• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1328-1336
• /
• 2019

To maintain the safe and optimal performance of batteries, accurate estimation of state of charge (SOC) is critical. In this paper, Long short-term memory network (LSTM) based on the artificial intelligence algorithm is applied to address the problem of the conventional coulomb-counting method. Different discharge cycles are concatenated to form the dataset for training and verification. In oder to improve the quality of input data for learning, preprocessing was performed. In addition, we compared learning ability and SOC estimation performance according to the structure of LSTM model and hyperparameter setup. The trained model was verified with a UDDS profile and achieved estimated accuracy of RMSE 0.82% and MAX 2.54%.

• Journal of KIISE
• /
• v.43 no.8
• /
• pp.902-909
• /
• 2016

Question answering system (QA system) is a system that finds an actual answer to the question posed by a user, whereas a typical search engine would only find the links to the relevant documents. Recent works related to the open domain QA systems are receiving much attention in the fields of natural language processing, artificial intelligence, and data mining. However, the prior works on QA systems simply replace all words that are not in the training data with a single token, even though such unseen words are likely to play crucial roles in differentiating the candidate answers from the actual answers. In this paper, we propose a method to compute vectors of such unseen words by taking into account the context in which the words have occurred. Next, we also propose a model which utilizes inverse document frequencies (IDF) to efficiently process unseen words by expanding the system's vocabulary. Finally, we validate that the proposed method and model improve the performance of a QA system through experiments.

• Journal of The Korean Astronomical Society
• /
• v.45 no.2
• /
• pp.31-38
• /
• 2012

In this study we apply Support Vector Machine (SVM) to the prediction of geo-effective halo coronal mass ejections (CMEs). The SVM, which is one of machine learning algorithms, is used for the purpose of classification and regression analysis. We use halo and partial halo CMEs from January 1996 to April 2010 in the SOHO/LASCO CME Catalog for training and prediction. And we also use their associated X-ray flare classes to identify front-side halo CMEs (stronger than B1 class), and the Dst index to determine geo-effective halo CMEs (stronger than -50 nT). The combinations of the speed and the angular width of CMEs, and their associated X-ray classes are used for input features of the SVM. We make an attempt to find the best model by using cross-validation which is processed by changing kernel functions of the SVM and their parameters. As a result we obtain statistical parameters for the best model by using the speed of CME and its associated X-ray flare class as input features of the SVM: Accuracy=0.66, PODy=0.76, PODn=0.49, FAR=0.72, Bias=1.06, CSI=0.59, TSS=0.25. The performance of the statistical parameters by applying the SVM is much better than those from the simple classifications based on constant classifiers.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.5
• /
• pp.871-879
• /
• 2020

Perceptual Ad-Blocking is a new advertising blocking technique that detects online advertising by using an artificial intelligence-based advertising image classification model. A recent study has shown that these Perceptual Ad-Blocking models are vulnerable to adversarial attacks using adversarial examples to add noise to images that cause them to be misclassified. In this paper, we prove that existing perceptual Ad-Blocking technique has a weakness for several adversarial example and that Defense-GAN and MagNet who performed well for MNIST dataset and CIFAR-10 dataset are good to advertising dataset. Through this, using Defense-GAN and MagNet techniques, it presents a robust new advertising image classification model for adversarial attacks. According to the results of experiments using various existing adversarial attack techniques, the techniques proposed in this paper were able to secure the accuracy and performance through the robust image classification techniques, and furthermore, they were able to defend a certain level against white-box attacks by attackers who knew the details of defense techniques.

• Journal of Digital Convergence
• /
• v.19 no.9
• /
• pp.181-188
• /
• 2021

Research and importance of legal services applied with AI so that it can be easily understood and predictable in difficult legal fields is increasing. In this study, based on the decision of the Tax Tribunal in the field of tax law, a model was built through self-learning through information collection and data processing, and the prediction results were answered to the user's query and the accuracy was verified. The proposed model collects information on tax decisions and extracts useful data through web crawling, and generates word vectors by applying Word2Vec's Fast Text algorithm to the optimized output through NLP. 11,103 cases of information were collected and classified from 2017 to 2019, and verified with 70% accuracy. It can be useful in various legal systems and prior research to be more efficient application.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.95-103
• /
• 2019

The global manufacturing industry has reached the limit to growth due to a long-term recession, the rise of labor cost and raw material. As a solution to these difficulties, we promote the 4th Industry Revolution based on ICT and sensor technology. Following this trend, this paper proposes the design of a model using manufacturing data in the protection film process for smart manufacturing innovation. In the protective film process, the manufacturing data of temperature, pressure, humidity, and motion and thermal image are acquired by various sensors for the raw material blending, stirring, extrusion, and inspection processes. While the acquired manufacturing data is stored in mass storage, A.I. platform provides time-series image analysis and its visualization.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.161-167
• /
• 2019

Recently, demand forecasting techniques have been actively studied due to interest in stable power supply with surging power demand, and increase in spread of smart meters that enable real-time power measurement. In this study, we proceeded the deep learning prediction model experiments which learns actual measured power usage data of home and outputs the forecasting result. And we proceeded pre-processing with moving average method. The predicted value made by the model is evaluated with the actual measured data. Through this forecasting, it is possible to lower the power supply reserve ratio and reduce the waste of the unused power. In this paper, we conducted experiments on three types of networks: Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short Term Memory (LSTM) and we evaluate the results of each scheme. Evaluation is conducted with following method: MSE(Mean Squared Error) method and MAE(Mean Absolute Error).

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.111-120
• /
• 2020

Despite the recent economic contraction caused by the Corona 19 incident, interest in the residential environment is growing as more people live at home due to the increase in telecommuting, thereby increasing demand for remodeling. In addition, the government's real estate policy is also expected to have a visible impact on the sales of the interior and furniture industries as it shifts from regulatory policy to the expansion of housing supply. Accurate demand forecasting is a problem directly related to inventory management, and a good demand forecast can reduce logistics and inventory costs due to overproduction by eliminating the need to have unnecessary inventory. However, it is a difficult problem to predict accurate demand because external factors such as constantly changing economic trends, market trends, and social issues must be taken into account. In this study, LSTM model and 1D-CNN model were compared and analyzed by artificial intelligence-based time series analysis method to produce reliable results for manufacturers producing furniture components.

• The Journal of Information Systems
• /
• v.31 no.1
• /
• pp.289-304
• /
• 2022

Purpose The development of the network and mobile industries has induced companies to invest in information systems, leading a new industrial revolution. The Journal of Information Systems, which developed the information system field into a theoretical and practical study in the 1990s, retains a 30-year history of information systems. This study aims to identify academic values and research trends of JIS by analyzing the trends. Design/methodology/approach This study aims to analyze the trend of JIS by compounding various methods, named as TLS mining analysis. TLS mining analysis consists of a series of analysis including Term Frequency-Inverse Document Frequency (TF-IDF) weight model, Latent Dirichlet Allocation (LDA) topic modeling, and a text mining with Semantic Network Analysis. Firstly, keywords are extracted from the research data using the TF-IDF weight model, and after that, topic modeling is performed using the Latent Dirichlet Allocation (LDA) algorithm to identify issue keywords. Findings The current study used the summery service of the published research paper provided by Korea Citation Index to analyze JIS. 714 papers that were published from 2002 to 2012 were divided into two periods: 2002-2011 and 2012-2021. In the first period (2002-2011), the research trend in the information system field had focused on E-business strategies as most of the companies adopted online business models. In the second period (2012-2021), data-based information technology and new industrial revolution technologies such as artificial intelligence, SNS, and mobile had been the main research issues in the information system field. In addition, keywords for improving the JIS citation index were presented.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2022

In computer vision research, the two-dimensional human pose is a very extensive research direction, especially in pose tracking and behavior recognition, which has very important research significance. The acquisition of human pose targets, which is essentially the study of how to accurately identify human targets from pictures, is of great research significance and has been a hot research topic of great interest in recent years. Human pose recognition is used in artificial intelligence on the one hand and in daily life on the other. The excellent effect of pose recognition is mainly determined by the success rate and the accuracy of the recognition process, so it reflects the importance of human pose recognition in terms of recognition rate. In this human body gesture recognition, the human body is divided into 17 key points for labeling. Not only that but also the key points are segmented to ensure the accuracy of the labeling information. In the recognition design, use the comprehensive data set MS COCO for deep learning to design a neural network model to train a large number of samples, from simple step-by-step to efficient training, so that a good accuracy rate can be obtained.