• Journal of Environmental Impact Assessment
• /
• v.33 no.1
• /
• pp.1-8
• /
• 2024

Amphibians are a taxonomic group that ecologically connects terrestrial ecosystems and aquatic ecosystems. They play a very important role in the food chain of the ecosystem. It is known that there are about 5,948 species distributed all over the world, but after the Industrial Revolution, due to industrialization and urbanization, there has been a decrease in species and populations. In particular, it is becoming a factor in exacerbating habitat fragmentation or fragmentation due to artificial canals. In orderto improve the survivalrate of wild animals in artificial canals, escape facilities are installed to reduce it. This study analyzed the slope, height of the escape facility, escape rate, and travel distance in the operating facility for Bombina orientalis, which mainly inhabits near forests. The slope of the escape facility showed a relatively similar escape success rate regardless of height at 50° and 60°, while at 70°, it showed a relatively high escape success rate at only 40cm in height. The success rate of escape from the waterway escape facility in operation was 14.71%, showing a very low utilization rate, and the recognition rate of the artificial canal escape facility was found to be very low as it moved along the side wall of the artificial canal. Therefore, in the case of a waterway escape facility for Bombina orientalis, it is possible to construct it at an angle of 60°, and if the side walls of the artificial canals are built within 60°, Bombina orientalis can move freely in both directions, overcoming the low utilization rate of existing waterway escape facilities. It is expected to minimize the impact of movement and death of artificial canals. In addition, if the spacing between escape facilities is narrowed from the installation standard of 30m and ramps are constructed in both directions upstream and downstream, the escape success rate of amphibians,reptiles, and small mammals otherthan lady frogs is expected to improve.

• Journal of the Korean Society of Radiology
• /
• v.18 no.2
• /
• pp.101-108
• /
• 2024

Recently, Metaverse technology has emerged as an important topic in various fields. Metaverse refers to a three-dimensional virtual space in which social and economic activities similar to the real world are possible. Among the 235 third-year students who applied the Metaversity app in the radiology department of this university from September to December 2023, 200 participated in a survey to determine the difference in student response and satisfaction when applying the Metaversity app. analyzed. First, the most satisfactory VOD viewing method was viewing through the Metaversity app, followed by viewing through the LMS. Second, 'I think online videos are appropriate for holiday reinforcement.' showed the highest score at 4.35±0.60, 'I want face-to-face classes and online classes to be held simultaneously.' was 4.25±0.87, and 'I think meta. 'I watched it well through the Metaversity app' was the lowest at 4.10±0.30, and 'VOD viewing through the Metaversity app was used appropriately in class' was the lowest at 3.99±0.75. Also, there was no significant difference in the response to the teaching method (p>0.05). Third, in terms of satisfaction with VOD viewing using the Metaversity app, 'Applying the Metaversity app was interesting and fun' ranked the highest at 4.24±0.88. The score was high, with 'Better improvement is needed to actively utilize the metaversity app' at 4.00±0.45, and 'I hope the metaversity app is implemented in other remote classes' at 3.77±0.88. appear. 'VOD classes through the Metaversity app are better than the existing LMS method.' was found to be 3.44±0.66. Additionally, there was no significant difference in satisfaction with classes according to age and gender (p>0.05). The correlation between response and satisfaction with the metaversity app is 0.601, which can be considered very significant (p>0.001). As a limitation of this study, although we surveyed students' satisfaction with using the Metaversity app, we were unable to investigate the satisfaction of instructors who interact with students. In the future, we did not consider the instructor's satisfaction in classes using the Metaversity app. Research must be conducted, and universities must have institutional support and continued interest until metaversity apps are selected and used to prepare for distance learning.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.23-43
• /
• 2016

As a result of the growth of Internet data and the rapid development of Internet technology, "big data" analysis has gained prominence as a major approach for evaluating and mining enormous data for various purposes. Especially, in recent years, people tend to share their experiences related to their leisure activities while also reviewing others' inputs concerning their activities. Therefore, by referring to others' leisure activity-related experiences, they are able to gather information that might guarantee them better leisure activities in the future. This phenomenon has appeared throughout many aspects of leisure activities such as movies, traveling, accommodation, and dining. Apart from blogs and social networking sites, many other websites provide a wealth of information related to leisure activities. Most of these websites provide information of each product in various formats depending on different purposes and perspectives. Generally, most of the websites provide the average ratings and detailed reviews of users who actually used products/services, and these ratings and reviews can actually support the decision of potential customers in purchasing the same products/services. However, the existing websites offering information on leisure activities only provide the rating and review based on one stage of a set of evaluation criteria. Therefore, to identify the main issue for each evaluation criterion as well as the characteristics of specific elements comprising each criterion, users have to read a large number of reviews. In particular, as most of the users search for the characteristics of the detailed elements for one or more specific evaluation criteria based on their priorities, they must spend a great deal of time and effort to obtain the desired information by reading more reviews and understanding the contents of such reviews. Although some websites break down the evaluation criteria and direct the user to input their reviews according to different levels of criteria, there exist excessive amounts of input sections that make the whole process inconvenient for the users. Further, problems may arise if a user does not follow the instructions for the input sections or fill in the wrong input sections. Finally, treating the evaluation criteria breakdown as a realistic alternative is difficult, because identifying all the detailed criteria for each evaluation criterion is a challenging task. For example, if a review about a certain hotel has been written, people tend to only write one-stage reviews for various components such as accessibility, rooms, services, or food. These might be the reviews for most frequently asked questions, such as distance between the nearest subway station or condition of the bathroom, but they still lack detailed information for these questions. In addition, in case a breakdown of the evaluation criteria was provided along with various input sections, the user might only fill in the evaluation criterion for accessibility or fill in the wrong information such as information regarding rooms in the evaluation criteria for accessibility. Thus, the reliability of the segmented review will be greatly reduced. In this study, we propose an approach to overcome the limitations of the existing leisure activity information websites, namely, (1) the reliability of reviews for each evaluation criteria and (2) the difficulty of identifying the detailed contents that make up the evaluation criteria. In our proposed methodology, we first identify the review content and construct the lexicon for each evaluation criterion by using the terms that are frequently used for each criterion. Next, the sentences in the review documents containing the terms in the constructed lexicon are decomposed into review units, which are then reconstructed by using the evaluation criteria. Finally, the issues of the constructed review units by evaluation criteria are derived and the summary results are provided. Apart from the derived issues, the review units are also provided. Therefore, this approach aims to help users save on time and effort, because they will only be reading the relevant information they need for each evaluation criterion rather than go through the entire text of review. Our proposed methodology is based on the topic modeling, which is being actively used in text analysis. The review is decomposed into sentence units rather than considering the whole review as a document unit. After being decomposed into individual review units, the review units are reorganized according to each evaluation criterion and then used in the subsequent analysis. This work largely differs from the existing topic modeling-based studies. In this paper, we collected 423 reviews from hotel information websites and decomposed these reviews into 4,860 review units. We then reorganized the review units according to six different evaluation criteria. By applying these review units in our methodology, the analysis results can be introduced, and the utility of proposed methodology can be demonstrated.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.35 no.3
• /
• pp.41-66
• /
• 2017

The purpose of this research is to empirically trace the junctures of Yigye-gugok managed by Gwan-am Hong Gyeong-mo, a grandson of Yigye Hong Yang-ho who originally designed Yigye-gugok, while reviewing the features of the forms and patterns of gugok. The results of the research are as follows. 1. Ui-dong was part of the domain of the capital during the Chosun dynasty, which also is located in the city of Seoul as a matter of administrative zone. Likewisely, Yigye-gugok is taken as a special meaning for it was one and only gugok. Starting with Mangyeong Waterfall as the $1^{st}$ gok, Yigye follows through the $2^{nd}$ gok of Jeokchwibyeong Rock, the $3^{rd}$ gok of Chanunbong Peak, the $4^{th}$ gok of Jinuigang Rock, the $5^{th}$ gok of Okkyeongdae Rock, the $6^{th}$ gok of Wolyeongdam Pond, the $7^{th}$ gok of Tagyeongam Rock, the $8^{th}$ gok of Myeongoktan Stream, and the $9^{th}$ gok of Jaeganjeong Pavilion. Of these, Mangyeong Waterfall, Chanunbong Peak, and Okkyeongdae Rock are distinct for their locations in as much as their features, while estimated locations for Jinuigang Rock, Wolyeongdam Pond, Myeongoktan Stream, and Jaeganjeong Pavilion were discovered. However, Jeokchwibyeong Rock and Tagyeongam Rock demonstrated multiple locations in close resemblance to documentary literatures within secretive proximity, whereas geography, scenery, and sighted objects were considered to evaluate the 1st estimated location. Through these endeavored, it was possible to identify the shipping routes and structures for the total distance of 2.1km running from the $1^{st}$ gok to the $9^{th}$ gok, which nears Gwanam's description of 5ri(里), or approximately 1.96km for gugok. 2. Set towards the end of the $18^{th}$ century, Yigye-gugok originated from a series of work shaping the space of Hong Yang-ho's tomb into a space for the family. Comparing Yigye-gugok to other gugoks, numerous differences are apparent from beyond the rather more general format such as adjoining the $8^{th}$ gok while paving through the lower directions from the upper directions of the water. This gives rises to the interpretation such that Yigye-gugok was positioned to separate the doman of the family from those of the other families in power, thereby taking over Ui-dong. Yet, the aspect of the possession of the space lends itself to the determination that the location positioned at the $8^{th}$ gok above Mangyeongpok Waterfall representing Wooyi-dong was a consequence of the centrifugal space creation efforts. 3. While writings and poetic works were manufactured in such large quantities in Yigye-gugok whose products of setters and managers seemed intended towards gugok-do and letters carved on the rocks among others, there is yet a tremendous lack of visual media in the same respect. 'Yigye-gugok Daejacheop' Specimens of Handwriting offers the traces of Gwanam's attempts to engrave gakja at the food of Yigye-gugok. This research was able to ascertain that 'Yigye-gugok Daejacheop' Specimens of Handwriting was a product of Hong Yang-ho's collections maintained under the auspices of the National Central Museum, which are renowned for Song Shi-yeol's penmanship.

• Animal Systematics, Evolution and Diversity
• /
• v.11 no.1
• /
• pp.39-64
• /
• 1995

A faunistic and ecological study on the occurrence of freshwater cladocerans and copepods was accomplished from Chindo, South Korea. Collections were made from total 35 stations, comprising the various freshwater habitats like reservoirs, streams, swamps, bogs, ricefields, ditch, pond, and spring during the periods of July 23-25, and November 1-3 in 1994. Twenty seven cladoceran species of 17 genera of 6 families in 2 orders, and 28 copepod species of 21 genera of 6 families in 3 orders were collected during this research period, of which Daphnia obtusa Kurz and Elaphoidella bidens (Schmeil) are newly recorded from Korea. In reservoirs, Diaphanosoma sp. and Thermocyclops taihokuensis were dominant in July, and then succeeded by Bosmina longirostris and Cyclops vicinus vicinus in November. Thermocyclops crassus co-occurred with 7: taihokuensis at both seasons, was frequent in November after T. taihokuensis precipitately decreased. In other stagnant waters, 7: taihokuensis and Moina weismanni were dominant at ponds in July and in November, respectively. At ricefields in July Moina macrocopa and T. taihokuensis were dominant, but in November M. macrocopa and Paracyclops fimbriatus were. At streams, cladocerans were relatively rare, but became more rich in November. The representative cladoceran species were Bosmina longirostris as a plankton, and Chydorus sphaericus as a epibenthic species. Concerning copepods, nearly all the stations of streams except a few ones adjacent to seashore showed the similiar species constitutions, of which E. serrulatus and M, pehpeiensis were most frequent and abundant. At a mountain streamlet and a spring, the occurrence of Alona sp., Attheyella byblis Chang and Kim, 1992 and A. tetraspinosa Chang, 1993 is quite interesting and deserved much attention in the taxonomical point of view. Seventeen major cladocerans and copepods from lentic habitats and 13 major cladocerans and copepods from lotic habitatats were clustered using average taxonomic distance and UPGMA to infer the co-occurrence relations among species. As for lentic habitats, two large phena were appeared at first. The one phenon consisted of Diaphanosoma sp. and T taihokuensis, and showed its predominancy over the various habitats and its dominancy was rapidly decreased in November. The other phenon frequently occurred rather in November, and subdivided into three subgroups. On the other hand, as for lotic habitats, 13 species were also grouped into 2 large phena. The first one comprised 4 species, which were dominant and highly frequent at nearly all the lotic habitats, and subdivided into three subgroups according to their seasonal fluctuation types. The second one was also subdivided into three phena, the first of which comprised only one species, Microcyclops varicans, and occurred at most of the stations along stream with steadiness through the research period; the second phenon, Chydorus sphaericus, occurred much frequently in November; the last phenon included a few heterogenous subgroups.

• Radiation Oncology Journal
• /
• v.27 no.1
• /
• pp.15-22
• /
• 2009

Purpose: This study was designed to evaluate the effects on bone mineral density (BMD) and related factors according to the distance from the radiation field at different sites. This study was conducted on patients with uterine cervical cancer who received pelvic radiotherapy. Materials and Methods: We selected 96 patients with cervical cancer who underwent determination of BMD from November 2002 to December 2006 after pelvic radiotherapy at Kosin University Gospel Hospital. The T-score and Z-score for the first lumbar spine (L1), fourth lumbar spine (L4) and femur neck (F) were analyzed to determine the difference in BMD among the sites by the use of ANOVA and the post-hoc test. The study subjects were evaluated for age, body weight, body mass index (BMI), post-radiotherapy follow-up duration, intracavitary radiotherapy (ICR) and hormonal replacement therapy (HRT). Association between the characteristics of the study subjects and T-score for each site was evaluated by the use of Pearson's correlation and multiple regression analysis. Results: The average T-score for all ages was -1.94 for the L1, -0.42 for the L4 and -0.53 for the F. The average Z-score for all ages was -1.11 for the L1, -0.40 for the L4 and -0.48 for the F. The T-score and Z-score for the L4 and F were significantly different from the scores for the L1 (p<0.05). There was no significant difference between the L4 and F. Results for patients younger than 60 years were the same as for all ages. Age and ICR were negatively correlated and body weight and HRT were positively correlated with the T-score for all sites (p<0.05). BMI was positively correlated with the T-score for the L4 and F (p<0.05). Based on the use of multiple regression analysis, age was negatively associated with the T-score for the L1 and F and was positively correlated for the L4 (p<0.05). Body weight was positively associated with the T-score for all sites (p<0.05). ICR was negatively associated with the T-score for the L1 (p<0.05). HRT was positively associated with the T-score for the L4 and F (p<0.05). Conclusion: The T-score and Z-score for the L4 and F were significantly higher than the scores for the L1, a finding in contrast to some previous studies on normal women. It was thought that radiation could partly influence BMD because of a higher T-score and Z-score for sites around the radiotherapy field. We suggest that a further long-term study is necessary to determine the clinical significance of these findings, which will influence the diagnosis of osteoporosis based on BMD in patients with cervical cancer who have received radiotherapy.

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

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

• 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.

• 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.