• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.47-60
• /
• 2012

Video data comes in the form of the unstructured and the complex structure. As the importance of efficient management and retrieval for video data increases, studies on the video parsing based on the visual features contained in the video contents are researched to reconstruct video data as the meaningful structure. The early studies on video parsing are focused on splitting video data into shots, but detecting the shot boundary defined with the physical boundary does not cosider the semantic association of video data. Recently, studies on structuralizing video shots having the semantic association to the video scene defined with the semantic boundary by utilizing clustering methods are actively progressed. Previous studies on detecting the video scene try to detect video scenes by utilizing clustering algorithms based on the similarity measure between video shots mainly depended on color features. However, the correct identification of a video shot or scene and the detection of the gradual transitions such as dissolve, fade and wipe are difficult because color features of video data contain a noise and are abruptly changed due to the intervention of an unexpected object. In this paper, to solve these problems, we propose the Scene Detector by using Color histogram, corner Edge and Object color histogram (SDCEO) that clusters similar shots organizing same event based on visual features including the color histogram, the corner edge and the object color histogram to detect video scenes. The SDCEO is worthy of notice in a sense that it uses the edge feature with the color feature, and as a result, it effectively detects the gradual transitions as well as the abrupt transitions. The SDCEO consists of the Shot Bound Identifier and the Video Scene Detector. The Shot Bound Identifier is comprised of the Color Histogram Analysis step and the Corner Edge Analysis step. In the Color Histogram Analysis step, SDCEO uses the color histogram feature to organizing shot boundaries. The color histogram, recording the percentage of each quantized color among all pixels in a frame, are chosen for their good performance, as also reported in other work of content-based image and video analysis. To organize shot boundaries, SDCEO joins associated sequential frames into shot boundaries by measuring the similarity of the color histogram between frames. In the Corner Edge Analysis step, SDCEO identifies the final shot boundaries by using the corner edge feature. SDCEO detect associated shot boundaries comparing the corner edge feature between the last frame of previous shot boundary and the first frame of next shot boundary. In the Key-frame Extraction step, SDCEO compares each frame with all frames and measures the similarity by using histogram euclidean distance, and then select the frame the most similar with all frames contained in same shot boundary as the key-frame. Video Scene Detector clusters associated shots organizing same event by utilizing the hierarchical agglomerative clustering method based on the visual features including the color histogram and the object color histogram. After detecting video scenes, SDCEO organizes final video scene by repetitive clustering until the simiarity distance between shot boundaries less than the threshold h. In this paper, we construct the prototype of SDCEO and experiments are carried out with the baseline data that are manually constructed, and the experimental results that the precision of shot boundary detection is 93.3% and the precision of video scene detection is 83.3% are satisfactory.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.57-75
• /
• 2019

In this paper, we conducted a study focusing on the innovation direction of the documentary model on the Internet of Things industry, which is the most actively industrialized among the core technologies of the 4th Industrial Revolution. Policy, economic, social, and technical issues were derived using PEST analysis for global trend analysis. It also presented future prospects for the Internet of Things industry of ICT-related global research institutes such as Gartner and International Data Corporation. Global research institutes predicted that competition in network technologies will be an issue for industrial Internet (IIoST) and IoT (Internet of Things) based on infrastructure and platforms. As a result of the PEST analysis, developed countries are pushing policies to respond to the fourth industrial revolution through cooperation of private (business/ research institutes) led by the government. It was also in the process of expanding related R&D budgets and establishing related policies in South Korea. On the economic side, the growth tax of the related industries (based on the aggregate value of the market) and the performance of the entity were reviewed. The growth of industries related to the fourth industrial revolution in advanced countries overseas was found to be faster than other industries, while in Korea, the growth of the "technical hardware and equipment" and "communication service" sectors was relatively low among industries related to the fourth industrial revolution. On the social side, it is expected to cause enormous ripple effects across society, largely due to changes in technology and industrial structure, changes in employment structure, changes in job volume, etc. On the technical side, changes were taking place in each industry, representing the health and medical sectors and manufacturing sectors, which were rapidly changing as they merged with the technology of the Fourth Industrial Revolution. In this paper, various management methodologies for innovation of existing business model were reviewed to cope with rapidly changing industrial environment due to the fourth industrial revolution. In addition, four criteria were established to select a management model to cope with the new business environment: 'Applicability', 'Agility', 'Diversity' and 'Connectivity'. The expert survey results in an AHP analysis showing that Business Model Canvas is best suited for business model innovation methodology. The results showed very high importance, 42.5 percent in terms of "Applicability", 48.1 percent in terms of "Agility", 47.6 percent in terms of "diversity" and 42.9 percent in terms of "connectivity." Thus, it was selected as a model that could be diversely applied according to the industrial ecology and paradigm shift. Business Model Canvas is a relatively recent management strategy that identifies the value of a business model through a nine-block approach as a methodology for business model innovation. It identifies the value of a business model through nine block approaches and covers the four key areas of business: customer, order, infrastructure, and business feasibility analysis. In the paper, the expansion and application direction of the nine blocks were presented from the perspective of the IoT company (ICT). In conclusion, the discussion of which Business Model Canvas models will be applied in the ICT convergence industry is described. Based on the nine blocks, if appropriate applications are carried out to suit the characteristics of the target company, various applications are possible, such as integration and removal of five blocks, seven blocks and so on, and segmentation of blocks that fit the characteristics. Future research needs to develop customized business innovation methodologies for Internet of Things companies, or those that are performing Internet-based services. In addition, in this study, the Business Model Canvas model was derived from expert opinion as a useful tool for innovation. For the expansion and demonstration of the research, a study on the usability of presenting detailed implementation strategies, such as various model application cases and application models for actual companies, is needed.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.51-66
• /
• 2018

As AI (Artificial Intelligence) technologies have been swiftly evolved, a lot of products and services are under development in various fields for better users' experience. On this technology advance, negative effects of AI technologies also have been discussed actively while there exists positive expectation on them at the same time. For instance, many social issues such as trolley dilemma and system security issues are being debated, whereas autonomous vehicles based on artificial intelligence have had attention in terms of stability increase. Therefore, it needs to check and analyse major social issues on artificial intelligence for their development and societal acceptance. In this paper, multi-categorical sentiment analysis is conducted over online public opinion on artificial intelligence after identifying the trending topics related to artificial intelligence for two years from January 2016 to December 2017, which include the event, match between Lee Sedol and AlphaGo. Using the largest web portal in South Korea, online news, news headlines and news comments were crawled. Considering the importance of trending topics, online public opinion was analysed into seven multiple sentimental categories comprised of anger, dislike, fear, happiness, neutrality, sadness, and surprise by topics, not only two simple positive or negative sentiment. As a result, it was found that the top sentiment is "happiness" in most events and yet sentiments on each keyword are different. In addition, when the research period was divided into four periods, the first half of 2016, the second half of the year, the first half of 2017, and the second half of the year, it is confirmed that the sentiment of 'anger' decreases as goes by time. Based on the results of this analysis, it is possible to grasp various topics and trends currently discussed on artificial intelligence, and it can be used to prepare countermeasures. We hope that we can improve to measure public opinion more precisely in the future by integrating empathy level of news comments.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.239-251
• /
• 2019

Statistical methods such as moving averages, Kalman filtering, exponential smoothing, regression analysis, and ARIMA (autoregressive integrated moving average) have been used for stock market predictions. However, these statistical methods have not produced superior performances. In recent years, machine learning techniques have been widely used in stock market predictions, including artificial neural network, SVM, and genetic algorithm. In particular, a case-based reasoning method, known as k-nearest neighbor is also widely used for stock price prediction. Case based reasoning retrieves several similar cases from previous cases when a new problem occurs, and combines the class labels of similar cases to create a classification for the new problem. However, case based reasoning has some problems. First, case based reasoning has a tendency to search for a fixed number of neighbors in the observation space and always selects the same number of neighbors rather than the best similar neighbors for the target case. So, case based reasoning may have to take into account more cases even when there are fewer cases applicable depending on the subject. Second, case based reasoning may select neighbors that are far away from the target case. Thus, case based reasoning does not guarantee an optimal pseudo-neighborhood for various target cases, and the predictability can be degraded due to a deviation from the desired similar neighbor. This paper examines how the size of learning data affects stock price predictability through k-nearest neighbor and compares the predictability of k-nearest neighbor with the random walk model according to the size of the learning data and the number of neighbors. In this study, Samsung electronics stock prices were predicted by dividing the learning dataset into two types. For the prediction of next day's closing price, we used four variables: opening value, daily high, daily low, and daily close. In the first experiment, data from January 1, 2000 to December 31, 2017 were used for the learning process. In the second experiment, data from January 1, 2015 to December 31, 2017 were used for the learning process. The test data is from January 1, 2018 to August 31, 2018 for both experiments. We compared the performance of k-NN with the random walk model using the two learning dataset. The mean absolute percentage error (MAPE) was 1.3497 for the random walk model and 1.3570 for the k-NN for the first experiment when the learning data was small. However, the mean absolute percentage error (MAPE) for the random walk model was 1.3497 and the k-NN was 1.2928 for the second experiment when the learning data was large. These results show that the prediction power when more learning data are used is higher than when less learning data are used. Also, this paper shows that k-NN generally produces a better predictive power than random walk model for larger learning datasets and does not when the learning dataset is relatively small. Future studies need to consider macroeconomic variables related to stock price forecasting including opening price, low price, high price, and closing price. Also, to produce better results, it is recommended that the k-nearest neighbor needs to find nearest neighbors using the second step filtering method considering fundamental economic variables as well as a sufficient amount of learning data.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.43-62
• /
• 2019

At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.63-88
• /
• 2019

The goal of this paper is to investigate changes in North Korea's domestic and foreign policies through automated text analysis over North Korea represented in South Korean mass media. Based on that data, we then analyze the status of text mining research, using a text mining technique to find the topics, methods, and trends of text mining research. We also investigate the characteristics and method of analysis of the text mining techniques, confirmed by analysis of the data. In this study, R program was used to apply the text mining technique. R program is free software for statistical computing and graphics. Also, Text mining methods allow to highlight the most frequently used keywords in a paragraph of texts. One can create a word cloud, also referred as text cloud or tag cloud. This study proposes a procedure to find meaningful tendencies based on a combination of word cloud, and co-occurrence networks. This study aims to more objectively explore the images of North Korea represented in South Korean newspapers by quantitatively reviewing the patterns of language use related to North Korea from 2016. 11. 1 to 2019. 5. 23 newspaper big data. In this study, we divided into three periods considering recent inter - Korean relations. Before January 1, 2018, it was set as a Before Phase of Peace Building. From January 1, 2018 to February 24, 2019, we have set up a Peace Building Phase. The New Year's message of Kim Jong-un and the Olympics of Pyeong Chang formed an atmosphere of peace on the Korean peninsula. After the Hanoi Pease summit, the third period was the silence of the relationship between North Korea and the United States. Therefore, it was called Depression Phase of Peace Building. This study analyzes news articles related to North Korea of the Korea Press Foundation database(www.bigkinds.or.kr) through text mining, to investigate characteristics of the Kim Jong-un regime's South Korea policy and unification discourse. The main results of this study show that trends in the North Korean national policy agenda can be discovered based on clustering and visualization algorithms. In particular, it examines the changes in the international circumstances, domestic conflicts, the living conditions of North Korea, the South's Aid project for the North, the conflicts of the two Koreas, North Korean nuclear issue, and the North Korean refugee problem through the co-occurrence word analysis. It also offers an analysis of South Korean mentality toward North Korea in terms of the semantic prosody. In the Before Phase of Peace Building, the results of the analysis showed the order of 'Missiles', 'North Korea Nuclear', 'Diplomacy', 'Unification', and ' South-North Korean'. The results of Peace Building Phase are extracted the order of 'Panmunjom', 'Unification', 'North Korea Nuclear', 'Diplomacy', and 'Military'. The results of Depression Phase of Peace Building derived the order of 'North Korea Nuclear', 'North and South Korea', 'Missile', 'State Department', and 'International'. There are 16 words adopted in all three periods. The order is as follows: 'missile', 'North Korea Nuclear', 'Diplomacy', 'Unification', 'North and South Korea', 'Military', 'Kaesong Industrial Complex', 'Defense', 'Sanctions', 'Denuclearization', 'Peace', 'Exchange and Cooperation', and 'South Korea'. We expect that the results of this study will contribute to analyze the trends of news content of North Korea associated with North Korea's provocations. And future research on North Korean trends will be conducted based on the results of this study. We will continue to study the model development for North Korea risk measurement that can anticipate and respond to North Korea's behavior in advance. We expect that the text mining analysis method and the scientific data analysis technique will be applied to North Korea and unification research field. Through these academic studies, I hope to see a lot of studies that make important contributions to the nation.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.127-137
• /
• 2019

Recidivism prediction has been a subject of constant research by experts since the early 1970s. But it has become more important as committed crimes by recidivist steadily increase. Especially, in the 1990s, after the US and Canada adopted the 'Recidivism Risk Assessment Report' as a decisive criterion during trial and parole screening, research on recidivism prediction became more active. And in the same period, empirical studies on 'Recidivism Factors' were started even at Korea. Even though most recidivism prediction studies have so far focused on factors of recidivism or the accuracy of recidivism prediction, it is important to minimize the prediction misclassification cost, because recidivism prediction has an asymmetric error cost structure. In general, the cost of misrecognizing people who do not cause recidivism to cause recidivism is lower than the cost of incorrectly classifying people who would cause recidivism. Because the former increases only the additional monitoring costs, while the latter increases the amount of social, and economic costs. Therefore, in this paper, we propose an XGBoost(eXtream Gradient Boosting; XGB) based recidivism prediction model considering asymmetric error cost. In the first step of the model, XGB, being recognized as high performance ensemble method in the field of data mining, was applied. And the results of XGB were compared with various prediction models such as LOGIT(logistic regression analysis), DT(decision trees), ANN(artificial neural networks), and SVM(support vector machines). In the next step, the threshold is optimized to minimize the total misclassification cost, which is the weighted average of FNE(False Negative Error) and FPE(False Positive Error). To verify the usefulness of the model, the model was applied to a real recidivism prediction dataset. As a result, it was confirmed that the XGB model not only showed better prediction accuracy than other prediction models but also reduced the cost of misclassification most effectively.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.47-64
• /
• 2021

The global spread of COVID-19 around the world has not only affected many parts of our daily life but also has a huge impact on many areas, including the economy and society. As the number of confirmed cases and deaths increases, medical staff and the public are said to be experiencing psychological problems such as anxiety, depression, and stress. The collective tragedy that accompanies the epidemic raises fear and anxiety, which is known to cause enormous disruptions to the behavior and psychological well-being of many. Long-term negative emotions can reduce people's immunity and destroy their physical balance, so it is essential to understand the psychological state of COVID-19. This study suggests a method of monitoring medial news reflecting current days which requires striving not only for physical but also for psychological quarantine in the prolonged COVID-19 situation. Moreover, it is presented how an easier method of analyzing social media networks applies to those cases. The aim of this study is to assist health policymakers in fast and complex decision-making processes. News plays a major role in setting the policy agenda. Among various major media, news headlines are considered important in the field of communication science as a summary of the core content that the media wants to convey to the audiences who read it. News data used in this study was easily collected using "Bigkinds" that is created by integrating big data technology. With the collected news data, keywords were classified through text mining, and the relationship between words was visualized through semantic network analysis between keywords. Using the KrKwic program, a Korean semantic network analysis tool, text mining was performed and the frequency of words was calculated to easily identify keywords. The frequency of words appearing in keywords of articles related to COVID-19 emotions was checked and visualized in word cloud 'China', 'anxiety', 'situation', 'mind', 'social', and 'health' appeared high in relation to the emotions of COVID-19. In addition, UCINET, a specialized social network analysis program, was used to analyze connection centrality and cluster analysis, and a method of visualizing a graph using Net Draw was performed. As a result of analyzing the connection centrality between each data, it was found that the most central keywords in the keyword-centric network were 'psychology', 'COVID-19', 'blue', and 'anxiety'. The network of frequency of co-occurrence among the keywords appearing in the headlines of the news was visualized as a graph. The thickness of the line on the graph is proportional to the frequency of co-occurrence, and if the frequency of two words appearing at the same time is high, it is indicated by a thick line. It can be seen that the 'COVID-blue' pair is displayed in the boldest, and the 'COVID-emotion' and 'COVID-anxiety' pairs are displayed with a relatively thick line. 'Blue' related to COVID-19 is a word that means depression, and it was confirmed that COVID-19 and depression are keywords that should be of interest now. The research methodology used in this study has the convenience of being able to quickly measure social phenomena and changes while reducing costs. In this study, by analyzing news headlines, we were able to identify people's feelings and perceptions on issues related to COVID-19 depression, and identify the main agendas to be analyzed by deriving important keywords. By presenting and visualizing the subject and important keywords related to the COVID-19 emotion at a time, medical policy managers will be able to be provided a variety of perspectives when identifying and researching the regarding phenomenon. It is expected that it can help to use it as basic data for support, treatment and service development for psychological quarantine issues related to COVID-19.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.177-190
• /
• 2021

Due to the development of the fourth industrial revolution technology, efforts are being made to improve areas that humans cannot handle by utilizing artificial intelligence techniques such as machine learning. Although on-demand production companies also want to reduce corporate risks such as delays in delivery by predicting total production time for orders, they are having difficulty predicting this because the total production time is all different for each order. The Theory of Constraints (TOC) theory was developed to find the least efficient areas to increase order throughput and reduce order total cost, but failed to provide a forecast of total production time. Order production varies from order to order due to various customer needs, so the total production time of individual orders can be measured postmortem, but it is difficult to predict in advance. The total measured production time of existing orders is also different, which has limitations that cannot be used as standard time. As a result, experienced managers rely on persimmons rather than on the use of the system, while inexperienced managers use simple management indicators (e.g., 60 days total production time for raw materials, 90 days total production time for steel plates, etc.). Too fast work instructions based on imperfections or indicators cause congestion, which leads to productivity degradation, and too late leads to increased production costs or failure to meet delivery dates due to emergency processing. Failure to meet the deadline will result in compensation for delayed compensation or adversely affect business and collection sectors. In this study, to address these problems, an entity that operates an order production system seeks to find a machine learning model that estimates the total production time of new orders. It uses orders, production, and process performance for materials used for machine learning. We compared and analyzed OLS, GLM Gamma, Extra Trees, and Random Forest algorithms as the best algorithms for estimating total production time and present the results.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.191-206
• /
• 2022

Recently, it is a de-facto approach to utilize a pre-trained language model(PLM) to achieve the state-of-the-art performance for various natural language tasks(called downstream tasks) such as sentiment analysis and question answering. However, similar to any other machine learning method, PLM tends to depend on the data distribution seen during the training phase and shows worse performance on the unseen (Out-of-Distribution) domain. Due to the aforementioned reason, there have been many efforts to develop domain-specified PLM for various fields such as medical and legal industries. In this paper, we discuss the training of a finance domain-specified PLM for the Korean language and its applications. Our finance domain-specified PLM, KB-BERT, is trained on a carefully curated financial corpus that includes domain-specific documents such as financial reports. We provide extensive performance evaluation results on three natural language tasks, topic classification, sentiment analysis, and question answering. Compared to the state-of-the-art Korean PLM models such as KoELECTRA and KLUE-RoBERTa, KB-BERT shows comparable performance on general datasets based on common corpora like Wikipedia and news articles. Moreover, KB-BERT outperforms compared models on finance domain datasets that require finance-specific knowledge to solve given problems.