• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.199-208
• /
• 2019

As the number of available satellites increases and technology advances, image information outputs are becoming increasingly diverse and a large amount of data is accumulating. In this study, we propose a change detection method for high-resolution satellite images that uses transfer learning and a deep learning network to overcome the limit caused by insufficient training data via the use of pre-trained information. The deep learning network used in this study comprises convolutional layers to extract the spatial and spectral information and convolutional long-short term memory layers to analyze the time series information. To use the learned information, the two initial convolutional layers of the change detection network are designed to use learned values from 40,000 patches of the ISPRS (International Society for Photogrammertry and Remote Sensing) dataset as initial values. In addition, 2D (2-Dimensional) and 3D (3-dimensional) kernels were used to find the optimized structure for the high-resolution satellite images. The experimental results for the KOMPSAT-3A (KOrean Multi-Purpose SATllite-3A) satellite images show that this change detection method can effectively extract changed/unchanged pixels but is less sensitive to changes due to shadow and relief displacements. In addition, the change detection accuracy of two sites was improved by using 3D kernels. This is because a 3D kernel can consider not only the spatial information but also the spectral information. This study indicates that we can effectively detect changes in high-resolution satellite images using the constructed image information and deep learning network. In future work, a pre-trained change detection network will be applied to newly obtained images to extend the scope of the application.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.59-83
• /
• 2018

With the increasing importance of sentiment analysis to grasp the needs of customers and the public, various types of deep learning models have been actively applied to English texts. In the sentiment analysis of English texts by deep learning, natural language sentences included in training and test datasets are usually converted into sequences of word vectors before being entered into the deep learning models. In this case, word vectors generally refer to vector representations of words obtained through splitting a sentence by space characters. There are several ways to derive word vectors, one of which is Word2Vec used for producing the 300 dimensional Google word vectors from about 100 billion words of Google News data. They have been widely used in the studies of sentiment analysis of reviews from various fields such as restaurants, movies, laptops, cameras, etc. Unlike English, morpheme plays an essential role in sentiment analysis and sentence structure analysis in Korean, which is a typical agglutinative language with developed postpositions and endings. A morpheme can be defined as the smallest meaningful unit of a language, and a word consists of one or more morphemes. For example, for a word '예쁘고', the morphemes are '예쁘(= adjective)' and '고(=connective ending)'. Reflecting the significance of Korean morphemes, it seems reasonable to adopt the morphemes as a basic unit in Korean sentiment analysis. Therefore, in this study, we use 'morpheme vector' as an input to a deep learning model rather than 'word vector' which is mainly used in English text. The morpheme vector refers to a vector representation for the morpheme and can be derived by applying an existent word vector derivation mechanism to the sentences divided into constituent morphemes. By the way, here come some questions as follows. What is the desirable range of POS(Part-Of-Speech) tags when deriving morpheme vectors for improving the classification accuracy of a deep learning model? Is it proper to apply a typical word vector model which primarily relies on the form of words to Korean with a high homonym ratio? Will the text preprocessing such as correcting spelling or spacing errors affect the classification accuracy, especially when drawing morpheme vectors from Korean product reviews with a lot of grammatical mistakes and variations? We seek to find empirical answers to these fundamental issues, which may be encountered first when applying various deep learning models to Korean texts. As a starting point, we summarized these issues as three central research questions as follows. First, which is better effective, to use morpheme vectors from grammatically correct texts of other domain than the analysis target, or to use morpheme vectors from considerably ungrammatical texts of the same domain, as the initial input of a deep learning model? Second, what is an appropriate morpheme vector derivation method for Korean regarding the range of POS tags, homonym, text preprocessing, minimum frequency? Third, can we get a satisfactory level of classification accuracy when applying deep learning to Korean sentiment analysis? As an approach to these research questions, we generate various types of morpheme vectors reflecting the research questions and then compare the classification accuracy through a non-static CNN(Convolutional Neural Network) model taking in the morpheme vectors. As for training and test datasets, Naver Shopping's 17,260 cosmetics product reviews are used. To derive morpheme vectors, we use data from the same domain as the target one and data from other domain; Naver shopping's about 2 million cosmetics product reviews and 520,000 Naver News data arguably corresponding to Google's News data. The six primary sets of morpheme vectors constructed in this study differ in terms of the following three criteria. First, they come from two types of data source; Naver news of high grammatical correctness and Naver shopping's cosmetics product reviews of low grammatical correctness. Second, they are distinguished in the degree of data preprocessing, namely, only splitting sentences or up to additional spelling and spacing corrections after sentence separation. Third, they vary concerning the form of input fed into a word vector model; whether the morphemes themselves are entered into a word vector model or with their POS tags attached. The morpheme vectors further vary depending on the consideration range of POS tags, the minimum frequency of morphemes included, and the random initialization range. All morpheme vectors are derived through CBOW(Continuous Bag-Of-Words) model with the context window 5 and the vector dimension 300. It seems that utilizing the same domain text even with a lower degree of grammatical correctness, performing spelling and spacing corrections as well as sentence splitting, and incorporating morphemes of any POS tags including incomprehensible category lead to the better classification accuracy. The POS tag attachment, which is devised for the high proportion of homonyms in Korean, and the minimum frequency standard for the morpheme to be included seem not to have any definite influence on the classification accuracy.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of Biomedical Engineering Research
• /
• v.19 no.1
• /
• pp.69-80
• /
• 1998

This research was designed to investigate how the exercise program affects paraplegic standing and walking employing functional electrical stimulation(FES). Emphasis was also given to fatigue of major lower extremity muscles induced by different types of electrical stimulation. We applied continuous and intermittent rectangular pulse trains to quadriceps of 10 normal subjects and 4 complete paraplegic patients. The frequencies were 20Hz and 80Hz, and the knee angle was fixed at 90$^{\circ}$and 150$^{\circ}$to investigate how muscle fatigue is related to muscle length. The knee extensor torque was measured and monitored. We have been training quadriceps and gastrocnemius of a male paraplegic patient by means of electrical stimulation for the past two year. FES standing was initiated when the knee extensors became strong enough to support the body weight, and then the patient started FES walking utilizing parallel bars and a walker. We used an 8-channel constant-voltage stimulator and surface electrodes. The experimental results indicated that paralyzed muscles fatigued rapidly around the optimal length contrary to normal muscles and confirmed that low frequency and intermittent stimulation delayed fatigue. Our exercise program increased muscle force by approximately 10 folds and decreased the fatigue index to half of the initial value. In addition, the exercise enabled the patient to voluntarily lift each leg up to 10cm, which was of great help to the swing phase of FES walking. Both muscle force and resistance to fatigue were significantly enhanced right after the exercise was applied every day instead of 6 days a week. Up to date, the patient can walk for more than two and half minutes at 10m/min while controlling the on/off time of the stimulator by pushing the toggle switch attached to the walker handle.

• Journal of Distribution Science
• /
• v.9 no.4
• /
• pp.43-50
• /
• 2011

Concerning the risk factors of the outbreak of a fire in a traditional market, most of those markets are located in downtown areas or residential areas; thus, although their location may be favorable in terms of marketability, they face a potential risk in that a fire may develop into a large blaze owing to poor environment or the absence of facilities prepared for disaster during a fire. Moreover, as many people are densely poised in the markets, it is very probable that a fire may occur owing to the excessive use of heaters in the winter as well as the reckless use of electric and gas facilities. It seems that traditional markets encounter difficulty being insured against fire, because of their vulnerability and that the vast majority of small-scale sellers are likely to suffer mental anguish and tremendous physical injury in case of a fire. However, most of those sellers in the traditional markets are hand-to-mouth sellers, and they lack awareness of safety concerns and have insufficient experience in safe facility management. As small-scale sellers constitute the majority in the traditional market, the subscription rate of fire insurance in most of the traditional markets is low for the reasons of their needy circumstances and their financial burden. Statistically, the subscription by street vendors is non-existent; therefore, these vendors have a fairly limited access to indemnification after fire damage. Because of these problems, this study's purpose is to identify the current level of insurance subscription by these markets, which are exposed to poor facilities and vulnerability to fire. In order to fix this, it appears that shop owners and consumers will have to band together. For this study, we executed a fire policyholder fact-finding mission at traditional markets with approximately 108 and 981 stores. The research method was executed by an investigation using one-on-one individual interviews using a questionnaire. The contents investigated current insurance subscriptions. The method of analysis looked at the difference of insured amount according to volume size through cross-tabulation of the difference of insured amount by possession form, difference of insured amount by market form, difference of insured amount by category of business, difference of insured amount by market size, etc. Furthermore, the study should be used to propose solutions for problems through theoretical review with the use of a literature research, because the field case study was through interviews with the persons concerned, and the survey of the current insurance subscriptions by traditional market shopkeepers. The traditional market would generally have difficulty affording fire insurance. Fire insurance subscription rates of most of the market proved to be inactive, because of the economic burden of payment. Lack of funds is thought to be the main factor that causes a lack of realization about the necessity of fire insurance. In addition to expensive insurance premiums, sometimes, the companies' valuation of the businesses is lower than their actual valuations, and they do not pay out enough during a claim. The research presents an improvement plan that, when presented at the traditional markets, may strengthen their ability to procure fire insurance through the help of the central government. Researchers connected with the traditional market mainly accomplish the initial research. However, although this research has its limitations, it offers considerable benefits. For future researchers, I would suggest looking at several regions for comparison.

• Journal of Global Scholars of Marketing Science
• /
• v.20 no.2
• /
• pp.173-178
• /
• 2010

A privately held, third generation family owned company, Boom Technologies, Inc. (BTI), a provider of products and services to the electric utility, telecommunications and contractor markets, continues to make progress in exporting. Although export sales only equaled 5% of total revenue in 2008, BTI has an entire export division. Their export division's Managing Director reveals the trial and errors of a privately held company and their quest for success overseas. From its inception, BTI has always believed its greatest asset is its employees. When export sales struggled due to lack of strategy and direction, BTI hired a Managing Director for its export division. With leadership and guidance from BTI's president and from the Managing Director, they utilized the department's skills and knowledge. Structural changes were made to expand their market presence abroad and increase export sales. As a result, export sales increased four-fold, area managers in new countries were added and distribution networks were successfully cultivated. At times, revenue generation was difficult to determine due to the structure of the company. Therefore, in 1996, the export division was restructured as a limited liability company. This allowed the company to improve the tracking of revenue and expenses. Originally, 80% of BTI's export sales came from two countries; therefore, the initial approach to selling overseas was not reaching their anticipated goals of expanding their foreign market presence. However, changes were made and now the company manages the details of selling to over 80 countries. There were three major export expansion challenges noted by the Managing Director: 1. Product and Shipping - The major obstacle for BTI was product assembly. Originally, the majority of the product was assembled in the United States, which increased shipping and packaging costs. With so many parts specified in the order, many times the order would arrive with parts missing. The missing parts could equate to tens of thousands of dollars. Shipping these missing parts separately in another shipment also cost tens of thousands of dollar, plus a delivery delay time of six to eight weeks; all of which came out of the BTI's pockets. 2. Product Adaptation - Safety and product standards varied widely for each of the 80 countries to which BTI exported. Weights, special licenses, product specification requirements, measurement systems, and truck stability can all differ from country to country and can serve as a type of barrier to entry, making it difficult to adapt products accordingly. Technical and safety standards are barriers that serve as a type of protection for the local industry and can stand in the way of successfully pursuing foreign markets. 3. Marketing Challenges - The importance of distribution creates many challenges for BTI as they attempt to determine how each country prefers to operate with regard to their distribution systems. Some countries have competition from a small competitor that only produces one competing product; whereas BTI manufactures over 100 products. Marketing material is another concern for BTI as they attempt to push marketing costs to the distributors. Adapting the marketing material can be costly in terms of translation and cultural differences. In addition, the size of paper in the United States differs from those in some countries, causing many problems when attempting to copy the same layout and With distribution being one of several challenges for BTI, the company claims their distribution network is one of their competitive advantages, as the location and names of their distributors are not revealed. In addition, BTI rotates two offerings yearly: training to their distributors one year and then the next is a distributor's meeting. With a focus on product and shipping, product adaptation, and marketing challenges, the intricacies of selling overseas takes time and patience. Another competitive advantage noted is BTI's cradle to grave strategy, where they follow the product from sale to its final resting place, whether the truck is leased or purchased new or used. They also offer service and maintenance plans with a detailed cost analysis provided to the company prior to purchasing or leasing the product. Expanding abroad will always create challenges for a company. As the Managing Director stated, "If you don't have patience (in the export business), you better do something else." Knowing how to adapt quickly provides BTI with the skills necessary to adjust to the changing needs of each country and its own unique challenges, allowing them to remain competitive.

• Progress in Medical Physics
• /
• v.26 no.3
• /
• pp.119-126
• /
• 2015

The purpose of this study is to analyze motion-induced dose error generated by each tumor motion parameters of irregular tumor motion in helical tomotherapy. To understand the effect of the irregular tumor motion, a simple analytical model was simulated. Moving cases that has tumor motion were divided into a slightly irregular tumor motion case, a large irregular tumor motion case and a patient case. The slightly irregular tumor motion case was simulated with a variability of 10% in the tumor motion parameters of amplitude (amplitude case), period (period case), and baseline (baseline case), while the large irregular tumor motion case was simulated with a variability of 40%. In the phase case, the initial phase of the tumor motion was divided into end inhale, mid exhale, end exhale, and mid inhale; the simulated dose profiles for each case were compared. The patient case was also investigated to verify the motion-induced dose error in 'clinical-like' conditions. According to the simulation process, the dose profile was calculated. The moving case was compared with the static case that has no tumor motion. In the amplitude, period, baseline cases, the results show that the motion-induced dose error in the large irregular tumor motion case was larger than that in the slightly irregular tumor motion case or regular tumor motion case. Because the offset effect was inversely proportion to irregularity of tumor motion, offset effect was smaller in the large irregular tumor motion case than the slightly irregular tumor motion case or regular tumor motion case. In the phase case, the larger dose discrepancy was observed in the irregular tumor motion case than regular tumor motion case. A larger motion-induced dose error was also observed in the patient case than in the regular tumor motion case. This study analyzed motion-induced dose error as a function of each tumor motion parameters of irregular tumor motion during helical tomotherapy. The analysis showed that variability control of irregular tumor motion is important. We believe that the variability of irregular tumor motion can be reduced by using abdominal compression and respiratory training.

• Asia pacific journal of information systems
• /
• v.19 no.1
• /
• pp.33-62
• /
• 2009

Internet computing is a disruptive IT innovation. Semantic Web can be considered as an IT innovation because the Semantic Web technology possesses the potential to reduce information overload and enable semantic integration, using capabilities such as semantics and machine-processability. How should organizations adopt the Semantic Web? What factors affect the adoption and diffusion of Semantic Web innovation? Most studies on adoption and diffusion of innovation use empirical analysis as a quantitative research methodology in the post-implementation stage. There is criticism that the positivist requiring theoretical rigor can sacrifice relevance to practice. Rapid advances in technology require studies relevant to practice. In particular, it is realistically impossible to conduct quantitative approach for factors affecting adoption of the Semantic Web because the Semantic Web is in its infancy. However, in an early stage of introduction of the Semantic Web, it is necessary to give a model and some guidelines and for adoption and diffusion of the technology innovation to practitioners and researchers. Thus, the purpose of this study is to present a model of adoption and diffusion of the Semantic Web and to offer propositions as guidelines for successful adoption through a qualitative research method including multiple case studies and in-depth interviews. The researcher conducted interviews with 15 people based on face-to face and 2 interviews by telephone and e-mail to collect data to saturate the categories. Nine interviews including 2 telephone interviews were from nine user organizations adopting the technology innovation and the others were from three supply organizations. Semi-structured interviews were used to collect data. The interviews were recorded on digital voice recorder memory and subsequently transcribed verbatim. 196 pages of transcripts were obtained from about 12 hours interviews. Triangulation of evidence was achieved by examining each organization website and various documents, such as brochures and white papers. The researcher read the transcripts several times and underlined core words, phrases, or sentences. Then, data analysis used the procedure of open coding, in which the researcher forms initial categories of information about the phenomenon being studied by segmenting information. QSR NVivo version 8.0 was used to categorize sentences including similar concepts. 47 categories derived from interview data were grouped into 21 categories from which six factors were named. Five factors affecting adoption of the Semantic Web were identified. The first factor is demand pull including requirements for improving search and integration services of the existing systems and for creating new services. Second, environmental conduciveness, reference models, uncertainty, technology maturity, potential business value, government sponsorship programs, promising prospects for technology demand, complexity and trialability affect the adoption of the Semantic Web from the perspective of technology push. Third, absorptive capacity is an important role of the adoption. Fourth, suppler's competence includes communication with and training for users, and absorptive capacity of supply organization. Fifth, over-expectance which results in the gap between user's expectation level and perceived benefits has a negative impact on the adoption of the Semantic Web. Finally, the factor including critical mass of ontology, budget. visible effects is identified as a determinant affecting routinization and infusion. The researcher suggested a model of adoption and diffusion of the Semantic Web, representing relationships between six factors and adoption/diffusion as dependent variables. Six propositions are derived from the adoption/diffusion model to offer some guidelines to practitioners and a research model to further studies. Proposition 1 : Demand pull has an influence on the adoption of the Semantic Web. Proposition 1-1 : The stronger the degree of requirements for improving existing services, the more successfully the Semantic Web is adopted. Proposition 1-2 : The stronger the degree of requirements for new services, the more successfully the Semantic Web is adopted. Proposition 2 : Technology push has an influence on the adoption of the Semantic Web. Proposition 2-1 : From the perceptive of user organizations, the technology push forces such as environmental conduciveness, reference models, potential business value, and government sponsorship programs have a positive impact on the adoption of the Semantic Web while uncertainty and lower technology maturity have a negative impact on its adoption. Proposition 2-2 : From the perceptive of suppliers, the technology push forces such as environmental conduciveness, reference models, potential business value, government sponsorship programs, and promising prospects for technology demand have a positive impact on the adoption of the Semantic Web while uncertainty, lower technology maturity, complexity and lower trialability have a negative impact on its adoption. Proposition 3 : The absorptive capacities such as organizational formal support systems, officer's or manager's competency analyzing technology characteristics, their passion or willingness, and top management support are positively associated with successful adoption of the Semantic Web innovation from the perceptive of user organizations. Proposition 4 : Supplier's competence has a positive impact on the absorptive capacities of user organizations and technology push forces. Proposition 5 : The greater the gap of expectation between users and suppliers, the later the Semantic Web is adopted. Proposition 6 : The post-adoption activities such as budget allocation, reaching critical mass, and sharing ontology to offer sustainable services are positively associated with successful routinization and infusion of the Semantic Web innovation from the perceptive of user organizations.

• Journal of Korean Society of Forest Science
• /
• v.94 no.4 s.161
• /
• pp.214-225
• /
• 2005

The mountain village development program in Korea started in the mountain villages, the 45.9% of total land and one of the typical marginal region, from 1995 to achieve the equilibrium development of national land and the sustainable mountain development in Chapter 13 in Agenda 21, and it has been accelerated to increase the happiness and the quality of life of mountain community residents through the expansion by province and the improvement of related laws and regulations. This study has been aimed to analyze the response of main stakeholder's -mountain village residents and local government officials - on mountain villages development, and to provide the future plan as community development. The survey and interview data were collected from the mountain villages which already developed 59 villages and developing 15 villages in 2003. The mountain village development program has achieved the positive aspects as community development plan in the several fields, - the voluntary participation of residents, the establishment of self-support spirit as the democratic civilians, the development of base of income increasement, the creation of comfortable living environment, the equilibrium development with the other regions. Especially the mountain residents and local government officials both highly satisfy with the development of base of income increasement and the creation of comfortable living environment which are the main concerns to both stakeholder. However through the mountain development program, it is not satisfied to increase the maintenance of local community and the strengthening of traditional value of mountain villages. Also to improve the sustainable income improvement effects, it is necessary to develop the income items and technical extension which good for the each region. In the decentralization era, it is necessary for local government should have the more active and multilateral activities for these. With this, the introduction of methods which the mountain community people and the local government officials could co-participate in the mountain villages' development from the initial stages and the renovation of related local government organizations and the cooperatives will be much helpful to the substantiality of mountain development program. Also it is essential for the assistance of central government to establish the complex plan and the mountain villages network for all mountain area and the exchange of information, the education and training of mountain villages leader who are the core factor for the developed mountain villages maintenance, the composition of national mountain villages representatives. In case the development proposals which based on the interests of the main stakeholder's on mountain community could be positively accepted, then the possibility of the mountain village development as one of community development will be successfully improved in future.