In recent years, the turnover phenomenon of new college graduates has been intensifying. The turnover of new employees creates many difficulties for businesses as it is difficult to recover the costs spent on their hiring and training. Therefore, it is necessary to promptly identify and effectively manage new employees who are inclined to change jobs. So far previous studies related to turnover intention have contributed to understanding the turnover phenomenon of new employees by identifying factors influencing turnover intention. However, with these factors, there is a limitation that it has not been able to present how much it is possible to predict employees who are actually willing to change jobs. Therefore, this study proposes a method of developing a machine learning-based turnover intention prediction model to overcome the limitations of previous studies. In this study, data from the Korea Employment Information Service's Job Movement Path Survey for college graduates were used, and OLS regression analysis was performed to confirm the influence of predictors. And model learning and classification were performed using a logistic regression (LR), k-nearest neighbor (KNN), and extreme gradient boosting (XGB) classifier. A novel finding of this research is the diminished or reversed influence of certain traditional factors, such as workload importance and the relevance of one's major field, on turnover intention. Instead, job security emerged as the most significant predictor. The model's accuracy rates, highest with XGB at 78.5%, demonstrate the efficacy of applying machine learning in turnover intention prediction, marking a significant advancement over traditional econometric models. This study breaks new ground by integrating advanced predictive analytics into turnover intention research, offering a more nuanced understanding of the factors influencing the turnover intentions of new college graduates. The insights gained could guide organizations in effectively managing and retaining new talent, highlighting the need for a focus on job security and organizational satisfaction, and the shifting relevance of traditional factors like job preference.

This study aims to improve the accuracy of forecasting the turnover intention of new college graduates by solving the imbalance data problem. For this purpose, data from the Korea Employment Information Service's Job Mobility Survey (Graduates Occupations Mobility Survey: GOMS) for college graduates were used. This data includes various items such as turnover intention, personal characteristics, and job characteristics of new college graduates, and the class ratio of turnover intention is imbalanced. For solving the imbalance data problem, the synthetic minority over-sampling technique (SMOTE) and generative adversarial networks (GAN) were used to balance class variables to examine the improvement of turnover intention prediction accuracy. After deriving the factors affecting the turnover intention by referring to previous studies, a turnover intention prediction model was constructed, and the model's prediction accuracy was analyzed by reflecting each data. As a result of the analysis, the highest predictive accuracy was found in class balanced data through generative adversarial networks rather than class imbalanced original data and class balanced data through SMOTE. The academic implication of this study is that first, the diversity of data sampling methods was presented by expanding and applying GAN, which are widely used in unstructured data sampling fields such as images and images, to structured data in business administration fields such as this study. Second, two refining processes were performed on data generated using generative adversarial networks to suggest a method for refining only data corresponding to a more minority class. The practical implication of this study is that it suggested a plan to predict the turnover intention of new college graduates early through the establishment of a predictive model using public data and machine learning.

PurposeAs the center of the fourth industrial revolution, artificial intelligence (AI) has marked its presence in various disciplines including the education field in the form of AI-powered learning applications. The purpose of this study is to build a research model capturing the relationships among use contexts, user gratification, attitude, learning performance and continuous intention to use an AI-powered English learning application.Design/methodology/approachUsing the use and gratification theory, use contexts and the belief-attitude-intention theory, this paper uses a quantitative approach based on a survey method for data collection and structural equation modeling for analysis. A total of 478 students from an international university in Guangdong, China, participated in the survey after using Liulishuo for two weeks.FindingsThe results showed that perceived use contexts affected all variables associated with gratifications-obtained and gratification-opportunities. With the exception of social integrativeness, all other gratification-based factors significantly affected attitude. The attitude in turn significantly influenced learning performance and continuous use intention.Originality/valueMobile AI-powered learning applications are at the center of research on technology-enhanced learning in the age of media and technology convergence. The study is timely and contributes to the discussion of the roles of use context and gratifications on technology users’ attitudes and behavioral intentions.

Lately, the Critical Pathway(CP) of Electronic Medical Record(EMR) is used to the guideline for a treatment in the public hospital. We propose a healthcare promotion service using disease pattern with lifestyle risk factors. We classify a medical historical patient data with disease codes with lifestyle risk factors (hypertension, diabetes, smoking, overweight, excessive alcohol intake, and low physical activity) to make the lifestyle risk factors through the classification. We finally make the clusters of disease code with lifestyle risk factors using the medical historical data based on EMR's electronic discharge summary data. As the result of that, we do a healthcare recommending service based on the disease pattern with lifestyle risk. We can build a medical help desk of a public hospital to support people as we check into the public hospital; how to get the procedure of curing, the desired curing clinical method for the healthcare promotion service by each disease code, and how to be better our healthcare. We evaluate the performance of the proposed system by experimenting with the datasets collected at the medical center to measure performance and report some experimental results.

Never before in history is the data growing at such a high volume, variety and velocity. It not only provides multi-sources of information for people to discover useful, important and valuable nuggets of information, but also increases the difficulty in finding such nuggets in almost all fields. Particularly, the field of healthcare is known for its dominical or ontological complexity and variety of clinical data or medical data regarding its variable data standards and data quality and so as the high data dimensionality. In order to effectively use the data at the hand to improve healthcare outcomes and processes, this paper illustrates a model called Risk Factor Detection and Disease Prediction (RFD-DP) model. The model incorporates statistics, data mining and MapReduce techniques on high dimensional clinical data to detect risk factors and generate predicator for a specified disease, hypertension disease. The experimental results indicate that the proposed model outperforms traditional feature selection and classification methods in terms of accuracy, F-score, and AUC. Consequently, the proposed model is promising to be applied to healthcare system.

FinTech is a newly emerged service that combines innovative financial services and latest mobile technology. Since this service is new, there is a lack of study that investigates consumer behavior in adopting the service. Founded on Regulatory Focus Theory, our study aims to explain two different factors that motivate the adoption of FinTech in China. We plan to collect data from university students who used Alipay and Tenpay (two of the leading FinTech companies in China). The findings from our study will be valuable to FinTech companies in strategizing and promoting usage of their services.

Along with the spread of digital music and recent growth in the digital music industry, the demands for music recommender are increasing. These days, listeners have increasingly preferred to digital real-time streamlining and downloading to listen to music because this is convenient and affordable for the listeners. In this paper, we propose music recommender system using learning listener's prefererece, such as Melon, Billboard, Bugs Music, Soribada, and Gini, with most popular current songs across all genres and styles. It is also necessary for us to make the task of calculating the preference with weight to reflect the preference of most popular current songs with its popular music charts on trends. We evaluated the proposed system on the data set of music sites to measure its performance. We reported some of the experimental result, which is better performance than the previous system.

In today's era of aging society, people want to handle personal health care by themselves in everyday life. In particular, the evolution of medical and IT convergence technology and mobile smart devices has made it possible for people to gather information on their health status anytime and anywhere easily using biometric information acquisition devices. Healthcare information systems can contribute to the improvement of the nation's healthcare quality and the reduction of related cost. However, there are no perfect security models or mechanisms for healthcare service applications, and privacy information can therefore be leaked. In this paper, we examine security requirements related to privacy protection in u-healthcare service and propose an extended RBAC based security model. We propose and design u-healthcare service integration platform (u-HCSIP) applying RBAC security model. The proposed u-HCSIP performs four main functions: storing and exchanging personal health records (PHR), recommending meals and exercise, buying/selling private health information or experience, and managing personal health data using smart devices.

Technology industry is experiencing its dramatic changes in the amount of data that requires management and the place that such an asset are stored. Despite the exponential growth of information, business leaders are expecting agility in order to complete a lot of works much faster and less expensively using data. With the generalized spread of smart devices under this rapidly changing digital environment and subsequent spread of wireless Internet users and communication expenditure, the amount of data via wireless Internet worldwide is increasing rapidly at a faster rate every year. However, the communication environment cannot catch up with the demands of consumers for the super high-speed wireless Internet. Accordingly, this paper aims to look at the establishment of the cloud storage-based file system that can provide services to meet the needs of users in the cloud computing environment via wireless Internet and the examples of the establishment of such a system.

It has been increasing the number and types of products on the u-commerce market and promoting interest in associated items rapidly. Therefore, agility and real time accessibility are crucial element in u-commerce. Existing collaborative filtering(CF) adopts evaluation methods based on personal profiles. However, these methods have been identified with difficulties in accurately analyzing the customers' tendencies and level of interest, as well as the problems of cost, consequently leaving customers unsatisfied. This paper proposes a new method of recommender system in u-commerce using cluster analysis of segmented merchandise to have different weights based on FRAT(Frequency, Recency, Amount and Type) method. Instead of using user's profiles for rating, we used an implicit method. It is necessary for us to make the task of preprocessing such as keeping FRAT method and clustering of merchandise category in order to recommend items with the profit/weight/importance of segmented merchandise. To verify improved performance of our proposing system compared to the previous system. We have conducted experiments with the same dataset, which was collected from a cosmetic web shopping mall.

This paper proposes an efficient purchase pattern clustering method based on SOM(Self-Organizing Map) for Personal Ontology Recommender System in u-Commerce under ubiquitous computing environment which is required by real time accessibility and agility. In this paper, it is necessary for us to keep clustering the user’s information to join the user’s score based on RFM factors using SOM network and the analysis of RFM to be able to reflect the attributes of the user in order to reflect frequently changing trends of purchase pattern by emphasizing the important users and items, and to improve better performance of recommendation. The proposed makes the task of an efficient purchase pattern clustering based on SOM for preprocessing so as to be possible to recommend by the loyalty of RFM factors as considering user’s propensity. To verify improved better performance of proposing system than the previous systems, we carry out the experiments in the same dataset collected in a cosmetic internet shopping mall.

An environmental monitoring application is designed to monitor and track various kinds of environmental phenomena such as water pollution and global warming.By collecting detected sensor data from the sensors installed at a target place, a monitoring system analyzes and predicts an environmental change.For smoothly answering a user query, a data abstraction model is designed to rapidly process an amount of sensor data by employing data filtering, data aggregation, and data summarization.In order to dynamically represent the different layer of sensor data in a region, we design FLSA (Flexible Layered Sensor Data Abstraction), which supports a flexible layer of SGSA (Slope Grid for Sensor Data Abstraction).When the sensor data is transmitted to a server, FLSA make some clusters to shows several layer of sensor data depending on sensor data gradient.Each cell of FLSA has a set of SGSA to represent each sensor data layer in the cell.This layered SGSA of FLSA is useful to represent a distributed sensor data in a cell.When an abstraction model is used to environmental monitoring, there is a trade-off between faster data processing and data representation.FLSA focuses on data representation to show detailed condition of a target place.

This paper proposes a new clustering method using the weighted preference based on RFM(Recency, Frequency, Monetary) Score for personalized recommendation in u-commerce under ubiquitous computing environment which is required by real time accessibility and agility. In this paper, using an implicit method without onerous question and answer to the users, not used user’s profile for rating, it is necessary for us to extract the most frequent purchase items from the whole purchase data and to calculate the weighted preference of item for customer in order to reduce customers’ search effort, to reflect frequently changing trends by emphasizing the important items and to improve the rate of recommendation with high purchasability. To verify improved better performance of proposing system than the previous systems, we carry out the experiments in the same dataset collected in a cosmetic internet shopping mall.

One essential task in extracting information from biomedical literature is the bio Named Entity Recognition (NER) process, which basically defines the boundaries between typical words and biomedical terminology in particular text data, and assigns them based on domain knowledge. This paper presents a semi supervised integration of completely different classifiers to cover knowledge from unlabeled data to recognize bio named entities in text. We modified the original co-training, a semi supervised learning algorithm, with a scalable feature processing schema, which extracts the bio NER feature from a number of unlabeled data and converts different types of feature sets. Our base result shows that the classifiers of co-training achieve significant learning from unlabeled data.

This paper proposes a new method using clustering of item preference based on Recency, Frequency, Monetary (RFM) for recommendation system in u-commerce under fixed mobile convergence service environment which is required by real time accessibility and agility. In this paper, using an implicit method without onerous question and answer to the users, not used user’s profile for rating to reduce customers’ search effort, it is necessary for us to keep the scoring of RFM to be able to reflect the attributes of the item and clustering in order to improve the accuracy of recommendation with high purchasability. To verify improved better performance of proposing system than the previous systems, we carry out the experiments in the same dataset collected in a cosmetic internet shopping mall.

Discovering access patterns from web log data is a typical sequential pattern mining application, and a lot of access pattern mining algorithms have been proposed. In this paper, we propose an improved approach of Gap-BIDE algorithm to extract user access patterns from web log data. Compared with the previous Gap-BIDE algorithm, a process of getting a large event set is proposed in the provided algorithm; the proposed approach can find out the frequent events by discarding the infrequent events which do not occur continuously in an accessing time before generating candidate patterns. In the experiment, we compare the previous access pattern mining algorithm with the proposed one, which shows that our approach is very efficient in discovering access patterns in large database.

TPM 활동은 TPM의 기본 방침 및 목표의 설정과 이를 달성하기 위한 TPM 활동성과를 측정하는 지표를 통한 성과의 정량화 등이 필요하다. 본 연구에서는 TPM 활동의 측정 요소를 분석하고, BSC 기반의 TPM 성과 측정방법과 정성적 성과의 정량화를 통한 지표의 경제적 효과 측정 방법을 제시하였다. TPM(Total Productive Maintenance) is a methodology to improve corporations' productivity and has been employed widely. At the initial stage of the TPM, we need to set basic plans and goals of the TPM. Also, quantization of performance is required through the TPM activity measurement indices to achieve the plans and the goals. We analyzed measurement factors of TPM activity by observation of previous researches and suggest a measure methodology of economic effect for the TPM performance measurement based on BSC and quantification of qualitative measurement.