ill children is needed to develop family nursing intervention and prove the effect of that and more qualitative research on the family with chronically ill children is needed to comprehensive indepth the family with chronically ill children. 3) Further research on the family with chronically ill children is needed to verify subjects and type of chronic disease, develop applicable measurement tools in Korea and identify relation between other concepts. 4) Family nursing researchers should make an effort to apply research result in various clinical settings and community settings, and try to carry out not only team research with clinical nurse but also other multidisciplinary researcher related to the family.