• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.131-145
• /
• 2020

In line with the trend of industrial innovation, IoT technology utilized in a variety of fields is emerging as a key element in creation of new business models and the provision of user-friendly services through the combination of big data. The accumulated data from devices with the Internet-of-Things (IoT) is being used in many ways to build a convenience-based smart system as it can provide customized intelligent systems through user environment and pattern analysis. Recently, it has been applied to innovation in the public domain and has been using it for smart city and smart transportation, such as solving traffic and crime problems using CCTV. In particular, it is necessary to comprehensively consider the easiness of securing real-time service data and the stability of security when planning underground services or establishing movement amount control information system to enhance citizens' or commuters' convenience in circumstances with the congestion of public transportation such as subways, urban railways, etc. However, previous studies that utilize image data have limitations in reducing the performance of object detection under private issue and abnormal conditions. The IoT device-based sensor data used in this study is free from private issue because it does not require identification for individuals, and can be effectively utilized to build intelligent public services for unspecified people. Especially, sensor data stored by the IoT device need not be identified to an individual, and can be effectively utilized for constructing intelligent public services for many and unspecified people as data free form private issue. We utilize the IoT-based infrared sensor devices for an intelligent pedestrian tracking system in metro service which many people use on a daily basis and temperature data measured by sensors are therein transmitted in real time. The experimental environment for collecting data detected in real time from sensors was established for the equally-spaced midpoints of 4×4 upper parts in the ceiling of subway entrances where the actual movement amount of passengers is high, and it measured the temperature change for objects entering and leaving the detection spots. The measured data have gone through a preprocessing in which the reference values for 16 different areas are set and the difference values between the temperatures in 16 distinct areas and their reference values per unit of time are calculated. This corresponds to the methodology that maximizes movement within the detection area. In addition, the size of the data was increased by 10 times in order to more sensitively reflect the difference in temperature by area. For example, if the temperature data collected from the sensor at a given time were 28.5℃, the data analysis was conducted by changing the value to 285. As above, the data collected from sensors have the characteristics of time series data and image data with 4×4 resolution. Reflecting the characteristics of the measured, preprocessed data, we finally propose a hybrid algorithm that combines CNN in superior performance for image classification and LSTM, especially suitable for analyzing time series data, as referred to CNN-LSTM (Convolutional Neural Network-Long Short Term Memory). In the study, the CNN-LSTM algorithm is used to predict the number of passing persons in one of 4×4 detection areas. We verified the validation of the proposed model by taking performance comparison with other artificial intelligence algorithms such as Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM) and RNN-LSTM (Recurrent Neural Network-Long Short Term Memory). As a result of the experiment, proposed CNN-LSTM hybrid model compared to MLP, LSTM and RNN-LSTM has the best predictive performance. By utilizing the proposed devices and models, it is expected various metro services will be provided with no illegal issue about the personal information such as real-time monitoring of public transport facilities and emergency situation response services on the basis of congestion. However, the data have been collected by selecting one side of the entrances as the subject of analysis, and the data collected for a short period of time have been applied to the prediction. There exists the limitation that the verification of application in other environments needs to be carried out. In the future, it is expected that more reliability will be provided for the proposed model if experimental data is sufficiently collected in various environments or if learning data is further configured by measuring data in other sensors.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1447-1460
• /
• 2021

Urbanization increases the amount of impervious surface and artificial heat emission, resulting in urban heat island (UHI) effect. Local climate zones (LCZ) are a classification scheme for urban areas considering urban land cover characteristics and the geometry and structure of buildings, which can be used for analyzing urban heat island effect in detail. This study aimed to examine the UHI effect by urban structure in Suwon and Daegu using the LCZ scheme. First, the LCZ maps were generated using Landsat 8 images and convolutional neural network (CNN) deep learning over the two cities. Then, Surface UHI (SUHI), which indicates the land surface temperature (LST) difference between urban and rural areas, was analyzed by LCZ class. The results showed that the overall accuracies of the CNN models for LCZ classification were relatively high 87.9% and 81.7% for Suwon and Daegu, respectively. In general, Daegu had higher LST for all LCZ classes than Suwon. For both cities, LST tended to increase with increasing building density with relatively low building height. For both cities, the intensity of SUHI was very high in summer regardless of LCZ classes and was also relatively high except for a few classes in spring and fall. In winter the SUHI intensity was low, resulting in negative values for many LCZ classes. This implies that UHI is very strong in summer, and some urban areas often are colder than rural areas in winter. The research findings demonstrated the applicability of the LCZ data for SUHI analysis and can provide a basis for establishing timely strategies to respond urban on-going climate change over urban areas.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.29-56
• /
• 2021

Recently, various types of products have been launched with the rapid growth of the e-commerce market. As a result, many users face information overload problems, which is time-consuming in the purchasing decision-making process. Therefore, the importance of a personalized recommendation service that can provide customized products and services to users is emerging. For example, global companies such as Netflix, Amazon, and Google have introduced personalized recommendation services to support users' purchasing decisions. Accordingly, the user's information search cost can reduce which can positively affect the company's sales increase. The existing personalized recommendation service research applied Collaborative Filtering (CF) technique predicts user preference mainly use quantified information. However, the recommendation performance may have decreased if only use quantitative information. To improve the problems of such existing studies, many studies using reviews to enhance recommendation performance. However, reviews contain factors that hinder purchasing decisions, such as advertising content, false comments, meaningless or irrelevant content. When providing recommendation service uses a review that includes these factors can lead to decrease recommendation performance. Therefore, we proposed a novel recommendation methodology through CNN-based review usefulness score prediction to improve these problems. The results show that the proposed methodology has better prediction performance than the recommendation method considering all existing preference ratings. In addition, the results suggest that can enhance the performance of traditional CF when the information on review usefulness reflects in the personalized recommendation service.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.43-61
• /
• 2019

Development of technologies in artificial intelligence has been rapidly increasing with the Fourth Industrial Revolution, and researches related to AI have been actively conducted in a variety of fields such as autonomous vehicles, natural language processing, and robotics. These researches have been focused on solving cognitive problems such as learning and problem solving related to human intelligence from the 1950s. The field of artificial intelligence has achieved more technological advance than ever, due to recent interest in technology and research on various algorithms. The knowledge-based system is a sub-domain of artificial intelligence, and it aims to enable artificial intelligence agents to make decisions by using machine-readable and processible knowledge constructed from complex and informal human knowledge and rules in various fields. A knowledge base is used to optimize information collection, organization, and retrieval, and recently it is used with statistical artificial intelligence such as machine learning. Recently, the purpose of the knowledge base is to express, publish, and share knowledge on the web by describing and connecting web resources such as pages and data. These knowledge bases are used for intelligent processing in various fields of artificial intelligence such as question answering system of the smart speaker. However, building a useful knowledge base is a time-consuming task and still requires a lot of effort of the experts. In recent years, many kinds of research and technologies of knowledge based artificial intelligence use DBpedia that is one of the biggest knowledge base aiming to extract structured content from the various information of Wikipedia. DBpedia contains various information extracted from Wikipedia such as a title, categories, and links, but the most useful knowledge is from infobox of Wikipedia that presents a summary of some unifying aspect created by users. These knowledge are created by the mapping rule between infobox structures and DBpedia ontology schema defined in DBpedia Extraction Framework. In this way, DBpedia can expect high reliability in terms of accuracy of knowledge by using the method of generating knowledge from semi-structured infobox data created by users. However, since only about 50% of all wiki pages contain infobox in Korean Wikipedia, DBpedia has limitations in term of knowledge scalability. This paper proposes a method to extract knowledge from text documents according to the ontology schema using machine learning. In order to demonstrate the appropriateness of this method, we explain a knowledge extraction model according to the DBpedia ontology schema by learning Wikipedia infoboxes. Our knowledge extraction model consists of three steps, document classification as ontology classes, proper sentence classification to extract triples, and value selection and transformation into RDF triple structure. The structure of Wikipedia infobox are defined as infobox templates that provide standardized information across related articles, and DBpedia ontology schema can be mapped these infobox templates. Based on these mapping relations, we classify the input document according to infobox categories which means ontology classes. After determining the classification of the input document, we classify the appropriate sentence according to attributes belonging to the classification. Finally, we extract knowledge from sentences that are classified as appropriate, and we convert knowledge into a form of triples. In order to train models, we generated training data set from Wikipedia dump using a method to add BIO tags to sentences, so we trained about 200 classes and about 2,500 relations for extracting knowledge. Furthermore, we evaluated comparative experiments of CRF and Bi-LSTM-CRF for the knowledge extraction process. Through this proposed process, it is possible to utilize structured knowledge by extracting knowledge according to the ontology schema from text documents. In addition, this methodology can significantly reduce the effort of the experts to construct instances according to the ontology schema.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.265-282
• /
• 2022

Sea surface temperature (SST) is a factor that greatly influences ocean circulation and ecosystems in the Earth system. As global warming causes changes in the SST near the Korean Peninsula, abnormal water temperature phenomena (high water temperature, low water temperature) occurs, causing continuous damage to the marine ecosystem and the fishery industry. Therefore, this study proposes a methodology to predict the SST near the Korean Peninsula and prevent damage by predicting abnormal water temperature phenomena. The study area was set near the Korean Peninsula, and ERA5 data from the European Center for Medium-Range Weather Forecasts (ECMWF) was used to utilize SST data at the same time period. As a research method, Long Short-Term Memory (LSTM) algorithm specialized for time series data prediction among deep learning models was used in consideration of the time series characteristics of SST data. The prediction model predicts the SST near the Korean Peninsula after 1- to 7-days and predicts the high water temperature or low water temperature phenomenon. To evaluate the accuracy of SST prediction, Coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) indicators were used. The summer (JAS) 1-day prediction result of the prediction model, R²=0.996, RMSE=0.119℃, MAPE=0.352% and the winter (JFM) 1-day prediction result is R²=0.999, RMSE=0.063℃, MAPE=0.646%. Using the predicted SST, the accuracy of abnormal sea surface temperature prediction was evaluated with an F1 Score (F1 Score=0.98 for high water temperature prediction in summer (2021/08/05), F1 Score=1.0 for low water temperature prediction in winter (2021/02/19)). As the prediction period increased, the prediction model showed a tendency to underestimate the SST, which also reduced the accuracy of the abnormal water temperature prediction. Therefore, it is judged that it is necessary to analyze the cause of underestimation of the predictive model in the future and study to improve the prediction accuracy.

• 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.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1463-1478
• /
• 2022

Maritime transport accounts for 99.7% of the exports and imports of the Republic of Korea; therefore, developing a vessel monitoring system for efficient operation is of significant interest. Several studies have focused on tracking and monitoring vessel movements based on automatic identification system (AIS) data; however, ships without AIS have limited monitoring and tracking ability. High-resolution optical satellite images can provide the missing layer of information in AIS-based monitoring systems because they can identify non-AIS vessels and small ships over a wide range. Therefore, it is necessary to investigate vessel monitoring and small vessel classification systems using high-resolution optical satellite images. This study examined the possibility of developing ship monitoring systems using Compact Advanced Satellite 500-1 (CAS500-1) satellite images by first training a deep learning model using satellite image data and then performing detection in other images. To determine the effectiveness of the proposed method, the learning data was acquired from ships in the Yellow Sea and its major ports, and the detection model was established using the You Only Look Once (YOLO) algorithm. The ship detection performance was evaluated for a domestic and an international port. The results obtained using the detection model in ships in the anchorage and berth areas were compared with the ship classification information obtained using AIS, and an accuracy of 85.5% and 70% was achieved using domestic and international classification models, respectively. The results indicate that high-resolution satellite images can be used in mooring ships for vessel monitoring. The developed approach can potentially be used in vessel tracking and monitoring systems at major ports around the world if the accuracy of the detection model is improved through continuous learning data construction.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.157-177
• /
• 2022

Investors are trading stocks by keeping a close watch on the order information submitted by domestic and foreign investors in real time through Limit Order Book information, so-called price current provided by securities firms. Will order information released in the Limit Order Book be useful in stock price prediction? This study analyzes whether it is significant as a predictor of future stock price up or down when order imbalances appear as investors' buying and selling orders are concentrated to one side during intra-day trading time. Using classification algorithms, this study improved the prediction accuracy of the order imbalance information on the short-term price up and down trend, that is the closing price up and down of the day. Day trading strategies are proposed using the predicted price trends of the classification algorithms and the trading performances are analyzed through empirical analysis. The 5-minute KOSPI200 Index Futures data were analyzed for 4,564 days from January 19, 2004 to June 30, 2022. The results of the empirical analysis are as follows. First, order imbalance information has a significant impact on the current stock prices. Second, the order imbalance information observed in the early morning has a significant forecasting power on the price trends from the early morning to the market closing time. Third, the Support Vector Machines algorithm showed the highest prediction accuracy on the day's closing price trends using the order imbalance information at 54.1%. Fourth, the order imbalance information measured at an early time of day had higher prediction accuracy than the order imbalance information measured at a later time of day. Fifth, the trading performances of the day trading strategies using the prediction results of the classification algorithms on the price up and down trends were higher than that of the benchmark trading strategy. Sixth, except for the K-Nearest Neighbor algorithm, all investment performances using the classification algorithms showed average higher total profits than that of the benchmark strategy. Seventh, the trading performances using the predictive results of the Logical Regression, Random Forest, Support Vector Machines, and XGBoost algorithms showed higher results than the benchmark strategy in the Sharpe Ratio, which evaluates both profitability and risk. This study has an academic difference from existing studies in that it documented the economic value of the total buy & sell order volume information among the Limit Order Book information. The empirical results of this study are also valuable to the market participants from a trading perspective. In future studies, it is necessary to improve the performance of the trading strategy using more accurate price prediction results by expanding to deep learning models which are actively being studied for predicting stock prices recently.

• 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.