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

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

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.30-43
• /
• 2018

Many studies have been carried out to retrieve images using colors, shapes, and textures which are characteristic of images. In addition, there is also progress in research related to the disease images of the crop. In this paper, to be a help to identify the disease occurred in crops grown in the agricultural field, we propose a similarity-based crop disease search system using the diseases image of horticulture crops. The proposed system improves the similarity retrieval performance compared to existing ones through the combination descriptor without using a single descriptor and applied the weight based calculation method to provide users with highly readable similarity search results. In this paper, a total of 13 Descriptors were used in combination. We used to retrieval of disease of six crops using a combination Descriptor, and a combination Descriptor with the highest average accuracy for each crop was selected as a combination Descriptor for the crop. The retrieved result were expressed as a percentage using the calculation method based on the ratio of disease names, and calculation method based on the weight. The calculation method based on the ratio of disease name has a problem in that number of images used in the query image and similarity search was output in a first order. To solve this problem, we used a calculation method based on weight. We applied the test image of each disease name to each of the two calculation methods to measure the classification performance of the retrieval results. We compared averages of retrieval performance for two calculation method for each crop. In cases of red pepper and apple, the performance of the calculation method based on the ratio of disease names was about 11.89% on average higher than that of the calculation method based on weight, respectively. In cases of chrysanthemum, strawberry, pear, and grape, the performance of the calculation method based on the weight was about 20.34% on average higher than that of the calculation method based on the ratio of disease names, respectively. In addition, the system proposed in this paper, UI/UX was configured conveniently via the feedback of actual users. Each system screen has a title and a description of the screen at the top, and was configured to display a user to conveniently view the information on the disease. The information of the disease searched based on the calculation method proposed above displays images and disease names of similar diseases. The system's environment is implemented for use with a web browser based on a pc environment and a web browser based on a mobile device environment.

• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.1-15
• /
• 2021

If it is difficult for us to make decisions, we ask for advice from friends or people around us. When we decide to buy products online, we read anonymous reviews and buy them. With the advent of the Data-driven era, IT technology's development is spilling out many data from individuals to objects. Companies or individuals have accumulated, processed, and analyzed such a large amount of data that they can now make decisions or execute directly using data that used to depend on experts. Nowadays, the recommender system plays a vital role in determining the user's preferences to purchase goods and uses a recommender system to induce clicks on web services (Facebook, Amazon, Netflix, Youtube). For example, Youtube's recommender system, which is used by 1 billion people worldwide every month, includes videos that users like, "like" and videos they watched. Recommended system research is deeply linked to practical business. Therefore, many researchers are interested in building better solutions. Recommender systems use the information obtained from their users to generate recommendations because the development of the provided recommender systems requires information on items that are likely to be preferred by the user. We began to trust patterns and rules derived from data rather than empirical intuition through the recommender systems. The capacity and development of data have led machine learning to develop deep learning. However, such recommender systems are not all solutions. Proceeding with the recommender systems, there should be no scarcity in all data and a sufficient amount. Also, it requires detailed information about the individual. The recommender systems work correctly when these conditions operate. The recommender systems become a complex problem for both consumers and sellers when the interaction log is insufficient. Because the seller's perspective needs to make recommendations at a personal level to the consumer and receive appropriate recommendations with reliable data from the consumer's perspective. In this paper, to improve the accuracy problem for "appropriate recommendation" to consumers, the recommender systems are proposed in combination with context-based deep learning. This research is to combine user-based data to create hybrid Recommender Systems. The hybrid approach developed is not a collaborative type of Recommender Systems, but a collaborative extension that integrates user data with deep learning. Customer review data were used for the data set. Consumers buy products in online shopping malls and then evaluate product reviews. Rating reviews are based on reviews from buyers who have already purchased, giving users confidence before purchasing the product. However, the recommendation system mainly uses scores or ratings rather than reviews to suggest items purchased by many users. In fact, consumer reviews include product opinions and user sentiment that will be spent on evaluation. By incorporating these parts into the study, this paper aims to improve the recommendation system. This study is an algorithm used when individuals have difficulty in selecting an item. Consumer reviews and record patterns made it possible to rely on recommendations appropriately. The algorithm implements a recommendation system through collaborative filtering. This study's predictive accuracy is measured by Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Netflix is strategically using the referral system in its programs through competitions that reduce RMSE every year, making fair use of predictive accuracy. Research on hybrid recommender systems combining the NLP approach for personalization recommender systems, deep learning base, etc. has been increasing. Among NLP studies, sentiment analysis began to take shape in the mid-2000s as user review data increased. Sentiment analysis is a text classification task based on machine learning. The machine learning-based sentiment analysis has a disadvantage in that it is difficult to identify the review's information expression because it is challenging to consider the text's characteristics. In this study, we propose a deep learning recommender system that utilizes BERT's sentiment analysis by minimizing the disadvantages of machine learning. This study offers a deep learning recommender system that uses BERT's sentiment analysis by reducing the disadvantages of machine learning. The comparison model was performed through a recommender system based on Naive-CF(collaborative filtering), SVD(singular value decomposition)-CF, MF(matrix factorization)-CF, BPR-MF(Bayesian personalized ranking matrix factorization)-CF, LSTM, CNN-LSTM, GRU(Gated Recurrent Units). As a result of the experiment, the recommender system based on BERT was the best.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.219-240
• /
• 2018

Sentiment analysis, which is one of the text mining techniques, is a method for extracting subjective content embedded in text documents. Recently, the sentiment analysis methods have been widely used in many fields. As good examples, data-driven surveys are based on analyzing the subjectivity of text data posted by users and market researches are conducted by analyzing users' review posts to quantify users' reputation on a target product. The basic method of sentiment analysis is to use sentiment dictionary (or lexicon), a list of sentiment vocabularies with positive, neutral, or negative semantics. In general, the meaning of many sentiment words is likely to be different across domains. For example, a sentiment word, 'sad' indicates negative meaning in many fields but a movie. In order to perform accurate sentiment analysis, we need to build the sentiment dictionary for a given domain. However, such a method of building the sentiment lexicon is time-consuming and various sentiment vocabularies are not included without the use of general-purpose sentiment lexicon. In order to address this problem, several studies have been carried out to construct the sentiment lexicon suitable for a specific domain based on 'OPEN HANGUL' and 'SentiWordNet', which are general-purpose sentiment lexicons. However, OPEN HANGUL is no longer being serviced and SentiWordNet does not work well because of language difference in the process of converting Korean word into English word. There are restrictions on the use of such general-purpose sentiment lexicons as seed data for building the sentiment lexicon for a specific domain. In this article, we construct 'KNU Korean Sentiment Lexicon (KNU-KSL)', a new general-purpose Korean sentiment dictionary that is more advanced than existing general-purpose lexicons. The proposed dictionary, which is a list of domain-independent sentiment words such as 'thank you', 'worthy', and 'impressed', is built to quickly construct the sentiment dictionary for a target domain. Especially, it constructs sentiment vocabularies by analyzing the glosses contained in Standard Korean Language Dictionary (SKLD) by the following procedures: First, we propose a sentiment classification model based on Bidirectional Long Short-Term Memory (Bi-LSTM). Second, the proposed deep learning model automatically classifies each of glosses to either positive or negative meaning. Third, positive words and phrases are extracted from the glosses classified as positive meaning, while negative words and phrases are extracted from the glosses classified as negative meaning. Our experimental results show that the average accuracy of the proposed sentiment classification model is up to 89.45%. In addition, the sentiment dictionary is more extended using various external sources including SentiWordNet, SenticNet, Emotional Verbs, and Sentiment Lexicon 0603. Furthermore, we add sentiment information about frequently used coined words and emoticons that are used mainly on the Web. The KNU-KSL contains a total of 14,843 sentiment vocabularies, each of which is one of 1-grams, 2-grams, phrases, and sentence patterns. Unlike existing sentiment dictionaries, it is composed of words that are not affected by particular domains. The recent trend on sentiment analysis is to use deep learning technique without sentiment dictionaries. The importance of developing sentiment dictionaries is declined gradually. However, one of recent studies shows that the words in the sentiment dictionary can be used as features of deep learning models, resulting in the sentiment analysis performed with higher accuracy (Teng, Z., 2016). This result indicates that the sentiment dictionary is used not only for sentiment analysis but also as features of deep learning models for improving accuracy. The proposed dictionary can be used as a basic data for constructing the sentiment lexicon of a particular domain and as features of deep learning models. It is also useful to automatically and quickly build large training sets for deep learning models.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.1
• /
• pp.64-72
• /
• 2009

The method to generate a digital elevation model(DEM) from contour lines causes a problem in which the low relief landform cannot be clearly presented due to the fact that it is significantly influenced by the expression of micro landform elements according to the interval of contours. Thus, this study attempts to develop a landcover burning method that recovers the micro relief landform of the DEM, which applies buffering and map algebra methods by inputting the elevation information to the landcover. In the recovering process of the micro landform, the DEM was recovered using the buffering method and elevation information through the map algebra for the landcover element for the micro landform among the primary DEM generation, making landcover map, and landcover elements. The recovering of the micro landform was applied based on stream landforms. The recovering of landforms using the buffering method was performed for the bar, which is a polygonal element, and wetland according to the properties of concave/convex through generating contours with a uniform interval in which the elevation information applied to the recovered landform. In the case of the linear elements, such as bank, road, waterway, and tributary, the landform can be recovered by using the elevation information through applying a map algebra function. Because the polygonal elements, such as stream channel, river terrace, and artificial objects (farmlands) are determined as a flat property, these are recovered by inputting constant elevation values. The results of this study were compared and analyzed for the degree of landform expression between the original DEM and the recovered DEM. In the results of the analysis, the DEM produced by using the conventional method showed few expressions in micro landform elements. The method developed in this study well described wetland, bar, landform around rivers, farmland, bank, river terrace, and artificial objects. It can be expected that the results of this study contribute to the classification and analysis of micro landforms, plain and the ecology and environment study that requires the recovering of micro landforms around streams and rivers.

• Journal of Korean Academic Society of Home Health Care Nursing
• /
• v.4
• /
• pp.5-22
• /
• 1997

The purpose of the study was to development an information delivery system for the home nursing service, to demonstrate and to evaluate the efficiency of it. The period of research conduct was from September 1996 to August 31, 1997. At the 1st stage to achieve the purpose, Firstly Assessment tool for the patients with cerebral vascular disease who have the first priority of HNS among the patients with various health problems at home was developed through literature review. Secondly, after identification of patient nursing problem by the home care nurse with the assessment tool, the patient's classification system developed by Park (1988) that was 128 nursing activities under 6 categories was used to identify the home care nurse's activities of the patient with CAV at home. The research team had several workshops with 5 clinical nurse experts to refine it. At last 110 nursing activities under 11 categories for the patients with CVA were derived. At the second stage, algorithms were developed to connect 110 nursing activities with the patient nursing problems identified by assessment tool. The computerizing process of the algorithms is as follows: These algorithms are realized with the computer program by use of the software engineering technique. The development is made by the prototyping method, which is the requirement analysis of the software specifications. The basic features of the usability, compatibility, adaptability and maintainability are taken into consideration. Particular emphasis is given to the efficient construction of the database. To enhance the database efficiency and to establish the structural cohesion, the data field is categorized with the weight of relevance to the particular disease. This approach permits the easy adaptability when numerous diseases are applied in the future. In paralleled with this, the expandability and maintainability is stressed through out the program development, which leads to the modular concept. However since the disease to be applied is increased in number as the project progress and since they are interrelated and coupled each other, the expand ability as well as maintainability should be considered with a big priority. Furthermore, since the system is to be synthesized with other medical systems in the future, these properties are very important. The prototype developed in this project is to be evaluated through the stage of system testing. There are various evaluation metrics such as cohesion, coupling and adaptability so on. But unfortunately, direct measurement of these metrics are very difficult, and accordingly, analytical and quantitative evaluations are almost impossible. Therefore, instead of the analytical evaluation, the experimental evaluation is to be applied through the test run by various users. This system testing will provide the viewpoint analysis of the user's level, and the detail and additional requirement specifications arising from user's real situation will be feedback into the system modeling. Also. the degree of freedom of the input and output will be improved, and the hardware limitation will be investigated. Upon the refining, the prototype system will be used as a design template. and will be used to develop the more extensive system. In detail. the relevant modules will be developed for the various diseases, and the module will be integrated by the macroscopic design process focusing on the inter modularity, generality of the database. and compatibility with other systems. The Home care Evaluation System is comprised of three main modules of : (1) General information on a patient, (2) General health status of a patient, and (3) Cerebrovascular disease patient. The general health status module has five sub modules of physical measurement, vitality, nursing, pharmaceutical description and emotional/cognition ability. The CVA patient module is divided into ten sub modules such as subjective sense, consciousness, memory and language pattern so on. The typical sub modules are described in appendix 3.

• Korean Journal of Ecology and Environment
• /
• v.46 no.2
• /
• pp.145-153
• /
• 2013

It is a global trend that the water management policy is shifting from a water quality-oriented assessment to the aquatic ecosystem-based assessment. The majority of aquatic ecosystem assessment systems were developed solely based on physicochemical factors (e.g., water quality and bed structure) and a limited number of organisms (e.g., plankton and benthic organisms). Only a few systems use plants for a health assessment, although plants are sensitive indicators reflecting long-term disturbances and alterations in water regimes. The development of an assessment system is underway to evaluate and manage lakes as ecosystem units in the Korean Ministry of Environment. We reviewed the existing multivariate health assessment methods of other leading countries, and discussed their applicability to Korean lakes. The application of multivariate assessment methods is costly and time consuming, in addition to the correlation problem among variables. However, a single variable is not available at this moment, and the multivariate method is an appropriate system due to its multidimensional evaluation and cumulative data generation. We, therefore, discussed multivariate assessment methods in three steps: selecting metrics, scoring metrics and assessing indices. In the step of selecting metrics, the best available metrics are species-related variables, such as composition and abundance, as well as richness and diversity. Indicator species, such as sensitive species, are the most frequently used in other countries, but their system of classification in Korea is not yet complete. In terms of scoring metrics, the lack of reference lakes with little anthropogenic impact make this step difficult, and therefore, the use of relative scores among the investigated lakes is a suitable alternative. Overall, in spite of several limitations, the development of a plant-based multivariate assessment method in Korea is possible using mostly field research data. Later, it could be improved based on qualitative metrics on plant species, and with the emergence of further survey data.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.12 no.2
• /
• pp.192-217
• /
• 2001

Object：This study was carried out to classify adolescents in runaway shelters by evaluating their psychopathology. And the ultimate purpose is to offer basic data for preventing adolescents‘ runaway and for diversifying runaway shelters suitable for the problem of individual adolescent. Method：128 adolescents who stay in the runaway shelters were asked to complete self-report qeustionnaires including basic sociodemographic data, Child Behavior Check List(CBCL), Minnesota Multiphasic Personality Inventory(MMPI), and Symptom Check List-90-Revised(SCL-90-R). Korean Wechsler Adult Intelligence Scale(K-WAIS)[or Korean Educational Developmental Institute-Wechsler Intelligence Scale for Children(KEDI-WISC)] and Bender-Gestalt test(BGT) were also done by clinical psychologists. Results：The most common age of the subjects were 15-year-old, and they dropped out their schools in the middle school most commonly. Mostly they were from middle class family and their parents' educational level were high school graduates. The first runaway episode was most common in the middleschool period, and their runaways were repeated. The most common frequency of runaways were more than 10 times. About 10% of them abused drugs and about 80% of them abused alcohol. One third of them had experiences of illegal problems and 10% of them engaged in sexual activity for money. 95 adolescents(83%) in CBCL, 42 adolescents(36%) in SCL-90-R, and 70 adolescents(69.3%) in MMPI showed clinical significance. In intelligence test, 22 adolescents(22%) were mentally retarded. In BGT, 35 adolescents(39.4%) manifested brain dysfunction signs. Conclusion：Runaway adolescents in the shelters have variable and severe psychopathology. Their psychopathology is classified as follows；The behavior disorder group, the mood disorder group with anxiety/depression, the somatic disorder group with somatic symptoms, and the psychosis group with possibility of severe psychopathology. Therefore it is very important to evaluate psychiatric problems of runaway adolescents, and specific therapeutic interventions according to their problems are required.