• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1800-1817
• /
• 2022

With the development of the economy and the improvement of living standards, the hot issues in the subject area have become the main research direction, and the mining of the hot issues in the subject currently has problems such as a large amount of data and a complex algorithm structure. Therefore, in response to this problem, this study proposes a method for extracting hot keywords in scientific journals based on the improved BERT model.It can also provide reference for researchers,and the research method improves the overall similarity measure of the ensemble,introducing compound keyword word density, combining word segmentation, word sense set distance, and density clustering to construct an improved BERT framework, establish a composite keyword heat analysis model based on I-BERT framework.Taking the 14420 articles published in 21 kinds of social science management periodicals collected by CNKI(China National Knowledge Infrastructure) in 2017-2019 as the experimental data, the superiority of the proposed method is verified by the data of word spacing, class spacing, extraction accuracy and recall of hot keywords. In the experimental process of this research, it can be found that the method proposed in this paper has a higher accuracy than other methods in extracting hot keywords, which can ensure the timeliness and accuracy of scientific journals in capturing hot topics in the discipline, and finally pass Use information technology to master popular key words.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.17-25
• /
• 2022

Recently the massive amount of data has been generated because of the number of edge devices increases. And especially, the number of raw unstructured HTML documents has been increased. Therefore, MRC(Machine Reading Comprehension) in which a natural language processing model finds the important information within an HTML document is becoming more important. In this paper, we propose HTDE(HTML Tag Depth Embedding Method), which allows the BERT to train the depth of the HTML document structure. HTDE makes a tag stack from the HTML document for each input token in the BERT and then extracts the depth information. After that, we add a HTML embedding layer that takes the depth of the token as input to the step of input embedding of BERT. Since tokenization using HTDE identifies the HTML document structures through the relationship of surrounding tokens, HTDE improves the accuracy of BERT for HTML documents. Finally, we demonstrated that the proposed idea showing the higher accuracy compared than the accuracy using the conventional embedding of BERT.

• Acta Via Serica
• /
• v.7 no.2
• /
• pp.109-132
• /
• 2022

Two of the main elements of Persian tangible heritage are rugs and gardens, which have evolved together from the dawn of Iranian history. Emerging from the same system of thought and geographical location, together they represent the Persians' world views, desires, dreams, and design paradigms. In this study, the Persian Garden's patterns, elements, typology, and meanings are introduced and compared with the same aspects of Persian rugs. This paper uses a qualitative comparative methodology to analyze rugs' designs and patterns in relation to Persian Gardens' design principles. Data is collected primarily through library study and observation. The author uses two categories for comparison: meanings and forms. First, the author identifies underlying meanings common to the two art forms and then introduces form, function, and general principal patterns into the analysis. There is a type of rug pattern, known as Chahar-Bagh (literally, "four gardens"), that mirrors a garden design, down to the details, which is the focus of this paper. Additionally, other representations of Persian Gardens in rug design, such as Shekargah ("hunting pattern"), are discussed, as are other rug patterns with fewer elements borrowed from garden design. The paper also considers several motifs that represent flora common in gardening on the Iranian plateau, some of which have symbolic meanings dating to the Zoroastrian era. By comparing these two mediums of art (garden and rug) in the context of Persian history and geography, it becomes clear that the Persian rug design, in its roots, is an attempt to bring a garden into interior space. The study shows that the forms, patterns, and meanings reflected in Persian rugs render the study of their designs incomplete without considering the history of gardens.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.6
• /
• pp.433-439
• /
• 2022

Muscle fatigue models to predict maximum endurance time (MET) are broadly classified as either 'empirical' or 'theoretical'. Empirical models are based on fitting experimental data and theoretical models on mathematical representations of physiological process. This paper examines the effectiveness of dynamic muscle fatigue model as theoretical model to predict maximum endurance time during forearm isometric contraction. Forty volunteers (20 females, 20 males) are participated in this study. Empirical models (exponential model and power model) and theoretical model (dynamic muscle fatigue model) are used to compare. Mean absolute deviation (MAD), correlation coefficient (r) and intraclass correlation (ICC) are calculated between theoretical model and empirical models. MAD are below 3.5%p, r and ICC are above 0.93 and 0.87, respectively. This results demonstrate that dynamic muscle fatigue model as theoretical model is valid to predict MET.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3836-3854
• /
• 2022

The student group division is benefit for universities to do the student management based on the group profile. With the widespread use of student smart cards on campus, especially where students living in campus residence halls, students' daily activities on campus are recorded with information such as smart card swiping time and location. Therefore, it is feasible to depict the students with the daily activity data and accordingly group students based on objective measuring from their campus behavior with some regular student attributions collected in the management system. However, it is challenge in feature representation due to diverse forms of the student data. To effectively and comprehensively represent students' behaviors for further student group division, we proposed to adopt activity data from student smart cards and student attributes as input data with taking account of activity and attribution relationship types from different perspective. Specially, we propose a novel student group division method based on a multi-view student attribute heterogeneous information network (MSA-HIN). The network nodes in our proposed MSA-HIN represent students with their multi-dimensional attribute information. Meanwhile, the edges are constructed to characterize student different relationships, such as co-major, co-occurrence, and co-borrowing books. Based on the MSA-HIN, embedded representations of students are learned and a deep graph cluster algorithm is applied to divide students into groups. Comparative experiments have been done on a real-life campus dataset collected from a university. The experimental results demonstrate that our method can effectively reveal the variability of student attributes and relationships and accordingly achieves the best clustering results for group division.

• Journal of the Korean Chemical Society
• /
• v.65 no.6
• /
• pp.455-467
• /
• 2021

The purpose of this study was to investigate the impact of negotiation-based peer and self-assessment activities on science-gifted students' modeling and students' perceptions of the impact of these assessment activities on modeling. For this purpose, 92 students in the 11th grade of a science high school, in a metropolitan city, were selected to conduct peer assessment, self-assessment, and science writing activities with four topics of Advanced Chemistry. The students' modeling was analyzed in terms of 'structuring scientific concepts', 'logic', 'multiple representations' and 'communication'. Based on the results, the mean scores of modeling increased for each element of evaluation according to the progress of assessment activities. Students' responses in the survey and interviews showed that students perceived the results of student assessment activities as valid, students also recognized the benefit of these assessment activities by referring to the assessment results before their next writing assignment.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.131-138
• /
• 2022

Git's commit message is closely related to the project life cycle, and by this characteristic, it can greatly contribute to cost reduction and improvement of work efficiency by identifying risk factors and project status of project operation activities. Among these related fields, there are many studies that classify commit messages as types of software maintenance, and the maximum accuracy among the studies is 87%. In this paper, the purpose of using a solution using the commit classification model is to design and implement a complex classification model that combines several models to increase the accuracy of the previously published models and increase the reliability of the model. In this paper, a dataset was constructed by extracting automated labeling and source changes and trained using the DistillBERT model. As a result of verification, reliability was secured by obtaining an F1 score of 95%, which is 8% higher than the maximum of 87% reported in previous studies. Using the results of this study, it is expected that the reliability of the model will be increased and it will be possible to apply it to solutions such as software and project management.

• The Mathematical Education
• /
• v.62 no.2
• /
• pp.257-268
• /
• 2023

The purpose of the study is to analyze the characteristics of open-ended tasks in terms of cognitive demands. For this purpose, we analyzed characteristics of open-ended tasks presented in the sequence units of three high school mathematics textbooks. The results of the study have revealed that low cognitive demand levels of open-ended tasks had characteristics including procedures within previous tasks or within those tasks. On the other hand, high cognitive demand levels of open-ended tasks had characteristics of actively exploring new conditions to gain access to what is being sought, requesting a basis for judgement, linking various representations to the concepts of sequences, or requiring a variety of answers. These results are significant in that they not only specified the characteristics of open-ended tasks with high cognitive demands in terms of the intended curriculum, but also provided a direction for the development of open-ended taks with high congitive demands.

• Korean Journal of Culture and Social Issue
• /
• v.25 no.3
• /
• pp.203-229
• /
• 2019

The purpose of this study was to identify the factors that constitute masculine norms of masculine in Korean society. The definition of masculinity was to conform to the male-dominated standard formed socially and culturally. The results of in-depth interviews with 20 male participants were used for a concept mapping analysis to explore the configural representations of Korean masculine norms. After extracting the key sentences related to masculine norms, the participants sorted the 55 key sentences based on similarities and assessed the importance, which was then analyzed with multidimensional scaling method and cluster analysis. The result showed two dimensions, one representing social-personal domain and the other implying dominance-support domain as well as six clusters of caregiver, leadership, emotion suppression, job ability and organizational social adaptation, Expects the masculine abilities, power and control. Finally, the implications of this study, limitations, and the suggestions for future research were discussed.