Traditional methods of measuring corneal ulcers were difficult to present objective basis for diagnosis because of the subjective judgment of the medical staff through photographs taken with special equipment. In this paper, we propose a method to detect the ulcer area on a pixel basis in corneal ulcer images using a semantic segmentation model. In order to solve this problem, we performed the experiment to detect the ulcer area based on the DeepLab model which has the highest performance in semantic segmentation model. For the experiment, the training and test data were selected and the backbone network of DeepLab model which set as Xception and ResNet, respectively were evaluated and compared the performances. We used Dice similarity coefficient and IoU value as an indicator to evaluate the performances. Experimental results show that when ‘crop & resized’ images are added to the dataset, it segment the ulcer area with an average accuracy about 93% of Dice similarity coefficient on the DeepLab model with ResNet101 as the backbone network. This study shows that the semantic segmentation model used for object detection also has an ability to make significant results when classifying objects with irregular shapes such as corneal ulcers. Ultimately, we will perform the extension of datasets and experiment with adaptive learning methods through future studies so that they can be implemented in real medical diagnosis environment.
It’s proposed and analyzed ML(Machine Learning) models to predict vehicle FC(Fuel Consumption) in real-time. The test driving was done for a car to measure vehicle speed, acceleration, road gradient and FC for training dataset. The various ML models were trained with feature data of speed, acceleration and road-gradient for target FC. There are two kind of ML models and one is regression type of linear regression and k-nearest neighbors regression and the other is classification type of k-nearest neighbors classifier, logistic regression, decision tree, random forest and gradient boosting in the study. The prediction accuracy is low in range of 0.5 ~ 0.6 for real-time FC and the classification type is more accurate than the regression ones. The prediction error for total FC has very low value of about 0.2 ~ 2.0% and regression models are more accurate than classification ones. It’s for the coefficient of determination (R2) of accuracy score distributing predicted values along mean of targets as the coefficient decreases. Therefore regression models are good for total FC and classification ones are proper for real-time FC prediction.
Image labeling must be preceded in order to perform object detection, and this task is considered a significant burden in building a deep learning model. Tens of thousands of images need to be trained for building a deep learning model, and human labelers have many limitations in labeling these images manually. In order to overcome these difficulties, this study proposes a method to perform object detection without significant performance degradation, even though labeling some images rather than the entire image. Specifically, in this study, low-resolution oriental painting images are converted into high-quality images using a super-resolution algorithm, and the effect of SSIM and PSNR derived in this process on the mAP of object detection is analyzed. We expect that the results of this study can contribute significantly to constructing deep learning models such as image classification, object detection, and image segmentation that require efficient image labeling.
In this paper, we propose a system that analyzes drone photographic images of panel-type factory roofs and conducts abnormal detection of bolts. Currently, inspectors directly climb onto the roof to carry out the inspection. However, safety accidents caused by working conditions at high places are continuously occurring, and new alternatives are needed. In response, the results of drone photography, which has recently emerged as an alternative to the dangerous environment inspection plan, will be easily inspected by finding the location of abnormal bolts using deep learning. The system proposed in this study proceeds with scanning the captured drone image using a sample image for the situation where the bolt cap is released. Furthermore, the scanned position is discriminated by using AI, and the presence/absence of the bolt abnormality is accurately discriminated. The AI used in this study showed 99% accuracy in test results based on VGGNet.
In this paper, we propose a new and simple self-supervised learning method that predicts the middle image of a face image sequence for automatic expression recognition. Automatic facial expression recognition can achieve high performance through deep learning methods, however, generally requires a expensive large data set. The size of the data set and the performance of the algorithm are tend to be proportional. The proposed method learns latent deep representation of a face through self-supervised learning using an existing dataset without constructing an additional dataset. Then it transfers the learned parameter to new facial expression reorganization model for improving the performance of automatic expression recognition. The proposed method showed high performance improvement for two datasets, CK+ and AFEW 8.0, and showed that the proposed method can achieve a great effect.
Currently, the problem of food shortage is emerging in our society due to climate problems and an increase population in the world. As a solution to this problem, we propose a multi-remote control smart farm that combines artificial intelligence (AI) and information and communication technology (ICT) technologies. The proposed smart farm integrates ICT technology to remotely control and manage crops without restrictions in space and time, and to multi-control the growing environment of crops. In addition, using Arduino and deep-learning technology, a smart farm capable of multiple control through a smart-phone application (APP) was proposed, and Ai technology with various data securing and diagnosis functions while observing crop growth in real-time was included. Various sensors in the smart farm are controlled by using the Arduino, and the data values of the sensors are stored in the built database, so that the user can check the stored data with the APP. For multiple control for multiple crops, each LED, COOLING FAN, and WATER PUMP for two or more growing environments were applied so that the user could control it conveniently. And by implementing an APP that diagnoses the growth stage through the Tensor-Flow framework using deep-learning technology, we developed an application that helps users to easily diagnose the growth status of the current crop.
A recommender system covers users, searches the items or services which users will like, and let users purchase them. Because recommendations from a recommender system are predictions of users’ preferences for the items which they do not purchase yet, it is rarely possible to be drawn a perfect answer. An evaluation has been conducted to determine whether a prediction is right or not. However, it can be lower user’s satisfaction if a recommender system focuses on only the preferences, that is caused by a ‘filter bubble effect’. The filter bubble effect is an algorithmic bias that skews or limits the information an individual user sees on the recommended list. It is the reason why multiple metrics are required to evaluate recommender systems, and a diversity metrics is mainly used for it. In this paper, we compare three different methods for enhancing diversity for personalized recommendation - bin packing, weighted random choice, greedy re-ranking - with a practical e-commerce data acquired from a fashion shopping mall. Besides, we present the difference between experimental results and F1 scores.
The traveling salesman problem(TSP) is one of the most famous combinatorial optimization problem.
So far, many metaheuristic search algorithms have been proposed to solve the problem, and one of them is local search. One of the very important factors in local search is neighbor generation method, and random-based neighbor generation methods such as inversion have been mainly used. This paper proposes 4 new greedy-based neighbor generation methods. Three of them are based on greedy insertion heuristic which insert selected cities one by one into the current best position. The other one is based on greedy rotation. The proposed methods are applied to first-choice hill-climbing search and simulated annealing which are representative local search algorithms. Through the experiment, we confirmed that the proposed greedy-based methods outperform the existing random-based methods. In addition, we confirmed that some greedy-based methods are superior to the existing local search methods.
In this paper, we propose a system which automatically generates SHACL schemas to describe and validate RDF knowledge graphs constructed by RML mappings. Unlike existing studies, the proposed system generates the schemas based on not only RML mapping rules but also metadata extracted from RML mapping input data in various formats such as CSV, JSON, XML or databases. Therefore, our schemas include the constraints on data type, string length, value range and cardinality, which were not present in the existing schemas. And we solves the problem with "repeated properties" which overlooked in existing studies. Through a conformance test consisting of 297 cases, we show that the proposed system generates correct constraints for the graphs. The proposed system can contribute to automation of the tedious and error-prone existing manual validation processes.
The purpose of this study is to critically review the global intellectual property regime, which has been in full swing since the mid-1990s, from the perspective of postcolonialism. More specifically, by looking at issues which were raised by the Postcolonial Piracy Studies, it attempted to relativize the global IP system. This paper confirmed the postcolonialist view that universal concepts could never be completely universal or pure, and confirmed the non-state legalities view of media piracy as a conduit for participation in the global network through ‘porous legalities’ concept of Lawrence Liang. Finally, this paper raised the need to understand various relationships between the informal media economy and the formal media economy in a balanced perspective, rather than relying only on the neat dichotomy logic of illegality/legal.
In this paper, we analyze 5G network slicing and propose an efficient network slice configuration method in 5G mobile networks. Network slicing can be identified and performed based on the network slice instance information in 5G mobile networks. In case of discordance between the UE’s network slice instance information and the network’s one, the unnecessary signalling overhead occurs, when the UE’s PDU Session Establishment request to the network fails. To solve this problem, this paper proposes two efficient network slice configuration methods, the UE-based ENSC(Efficient Network Slice Configuration) method and the Network-based ENSC method. The proposed schemes perform the prompt the configuration and provision of the updated network slice instance information between the UE and network and improve battery and resource efficiency and minimize unnecessary signalling overhead compared to existing methods in 5G mobile networks.
In this paper, we analyze the feasibility of the IP spoofing attack exploiting null security algorithms in 5G networks based on 3GPP standard specifications. According to 3GPP standard specifications, the initial Registration Request message is not protected by encryption and integrity. The IP spoofing attack exploits the vulnerability that allows a malicious gNB (next generation Node B) to modify the contents of the initial Registration Request message of a victim UE (User Equipment) before forwarding it to AMF (Access and Mobility Management Function). If the attack succeeds, the victim UE is disconnected from the 5G network and a malicious UE gets Internet services, while the 5G operator will charge the victim UE. In this paper, we analyze the feasibility of the IP spoofing attack by analyzing whether each signaling message composing the attack conforms to the 3GPP Rel-17 standard specifications. As a result of the analysis, it is determined that the IP spoofing attack is not feasible in the 5G system implemented according to the 3GPP Rel-17 standard specifications.
In this paper, the virtual environment using rack server type HPC and 3U VPX server type HPC was applied and tested to the basic functions of the Jangbogo-III class submarine combat system developed for the first time in Korea. Based on this test results, the possibility of applying virtualization to the domestic submarine combat system to be developed in the future is confirmed.
Existing studies have been limited to deriving applicable virtualization solutions through simple performance analysis of virtualization solutions or applying virtualization to some functions of the surface ship combat system, but in this paper, the application of virtualization is expanded to the submarine combat system through testing.
In this paper, we propose an FA-RBAC (FA-RBAC) model based on flexible properties. This model is assigned attribute-role-centric, making it easy to manage objects, as efficient as access control, and as the network environment changes, it can provide flexible access control. In addition, fine-grained permissions and simple access control can be achieved while balancing the advantages and disadvantages of the RBAC and ABAC models, reducing the number of access control rules by combining static attribute-based roles and dynamic attribute-based rules, and verifying the validity and performance benefits of the proposed model through comparison analysis and simulation.
The goal of this study is to develop a mobile application so that a person who is new to chemistry can easily acquire the knowledge necessary for chemical structure learning using image tracking technology. The point of this study is to provide a new chemical structure learning experience by recognizing a two-dimensional picture, augmenting the chemical structure into a three-dimensional object, showing it on the user's screen, and using a service that simultaneously provides related information in multiple fields. characteristic. Login API and real-time database technology were used for safe and real-time data management, and an application was developed using image tracking technology for image recognition and 3D object augmentation service. In the future, we plan to use the chemical structure data library to efficiently load and output data.
The popularity of e-commerce systems on the Internet is increasing day by day, and the recommendation system, as a core function of these systems, greatly reduces the effort to search for desired products by recommending products that customers may prefer. The collaborative filtering technique is a recommendation algorithm that has been successfully implemented in many commercial systems, but despite its popularity and usefulness in academia, the memory-based implementation has inaccuracies in its reference neighbor. To solve this problem, this study proposes a new time-aware collaborative filtering technique that integrates and utilizes the neighbors of each item and each user, weighting the recent similarity more than the past similarity with them, and reflecting it in the recommendation list decision. Through the experimental evaluation, it was confirmed that the proposed method showed superior performance in terms of prediction accuracy than other existing methods.
This study attempted to investigate what kind of perception people in their 20s have about masks and to find out the characteristics of each type by categorizing the perception. The Q methodology was used for the study. The cognition types of masks were categorized into three. Type 1 was a ‘always wear impact-important type’ that always wears masks and thinks masks affect non-verbal communication and the wearer's image. Type 2 was a ‘function-important negative recognition type’ that wears masks to prevent germs and thinks that masks have a great negative impact. Type 3 was a ‘concealment wear positive image type’ that wears a mask to cover the face and thinks that a person looks young when wearing a mask. It is thought that the development of masks of various designs and functions reflecting the needs of consumers should be carried out. Also, it is thought that various products should be developed and sold so that consumers can choose according to important considerations such as design, fit, and function.
This study was conducted to find out the relationship between the perception of the necessity and importance of creative teaching methods and core competencies in universities. A total of 142 people who voluntarily agreed to participate in the study were selected and surveyed using the Naver online questionnaire. It was found that the necessity and importance of creative teaching methods was related to the sub-factors of core competencies such as practical field competency, problem-solving competency, convergence competency, communication competency, job ethics, community consciousness. University education should actively introduce and apply creative teaching methods such as action learning and PBL, focusing on improving core competencies, which are actual abilities to be performed in the field.
In this study, using data from the second wave of Panel Survey of Employment for The Disabled[PESD] (2016) to the sixth year (2021), the longitudinal changes between disability acceptance and job satisfaction of adult wage workers aged 20 or older with disabilities and the correlation An autoregressive cross-lagged model was applied to analyze the causal relationship. As a result of the analysis, first, the disability acceptance and job satisfaction at the previous time point of the disabled workers were stably significant to the disability acceptance(β=.556~.610) and job satisfaction(β=.554~.585) at the later time point. Second, disability acceptance at the previous point in time for wage workers with disabilities crosses the job satisfaction at the later time point(β=.077~.090), and the job satisfaction at the previous point crosses the disability acceptance at the later time point(β=.087~.092). Third, as a result of model fit analysis according to the gender group of wage workers with disabilities, the difference in the autoregressive effect between disability acceptance and job satisfaction and the cross-lagged effect between disability acceptance and job satisfaction according to the passage of time was not significant.
In this paper, we developed a system that intelligently identifies skin image data from big data collected from social media Instagram and extracts standardized skin sample data for skin condition diagnosis and management. The system proposed in this paper consists of big data collection and analysis stage, skin image analysis stage, training data preparation stage, artificial neural network training stage, and skin image identification stage. In the big data collection and analysis stage, big data is collected from Instagram and image information for skin condition diagnosis and management is stored as an analysis result. In the skin image analysis stage, the evaluation and analysis results of the skin image are obtained using a traditional image processing technique. In the training data preparation stage, the training data were prepared by extracting the skin sample data from the skin image analysis result. And in the artificial neural network training stage, an artificial neural network AnnSampleSkin that intelligently predicts the skin image type using this training data was built up, and the model was completed through training. In the skin image identification step, skin samples are extracted from images collected from social media, and the image type prediction results of the trained artificial neural network AnnSampleSkin are integrated to intelligently identify the final skin image type.
The skin image identification method proposed in this paper shows explain high skin image identification accuracy of about 92% or more, and can provide standardized skin sample image big data. The extracted skin sample set is expected to be used as standardized skin image data that is very efficient and useful for diagnosing and managing skin conditions.
In this study, the authors analyzed the effect of demographic and mobile usage characteristics on mobile shopping addiction. In particular, this study focused on identifying the differences in shopping addiction between countries that were rarely covered in previous studies. As a result of the analysis, gender and age were identified as significant independent variables in demographic characteristics, and it was analyzed that there was a statistically significant moderating effect between these variables and nationality. In the mobile usage, the initial time of use was found to be a significant independent variable, and it was analyzed that there was also a moderating effect between the variable and nationality. The results of this study can be used as a clue to establishing marketing strategies for providing customized products and services from a corporate perspective, and can provide useful guidelines for resolving shopping addiction from a public policy perspective.
Based on the success model and Expectation Confirmation model of information system, the concept model of mobile bus payment App users' willingness to continue using is constructed by introducing function quality and interface design quality. A total of 264 valid questionnaires are obtained by issuing online questionnaires, and the model is tested by SmartPLS3.0 software The results show that users' perceptions of information quality, system quality and interface design quality will affect users' perceived usefulness and satisfaction through the scene, and then affect users' willingness to continue to use; Perceived functional quality has a significant impact on perceived usefulness, but has no significant impact on satisfaction. Perceived usefulness has a significant impact on user satisfaction.
Innovation is not only one of the factors determining the competitiveness of national regions, but also an engine for economic development, and plays an important role in breaking out of the trap of middle-income countries. This paper constructs a regional innovation index from the perspectives of innovation input, innovation output, and innovation environment, and measures the regional innovation index of 31 provinces, municipalities, and autonomous regions in China from 2006 to 2019 by using principal component analysis and cluster analysis. The results concluded that there are large provincial and municipal differences in China's regional innovation capacities, and the provinces with higher comprehensive levels are mainly concentrated in the southeastern coastal region. Cluster analysis divides the 31 provinces, municipalities, and autonomous regions into five types, and the results find that the respectively developed coastal regions are in the high-level and the high-level regions relying on the advantages of location and national policies.
One of the important research streams in the privacy literature for the past decade has been to discover factors affecting the decision-making process related to self-disclosure, called the cost-benefit analysis. However, although human behavior is greatly influenced by affective as well as cognitive factors, most of the factors found in previous studies are those with cognitive properties. Based on the awareness of this imbalanced situation, the study examines the role of affective factors on self-dislosure decision-making, especially SNS enjoyment and SNS fatigue. As a result of data analysis, the study finds that the influence of these affective factors is significant, and the influence of SNS enjoyment is greater than that of SNS fatigue. As for the relationship between the affective factors and the decision-making factors, the study finds that the positive affect(enjoyment) relates to only the positive evaluation factor(benefit) and the negative affect(fatigue) relates only the negative evaluation factor(cost), which demonstrate the congruent effect mechanism. Based on the result, the study discusses meaningful implications and suggestions for future studies.
In this paper, we propose a phenomenon that analyze the impact of market sentiment on China's real estate market through the perspective of behavioral economics. Previously, real estate market analyzation basically focus on some fundamental principles which include market price, monetary policies and income, etc. However, little research has explored market sentiment and its influence. By using principal components analysis (PCA), this study first creates buyer’s sentiment and seller’s sentiment to measure the heat of China's real estate market. Different from using traditional estimation method, the vector autoregressive model (VAR) is used to analyze how both sentiments affect real estate return. The overall results show that from unit root test and impulse response analyzation, the impact of seller’s sentiment is positive to real estate market while buyer’s sentiment is negative. At the same time, the higher seller’s sentiment will have different influence on the housing market compared with the higher buyer’s sentiment.
The purpose of this study is to make recommendations for developing a Metaverse platform for educational purpose by utilizing focus group interviews with elementary, middle, and high school teachers having experience on metaverse in teaching. 10 teachers participated in the study, and data was collected for two months from January to February in 2022, and two focus groups were formed and interviewed.
Data was analyzed by applying content analysis. The results showed that there were 17 sub-themes derived from 6 main guiding questions(What are the advantages of using Metaverse platform in education? What are the advantages of utilizing Metaverse as one of educational software? What are the possible and appropriate classes utilizing Metaverse in future education? What are the possible problems when using Metaverse in education? What are the essential functions which Metaverse should have in education? and Could you provide us with policy recommendations in building Metaverse platform for educational purpose?). Finally, based on the results, recommendations for building Metaverse platform for educational purpose are suggested and limitations of the study and possible future study are discussed.
Recently, the topics of SW liberal-arts education are diversifying, from ‘Computational Thinking(CT)’ to ‘Programming, Data Analysis and Artificial Intelligence(AI)’ in universities. We expect that the diversification of SW liberal-arts subjects does not just mean that the learning contents are different, but also differentiates the educational goals and educational effects of each subject. In this paper, we conducted a case study to analyze the educational effect according to the educational goals of two SW liberal-arts subjects, CT and Data Analysis Fundamentals(DA), for humanities college students. We confirmed that the educational effect of ‘CT Efficacy’ increased significantly in accordance with the common educational goal of ‘Improving CT-based SW convergence competency’ in both subjects.
However, we also analyzed the difference in the educational effects of ‘CT(the goal of basic SW education)’ and ‘DA(the goal of major-friendly SW education)’, which have different subject goals.
‘CT’ mainly showed an educational effect on how to solve general daily problems, and ‘DA’ showed confidence in how to solve major problems along with general problems.
The purpose of this study is to present a case of the development and application of a one-time special lecture program that requires the use of computers in frontline elementary and secondary schools. For this purpose, the researcher developed an Arduino-based special lecture program that works as a teaching tool to help with the functions of a student PC with a Raspberry Pi. This special lecture program was applied at three elementary and middle schools near K-University, and then the program was evaluated. The results of this study are as follows. First, the researcher developed a teaching aid for PC functions to be used in special lectures. Second, teaching and learning materials for visiting special lecture education programs using Arduino were developed. Third, in the special lecture, a teaching-learning method was used to guide a small number of students individually. Fourth, the special lecture program resulted in high satisfaction. The results of this study can be a useful reference for teachers who plan one-time special lecture programs requiring computers or for those who want to apply physical computing-related devices in an educational field.
This study aims to investigate the effect of self-directed learning ability and cooperative ability on educational satisfaction through learning attitude in SW education for middle and high school students.
For this purpose, a survey was conducted on middle and high school students residing in A metropolitan city, and the responses of 321 students were analyzed. The main research results are as follows. First, male students' self-directed learning ability and learning attitude were statistically significantly higher than female students. High school students were statistically significantly higher in all variables than middle school students. Second, learning attitude was found to partially mediate the effect of self-directed learning ability on educational satisfaction. Third, learning attitude partially mediated the effect of cooperative ability on educational satisfaction. The results of this study suggest that to increase satisfaction with SW education, SW education strategies must be differentiated according to gender and school level, and instructional design that can promote the above three variables is required.