• Asia-Pacific Journal of Business
• /
• v.13 no.3
• /
• pp.293-309
• /
• 2022

Purpose - The purpose of this study is to explore the possibility of predicting the degree of smartphone overdependence based on mobile phone usage patterns. Design/methodology/approach - In this study, a survey conducted by Korea Internet and Security Agency(KISA) called "problematic smartphone use survey" was analyzed. The survey consists of 180 questions, and data were collected from 29,712 participants. Based on the data on the smartphone usage pattern obtained through the questionnaire, the smartphone addiction level was predicted using machine learning techniques. k-NN, gradient boosting, XGBoost, CatBoost, AdaBoost and random forest algorithms were employed. Findings - First, while various factors together influence the smartphone overdependence level, the results show that all machine learning techniques perform well to predict the smartphone overdependence level. Especially, we focus on the features which can be obtained from the smartphone log data (without psychological factors). It means that our results can be a basis for diagnostic programs to detect problematic smartphone use. Second, the results show that information on users' age, marriage and smartphone usage patterns can be used as predictors to determine whether users are addicted to smartphones. Other demographic characteristics such as sex or region did not appear to significantly affect smartphone overdependence levels. Research implications or Originality - While there are some studies that predict smartphone overdependence level using machine learning techniques, but the studies only present algorithm performance based on survey data. In this study, based on the information gain measure, questions that have more influence on the smartphone overdependence level are presented, and the performance of algorithms according to the questions is compared. Through the results of this study, it is shown that smartphone overdependence level can be predicted with less information if questions about smartphone use are given appropriately.

• Journal of the Korean Society for information Management
• /
• v.20 no.3
• /
• pp.111-127
• /
• 2003

The purpose of this study is to ascertain whether event tracking is more effective in event retrieval than information filtering. This study examined the two techniques for event retrieval to suggest the more effective one. The event-retrieval performances of the event tracking technique based on a kNN classifier and the query-based information filtering technique were compared. Two event tracking experiments, one with the static training set and the other with the dynamic training set , were carried out. Two information filtering experiments, one with initial queries and the other with refined queries, were also carried out to evaluate the event-retrieval effectiveness. We found that the event tracking technique with the static training set performed better than on with the dynamic training set. It was also found that the information fitering technique using intial queries performed better than one using the refined queries. In conclusion, the comparison of the best cases of event tracking and information filtering revealed that the information filtering technique outperformed the event tracking technique in event retrieval.

• Journal of Korea Water Resources Association
• /
• v.33 no.4
• /
• pp.505-515
• /
• 2000

THe purpose of this study is to forecast of runoff hydrographs according to rainfall event in a stream. The neural network theory as a hydrologic blackbox model is used to solve hydrological problems. The Back-Propagation(BP) algorithm by the Levenberg-Marquardt(LM) techniques and Radial Basis Function(RBF) network in Neural Network(NN) models are used. Runoff hydrograph is forecasted in Bocheongstream basin which is a IHP the representative basin. The possibility of a simulation for runoff hydrographs about unlearned stations is considered. The results show that NN models are performed to effective learning for rainfall-runoff process of hydrologic system which involves a complexity and nonliner relationships. The RBF networks consist of 2 learning steps. The first step is an unsupervised learning in hidden layer and the next step is a supervised learning in output layer. Therefore, the RBF networks could provide rather time saved in the learning step than the BP algorithm. The peak discharge both BP algorithm and RBF network model in the estimation of an unlearned are a is trended to observed values.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1435-1440
• /
• 2021

With the advent of the low interest rate era, many investors are flocking to the stock market. In the past stock market, people invested in stocks labor-intensively through company analysis and their own investment techniques. However, in recent years, stock investment using artificial intelligence and data has been widely used. The success rate of stock prediction through artificial intelligence is currently not high, so various artificial intelligence models are trying to increase the stock prediction rate. In this study, we will look at various artificial intelligence models and examine the pros and cons and prediction rates between each model. This study investigated as stock prediction programs using artificial intelligence artificial neural network (ANN), deep learning or hierarchical learning (DNN), k-nearest neighbor algorithm(k-NN), convolutional neural network (CNN), recurrent neural network (RNN), and LSTMs.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1872-1879
• /
• 2022

Recently, with the development of artificial intelligence technology, research to use artificial intelligence to detect hacking attacks is being actively conducted. However, the fact that security data is a representative imbalanced data is recognized as a major obstacle in composing the learning data, which is the key to the development of artificial intelligence models. Therefore, in this paper, we propose a W-VAE oversampling technique that applies VAE, a deep learning generation model, to data extraction for oversampling, and sets the number of oversampling for each class through weight calculation using K-NN for sampling. In this paper, a total of five oversampling techniques such as ROS, SMOTE, and ADASYN were applied through NSL-KDD, an open network security dataset. The oversampling method proposed in this paper proved to be the most effective sampling method compared to the existing oversampling method through the F1-Score evaluation index.

• Proceedings of the KIPE Conference
• /
• 1997.07a
• /
• pp.352-356
• /
• 1997

This paper present the design of a novel neural-network (NN) based pulse-width modulation (PWM) techniques for a three-level power converter of electric trains along with nonlinear mapping of essential switching patterns and fault tolerance, which are inherent characteristics of NNs. Considering the importance of safety, power factor and harmonics of electric train power converters, two-level type and three-level type of power converters using NNs are precisely investigated and compared in computer simulation. A computer simulation shows that a new current control scheme provides an improved performance over a fixed-band hysteresis current control in many aspects.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.287-290
• /
• 2000

In this paper we have presented approach to automatic the direction feature vectors detection, which detects the ridge line directly in gray scale images. In spite of a greater conceptual complexity, we have shown that our technique has less computational complexity than the complexity of the techniques which require binarization and thinning. Afterwards a various direction feature vectors is changed four direction feature vectors. In this paper used matching method is four direction feature vectors based matching. This four direction feature vectors consist feature patterns in fingerprint images. This feature patterns were used for identification of individuals inputed multilayer Neural Networks(NN) which has capability of excellent pattern identification.

• Journal of Korea Spatial Information System Society
• /
• v.11 no.2
• /
• pp.7-12
• /
• 2009

In this paper, we discuss the problem of continuous k.nearest neighbors (CKNN) monitoring over distributed streams wavelet synopses, which also considered sliding window structure under stream based kNN query. We developed traditional skylines techniques and propose a new method which called DR.skylines to process CKNN queries as a bandwidth.efficient approach. It tries to process CKNN queries on synopses for optimized sliding window time and space computation.

• Communications for Statistical Applications and Methods
• /
• v.26 no.6
• /
• pp.591-610
• /
• 2019

Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.

• Korea-Australia Rheology Journal
• /
• v.14 no.4
• /
• pp.161-174
• /
• 2002

A new technique for numerical calculation of viscoelastic flow based on the combination of Neural Net-works (NN) and Brownian Dynamics simulation or Stochastic Simulation Technique (SST) is presented in this paper. This method uses a "universal approximator" based on neural network methodology in combination with the kinetic theory of polymeric liquid in which the stress is computed from the molecular configuration rather than from closed form constitutive equations. Thus the new method obviates not only the need for a rheological constitutive equation to describe the fluid (as in the original Calculation Of Non-Newtonian Flows: Finite Elements St Stochastic Simulation Techniques (CONNFFESSIT) idea) but also any kind of finite element-type discretisation of the domain and its boundary for numerical solution of the governing PDE's. As an illustration of the method, the time development of the planar Couette flow is studied for two molecular kinetic models with finite extensibility, namely the Finitely Extensible Nonlinear Elastic (FENE) and FENE-Peterlin (FENE-P) models.P) models.