• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Asia pacific journal of information systems
• /
• v.21 no.1
• /
• pp.103-122
• /
• 2011

Recently, numerous documents have been made available electronically. Internet search engines and digital libraries commonly return query results containing hundreds or even thousands of documents. In this situation, it is virtually impossible for users to examine complete documents to determine whether they might be useful for them. For this reason, some on-line documents are accompanied by a list of keywords specified by the authors in an effort to guide the users by facilitating the filtering process. In this way, a set of keywords is often considered a condensed version of the whole document and therefore plays an important role for document retrieval, Web page retrieval, document clustering, summarization, text mining, and so on. Since many academic journals ask the authors to provide a list of five or six keywords on the first page of an article, keywords are most familiar in the context of journal articles. However, many other types of documents could not benefit from the use of keywords, including Web pages, email messages, news reports, magazine articles, and business papers. Although the potential benefit is large, the implementation itself is the obstacle; manually assigning keywords to all documents is a daunting task, or even impractical in that it is extremely tedious and time-consuming requiring a certain level of domain knowledge. Therefore, it is highly desirable to automate the keyword generation process. There are mainly two approaches to achieving this aim: keyword assignment approach and keyword extraction approach. Both approaches use machine learning methods and require, for training purposes, a set of documents with keywords already attached. In the former approach, there is a given set of vocabulary, and the aim is to match them to the texts. In other words, the keywords assignment approach seeks to select the words from a controlled vocabulary that best describes a document. Although this approach is domain dependent and is not easy to transfer and expand, it can generate implicit keywords that do not appear in a document. On the other hand, in the latter approach, the aim is to extract keywords with respect to their relevance in the text without prior vocabulary. In this approach, automatic keyword generation is treated as a classification task, and keywords are commonly extracted based on supervised learning techniques. Thus, keyword extraction algorithms classify candidate keywords in a document into positive or negative examples. Several systems such as Extractor and Kea were developed using keyword extraction approach. Most indicative words in a document are selected as keywords for that document and as a result, keywords extraction is limited to terms that appear in the document. Therefore, keywords extraction cannot generate implicit keywords that are not included in a document. According to the experiment results of Turney, about 64% to 90% of keywords assigned by the authors can be found in the full text of an article. Inversely, it also means that 10% to 36% of the keywords assigned by the authors do not appear in the article, which cannot be generated through keyword extraction algorithms. Our preliminary experiment result also shows that 37% of keywords assigned by the authors are not included in the full text. This is the reason why we have decided to adopt the keyword assignment approach. In this paper, we propose a new approach for automatic keyword assignment namely IVSM(Inverse Vector Space Model). The model is based on a vector space model. which is a conventional information retrieval model that represents documents and queries by vectors in a multidimensional space. IVSM generates an appropriate keyword set for a specific document by measuring the distance between the document and the keyword sets. The keyword assignment process of IVSM is as follows: (1) calculating the vector length of each keyword set based on each keyword weight; (2) preprocessing and parsing a target document that does not have keywords; (3) calculating the vector length of the target document based on the term frequency; (4) measuring the cosine similarity between each keyword set and the target document; and (5) generating keywords that have high similarity scores. Two keyword generation systems were implemented applying IVSM: IVSM system for Web-based community service and stand-alone IVSM system. Firstly, the IVSM system is implemented in a community service for sharing knowledge and opinions on current trends such as fashion, movies, social problems, and health information. The stand-alone IVSM system is dedicated to generating keywords for academic papers, and, indeed, it has been tested through a number of academic papers including those published by the Korean Association of Shipping and Logistics, the Korea Research Academy of Distribution Information, the Korea Logistics Society, the Korea Logistics Research Association, and the Korea Port Economic Association. We measured the performance of IVSM by the number of matches between the IVSM-generated keywords and the author-assigned keywords. According to our experiment, the precisions of IVSM applied to Web-based community service and academic journals were 0.75 and 0.71, respectively. The performance of both systems is much better than that of baseline systems that generate keywords based on simple probability. Also, IVSM shows comparable performance to Extractor that is a representative system of keyword extraction approach developed by Turney. As electronic documents increase, we expect that IVSM proposed in this paper can be applied to many electronic documents in Web-based community and digital library.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.10 no.3
• /
• pp.80-92
• /
• 2007

Forest fire is the dominant large-scale disturbance mechanism in the Korean temperate forest, and it strongly influences forest structure and function. Moreover burn severity incorporates both short- and long-term post-fire effects on the local and regional environment. Burn severity is defined by the degree to which an ecosystem has changed owing to the fire. Vegetation rehabilitation may specifically vary according to burn severity after fire. To understand burn severity and process of vegetation rehabilitation at the damaged area after large-fire is required a lot of man powers and budgets. However the analysis of burn severity in the forest area using satellite imagery can acquire rapidly information and more objective results remotely in the large-fire area. Space and airbone sensors have been used to map area burned, assess characteristics of active fires, and characterize post-fire ecological effects. For classifying fire damaged area and analyzing burn severity of Samcheok fire area occurred in 2000, Cheongyang fire in 2002, and Yangyang fire in 2005 we utilized Normalized Burn Ratio(NBR) technique. The NBR is temporally differenced between pre- and post-fire datasets to determine the extent and degree of change detected from burning. In this paper we use pre- and post-fire imagery from the Landsat TM and ETM+ imagery to compute the NBR and evaluate large-scale patterns of burn severity at 30m spatial resolution. 65% in the Samcheok fire area, 91% in the Cheongyang fire area and 65% in the Yangyang fire area were corresponded to burn severity class above 'High'. Therefore the use of a remotely sensed Differenced Normalized Burn Ratio(${\Delta}NBR$) by RS and GIS allows for the burn severity to be quantified spatially by mapping damaged domain and burn severity across large-fire area.

• Industry Promotion Research
• /
• v.7 no.2
• /
• pp.43-49
• /
• 2022

This study aims to study Esping-Anderson's theory of welfare state system, develop a model of welfare state suitable for Korea's situation, and apply it to reality. In this research method, basic research and analysis of ideology is used, focusing on Esping-Anderson's welfare state system theory, and applying it appropriately to the Korean situation. Studies on the model of the welfare state have been studied after the classification of complementary and institutional models asserted by Willensky and Lebo in 1965. In addition, Esping-Andersen asserts three things as a model of the welfare state according to ideology. First, the role of the market is central to the liberal welfare system that best fits the image of classical capitalism, and individualistic solidarity through the market. The role of the state or family, which can be a hindrance, is actually marginalized. In addition, in order to maximize individualistic solidarity through the market, de-commodification in the national domain tends to be minimized. Second, the conservative welfare system has a strong familistic element, so the source of social solidarity is the family, and the state plays a role of supporting and supplementing the characteristics of this family. In the conservative system, de-commodification appears to be high among household heads, or the welfare system takes on a corporatist and nationalistic form, it can be said that these characteristics are reflected. Third, in the social democratic welfare system, the source of social solidarity is the state. Therefore, the role of the state is large, the state has a high possibility of decommodification, and it has the characteristics of substitutes for the family and the market through universalist intervention. This study applies Esping-Anderson's three welfare state models to study a model suitable for the Korean situation. In conclusion, Esping-Anderson's three welfare state models can be classified into a market-oriented model based on a liberal welfare system, a status-oriented model based on a conservative corporatist welfare system, and a solidarity-oriented model based on a social-democratic welfare system, presented a compromise between liberalism and conservatism as a Korean model.

• Korean Journal of Remote Sensing
• /
• v.40 no.3
• /
• pp.295-305
• /
• 2024

This study aims to analyze the micro-sedimentary structures of the Hwangdo tidal flats using ultra-high resolution unmanned aerial vehicle (UAV) data. Tidal flats, located in the transitional area between land and sea, constantly change due to tidal activities and provide a unique environment important for understanding sedimentary processes and environmental conditions. Traditional field observation methods are limited in spatial and temporal coverage, and existing satellite imagery does not provide sufficient resolution to study micro-sedimentary structures. To overcome these limitations, high-resolution images of the Hwangdo tidal flats in Chungcheongnam-do were acquired using UAVs. This area has experienced significant changes in its sedimentary environment due to coastal development projects such as sea wall construction. From May 17 to 18, 2022, sediment samples were collected from 91 points during field surveys and 25 in-situ points were intensively analyzed. UAV data with a spatial resolution of approximately 0.9 mm allowed identifying and extracting parameters related to micro-sedimentary structures. For mud cracks, the length of the major axis of the polygons was extracted, and the wavelength and ripple symmetry index were extracted for ripple marks. The results of the study showed that in areas with mud content above 80%, mud cracks formed at an average major axis length of 37.3 cm. In regions with sand content above 60%, ripples with an average wavelength of 8 cm and a ripple symmetry index of 2.0 were formed. This study demonstrated that micro-sedimentary structures of tidal flats can be effectively analyzed using ultra-high resolution UAV data without field surveys. This highlights the potential of UAV technology as an important tool in environmental monitoring and coastal management and shows its usefulness in the study of sedimentary structures. In addition, the results of this study are expected to serve as baseline data for more accurate sedimentary facies classification.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.171-183
• /
• 2012

In the development of technologies, the exhibition industry has received much attention from governments and companies as an important way of marketing activities. Also, the exhibitors have considered the exhibition as new channels of marketing activities. However, the growing size of exhibitions for net square feet and the number of visitors naturally creates the competitive environment for them. Therefore, to make use of the effective marketing tools in these environments, they have planned and implemented many promotion technics. Especially, through smart environment which makes them provide real-time information for visitors, they can implement various kinds of promotion. However, promotions ignoring visitors' various needs and preferences can lose the original purposes and functions of them. That is, as indiscriminate promotions make visitors feel like spam, they can't achieve their purposes. Therefore, they need an approach using STP strategy which segments visitors through right evidences (Segmentation), selects the target visitors (Targeting), and give proper services to them (Positioning). For using STP Strategy in the smart exhibition environment, we consider these characteristics of it. First, an exhibition is defined as market events of a specific duration, which are held at intervals. According to this, exhibitors who plan some promotions should different events and promotions in each exhibition. Therefore, when they adopt traditional STP strategies, a system can provide services using insufficient information and of existing visitors, and should guarantee the performance of it. Second, to segment automatically, cluster analysis which is generally used as data mining technology can be adopted. In the smart exhibition environment, information of visitors can be acquired in real-time. At the same time, services using this information should be also provided in real-time. However, many clustering algorithms have scalability problem which they hardly work on a large database and require for domain knowledge to determine input parameters. Therefore, through selecting a suitable methodology and fitting, it should provide real-time services. Finally, it is needed to make use of data in the smart exhibition environment. As there are useful data such as booth visit records and participation records for events, the STP strategy for the smart exhibition is based on not only demographical segmentation but also behavioral segmentation. Therefore, in this study, we analyze a case of the promotion methodology which exhibitors can provide a differentiated service to segmented visitors in the smart exhibition environment. First, considering characteristics of the smart exhibition environment, we draw evidences of segmentation and fit the clustering methodology for providing real-time services. There are many studies for classify visitors, but we adopt a segmentation methodology based on visitors' behavioral traits. Through the direct observation, Veron and Levasseur classify visitors into four groups to liken visitors' traits to animals (Butterfly, fish, grasshopper, and ant). Especially, because variables of their classification like the number of visits and the average time of a visit can estimate in the smart exhibition environment, it can provide theoretical and practical background for our system. Next, we construct a pilot system which automatically selects suitable visitors along the objectives of promotions and instantly provide promotion messages to them. That is, based on the segmentation of our methodology, our system automatically selects suitable visitors along the characteristics of promotions. We adopt this system to real exhibition environment, and analyze data from results of adaptation. As a result, as we classify visitors into four types through their behavioral pattern in the exhibition, we provide some insights for researchers who build the smart exhibition environment and can gain promotion strategies fitting each cluster. First, visitors of ANT type show high response rate for promotion messages except experience promotion. So they are fascinated by actual profits in exhibition area, and dislike promotions requiring a long time. Contrastively, visitors of GRASSHOPPER type show high response rate only for experience promotion. Second, visitors of FISH type appear favors to coupon and contents promotions. That is, although they don't look in detail, they prefer to obtain further information such as brochure. Especially, exhibitors that want to give much information for limited time should give attention to visitors of this type. Consequently, these promotion strategies are expected to give exhibitors some insights when they plan and organize their activities, and grow the performance of them.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.123-132
• /
• 2013

As the smartphones are equipped with various sensors such as the accelerometer, GPS, gravity sensor, gyros, ambient light sensor, proximity sensor, and so on, there have been many research works on making use of these sensors to create valuable applications. Human activity recognition is one such application that is motivated by various welfare applications such as the support for the elderly, measurement of calorie consumption, analysis of lifestyles, analysis of exercise patterns, and so on. One of the challenges faced when using the smartphone sensors for activity recognition is that the number of sensors used should be minimized to save the battery power. When the number of sensors used are restricted, it is difficult to realize a highly accurate activity recognizer or a classifier because it is hard to distinguish between subtly different activities relying on only limited information. The difficulty gets especially severe when the number of different activity classes to be distinguished is very large. In this paper, we show that a fairly accurate classifier can be built that can distinguish ten different activities by using only a single sensor data, i.e., the smartphone accelerometer data. The approach that we take to dealing with this ten-class problem is to use the ensemble of nested dichotomy (END) method that transforms a multi-class problem into multiple two-class problems. END builds a committee of binary classifiers in a nested fashion using a binary tree. At the root of the binary tree, the set of all the classes are split into two subsets of classes by using a binary classifier. At a child node of the tree, a subset of classes is again split into two smaller subsets by using another binary classifier. Continuing in this way, we can obtain a binary tree where each leaf node contains a single class. This binary tree can be viewed as a nested dichotomy that can make multi-class predictions. Depending on how a set of classes are split into two subsets at each node, the final tree that we obtain can be different. Since there can be some classes that are correlated, a particular tree may perform better than the others. However, we can hardly identify the best tree without deep domain knowledge. The END method copes with this problem by building multiple dichotomy trees randomly during learning, and then combining the predictions made by each tree during classification. The END method is generally known to perform well even when the base learner is unable to model complex decision boundaries As the base classifier at each node of the dichotomy, we have used another ensemble classifier called the random forest. A random forest is built by repeatedly generating a decision tree each time with a different random subset of features using a bootstrap sample. By combining bagging with random feature subset selection, a random forest enjoys the advantage of having more diverse ensemble members than a simple bagging. As an overall result, our ensemble of nested dichotomy can actually be seen as a committee of committees of decision trees that can deal with a multi-class problem with high accuracy. The ten classes of activities that we distinguish in this paper are 'Sitting', 'Standing', 'Walking', 'Running', 'Walking Uphill', 'Walking Downhill', 'Running Uphill', 'Running Downhill', 'Falling', and 'Hobbling'. The features used for classifying these activities include not only the magnitude of acceleration vector at each time point but also the maximum, the minimum, and the standard deviation of vector magnitude within a time window of the last 2 seconds, etc. For experiments to compare the performance of END with those of other methods, the accelerometer data has been collected at every 0.1 second for 2 minutes for each activity from 5 volunteers. Among these 5,900 ($=5{\times}(60{\times}2-2)/0.1$) data collected for each activity (the data for the first 2 seconds are trashed because they do not have time window data), 4,700 have been used for training and the rest for testing. Although 'Walking Uphill' is often confused with some other similar activities, END has been found to classify all of the ten activities with a fairly high accuracy of 98.4%. On the other hand, the accuracies achieved by a decision tree, a k-nearest neighbor, and a one-versus-rest support vector machine have been observed as 97.6%, 96.5%, and 97.6%, respectively.

• 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.