• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• 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.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• The Korean Journal of Air & Space Law and Policy
• /
• v.32 no.2
• /
• pp.155-188
• /
• 2017

On the one hand, the 4th Industrial Revolution provides a positive opportunity to build a new civilization paradigm for mankind. However, on the other hand, due to the 4th Industrial Revolution, artificial intelligence such as 'Goggle Alpha Go' revolutionized and even the human ability was replaced with a 'Silicon Chip' as the opportunity to communicate decreases, the existence of human beings is weakened. And there is a growing concern that the number of violent crimes, such as psychopath, which hunts humans as games, will increase. Moreover, recent international terrorism is being developed in a form similar to 'Psychopathic Violent-Crime' that indiscriminately attacks innocent people. So, the probability that terrorist organizations abuse the positive effects provided by the Fourth Industrial Revolution as means of terrorism is increasing. Therefore, the paradigm of aviation terrorism is expected to change in a way that attacks airport facilities and users rather than aircraft. Because airport facilities are crowded, and psychopathic terrorists are easily accessible. From this point of view, our counter terrorism system of aviation has many weak points in various aspects such as: (1) limitations of counter-terrorism center (2) inefficient on-site command and control system (3) separated organization for aviation security consultation (4) dispersed information collection function in government (5) vulnerable to cyber attack (6) lack of international cooperation network for aviation terrorism. Consequently, it is necessary to improve the domestic counter terrorism system of aviation so as to preemptively respond to the international terrorism. This study propose the following measures to improve the aviation security system by (1) create 'Aviation Special Judicial Police' (2) revise the anti-terrorism law and aviation security law (3) Strengthening the ability respond to terrorism in cyberspace (4) building an international cooperation network for aviation terrorism.

• Food Science and Industry
• /
• v.55 no.2
• /
• pp.188-202
• /
• 2022

In the insect industry, as the scope of application of insects is expanded from pet insects and natural enemies to feed, edible and medicinal insects, the demand for quality control of insect raw materials is increasing, and interest in securing the safety of insect products is increasing. In the process of expanding the industrial scale, controlling the temperature and humidity and air quality in the insect breeding room and preventing the spread of pathogens and other pollutants are important success factors. It requires a controlled environment under the operating system. European commercial insect breeding facilities have attracted considerable investor interest, and insect companies are building large-scale production facilities, which became possible after the EU approved the use of insect protein as feedstock for fish farming in July 2017. Other fields, such as food and medicine, have also accelerated the application of cutting-edge technology. In the future, the global insect industry will purchase eggs or small larvae from suppliers and a system that focuses on the larval fattening, i.e., production raw material, until the insects mature, and a system that handles the entire production process from egg laying, harvesting, and initial pre-treatment of larvae., increasingly subdivided into large-scale production systems that cover all stages of insect larvae production and further processing steps such as milling, fat removal and protein or fat fractionation. In Korea, research and development of insect smart factory farms using artificial intelligence and ICT is accelerating, so insects can be used as carbon-free materials in secondary industries such as natural plastics or natural molding materials as well as existing feed and food. A Korean-style customized breeding system for shortening the breeding period or enhancing functionality is expected to be developed soon.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.1 s.15
• /
• pp.51-63
• /
• 2000

Dynamic traffic assignment(DTA) has been a topic of substantial research during the past decade. While DTA is gradually maturing, many aspects of DTA still need improvement, especially regarding its formulation and solution algerian Recently, with its promise for In(Intelligent Transportation System) and GIS(Geographic Information System) applications, DTA have received increasing attention. This potential also implies higher requirement for DTA modeling, especially regarding its solution efficiency for real-time implementation. But DTA have many mathematical difficulties in searching process due to the complexity of spatial and temporal variables. Although many solution algorithms have been studied, conventional methods cannot iud the solution in case that objective function or constraints is not convex. In this paper, the genetic algorithm to find the solution of DTA is applied and the Merchant-Nemhauser model is used as DTA model because it has a nonconvex constraint set. To handle the nonconvex constraint set the GENOCOP III system which is a kind of the genetic algorithm is used in this study. Results for the sample network have been compared with the results of conventional method.

• Journal of the Korean Society of Safety
• /
• v.7 no.2
• /
• pp.63-70
• /
• 1992

The aim of this research is to obtain a basic quantitative understanding of the effect of a noncondensable gas on the absorption of water vapor by a $H_2O$ / LiBr combination with n-octanol as the surfactant. Nonflowing aqueous solutions of LiBr (40,45,50 mass％) were exposed to saturated water vapor following the addition of an n-octanol sufactant (0.01 and 0.6 mass％). A small amount of a noncondensable gas (air) was allowed into the absorber (0.03 volume％) and its effect was analyzed by measuring the amount of water vapor absorbed. This study will aid to predict the performance of heat pump and safety operating condition when the noncondensable gas is not allowed in the absorber The results indicate that, in the presence of small amounts of a noncondensable gas, vapor absorption enhancement ratios are less than half o( those obtained under the same experimental conditions when a noncondensable gas is not present (1). The presence of a noncondensable gas causes the partial vapor pressure of air to increase at the vapor / liquid interface, which results in an instability of vapor absorption rate nd. hence, in an inhibition of interfacial disturbance.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.71-88
• /
• 2017

Language models were originally developed for speech recognition and language processing. Using a set of example sentences, a language model predicts the next word or character based on sequential input data. N-gram models have been widely used but this model cannot model the correlation between the input units efficiently since it is a probabilistic model which are based on the frequency of each unit in the training set. Recently, as the deep learning algorithm has been developed, a recurrent neural network (RNN) model and a long short-term memory (LSTM) model have been widely used for the neural language model (Ahn, 2016; Kim et al., 2016; Lee et al., 2016). These models can reflect dependency between the objects that are entered sequentially into the model (Gers and Schmidhuber, 2001; Mikolov et al., 2010; Sundermeyer et al., 2012). In order to learning the neural language model, texts need to be decomposed into words or morphemes. Since, however, a training set of sentences includes a huge number of words or morphemes in general, the size of dictionary is very large and so it increases model complexity. In addition, word-level or morpheme-level models are able to generate vocabularies only which are contained in the training set. Furthermore, with highly morphological languages such as Turkish, Hungarian, Russian, Finnish or Korean, morpheme analyzers have more chance to cause errors in decomposition process (Lankinen et al., 2016). Therefore, this paper proposes a phoneme-level language model for Korean language based on LSTM models. A phoneme such as a vowel or a consonant is the smallest unit that comprises Korean texts. We construct the language model using three or four LSTM layers. Each model was trained using Stochastic Gradient Algorithm and more advanced optimization algorithms such as Adagrad, RMSprop, Adadelta, Adam, Adamax, and Nadam. Simulation study was done with Old Testament texts using a deep learning package Keras based the Theano. After pre-processing the texts, the dataset included 74 of unique characters including vowels, consonants, and punctuation marks. Then we constructed an input vector with 20 consecutive characters and an output with a following 21st character. Finally, total 1,023,411 sets of input-output vectors were included in the dataset and we divided them into training, validation, testsets with proportion 70:15:15. All the simulation were conducted on a system equipped with an Intel Xeon CPU (16 cores) and a NVIDIA GeForce GTX 1080 GPU. We compared the loss function evaluated for the validation set, the perplexity evaluated for the test set, and the time to be taken for training each model. As a result, all the optimization algorithms but the stochastic gradient algorithm showed similar validation loss and perplexity, which are clearly superior to those of the stochastic gradient algorithm. The stochastic gradient algorithm took the longest time to be trained for both 3- and 4-LSTM models. On average, the 4-LSTM layer model took 69% longer training time than the 3-LSTM layer model. However, the validation loss and perplexity were not improved significantly or became even worse for specific conditions. On the other hand, when comparing the automatically generated sentences, the 4-LSTM layer model tended to generate the sentences which are closer to the natural language than the 3-LSTM model. Although there were slight differences in the completeness of the generated sentences between the models, the sentence generation performance was quite satisfactory in any simulation conditions: they generated only legitimate Korean letters and the use of postposition and the conjugation of verbs were almost perfect in the sense of grammar. The results of this study are expected to be widely used for the processing of Korean language in the field of language processing and speech recognition, which are the basis of artificial intelligence systems.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.191-207
• /
• 2021

Up to this day, mobile communications have evolved rapidly over the decades, mainly focusing on speed-up to meet the growing data demands of 2G to 5G. And with the start of the 5G era, efforts are being made to provide such various services to customers, as IoT, V2X, robots, artificial intelligence, augmented virtual reality, and smart cities, which are expected to change the environment of our lives and industries as a whole. In a bid to provide those services, on top of high speed data, reduced latency and reliability are critical for real-time services. Thus, 5G has paved the way for service delivery through maximum speed of 20Gbps, a delay of 1ms, and a connecting device of 106/㎢ In particular, in intelligent traffic control systems and services using various vehicle-based Vehicle to X (V2X), such as traffic control, in addition to high-speed data speed, reduction of delay and reliability for real-time services are very important. 5G communication uses high frequencies of 3.5Ghz and 28Ghz. These high-frequency waves can go with high-speed thanks to their straightness while their short wavelength and small diffraction angle limit their reach to distance and prevent them from penetrating walls, causing restrictions on their use indoors. Therefore, under existing networks it's difficult to overcome these constraints. The underlying centralized SDN also has a limited capability in offering delay-sensitive services because communication with many nodes creates overload in its processing. Basically, SDN, which means a structure that separates signals from the control plane from packets in the data plane, requires control of the delay-related tree structure available in the event of an emergency during autonomous driving. In these scenarios, the network architecture that handles in-vehicle information is a major variable of delay. Since SDNs in general centralized structures are difficult to meet the desired delay level, studies on the optimal size of SDNs for information processing should be conducted. Thus, SDNs need to be separated on a certain scale and construct a new type of network, which can efficiently respond to dynamically changing traffic and provide high-quality, flexible services. Moreover, the structure of these networks is closely related to ultra-low latency, high confidence, and hyper-connectivity and should be based on a new form of split SDN rather than an existing centralized SDN structure, even in the case of the worst condition. And in these SDN structural networks, where automobiles pass through small 5G cells very quickly, the information change cycle, round trip delay (RTD), and the data processing time of SDN are highly correlated with the delay. Of these, RDT is not a significant factor because it has sufficient speed and less than 1 ms of delay, but the information change cycle and data processing time of SDN are factors that greatly affect the delay. Especially, in an emergency of self-driving environment linked to an ITS(Intelligent Traffic System) that requires low latency and high reliability, information should be transmitted and processed very quickly. That is a case in point where delay plays a very sensitive role. In this paper, we study the SDN architecture in emergencies during autonomous driving and conduct analysis through simulation of the correlation with the cell layer in which the vehicle should request relevant information according to the information flow. For simulation: As the Data Rate of 5G is high enough, we can assume the information for neighbor vehicle support to the car without errors. Furthermore, we assumed 5G small cells within 50 ~ 250 m in cell radius, and the maximum speed of the vehicle was considered as a 30km ~ 200 km/hour in order to examine the network architecture to minimize the delay.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.149-169
• /
• 2018

Korea is currently accumulating a large amount of data in public institutions based on the public data open policy and the "Government 3.0". Especially, a lot of data is accumulated in the tourism field. However, the academic discussions utilizing the tourism data are still limited. Moreover, the openness of the data of restaurants, hotels, and online tourism information, and how to use SNS Big Data in tourism are still limited. Therefore, utilization through tourism big data analysis is still low. In this paper, we tried to analyze influencing factors on foreign tourists' satisfaction in Korea through numerical data using data mining technique and R programming technique. In this study, we tried to find ways to revitalize the tourism industry by analyzing about 36,000 big data of the "Survey on the actual situation of foreign tourists from 2013 to 2015" surveyed by the Korea Culture & Tourism Research Institute. To do this, we analyzed the factors that have high influence on the 'Satisfaction', 'Revisit intention', and 'Recommendation' variables of foreign tourists. Furthermore, we analyzed the practical influences of the variables that are mentioned above. As a procedure of this study, we first integrated survey data of foreign tourists conducted by Korea Culture & Tourism Research Institute, which is stored in the tourist information system from 2013 to 2015, and eliminate unnecessary variables that are inconsistent with the research purpose among the integrated data. Some variables were modified to improve the accuracy of the analysis. And we analyzed the factors affecting the dependent variables by using data-mining methods: decision tree(C5.0, CART, CHAID, QUEST), artificial neural network, and logistic regression analysis of SPSS IBM Modeler 16.0. The seven variables that have the greatest effect on each dependent variable were derived. As a result of data analysis, it was found that seven major variables influencing 'overall satisfaction' were sightseeing spot attraction, food satisfaction, accommodation satisfaction, traffic satisfaction, guide service satisfaction, number of visiting places, and country. Variables that had a great influence appeared food satisfaction and sightseeing spot attraction. The seven variables that had the greatest influence on 'revisit intention' were the country, travel motivation, activity, food satisfaction, best activity, guide service satisfaction and sightseeing spot attraction. The most influential variables were food satisfaction and travel motivation for Korean style. Lastly, the seven variables that have the greatest influence on the 'recommendation intention' were the country, sightseeing spot attraction, number of visiting places, food satisfaction, activity, tour guide service satisfaction and cost. And then the variables that had the greatest influence were the country, sightseeing spot attraction, and food satisfaction. In addition, in order to grasp the influence of each independent variables more deeply, we used R programming to identify the influence of independent variables. As a result, it was found that the food satisfaction and sightseeing spot attraction were higher than other variables in overall satisfaction and had a greater effect than other influential variables. Revisit intention had a higher ${\beta}$ value in the travel motive as the purpose of Korean Wave than other variables. It will be necessary to have a policy that will lead to a substantial revisit of tourists by enhancing tourist attractions for the purpose of Korean Wave. Lastly, the recommendation had the same result of satisfaction as the sightseeing spot attraction and food satisfaction have higher ${\beta}$ value than other variables. From this analysis, we found that 'food satisfaction' and 'sightseeing spot attraction' variables were the common factors to influence three dependent variables that are mentioned above('Overall satisfaction', 'Revisit intention' and 'Recommendation'), and that those factors affected the satisfaction of travel in Korea significantly. The purpose of this study is to examine how to activate foreign tourists in Korea through big data analysis. It is expected to be used as basic data for analyzing tourism data and establishing effective tourism policy. It is expected to be used as a material to establish an activation plan that can contribute to tourism development in Korea in the future.