• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.181-188
• /
• 2024

Traditional profanity detection methods have limitations in identifying intentionally altered profanities. This paper introduces a new method based on Named Entity Recognition, a subfield of Natural Language Processing. We developed a profanity detection technique using sequence labeling, for which we constructed a dataset by labeling some profanities in Korean malicious comments and conducted experiments. Additionally, to enhance the model's performance, we augmented the dataset by labeling parts of a Korean hate speech dataset using one of the large language models, ChatGPT, and conducted training. During this process, we confirmed that filtering the dataset created by the large language model by humans alone could improve performance. This suggests that human oversight is still necessary in the dataset augmentation process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1868-1887
• /
• 2024

Recommendation systems research is a subfield of information retrieval, as these systems recommend appropriate items to users during their visits. Appropriate recommendation results will help users save time searching while increasing productivity at work, travel, or shopping. The problem becomes more difficult when the items are geographical locations on the ground, as they are associated with a wealth of contextual information, such as geographical location, opening time, and sequence of related locations. Furthermore, on social networking platforms that allow users to check in or express interest when visiting a specific location, their friends receive this signal by spreading the word on that online social network. Consideration should be given to relationship data extracted from online social networking platforms, as well as their impact on the geolocation recommendation process. In this study, we compare the similarity of geographic locations based on their distance on the ground and their correlation with users who have checked in at those locations. When calculating feature embeddings for users and locations, social relationships are also considered as attention signals. The similarity value between location and correlation between users will be exploited in the overall architecture of the recommendation model, which will employ graph convolution networks to generate recommendations with high precision and recall. The proposed model is implemented and executed on popular datasets, then compared to baseline models to assess its overall effectiveness.

• Journal of the Korean Society for information Management
• /
• v.21 no.1
• /
• pp.23-53
• /
• 2004

The purpose of this study is to analyze the identity and relationship of library and information science by exploring theoretical aspects of LIS research, including theory building and theory use. The sample of this study consists of 1,661 research articles published from 1984 to 2003 in two Korean and two American core LIS journals. Theory articles are analyzed with two scales, such as '4-degree of theory efficiency' and '5-degree of theory use' Each article is coded in terms of journal, country, publication year, subfield, and methodology of the article. and affiliation, department, and research experience of the first author. The theories used therein are coded according to their origin and age. Also, an author co-citation technique is applied to represent intellectual structure on a two-dimensional map, which has been constructed by theory use of LIS authors fur 20 years.

• The Korean Journal of Physiology and Pharmacology
• /
• v.10 no.4
• /
• pp.167-172
• /
• 2006

In the present study, we developed a simple method to predict the neuronal cell death in the mouse hippocampus and striatum following transient global forebrain ischemia by evaluating both cerebral blood flow and the plasticity of the posterior communicating artery (PcomA). Male C57BL/6 mice were anesthetized with halothane and subjected to bilateral occlusion of the common carotid artery (BCCAO) for 30 min. The regional cerebral blood flow (rCBF) was measured by laser Doppler flowmetry. The plasticity of PcomA was visualized by intravascular perfusion of India ink solution. When animals had the residual cortical microperfusion less than 15% as well as the smaller PcomA whose diameter was less than one third compared with that of basilar artery, neuronal damage in the hippocampal subfields including CA1, CA2, and CA4, and in the striatum was consistently observed. Especially, when mice met these two criteria, marked neuronal damage was observed in CA2 subfield of the hippocampus. In contrast, after transient BCCAO, neuronal damage was consistently produced in the striatum, dependent more on the degree of rCBF reduction than on the plasticity of PcomA. The present study provided simple and highly reproducible criteria to induce the neuronal cell death in the vulnerable mice brain areas including the hippocampus and striatum after transient global forebrain ischemia.

• The Korean Journal of Physiology and Pharmacology
• /
• v.20 no.2
• /
• pp.185-192
• /
• 2016

Ampicillin, a ${\beta}$-lactam antibiotic, dose-dependently protects neurons against ischemic brain injury. The present study was performed to investigate the neuroprotective mechanism of ampicillin in a mouse model of transient global forebrain ischemia. Male C57BL/6 mice were anesthetized with halothane and subjected to bilateral common carotid artery occlusion for 40 min. Before transient forebrain ischemia, ampicillin (200 mg/kg, intraperitoneally [i.p.]) or penicillin G (6,000 U/kg or 20,000 U/kg, i.p.) was administered daily for 5 days. The pretreatment with ampicillin but not with penicillin G significantly attenuated neuronal damage in the hippocampal CA1 subfield. Mechanistically, the increased activity of matrix metalloproteinases (MMPs) following forebrain ischemia was also attenuated by ampicillin treatment. In addition, the ampicillin treatment reversed increased immunoreactivities to glial fibrillary acidic protein and isolectin B4, markers of astrocytes and microglia, respectively. Furthermore, the ampicillin treatment significantly increased the level of glutamate transporter-1, and dihydrokainic acid (DHK, 10 mg/kg, i.p.), an inhibitor of glutamate transporter-1 (GLT-1), reversed the neuroprotective effect of ampicillin. Taken together, these data indicate that ampicillin provides neuroprotection against ischemia-reperfusion brain injury, possibly through inducing the GLT-1 protein and inhibiting the activity of MMP in the mouse hippocampus.

• Quality Improvement in Health Care
• /
• v.10 no.2
• /
• pp.204-215
• /
• 2003

Background : ICD-10 Classification, which is used domestically as well as internationally, has limited use in the clinical practice since it is developed for at disease statistics and epidemiology. Therefore, the purposes of this study were to improve the quality of diagnosis by constructing a new disease classification based on the diagnoses doctors currently make in the clinical setting and connecting this classification with OCS and EMR, and to meet the demands of doctors for high quality medical study data in medical research. Methods : The specialists in each ophthalmic subfield collected clinical diagnoses and abbreviations based on the ophthalmology textbooks and confirmed the classifications. Total number of clinical diagnoses collected was totaled 672, for which ideal diagnoses had been selected and a new model of disease classification model in connection with ICD-10 was constructed. The constructed classification of clinical diagnoses consisted of six steps: the first step was the classification by ophthalmic subspecialty field; the second to fifth steps were the detailed classification by each specialty field; the sixth step was the classification by site. Results : After introducing the new disease classification, research on the use and a pre-post comparison was conducted. The result from the research on the use of the clinical diagnoses in inpatient and outpatient care has shown a gradually increasing tendency. From the pre-post comparison of EMR discharge summary diagnoses, the result demonstrated that the diagnosis was stated correctly and in detail. Since the diagnosis was stated correctly, code classification became correct as well, which makes it possible to construct high quality medical DB. Conclusion : This construction of clinical diagnoses provides the medical team with high quality medical information. It is also expected to increase the accuracy and efficiency of service in the department of medical record and department of insurance investigation. In the future, if hospitals wish to construct a classification of clinical diagnosis and a standard proposal of clinical diagnosis is presented by a medical society, the standardization of diagnosis seems to be possible.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1196-1213
• /
• 2020

There is a growing interest in the development of smart environments through predicting the behaviors of inhabitants of smart spaces in the recent past. Various smart services are deployed in modern smart cities to facilitate residents and city administration. Prediction algorithms are broadly used in the smart fields in order to well equip the smart services for the future demands. Hence, an accurate prediction technology plays a vital role in the smart services. In this paper, we take out an extensive survey of smart spaces such as smart homes, smart farms and smart cars and smart applications such as smart health and smart energy. Our extensive survey is based on more than 400 articles and the final list of research studies included in this survey consist of 134 research papers selected using Google Scholar database for period of 2008 to 2018. In this survey, we highlight the role of prediction algorithms in each sub-domain of smart Internet of Things (IoT) environments. We also discuss the main algorithms which play pivotal role in a particular IoT subfield and effectiveness of these algorithms. The conducted survey provides an efficient way to analyze and have a quick understanding of state of the art work in the targeted domain. To the best of our knowledge, this is the very first survey paper on main categories of prediction algorithms covering statistical, heuristic and hybrid approaches for smart environments.

• Journal of the Korea Convergence Society
• /
• v.11 no.5
• /
• pp.1-8
• /
• 2020

Machine translation refers to a system where a computer translates a source sentence into a target sentence. There are various subfields of machine translation. APE (Automatic Post Editing) is a subfield of machine translation that produces better translations by editing the output of machine translation systems. In other words, it means the process of correcting errors included in the translations generated by the machine translation system to make proofreading. Rather than changing the machine translation model, this is a research field to improve the translation quality by correcting the result sentence of the machine translation system. Since 2015, APE has been selected for the WMT Shaed Task. and the performance evaluation uses TER (Translation Error Rate). Due to this, various studies on the APE model have been published recently, and this paper deals with the latest research trends in the field of APE.

• Journal of Korean Society of Archives and Records Management
• /
• v.24 no.2
• /
• pp.65-88
• /
• 2024

This pilot study explores a method of extracting metadata values and descriptions from records using named entity recognition (NER), a technique in natural language processing (NLP), a subfield of artificial intelligence. The study focuses on handwritten records from the Guro Industrial Complex, produced during the 1960s and 1970s, comprising approximately 1,200 pages and 80,000 words. After the preprocessing process of the records, which included digitization, the study employed a publicly available language API based on Google's Bidirectional Encoder Representations from Transformers (BERT) language model to recognize entity names within the text. As a result, 173 names of people and 314 of organizations and institutions were extracted from the Guro Industrial Complex's past records. These extracted entities are expected to serve as direct search terms for accessing the contents of the records. Furthermore, the study identified challenges that arose when applying the theoretical methodology of NLP to real-world records consisting of semistructured text. It also presents potential solutions and implications to consider when addressing these issues.

• International Journal of Heart Failure
• /
• v.6 no.1
• /
• pp.11-19
• /
• 2024

The prevalence of heart failure (HF) is increasing, necessitating accurate diagnosis and tailored treatment. The accumulation of clinical information from patients with HF generates big data, which poses challenges for traditional analytical methods. To address this, big data approaches and artificial intelligence (AI) have been developed that can effectively predict future observations and outcomes, enabling precise diagnoses and personalized treatments of patients with HF. Machine learning (ML) is a subfield of AI that allows computers to analyze data, find patterns, and make predictions without explicit instructions. ML can be supervised, unsupervised, or semi-supervised. Deep learning is a branch of ML that uses artificial neural networks with multiple layers to find complex patterns. These AI technologies have shown significant potential in various aspects of HF research, including diagnosis, outcome prediction, classification of HF phenotypes, and optimization of treatment strategies. In addition, integrating multiple data sources, such as electrocardiography, electronic health records, and imaging data, can enhance the diagnostic accuracy of AI algorithms. Currently, wearable devices and remote monitoring aided by AI enable the earlier detection of HF and improved patient care. This review focuses on the rationale behind utilizing AI in HF and explores its various applications.