• The Journal of Information Systems
• /
• v.31 no.4
• /
• pp.01-23
• /
• 2022

Purpose This study aims to propose a deep learning-based fake review detection model by combining authors' linguistic features and semantic information of reviews. Design/methodology/approach This study used 358,071 review data of Yelp to develop fake review detection model. We employed linguistic inquiry and word count (LIWC) to extract 24 linguistic features of authors. Then we used deep learning architectures such as multilayer perceptron(MLP), long short-term memory(LSTM) and transformer to learn linguistic features and semantic features for fake review detection. Findings The results of our study show that detection models using both linguistic and semantic features outperformed other models using single type of features. In addition, this study confirmed that differences in linguistic features between fake reviewer and authentic reviewer are significant. That is, we found that linguistic features complement semantic information of reviews and further enhance predictive power of fake detection model.

• New & Renewable Energy
• /
• v.18 no.2
• /
• pp.18-25
• /
• 2022

In this study, we propose a wind power generation prediction system that applies machine learning and data mining to predict wind power generation. This system increases the utilization rate of new and renewable energy sources. For time-series data, the data set was established by measuring wind speed, wind generation, and environmental factors influencing the wind speed. The data set was pre-processed so that it could be applied appropriately to the model. The prediction system applied the CNN (Convolutional Neural Network) to the data mining process and then used the LSTM (Long Short-Term Memory) to learn and make predictions. The preciseness of the proposed system is verified by comparing the prediction data with the actual data, according to the presence or absence of data mining in the model of the prediction system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.2033-2036
• /
• 2004

A novel approach to estimate the real time moving trajectory of an object is proposed in this paper. The object position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Kalman filter and neural networks are utilized. Since the Kalman filter needs to approximate a non-linear system into a linear model to estimate the states, there always exist errors as well as uncertainties again. To resolve this problem, the neural networks are adopted in this approach, which have high adaptability with the memory of the input-output relationship. Kohonen Network(Self-Organized Map) is selected to learn the motion trajectory since it is spatially oriented. The superiority of the proposed algorithm is demonstrated through the real experiments.

• The Magazine of the IEIE
• /
• v.42 no.7
• /
• pp.26-38
• /
• 2015

고집적화를 위한 Floating Gate NAND 개발과정에서 몇 차례 기술적 한계상황에 직면하였었지만, Air-Gap, Double patterning, Multi-level Cell, Error Correction Code과 같은 breakthrough idea 을 활용하여 1Xnm까지 성공적인 scale-down 을 하였고 10nm 까지도 바라보고 있지만, 10nm 미만으로는 적절한 방안을 찾지 못한 상황입니다. CTD 의 3D NAND Flash는 Aspect Ratio, Poly channel의 intrinsic 특성, Data 보존 능력 등 해결 해야 할 issue 들이 남아 있지만, F.G Flash 의 지난 20년간 Lesson-learn 과 Band engineering, Channel Si, PUC 의 요소기술 개발 및 System algorithm 개발, QLC 개발 등을 통하여 F.G Flash를 넘어 지속적인 Cost-down 이 가능할 것입니다.

• Journal of The Korean Association For Science Education
• /
• v.37 no.6
• /
• pp.993-1003
• /
• 2017

Teachers expect team-based project learning to help students develop collaborative and real-world problem solving skills. In practice, however, students tend to solve problems with simple division of labor, and there is a tendency that learning transfer does not occur in solving problems. The purpose of this study is to develop a collaborative learning model based on the transactive memory system (TMS) and to verify its effectiveness. The collaborative learning model based on the TMS is composed of three stages. The first stage is developing TMS. In this stage, the students learn physics concepts and make knowledge about the expertise of group members through peer instruction. The second stage, activating TMS, is building trust through solving well-defined problems for developing near-transfer. And in the third stage, applying TMS, the students solve an ill-defined problem based on real-world context for practicing far-transfer. Based on this model, a 15-week program including two projects on geometric optics and sound waves was developed and applied to 60 college students. The data for five weeks of one project were collected and analyzed. As a result, the TMS of the experimental group with the TMS-based collaborative learning model improved stepwise. Whereas, the difference between the first week and the last week was statistically significant, while the TMS change of the comparison group using the general project learning model was not significant. Also, the experimental group showed that the learning transfer occurred better in the project than the comparison group. A collaborative learning model based on TMS can be used to learn how students gain synergy through collaboration and how students collaboratively transfer the learned concepts in problem solving.

• Journal of Service Research and Studies
• /
• v.13 no.2
• /
• pp.99-113
• /
• 2023

In a customer-based industry, customer retention is the competitiveness of a company, and improving customer retention improves the competitiveness of the company. Therefore, accurate prediction and management of potential dormant customers is paramount to increasing the competitiveness of the enterprise. In particular, there are numerous competitors in the domestic card industry, and the government is introducing an automatic closing system for dormant card management. As a result of these social changes, the card industry must focus on better predicting and managing potential dormant cards, and better predicting dormant customers is emerging as an important challenge. In this study, the Recurrent Neural Network (RNN) methodology was used to predict potential dormant customers in the card industry, and in particular, Long-Short Term Memory (LSTM) was used to efficiently learn data for a long time. In addition, to redefine the variables needed to predict dormant customers in the card industry, Unified Theory of Technology (UTAUT), an integrated technology acceptance theory, was applied to redefine and group the variables used in the model. As a result, stable model accuracy and F-1 score were obtained, and Hit-Ratio proved that models using LSTM can produce stable results compared to other algorithms. It was also found that there was no moderating effect of demographic information that could occur in UTAUT, which was pointed out in previous studies. Therefore, among variable selection models using UTAUT, dormant customer prediction models using LSTM are proven to have non-biased stable results. This study revealed that there may be academic contributions to the prediction of dormant customers using LSTM algorithms that can learn well from previously untried time series data. In addition, it is a good example to show that it is possible to respond to customers who are preemptively dormant in terms of customer management because it is predicted at a time difference with the actual dormant capture, and it is expected to contribute greatly to the industry.

• Journal of the Korea Convergence Society
• /
• v.7 no.4
• /
• pp.133-140
• /
• 2016

This paper suggests designing how to acquire English vocabularies on the smart devices based on the research that a ground-breaking English Vocabulary Learning Contents needs developing. The method makes it possible to develop the contents which helps the learners to master English vocabularies effectively on the smart phone. The core idea of this paper is as in the following: 1) English learners learn 30 vocabularies for three minutes 10 times (one is for a new learning and the other nine ones are for reviews about the first learning) a day. 2) Considering Ebbinghaus Forgetting Curve, the reflection study proposes to provide the learners with three times' reviews: one day, 10days, and 30days later from which they learn the first 30 vocabularies. This contents is mainly made up of 5 developing sections (1)to generate App ID, (2)to access App, (3)to set up Alarm, (4)to process Word learning, and (5)to monitor the result of learning. This proposed idea is optimized to enhance the memory by Ebbinghaus Periodic Repetitive Method, which makes the learners satisfied with their English vocabulary learning.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.4
• /
• pp.143-150
• /
• 2013

The School Curriculum amend in 2007 mandates the contents from which students can learn the principles and concepts of computer science. Computer Science is one of the most rapidly changing subjects, and the Informatics textbook should accurately explain the basic principles and concepts based on the latest technology. However, we found that the middle school textbooks in circulation lack accuracy and consistency in describing CPU. This paper attempted to discover the root-cause of the fallacy and suggest timely and appropriate explanation based on the historical and technical analysis. According to our study, it is appropriate to state that CPU is composed of datapath and control unit. The Datapath performs operations on data and holds data temporarily, and it is composed of the hardware components such as memory, register, ALU and adder. The Control unit decides the operation types of datapath elements, main memory and I/O devices. Nevertheless, considering the technological literacy of middle school students, we suggest the terms, 'arithmetic part' and 'control part' instead of datapath and control unit.

• Nuclear Engineering and Technology
• /
• v.52 no.7
• /
• pp.1429-1435
• /
• 2020

Applying an accurate parametric prediction model to identify abnormal or false pressurizer water levels (PWLs) is critical to the safe operation of marine pressurized water reactors (PWRs). Recently, deep-learning-based models have proved to be a powerful feature extractor to perform high-accuracy prediction. However, the effectiveness of models still suffers from two issues in PWL prediction: the correlations shifting over time between PWL and other feature parameters, and the example imbalance between fluctuation examples (minority) and stable examples (majority). To address these problems, we propose a cost-sensitive mechanism to facilitate the model to learn the feature representation of later examples and fluctuation examples. By weighting the standard mean square error loss with a cost-sensitive factor, we develop a Cost-Sensitive Long Short-Term Memory (CSLSTM) model to predict the PWL of PWRs. The overall performance of the CSLSTM is assessed by a variety of evaluation metrics with the experimental data collected from a marine PWR simulator. The comparisons with the Long Short-Term Memory (LSTM) model and the Support Vector Regression (SVR) model demonstrate the effectiveness of the CSLSTM.

• Journal of Convergence for Information Technology
• /
• v.7 no.6
• /
• pp.181-186
• /
• 2017

In recent years, robots have been actively used for children's creativity learning and play, but most robots have a stereotyped form and have a high dependency on the program, making it difficult to learn creativity and play. In order to compensate for these drawbacks, We have created a robot that can easily and reliably combine each other. The robot can memorize the desired operation and execute the memorized operation by using one button. Also, in case multiple modules are combined, pressing the button once on any module makes it possible to easily adjust the operation of all the combined modules. In order to verify the actual operation, two, three, and five modules are combined to demonstrate the usefulness of the proposed structure and algorithm by implementing a gobbling motion and a walking robot. It is required to study intelligent modular robots that can control over the Internet by supplementing the wireless connection method.