• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.95-110
• /
• 2013

Recently, the amount of unstructured data being generated through a variety of social media has been increasing rapidly, resulting in the increasing need to collect, store, search for, analyze, and visualize this data. This kind of data cannot be handled appropriately by using the traditional methodologies usually used for analyzing structured data because of its vast volume and unstructured nature. In this situation, many attempts are being made to analyze unstructured data such as text files and log files through various commercial or noncommercial analytical tools. Among the various contemporary issues dealt with in the literature of unstructured text data analysis, the concepts and techniques of opinion mining have been attracting much attention from pioneer researchers and business practitioners. Opinion mining or sentiment analysis refers to a series of processes that analyze participants' opinions, sentiments, evaluations, attitudes, and emotions about selected products, services, organizations, social issues, and so on. In other words, many attempts based on various opinion mining techniques are being made to resolve complicated issues that could not have otherwise been solved by existing traditional approaches. One of the most representative attempts using the opinion mining technique may be the recent research that proposed an intelligent model for predicting the direction of the stock index. This model works mainly on the basis of opinions extracted from an overwhelming number of economic news repots. News content published on various media is obviously a traditional example of unstructured text data. Every day, a large volume of new content is created, digitalized, and subsequently distributed to us via online or offline channels. Many studies have revealed that we make better decisions on political, economic, and social issues by analyzing news and other related information. In this sense, we expect to predict the fluctuation of stock markets partly by analyzing the relationship between economic news reports and the pattern of stock prices. So far, in the literature on opinion mining, most studies including ours have utilized a sentiment dictionary to elicit sentiment polarity or sentiment value from a large number of documents. A sentiment dictionary consists of pairs of selected words and their sentiment values. Sentiment classifiers refer to the dictionary to formulate the sentiment polarity of words, sentences in a document, and the whole document. However, most traditional approaches have common limitations in that they do not consider the flexibility of sentiment polarity, that is, the sentiment polarity or sentiment value of a word is fixed and cannot be changed in a traditional sentiment dictionary. In the real world, however, the sentiment polarity of a word can vary depending on the time, situation, and purpose of the analysis. It can also be contradictory in nature. The flexibility of sentiment polarity motivated us to conduct this study. In this paper, we have stated that sentiment polarity should be assigned, not merely on the basis of the inherent meaning of a word but on the basis of its ad hoc meaning within a particular context. To implement our idea, we presented an intelligent investment decision-support model based on opinion mining that performs the scrapping and parsing of massive volumes of economic news on the web, tags sentiment words, classifies sentiment polarity of the news, and finally predicts the direction of the next day's stock index. In addition, we applied a domain-specific sentiment dictionary instead of a general purpose one to classify each piece of news as either positive or negative. For the purpose of performance evaluation, we performed intensive experiments and investigated the prediction accuracy of our model. For the experiments to predict the direction of the stock index, we gathered and analyzed 1,072 articles about stock markets published by "M" and "E" media between July 2011 and September 2011.

• Journal of Korean Society of Forest Science
• /
• v.12 no.1
• /
• pp.31-43
• /
• 1971

In order to examine the taxonomic difference between the type of Pinus parviflora S. et Z. native to the Dagelet Island and the type of the species introduced to a number of places of the inland of South Korea, investigations on principal characters of needle, cone and seed were made with a hope to obtain informations on the evaluation of the species for possible use in the reforestation program in Korea in the future. Pinus parviflora is belonged to the Sub-genus Haploxylon of Genus Pinus and it has been speculated among dendrologists that this speoies is not monotypic. 308 rendomly selected trees from 8 different elevations of a natural stand of P. parviflora in the Dagelet Island, and 168 trees of P. parviflora growing at 15 different locations of the inland of South Korea were employed as samples along with 300 trees of P. koraiensis as control. The results obtained are summarized as follows: 1. The needle length of the Pinus parviflora of the Dagelet Island is longer than that of the species growing in the inland by 21-35 percent with statistical significancy. (Table 2) 2. In the cross section of needle, no resin canal was observed in about 50-70 percent of the sample trees of the Dagelet Island, whereas the resin canals appearing at external in most cases were observed in all sample trees from the inland. Consequently, the number of resin canals per needle was 0.4-0.9 with the Dagelet Island type and 2.0-2.7 with the inland type and these differences were statistically significant. (Table 3, Fig.2) 3. The Pinus parvviflora type of the Dagelet Island bas yellowish brown cones, and the Pinus parviflora type of Suwon and Kwangyang has redish brown cones. In both the length of cone and the number of cone scale, the difference between the type of the Dagelet Island and the type of the inland was also statistically significant. The cone scales of the Dagelet Island type are slightly opened, whereas the cone scales are widely opened with both of Suwon and Kwangyang type. (Table 4, Fig. 3) 4. the seed color, of the Dagelet Island type is yellowish brown, while it is greyish brown with Kwangyang and Suwon type. In the length and width of seed, the Dagelet Island type showed significantly larger values than that of the inland type. The length of seed was longest with the Kwangyang type being followed by Suwon and the Dagelet Island type in ordar. The seed wing of the Kwangyang type are longer than the seed, while that of the Dagelet Island type is degenerated to be shorter than the seed. (Table 5, Fig. 4) 5. The Pinus parviflora type of the Dagelat Island is similar in many respects to the southern type of Pinus parviflora of Japan except that many has no resin canals in the needle. 6. On the basis of the results obtained in this study, it may be concluded that the type of Pinus parviflora of the Dagelet Island is significantly different from the type of the species introduced to the inland and that there is no recognizable variation between the population of the different altitude of the Dagelet Island and the individual variation within population is also negligible. In the light of the high value of the tree not only as an ornamental tree but as an economical tree, The type of Pinus parviflora of the Dagelet Island is considered to be recommendable to be used for the future reforestation program of Korea.

• The Journal of Korean Society for Radiation Therapy
• /
• v.30 no.1_2
• /
• pp.191-199
• /
• 2018

Purpose : In this study, we evaluated the usefulness of colloid gel(slime) as a compensator for irregular patient surfaces in radiation therapy. Materials and Methods : For this study, colloid gel suitable for treatment was made and four experiments were conducted to evaluate the applicability of radiation therapy. Trilogy(Varian) and CT(SOMATOM, Siemens) were used as treatment equipment and CT equipment. First, the homogeneity according to the composition of colloid gel was measured using EBT3 Film(RIT). Second, the Hounsfield Unit(HU) value of colloid gel was measured and confirmed by CRIS phantom, Eclipse RTP(Eclipse 13.1, Varian) and CT. Third, to measure the deformation and degeneration of colloid gel during the treatment period, it was measured 3 times daily for 2 weeks using an ion chamber(PTW-30013, PTW). The fourth experiment was compared the treatment plan and measured dose distributions using bolus, rice, colloid gel and additional, dose profiles in an environment similar to actual treatment using our own acrylic phantom. Result : First experiment, density of the colloid gel cases 1, 2 and 3 was $1.02g/cm^3$, $0.99g/cm^3$ and $0.96g/cm^3$. When the homogeneity was measured at 6 MV and 9 MeV, case 1 was more homogeneous than the other cases, as 1.55 and 1.98. In the second experiment, the HU values of case 1, 2, 3 were 15 and when the treatment plan was compared with the measured doses, the difference was within 1 % at all 9, 12 MeV and a difference of -1.53 % and -1.56 % within the whole 2 % at 6 MV. In the third experiment, the dose change of colloid gel was measured to be about 1 % for 2 weeks. In the fourth experiment, the dose difference between the treatment plan and EBT3 film was similar for both colloid gel and bolus, rice at 6 MV. But colloid gel showed less dose difference than bolus and rice at 9 MeV. Also, dose profile of colloid gel showed a more uniform dose distribution than the bolus and rice. Conclusion : In this study, the density of colloid gel prepared for radiation therapy was $1.02g/cm^3$ similar to the density of water, and alteration or deformation was not observed during the radiotherapy process. Although we pay attention to the density when manufacturing colloid gel, it is sufficient in that it can deliver the dose uniformly through the compensation of the patient's body surface more than the bolus and rice, and can be manufactured at low cost. Further studies and studies for clinical applications are expected to be applicable to radiation therapy.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.39-55
• /
• 2019

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.

• The Journal of Korean Society for Radiation Therapy
• /
• v.31 no.1
• /
• pp.51-56
• /
• 2019

Purpose: The usefulness of using single-electron radiation for secondary radiotherapy of breast cancer patients after surgery is assessed and the use of a combine of different energy. Methods and materials : In this study, 40 patients (group A) using energy 6 MeV and 9 MeV, and 19 patients (group B) using a combine of 9 MeV and 12 MeV were studied among 59 patients who performed secondary care using combine electronic radiation. Each patient in each group, 6 MeV, 9 MeV, Combine(6 MeV / 9 MeV) and 9 MeV, 12 MeV, Combine (9 MeV / 12 MeV) were developed in different ways, and the maximum doses delivered to the original hospital, D95, D5, and $V_3$, $V_5$, $V_{10}$ were compared. Result: The D95 mean value of Group A treatment plan was $785.33{\pm}225.37cGy$, $1121.79{\pm}87.02cGy$ at 9 MeV, and $1010.98{\pm}111.17cGy$ at 6 MeV / 9 MeV, and the mean value at 6 MeV / 9 MeV was most appropriate for the dose. The mean values of the low dose area $V_3$ and $V_5$ in the lung of the breast direction being treated were $3.24{\pm}3.49%$ and $0.72{\pm}1.55%$ at 6 MeV, the highest 9 MeV at $7.25{\pm}4.59%$, $3.07{\pm}2.64%$, the lowest at 6 MeV. Maximum and average lung dose was $727.78{\pm}137.27cGy$ at 6 MeV / 9 MeV, $49.16{\pm}24.44cGy$, highest 9 MeV at $998.97{\pm}114.35cGy$, $85.33{\pm}41.18cGy$, and lowest 6 MeV at $387.78{\pm}208.88cGy$, $9.27{\pm}6.60cGy$. The value of $V_{10}$ was all close to zero. Group B appeared in the pattern of Group A. Conclusion: Relative differences in low-dose areas of the lungs $V_3$ and $V_5$ were seen and were most effective in the dose transfer of tumor bed in the application of combined energy. It is thought that the method of using electronic energy in further radiation treatments for breast cancer is a more effective way to use the energy effect of limiting energy resources, and that if you think about it again, it could be a little more beneficial radiation treatment for patients.

• Korean Journal of Heritage: History & Science
• /
• v.43 no.1
• /
• pp.160-189
• /
• 2010

This study has been designed to grasp the present situation, shapes and meaning of the standing stones and rock pillars in the whole area of Noseong Mountain Fortress in Nonsan City which have never been academically reported yet. Accordingly, the research was carried out to grasp the spatial identity of Noseong Mt. and Noseong Mountain Fortress and the dispersion of standing stones scattered around inside and outside Noseong Mountain Fortress, while the shapes and structural characteristics of stones were investigated and analyzed focusing on Chongsuk Temple, which was considered to have the highest density of standing stones and greatest values for preservation as a cultural property. In consideration of the reference to the 'Top Sa' (tower temple) at the 'Bul Woo Jo' (Article about Buddhism Houses) of 'Shinjoong Dongguk Yeoji Seungram', theoretical existence of the temple according to surveying investigation, and the excavation records of roof tile pieces with the name of 'Gwan Eum Temple', it is presumed that there had been a Buddhist sanctum inside the fortress and it could be connected to the carved letters, 'Chongsuk Temple'. According the observation survey, the 6th place of standing stones among many other places inside the fortress shows that Chongsuk Temple appears to have the strong characteristics of artificially constructed space in consideration of the size of trees and stones, the composite trend of tree and stone composition, and trace of the adjacent well and strand and the construction of stairway leading to the stone gate. Along with the constellation of the Big Dipper carved on a rock at the same space, the stones, on which the letters of 'Shinseonam', 'Chilseongam' and 'Daejangam' were carved, including 'Chongsuksa', and the carved statue of Buddha, which was assumed to be Avalokitesvara Guan Yin, have offered clue which make it possible to infer that the space was a space for Chilseong and Mountain god(Folk Belief) that had originated from the combination of Buddhism, Taoism and folk religion. According to the actual measurement of standing stones at Chonsuk Temple, it was identified that there were big differences in height among 24 stones in total, ranging from 402~29cm and the averaged distance between each stone appeared to be 23.6cm. And the shape of stones appeared to be standing or flat, and various stones such as mountain-like stones and Buddha-like stones were placed in a special arrangement or assorted arrangement, but the direction of the stones had a consistency pointing to the west. And comparing to the trace of construction of ZEN Landscape Garden well known in the country, the three flat stones except for the standing and shaped stones appeared to have the shape of meditation statue, which is the typical formational factors of a ZEN Landscape Garden, on the basis of formational technique of stones. Among them, the flat stone facing the Buddhist saint statue, was formed by way of symbolization of three-mountain stone, which was assumed to be an offering stone for sacrificial food rather than carrying out ZEN Meditation. In consideration of the formation of standing stones at Chong-suk Temple, which was carried out in the composite stoning method based using the scalene triangle with ratio of 3:5:7 in order to seek the in-depth beauty based on the stone statues of three Buddhas where the three factors such as heaven, earth and humans are embodied in the elevated or flat formation, the stones at Chongsuk Temple and the space seemed to the trace of contracted garden construction that was formed with stones for a temple, so that could be used for ZEN meditation.

• The Journal of Korean Society for Radiation Therapy
• /
• v.31 no.1
• /
• pp.25-32
• /
• 2019

Purpose: The size, shape, and volume of prosthetic appliance depend on the metal artifacts resulting from dental implant during head and neck treatment with radiation. This reduced the accuracy of contouring targets and surrounding normal tissues in radiation treatment plan. Therefore, the purpose of this study is to obtain the images of metal representing the size of tooth through MVCT, SMART-MAR CT and KVCT, evaluate the volumes, apply them into the proton therapy plan, and analyze the difference of dose distribution. Materials and Methods : Metal A ($0.5{\times}0.5{\times}0.5cm$), Metal B ($1{\times}1{\times}1cm$), and Metal C ($1{\times}2{\times}1cm$) similar in size to inlay, crown, and bridge taking the treatments used at the dentist's into account were made with Cerrobend ($9.64g/cm^3$). Metal was placed into the In House Head & Neck Phantom and by using CT Simulator (Discovery CT 590RT, GE, USA) the images of KVCT and SMART-MAR were obtained with slice thickness 1.25 mm. The images of MVCT were obtained in the same way with $RADIXACT^{(R)}$ Series (Accuracy $Precision^{(R)}$, USA). The images of metal obtained through MVCT, SMART-MAR CT, and KVCT were compared in both size of axis X, Y, and Z and volume based on the Autocontour Thresholds Raw Values from the computerized treatment planning equipment Pinnacle (Ver 9.10, Philips, Palo Alto, USA). The proton treatment plan (Ray station 5.1, RaySearch, USA) was set by fusing the contour of metal B ($1{\times}1{\times}1cm$) obtained from the above experiment by each CT into KVCT in order to compare the difference of dose distribution. Result: Referencing the actual sizes, it was appeared: Metal A (MVCT: 1.0 times, SMART-MAR CT: 1.84 times, and KVCT: 1.92 times), Metal B (MVCT: 1.02 times, SMART-MAR CT: 1.47 times, and KVCT: 1.82 times), and Metal C (MVCT: 1.0 times, SMART-MAR CT: 1.46 times, and KVCT: 1.66 times). MVCT was measured most similarly to the actual metal volume. As a result of measurement by applying the volume of metal B into proton treatment plan, the dose of $D_{99%}$ volume was measured as: MVCT: 3094 CcGE, SMART-MAR CT: 2902 CcGE, and KVCT: 2880 CcGE, against the reference 3082 CcGE Conclusion: Overall volume and axes X and Z were most identical to the actual sizes in MVCT and axis Y, which is in the superior-Inferior direction, was regular in length without differences in CT. The best dose distribution was shown in MVCT having similar size, shape, and volume of metal when treating head and neck protons. Thus it is thought that it would be very useful if the contour of prosthetic appliance using MVCT is applied into KVCT for proton treatment plan.

• Korean Journal of Heritage: History & Science
• /
• v.37
• /
• pp.371-405
• /
• 2004

International circulation of cultural assets involves numerous countries thereby making an approach based on international law essential to resolving this problem. Since the end of the $2^{nd}$ World War, as the value of cultural assets evolved from material value to moral and ethical values, with emphasis on establishing national identities, newly independent nations and former colonial states took issue with ownership of cultural assets which led to the need for international cooperation and statutory provisions for the return of cultural assets. UNESCO's 1954 "Convention for the Protection of Cultural Property in the Event of Armed Conflict" as preparatory measures for the protection of cultural assets, the 1970 "Convention on the Means of Prohibiting and Preventing the Illicit Import and Transfer of Ownership of Cultural Property" to regulate transfer of cultural assets, and the 1995 "Unidroit Convention on Stolen or Illegally Exported Cultural Objects" which required the return of illegally acquired cultural property are examples of international agreements established on illegal transfers of cultural assets. In addition, the UN agency UNESCO established the Division of Cultural Heritage to oversee cultural assets related matters, and the UN since its 1973 resolution 3187, has continued to demonstrate interest in protection of cultural assets. The resolution 3187 affirms the return of cultural assets to the country of origin, advises on preventing illegal transfers of works of art and cultural assets, advises cataloguing cultural assets within the respective countries and, conclusively, recommends becoming a member of UNESCO, composing a forum for international cooperation. Differences in defining cultural assets pose a limitation on international agreements. While the 1954 Convention states that cultural assets are not limited to movable property and includes immovable property, the 1970 Convention's objective of 'Prohibiting and preventing the illicit import, export and transfer of ownership of cultural property' effectively limits the subject to tangible movable cultural property. The 1995 Convention also has tangible movable cultural property as its subject. On this point, the two conventions demonstrate distinction from the 1954 Convention and the 1972 Convention that focuses on immovable cultural property and natural property. The disparity in defining cultural property is due to the object and purpose of the convention and does not reflect an inherent divergence. In the case of Korea, beginning with the 1866 French invasion, 36 years of Japanese colonial rule, military rule and period of economic development caused outflow of numerous cultural assets to foreign countries. Of course, it is neither possible nor necessary to have all of these cultural properties returned, but among those that have significant value in establishing cultural and historical identity or those that have been taken symbolically as a demonstration of occupational rule can cause issues in their return. In these cases, the 1954 Convention and the ratification of the first legislation must be actively considered. In the return of cultural property, if the illicit acquisition is the core issue, it is a simple matter of following the international accords, while if it rises to the level of diplomatic discussions, it will become a political issue. In that case, the country requesting the return must convince the counterpart country. Realizing a response to the earnest need for preventing illicit trading of cultural assets will require extensive national and civic societal efforts in the East Asian area to overcome its current deficiencies. The most effective way to prevent illicit trading of cultural property is rapid circulation of information between Interpol member countries, which will require development of an internet based communication system as well as more effective deployment of legislation to prevent trading of illicitly acquired cultural property, subscription to international conventions and cataloguing collections.

• Korean Journal of Heritage: History & Science
• /
• v.39
• /
• pp.351-378
• /
• 2006

With the development of media, the methods for the documentation of intangible cultural heritage have been also developed and diversified. As well as the previous analogue ways of documentation, the have been recently applying new multi-media technologies focusing on digital pictures, sound sources, movies, etc. Among the new technologies, the documentation of intangible cultural heritage using the method of 'Motion Capture' has proved itself prominent especially in the fields that require three-dimensional documentation such as dances and performances. Motion Capture refers to the documentation technology which records the signals of the time varing positions derived from the sensors equipped on the surface of an object. It converts the signals from the sensors into digital data which can be plotted as points on the virtual coordinates of the computer and records the movement of the points during a certain period of time, as the object moves. It produces scientific data for the preservation of intangible cultural heritage, by displaying digital data which represents the virtual motion of a holder of an intangible cultural heritage. National Research Institute of Cultural Properties (NRICP) has been working on for the development of new documentation method for the Important Intangible Cultural Heritage designated by Korean government. This is to be done using 'motion capture' equipments which are also widely used for the computer graphics in movie or game industries. This project is designed to apply the motion capture technology for 3 years- from 2005 to 2007 - for 11 performances from 7 traditional dances of which body gestures have considerable values among the Important Intangible Cultural Heritage performances. This is to be supported by lottery funds. In 2005, the first year of the project, accumulated were data of single dances, such as Seungmu (monk's dance), Salpuri(a solo dance for spiritual cleansing dance), Taepyeongmu (dance of peace), which are relatively easy in terms of performing skills. In 2006, group dances, such as Jinju Geommu (Jinju sword dance), Seungjeonmu (dance for victory), Cheoyongmu (dance of Lord Cheoyong), etc., will be documented. In the last year of the project, 2007, education programme for comparative studies, analysis and transmission of intangible cultural heritage and three-dimensional contents for public service will be devised, based on the accumulated data, as well as the documentation of Hakyeonhwadae Habseolmu (crane dance combined with the lotus blossom dance). By describing the processes and results of motion capture documentation of Salpuri dance (Lee Mae-bang), Taepyeongmu (Kang seon-young) and Seungmu (Lee Mae-bang, Lee Ae-ju and Jung Jae-man) conducted in 2005, this report introduces a new approach for the documentation of intangible cultural heritage. During the first year of the project, two questions have been raised. First, how can we capture motions of a holder (dancer) without cutoffs during quite a long performance? After many times of tests, the motion capture system proved itself stable with continuous results. Second, how can we reproduce the accurate motion without the re-targeting process? The project re-created the most accurate motion of the dancer's gestures, applying the new technology to drew out the shape of the dancers's body digital data before the motion capture process for the first time in Korea. The accurate three-dimensional body models for four holders obtained by the body scanning enhanced the accuracy of the motion capture of the dance.

• 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.