• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4976-4994
• /
• 2018

The diffusion-based salient object detection methods have shown excellent detection results and more efficient computation in recent years. However, the current diffusion-based salient object detection methods still have disadvantage of detecting the object appearing at the image boundaries and different scales. To address the above mentioned issues, this paper proposes a multi-scale diffusion-based salient object detection algorithm with background and objectness seeds. In specific, the image is firstly over-segmented at several scales. Secondly, the background and objectness saliency of each superpixel is then calculated and fused in each scale. Thirdly, manifold ranking method is chosen to propagate the Bayessian fusion of background and objectness saliency to the whole image. Finally, the pixel-level saliency map is constructed by weighted summation of saliency values under different scales. We evaluate our salient object detection algorithm with other 24 state-of-the-art methods on four public benchmark datasets, i.e., ASD, SED1, SED2 and SOD. The results show that the proposed method performs favorably against 24 state-of-the-art salient object detection approaches in term of popular measures of PR curve and F-measure. And the visual comparison results also show that our method highlights the salient objects more effectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.1886-1908
• /
• 2020

With the technical advances, the amount of big data is increasing day-by-day such that the traditional software tools face a burden in handling them. Additionally, the presence of the imbalance data in big data is a massive concern to the research industry. In order to assure the effective management of big data and to deal with the imbalanced data, this paper proposes a new indexing algorithm for retrieving big data in the MapReduce framework. In mappers, the data clustering is done based on the Sparse Fuzzy-c-means (Sparse FCM) algorithm. The reducer combines the clusters generated by the mapper and again performs data clustering with the Sparse FCM algorithm. The two-level query matching is performed for determining the requested data. The first level query matching is performed for determining the cluster, and the second level query matching is done for accessing the requested data. The ranking of data is performed using the proposed Monarch chaotic whale optimization algorithm (M-CWOA), which is designed by combining Monarch butterfly optimization (MBO) [22] and chaotic whale optimization algorithm (CWOA) [21]. Here, the Parametric Enabled-Similarity Measure (PESM) is adapted for matching the similarities between two datasets. The proposed M-CWOA outperformed other methods with maximal precision of 0.9237, recall of 0.9371, F1-score of 0.9223, respectively.

• Language and Information
• /
• v.14 no.2
• /
• pp.159-181
• /
• 2010

This paper presents a hybrid approach to the sentiment analysis of online texts. The sentiment of a text refers to the feelings that the author of a text has towards a certain topic. Many existing approaches employ either a pattern-based approach or a machine learning based approach. The former shows relatively high precision in classifying the sentiments, but suffers from the data sparseness problem, i.e. the lack of patterns. The latter approach shows relatively lower precision, but 100% recall. The approach presented in the current work adopts the merits of both approaches. It combines the pattern-based approach with the machine learning based approach, so that the relatively high precision and high recall can be maintained. Our experiment shows that the hybrid approach improves the F-measure score for more than 50% in comparison with the pattern-based approach and for around 1% comparing with the machine learning based approach. The numerical improvement from the machine learning based approach might not seem to be quite encouraging, but the fact that in the current approach not only the sentiment or the polarity information of sentences but also the additional information such as target of sentiments can be classified makes the current approach promising.

• Women's Health Nursing
• /
• v.16 no.1
• /
• pp.87-94
• /
• 2010

Purpose: The purpose of this study was to examine the effects of a 16-week Self-help Tai Chi for Arthritis (SHTC) combined with health education for Korean American older women. Methods: This research was a designed quasiexperimental pre-posttest. Forty one women aged 55~79 were recruited 20 in SHTC group 21 in control group and, but twelve in SHTC group and thirteen in control group were left after 16 weeks. SHTC group was educated for 1 hour health education and 1hour TCA, once a week during 16 wks. Measurements for comparison were taken three times, at baseline, 8 wks and 16wks. The effect were evaluated with self-efficacy, shoulder flexibility, back flexibility, both hand grip strength and standing balance with closed eyes. Results: All variables except for left hand grip strength at baseline had significant homogeneity between both groups. After 16 weeks intervention, there was a significant interaction effect of time and group on right hand grip strength by repeated measure of ANOVA (F=3.398, p=.044). No significant interaction effects were found on self-efficacy, shoulder and back flexibility, left hand grip strength and standing balance with closed eyes. Conclusion: I can suggest this self-help Tai Chi program may be effective partially, but further research is needed to establish the best times and periods to intervene for a better effect.

• Korean Journal of Adult Nursing
• /
• v.16 no.1
• /
• pp.49-59
• /
• 2004

Purpose: This study is a descriptive research study to measure the quality of life of those who suffer from breast cancer and take the chemotherapy. Method: The Subjects were 70 breast cancer patients who took the chemotherapy from September 2 to October 31, 2003. Quality of life was measured by Ferrell's measurements. Result: Quality of life indicators were spiritual domain=6.44, physical domain=5.45, social domain=4.15, and mental domain=3. 95. Whole quality of life was 4. 68 out of 10 points. The quality of life of those with a practicing religion was significantly higher than those without(F=3.88, P=0.026). Subjects who were less than 2 months post-operation had higher points in the physical domain than those who were more than 2 months post-operation (t= 2.76, p=0.007). Subjects who had less than 4 treatments of chemotherapy had higher points in the physical domain than those who had more than 4 treatments of chemotherapy (t=2.03, p=0.046). Conclusion: The results of this study serve as a meaningful source to promote quality of life of breast cancer patients who undergo chemotherapy. The results can also be applied to the development of education programs and counseling materials for chemotherapy patients. Health care strategy can also raise the quality of life of brest cancer patients.

• Korean Journal of Adult Nursing
• /
• v.24 no.1
• /
• pp.52-63
• /
• 2012

Purpose: The purpose of this study was to measure the quality of life (QOL) and to identify the factors influencing QOL in gynecological cancer patients. Methods: The subjects of this study were 242 people who were receiving medical therapy or follow-up after surgery from one general hospital in Daegu. Data were collected from August 1, 2010 to January 31, 2011. A questionnaire including questions on QOL, distress score, distress problem, depression, anxiety, insomnia, perceived health status and body image were completed by the subjects. Results: The mean score of QOL was $70.68{\pm}13.40$. Religion, job, presence of spouse, level of education, household income, financial compensation, disease stage and recurrence were the significant factors related to QOL. Distress score, distress problem, depression, anxiety, insomnia, perceived health status and body image were also significant factors influencing QOL. Sixty eight percent of the variance in subjective overall QOL can be explained by body image, distress problem, distress score, anxiety, level of education and perceived health status (Cum $R^2$=0.689, F=76.316, $p$ <.001). Body image was the most important factor related to QOL. Conclusion: An integrative care program which includes general, disease-related and psychosocial characteristics of patients is essential to improve QOL in gynecological cancer patients.

• Fashion, Industry and Education
• /
• v.14 no.2
• /
• pp.47-59
• /
• 2016

This research is concerned with comparing fluctuation in the Korean and the US economies in order to ascertain the degree to which the former is influenced by changes in the latter. The aim of this research is to explore business cycles, to examine consumer expenditure in Korea and the US, and to discover the relationships between business fluctuation indexes and overall expenditure. Statistical data from the national statistics of Korea and the US during period from 1990 to 2015 were used. The instrument included a measure of GDP, unemployment rates, GDP deflator rate (inflation rates), and household income and expenditure. For the average annual household expenditures, food, apparel and transportation expenditure data were compared across the two countries. Data were collected separately from different (though comparable) sources and were analyzed using relatively straight forward statistical techniques. It was found that Korean and the US consumers' income and expenditure were greatly affected by economic fluctuations. Total expenditure and the expenditures for food and transportation were much influenced by business fluctuation in the US, whereas, the expenditures for apparel were much influenced by business fluctuation in Korea.

• Journal of ILASS-Korea
• /
• v.2 no.4
• /
• pp.7-14
• /
• 1997

Laser Raman scattering method has been applied to measure equivalence ratio of methane/air mixture in injected spray. We used high power KrF excimer laser$(\lambda=248nm)$ and a high gain ICCD camera to capture low intensity signal. Raman shifts and Raman scattering cross -sections of $H_2,\;O_2,\;N_2,\;CO_2,\;CH_4\;and\;C_3H_8$ are measured precisely. Our results show an excellent agreement with those of other groups. Mole fraction measurement of $O_2\;and\;N_2$ from air shows that $O_2:N_2=0.206:0.794$. We used gas injector which was operated at 1 bar. Methane is used as a fuel. Spray region is $10mm\times37mm$ and this region is divided into 80 points. In Raman signals are obtained and ensemble averaged for each point. 3-d and contour plot of distribution of equuivalence ratio is presented. Our measured results show that the equivalence ratio of methane/air mixture in methane-rich region is reasonable. However, more study is necessary for methane-lean region because background noise level is almost same as Raman intensity of methane.

• Annual Conference on Human and Language Technology
• /
• 2005.10a
• /
• pp.7-12
• /
• 2005

본 논문은 은닉 마코프 모델(hidden Markov Model: HMM)을 2 단계로 적용하여 논문 모집공고(Call-for-Paper: CFP)에서 필요한 정보를 추출하는 방법을 제안한다. HMM은 순차적인 흐름의 정보를 담고 있는 데이터를 잘 설명할 수 있으며 CFP가 담고 있는 정보에는 순서가 있기 때문에, CFP를 HMM으로 설명할 수 있다. 하지만, 문서를 전체적으로(global) 파악하는 HMM만으로는 정보의 정확한 경계를 파악할 수 없다. 따라서 첫 번째 단계로 CFP문서에서 구(phrase) 단위를 구성하는 단어의 열에 대한 HMMs을 통해 국부적으로(local) 정보의 경계와 대강의 종류를 파악한다. 그리고 두 번째 단계에서 전체적인 문서의 내용 흐름에 근거하여 구축된 HMM을 이용하여 그 정보가 세부적으로 어떤 종류의 정보인지 정한다. PASCAL challenge에서 제공받은 Cff 말뭉치에 대한 첫 번째 단계의 실험 결과, 0.60의 재현률과 0.61의 정확률을 보였으며, 정확률과 재현률을 바탕으로 F-measure를 측정한 결과 0.60이었다.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.127-132
• /
• 2014

본 논문은 위키피디아로부터 한국어-영어 간 병렬 문장을 추출하기 위해 이질적 언어 자원의 순차적 매칭을 적용한 유사도 계산 방법을 제안한다. 선행 연구에서는 병렬 문장 추출을 위해 언어 자원별로 유사도를 계산하여 선형 결합하였고, 토픽모델을 이용해 추정한 단어의 토픽 분포를 유사도 계산에 추가로 이용함으로써 병렬 문장 추출 성능을 향상시켰다. 하지만, 이는 언어 자원들이 독립적으로 사용되어 각 언어자원이 가지는 오류가 문장 간 유사도 계산에 반영되는 문제와 관련이 적은 단어 간의 분포가 유사도 계산에 반영되는 문제가 있다. 본 논문에서는 이질적인 언어 자원들을 이용해 순차적으로 단어를 매칭함으로써 언어 자원들의 독립적인 사용으로 각 자원의 오류가 유사도에 반영되는 문제를 해결하였고, 관련이 높은 단어의 분포만을 유사도 계산에 이용함으로써 관련이 적은 단어의 분포가 반영되는 문제를 해결하였다. 실험을 통해, 언어 자원들을 이용해 순차적으로 매칭한 유사도 계산 방법은 선행 연구에 비해 F1-score 48.4%에서 51.3%로 향상된 성능을 보였고, 관련이 높은 단어의 분포만을 유사도 계산에 이용한 방법은 약 10%에서 34.1%로 향상된 성능을 얻었다. 마지막으로, 제안한 유사도 방법들을 결합함으로써 선행연구의 51.6%에서 2.7%가 향상된 54.3%의 성능을 얻었다.