• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2768-2787
• /
• 2023

As an important research direction of the application of computer science in the medical field, the automatic generation technology of radiology report has attracted wide attention in the academic community. Because the proportion of normal regions in radiology images is much larger than that of abnormal regions, words describing diseases are often masked by other words, resulting in significant feature loss during the calculation process, which affects the quality of generated reports. In addition, the huge difference between visual features and semantic features causes traditional multi-modal fusion method to fail to generate long narrative structures consisting of multiple sentences, which are required for medical reports. To address these challenges, we propose a multi-feature optimization Transformer (MFOT) for generating radiology reports. In detail, a multi-dimensional mapping attention (MDMA) module is designed to encode the visual grid features from different dimensions to reduce the loss of primary features in the encoding process; a feature pre-fusion (FP) module is constructed to enhance the interaction ability between multi-modal features, so as to generate a reasonably structured radiology report; a detail enhanced attention (DEA) module is proposed to enhance the extraction and utilization of key features and reduce the loss of key features. In conclusion, we evaluate the performance of our proposed model against prevailing mainstream models by utilizing widely-recognized radiology report datasets, namely IU X-Ray and MIMIC-CXR. The experimental outcomes demonstrate that our model achieves SOTA performance on both datasets, compared with the base model, the average improvement of six key indicators is 19.9% and 18.0% respectively. These findings substantiate the efficacy of our model in the domain of automated radiology report generation.

• The Journal of Korean Medicine
• /
• v.45 no.3
• /
• pp.91-102
• /
• 2024

Objectives: Recent trends in traditional Korean medicine (TKM) lung cancer treatment involve the administration of a few ready-made herbal formulas in batches. However, utilizing a TKM pathology-based formulation of herbs can fill in the gaps in holistic treatment that are often missed in a one-size-fits-all approach. The author aimed to analyze treatment trends between a traditional Chinese medicine (TCM) cancer treatment specialty book and a series of Korean lung cancer TKM treatment case reports. Methods: The frequently used pattern identification types, herbal formulas, and herbs in the lung cancer chapter of a TCM cancer treatment specialty book and case reports of TKM treatment of lung cancer were analyzed in a comparative manner. Results: Twenty-four pattern identification types for lung cancer were derived from the TCM book, and they were Phlegm-blood stasis, lung heat, and deficiency type. Six types of pattern identification types were derived from the 20 cases reports of TKM treatment, and they were blood stasis due to qi stagnation and deficiency type. Twelve cases were treated with ready-made anti-tumor herbal preparations without performing a pattern identification, accounting for two-thirds of the cases. Conclusions: The treatment of lung cancer in TCM is characterized by the use of pattern identification to formulate herbal formulas with simultaneous administration of anti-tumor herbs within the same formula. The treatment of lung cancer in TKM is relatively infrequent in its use of pattern identification. In addition, herbal formulas derived through the process of pattern identification and derived for anti-tumor purposes were often administered separately.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.287-316
• /
• 2023

As global energy crisis and the COVID-19 pandemic have emerged as social issues, there is a growing demand for companies to move away from profit-centric business models and embrace sustainable management that balances environmental, social, and governance (ESG) factors. ESG activities of companies vary across industries, and industry-specific weights are applied in ESG evaluations. Therefore, it is important to develop strategic management approaches that reflect the characteristics of each industry and the importance of each ESG factor. Additionally, with the stance of strengthened focus on ESG disclosures, specific guidelines are needed to identify and report on sustainable management activities of domestic companies. To understand corporate sustainability strategies, analyzing ESG reports and news articles by industry can help identify strategic characteristics in specific industries. However, each company has its own unique strategies and report structures, making it difficult to grasp detailed trends or action items. In our study, we analyzed ESG reports (2019-2021) and news articles (2019-2022) of six companies in the 'Finance,' 'Manufacturing,' and 'IT' sectors to examine the sustainability strategies of leading domestic ESG companies. Text mining techniques such as keyword frequency analysis and topic modeling were applied to identify industry-specific, ESG element-specific management strategies and issues. The analysis revealed that in the 'Finance' sector, customer-centric management strategies and efforts to promote an inclusive culture within and outside the company were prominent. Strategies addressing climate change, such as carbon neutrality and expanding green finance, were also emphasized. In the 'Manufacturing' sector, the focus was on creating sustainable communities through occupational health and safety issues, sustainable supply chain management, low-carbon technology development, and eco-friendly investments to achieve carbon neutrality. In the 'IT' sector, there was a tendency to focus on technological innovation and digital responsibility to enhance social value through technology. Furthermore, the key issues identified in the ESG factors were as follows: under the 'Environmental' element, issues such as greenhouse gas and carbon emission management, industry-specific eco-friendly activities, and green partnerships were identified. Under the 'Social' element, key issues included social contribution activities through stakeholder engagement, supporting the growth and coexistence of members and partner companies, and enhancing customer value through stable service provision. Under the 'Governance' element, key issues were identified as strengthening board independence through the appointment of outside directors, risk management and communication for sustainable growth, and establishing transparent governance structures. The exploration of the relationship between ESG disclosures in reports and ESG issues in news articles revealed that the sustainability strategies disclosed in reports were aligned with the issues related to ESG disclosed in news articles. However, there was a tendency to strengthen ESG activities for prevention and improvement after negative media coverage that could have a negative impact on corporate image. Additionally, environmental issues were mentioned more frequently in news articles compared to ESG reports, with environmental-related keywords being emphasized in the 'Finance' sector in the reports. Thus, ESG reports and news articles shared some similarities in content due to the sharing of information sources. However, the impact of media coverage influenced the emphasis on specific sustainability strategies, and the extent of mentioning environmental issues varied across documents. Based on our study, the following contributions were derived. From a practical perspective, companies need to consider their characteristics and establish sustainability strategies that align with their capabilities and situations. From an academic perspective, unlike previous studies on ESG strategies, we present a subdivided methodology through analysis considering the industry-specific characteristics of companies.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.31 no.4
• /
• pp.169-176
• /
• 2020

Exploring the risk factors of adolescent suicide is important for effective suicide prevention. This study explored the clustering of adolescent suicides based on six risk factors: mental disorder, broken family, depression, anxiety, previous suicide attempts, and deviant behaviors. Using 173 student suicide reports obtained from the Ministry of Education, we evaluated the associations between suicide and variables related to mental disorders; dysfunctional family life; depression and anxiety; previous suicide attempts; deviant behaviors such as drinking and smoking; and school life characteristics, including attendance and discipline, problems within the past year, and incidents prior to suicide. In addition, reports of warning signs just before suicide were included in the analysis. The two-stage cluster analysis classified the students into three clusters: the silent type (cluster 1; 48.55%), in which no risk factors were observed; environmental-risk type (cluster 2: 24.28%), which featured a high frequency of broken households, deviant behaviors such as smoking/drinking and running away from home; and depressive type (cluster 3: 27.17%), which featured a high frequency of mental health problems such as depression, anxiety, and suicide attempts. Identifying the sub-types of adolescent suicide may help to inform tailored suicide prevention and intervention strategies in school.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2005.04a
• /
• pp.680-687
• /
• 2005

This study presents a schema matching technique which can be applied to XML semantic model of structural calculation reports of steel-box bridges. The semantic model of structural calculation documents was developed by extracting the optimized common elements from the analyses of various existing structural calculation documents, and the standardized semantic model was schematized by using XML Schema. In addition, the similarity measure technique and the relaxation labeling technique were employed to develop the schema matching algorithm. The former takes into account the element categories and their features, and the latter considers the structural constraints in the semantic model. The standardized XML semantic model of steel-box bridge's structural calculation documents called target schema was compared with existing nonstandardized structural calculation documents called primitive schema by the developed schema matching algorithm Some application examples show the importance of the development of standardized target schema for structural calculation documents and the effectiveness and efficiency of schema matching technique in the examination of the degree of document standardization in structural calculation reports.

• Korean Journal of Adult Nursing
• /
• v.23 no.1
• /
• pp.10-19
• /
• 2011

Purpose: The purpose of this study was to evaluate the impact of a protocol of cryotherapy and Tai Chi on women with Fibrolmyalgia Syndrome. Methods: The study design was a pretest and posttest quasi-experimental, nonrandom assignment. The subjects were 48 outpatients with a diagnosis of fibromyalgia based on the American College of Rheumatology Standards. The setting was a University Medical Center in S city. The protocol was self administered ten times a week, for a two week period resulting in twenty treatments. Results: A protocol of cryotherapy and Tai Chi self-help program showed significant improvement in the fibromyalgia impact as measured by reports of physical impairment, feeing good, number of missed work days, ability to perform work, reports of pain, fatigue, rest, stiffness, anxiety and depression as reported by the comparison group (p<.001). No significant differences between the two regarding in reports of the tender points (p=.062). Conclusion: The results suggested that a protocol of cryotherapy and Tai Chi self-help program may be a promising multidisciplinary strategy for fibromyalgia patients.

• Journal of Oriental Neuropsychiatry
• /
• v.27 no.2
• /
• pp.77-87
• /
• 2016

Objectives This study was aimed to analyze the reports of qualitative research published in domestic Korean medicine journals.Methods Eleven published qualitative research studies were selected for analysis. Selected reports were analyzed by Consolidated Criteria for Reporting Qualitative Research (COREQ), a reporting guideline for qualitative research.Results In the 1st domain, descriptions of personal characteristics, interviewer's bias or assumption were insufficient. In the 2nd domain, descriptions such as presence of non-participants, research questions for the interview guidelines, data saturation and transcript return to participants were insufficient. In the 3rd domain, descriptions of items related to number of data coder, participants evaluating the finding, and clarity of minor themes were insufficient.Conclusions Qualitative studies in Korean Medicine have increased. COREQ should be considered by investigators who report qualitative research, in order to improve the quality of research.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.6
• /
• pp.61-71
• /
• 2020

The study examines the impact of corporate governance mechanisms, such as board characteristics on corporate social responsibility disclosure (CSRD). The data on CSRD items and board characteristics have been collected by content analysis of the annual reports of 30 publicly-listed banks in Bangladesh covering six years, from 2013 to 2018. More specifically, the directors' report, the chairman's statement, notes to the financial statement and CSR disclosure reports included in annual reports were used to collect the CSRD data. The empirical analysis applies the ordinary least square and the generalized method of moments. The results of the study have revealed that board size, board independence, female board member, and foreign directors have a significant positive impact on CSRD. By contrast, political directors and audit committee size have a negative impact on CSRD. Interestingly, accounting experts on boards ensure more CSRD as they curb the influence of politicians on the board. Thus, it is better to increase accounting experts and decrease politicians on the board. These findings provide valuable insights into the process of forming a suitable CSR policy by connecting the efforts of the board, government, and regulatory bodies to enhance the performance of banks to CSR as well as to CSRD.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.2910-2925
• /
• 2017

Inadequate and inappropriate intake of food is known to cause various health issues and diseases. Due to lack of concise information about healthy diet, people have to rely on medicines instead of taking preventive measures in food intake. Due to diversity in food components and large number of dietary sources, it is challenging to perform real-time selection of diet patterns that must fulfill one's nutrition needs. Particularly, selection of proper diet is critical for patients suffering from various diseases. In this article, we highlight the issue of selection of proper diet that must fulfill patients' nutrition requirements. To address this issue, we present a cloud based food recommendation system, called Diet-Right, for dietary recommendations based on users' pathological reports. The model uses ant colony algorithm to generate optimal food list and recommends suitable foods according to the values of pathological reports. Diet-Right can play a vital role in controlling various diseases. The experimental results show that compared to single node execution, the convergence time of parallel execution on cloud is approximately 12 times lower. Moreover, adequate accuracy is attainable by increasing the number of ants.

• The Journal of the Korea Contents Association
• /
• v.16 no.8
• /
• pp.278-291
• /
• 2016

This study examined research trends via network analyses of keywords appeared in academic research articles about news reports in South Korea during the last 10 years from 2006 to 2015. Keyword network analyses of 4410 keywords from 1108 articles suggested that framing, agenda setting, third-person effect, selective exposure, and uses and gratification were main theories but most studies used framing theory. Research areas included news reports on politics, economics, science, world issues, or tour. However, research on news reports covering culture, sports or daily life were not identified. In terms of media, research on both traditional and emerging media were ample. Research on broadcasting new, online news, and social media were frequently observed.