• Journal of Creative Information Culture
• /
• v.7 no.4
• /
• pp.235-242
• /
• 2021

Recently, many human activity recognition(HAR) researches using smartphone sensor data have been studied. HAR can be utilized in various fields, such as life pattern analysis, exercise measurement, and dangerous situation detection. However researches have been focused on recognition of basic human behaviors or efficient battery use. In this paper, exercising activities performed indoors and outdoors were defined and recognized. Data collection and pre-processing is performed to recognize the defined activities by SVM, random forest and gradient boosting model. In addition, the recognition result is determined based on voting class approach for accuracy and stable performance. As a result, the proposed activities were recognized with high accuracy and in particular, similar types of indoor and outdoor exercising activities were correctly classified.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.55-61
• /
• 2022

Today's payment systems are becoming unmanned and changing to a way of paying with kiosks. This has the advantage of convenient payment because consumers can select a menu and specify the number of products to be purchased with just a touch of the screen. However, from the point of view of system security, the actual kiosk system has various vulnerabilities. This can hijack the administrator account, gain system privileges, and perform malicious actions. In addition, it is exposed to a number of security threats, such as the possibility of wasting unnecessary resources by abnormally increasing the number of payments, and causing the device to fail to operate normally. Therefore, in this paper, if any node of a participant in the solana blockchain approves an incorrect fork, the stake of the voting nodes is deleted. Also, since all participants can see the transaction history due to the nature of the block chain, I intend to write a thesis on a system that improves the vulnerability of kiosk payments by separating the access rights through the private blockchain.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.17-28
• /
• 2022

The cable component of cable-stayed bridges is gradually impacted by weather conditions, vehicle loads, and material corrosion. The stayed cable is a critical load-carrying part that closely affects the operational stability of a cable-stayed bridge. Damaged cables might lead to the bridge collapse due to their tension capacity reduction. Thus, it is necessary to develop structural health monitoring (SHM) techniques that accurately identify damaged cables. In this work, a combinational identification method of three efficient techniques, including statistical analysis, clustering, and neural network models, is proposed to detect the damaged cable in a cable-stayed bridge. The measured dataset from the bridge was initially preprocessed to remove the outlier channels. Then, the theory and application of each technique for damage detection were introduced. In general, the statistical approach extracts the parameters representing the damage within time series, and the clustering approach identifies the outliers from the data signals as damaged members, while the deep learning approach uses the nonlinear data dependencies in SHM for the training model. The performance of these approaches in classifying the damaged cable was assessed, and the combinational identification method was obtained using the voting ensemble. Finally, the combination method was compared with an existing outlier detection algorithm, support vector machines (SVM). The results demonstrate that the proposed method is robust and provides higher accuracy for the damaged cable detection in the cable-stayed bridge.

• Journal of Internet of Things and Convergence
• /
• v.8 no.1
• /
• pp.11-16
• /
• 2022

Efforts to incorporate blockchain into various fields are continuing as cryptocurrency transactions become more active. Blockchain has the characteristic that once recorded facts cannot be modified or deleted. Due to these characteristics, the use in the field of recording and proving certain facts, such as voting or proof of ownership, is attracting attention. In this paper, users who want to participate in the transaction process using private blockchain, one of the types of blockchain, are divided into real estate brokers, building owners, and purchasers (lessors), and roles are assigned to each user. In addition, we would like to propose a system to increase reliability through the participation of institutions. Through this, we intend to not only present a real estate transaction system that prevents damage from real estate fraud related to false sales and fraudulent contracts, but also enhances reliability and contributes to finding ways to utilize blockchain in the future.

• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.35-43
• /
• 2022

This paper studies how to improve the identification rate of laryngeal disability speech data by convolutional neural network (CNN) and machine learning ensemble learning methods. In general, the number of laryngeal dysfunction speech data is small, so even if identifiers are constructed by statistical methods, the phenomenon caused by overfitting depending on the training method can lead to a decrease the identification rate when exposed to external data. In this work, we try to combine results derived from CNN models and machine learning models with various accuracy in a multi-voting manner to ensure improved classification efficiency compared to the original trained models. The Pusan National University Hospital (PNUH) dataset was used to train and validate algorithms. The dataset contains normal voice and voice data of benign and malignant tumors. In the experiment, an attempt was made to distinguish between normal and benign tumors and malignant tumors. As a result of the experiment, the random forest method was found to be the best ensemble method and showed an identification rate of 85%.

• Design Convergence Study
• /
• v.17 no.3
• /
• pp.91-108
• /
• 2018

Rather the ballot paper design could influence voting behavior, there is less study upon the designing ballot paper and the importance of information design. This study examines the possibility of error occurring in the ballot paper design under the rules of Public Official Election Act. To do this, we conducted a heuristic evaluation method to review regulations, and an empirical experiment with closed groups. From this, we found that (1) diverse cases of ballot paper can be produced, and (2) various fonts, sizes, and materials can be used. Accordingly, it is inevitable to deliver regulations on (1) the usage of chromaticity and image, (2) the applying universal designed-typography, and (3) the margin for the spacing between ballot boxes. This study, at the end, suggests institutional measures for securing the validity and legitimacy on the decision-making process to remove latent ambiguity in ballot paper designing.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.305-307
• /
• 2021

Alzheimer's Disease (AD) is a cognitive disorder characterized by memory impairment that can be assessed at early stages based on administering clinical tests. However, the AD pathophysiological mechanism is still poorly understood due to the difficulty of distinguishing different levels of AD severity, even using a variety of brain modalities. Therefore, in this study, we present a hybrid EEG-fNIRS modalities to compensate for each other's weaknesses with the help of Machine Learning (ML) techniques for classifying four subject groups, including healthy controls (HC) and three distinguishable groups of AD levels. A concurrent EEF-fNIRS setup was used to record the data from 41 subjects during Oddball and 1-back tasks. We employed both a traditional neural network (NN) and a CNN-LSTM hybrid model for fNIRS and EEG, respectively. The final prediction was then obtained by using majority voting of those models. Classification results indicated that the hybrid EEG-fNIRS feature set achieved a higher accuracy (71.4%) by combining their complementary properties, compared to using EEG (67.9%) or fNIRS alone (68.9%). These findings demonstrate the potential of an EEG-fNIRS hybridization technique coupled with ML-based approaches for further AD studies.

• Journal of dental hygiene science
• /
• v.23 no.2
• /
• pp.93-102
• /
• 2023

Background: To investigate political participation by dental hygiene students and analyze the differences therein based on the learning efficacy of dental hygiene policy. Methods: A total of 239 dental hygiene students who were expected to graduate responded to the survey. The data were collected online using a structured questionnaire consisting of 6 items on general characteristics, 10 on political participation, and 15 on the learning efficacy of dental hygiene policy. Statistical analysis was performed using SPSS 23.0. Political participation based on the learning efficacy of dental hygiene policy was analyzed using independent t-tests, ANOVA, and multiple regression analysis (p<0.05). Results: Among the dental hygiene students, 60.7% voted in all three recent presidential, general, and local elections, and 14.2% did not. For political parties supported, 65.7% responded that they had "no supporting party," and 34.3% indicated that they had a "supporting party." In terms of the level of political participation of dental hygiene students (0~50 points), the average score was 25.8 points, with the average passive political participation (0~25 points) score at 15.6 points and the average active political participation (0~25 points) score at 10.2 points. With an increase in dental hygiene policy learning efficacy, both passive and active political participation showed higher scores (p<0.05). Conclusion: Dental hygiene students showed low political participation. The presence of a supporting party, higher voting participation, and higher learning efficacy of dental hygiene policy were associated with higher passive and active political participation. Therefore, to increase this population's interest in political participation, various opportunities for related learning need to be promoted and provided in academia, leading to the enhancement of their political capabilities. In this manner, dental hygienists should expand their capabilities in various roles such as advocates, policy makers, and leaders.

• Korean Journal of Legislative Studies
• /
• v.27 no.3
• /
• pp.155-188
• /
• 2021

This study examines dynamics in election news making. It is important to understand when and how news media produce election news in order to grasp news making and voting behavior. The news media sometimes make election news by focusing on issues and policies. Often they frame elections as a game and focus on election strategies while covering elections. This article argues that as time goes by during the election period, the number of policy news tends to decrease while the frequency of strategic news is likely to increase. Also, TV's and newspapers show distinctive patterns of election news making. In order to examine the arguments, this study categorizes election news stories into policy and strategic news stories produced during the 2020 Korean congressional elections and constructs daily time-series data of them. The results of structural break and regression analyses partially support the arguments.

• Korean Journal of Legislative Studies
• /
• v.27 no.3
• /
• pp.35-68
• /
• 2021

In the German federal election in 2021, the Social Democrats returned to power by a narrow margin and the Green Party emerged as the biggest winner. The two political parties took the lead by proposing policies that met the expectations of the people in the policies of climate and environment, pandemic response and health, and labor and social security. The Merkel effect did not play a significant role in the election, and it is highly likely that it will lead to government policy after the formation of a coalition. While the class cleavage in voting behavior has weakened, the generational cleavage has grown relatively large. Older people showed more support for the two major parties, while younger people showed higher support for the Green Party and the FDP. If the generational cleavage continues, it can be linked to the growth of the Green Party and the FDP, the continued weakening of the two major parties and the emergence of other new parties. In addition, the regional cleavage between the former East and West Germany still remain, which will affect the direction of the AfD and the Left and combine with other political cleavages. The 2021 German federal election can be said to be an election that heralds the realignment of the political party system.