• Journal of Global Scholars of Marketing Science
• /
• v.20 no.3
• /
• pp.239-248
• /
• 2010

This paper describes a collaborative project between academia and industry which focused on improving the marketing and product development strategies for two private label apparel brands of a large regional department store chain in the southeastern United States. The goal of the project was to revitalize product lines of the two brands by incorporating student ideas for new solutions, thereby giving the students practical experience with a real-life industry situation. There were a number of key players involved in the project. A privately-owned department store chain based in the southeastern United States which was seeking an academic partner had recognized a need to update two existing private label brands. They targeted middle-aged consumers looking for casual, moderately priced merchandise. The company was seeking to change direction with both packaging and presentation, and possibly product design. The branding and product development divisions of the company contacted professors in an academic department of a large southeastern state university. Two of the professors agreed that the task would be a good fit for their classes - one was a junior-level Intermediate Brand Management class; the other was a senior-level Fashion Product Development class. The professors felt that by working collaboratively on the project, students would be exposed to a real world scenario, within the security of an academic learning environment. Collaboration within an interdisciplinary team has the advantage of providing experiences and resources beyond the capabilities of a single student and adds "brainpower" to problem-solving processes (Lowman 2000). This goal of improving the capabilities of students directed the instructors in each class to form interdisciplinary teams between the Branding and Product Development classes. In addition, many universities are employing industry partnerships in research and teaching, where collaboration within temporal (semester) and physical (classroom/lab) constraints help to increase students' knowledge and experience of a real-world situation. At the University of Tennessee, the Center of Industrial Services and UT-Knoxville's College of Engineering worked with a company to develop design improvements in its U.S. operations. In this study, Because should be lower case b with a private label retail brand, Wickett, Gaskill and Damhorst's (1999) revised Retail Apparel Product Development Model was used by the product development and brand management teams. This framework was chosen because it addresses apparel product development from the concept to the retail stage. Two classes were involved in this project: a junior level Brand Management class and a senior level Fashion Product Development class. Seven teams were formed which included four students from Brand Management and two students from Product Development. The classes were taught the same semester, but not at the same time. At the beginning of the semester, each class was introduced to the industry partner and given the problem. Half the teams were assigned to the men's brand and half to the women's brand. The teams were responsible for devising approaches to the problem, formulating a timeline for their work, staying in touch with industry representatives and making sure that each member of the team contributed in a positive way. The objective for the teams was to plan, develop, and present a product line using merchandising processes (following the Wickett, Gaskill and Damhorst model) and develop new branding strategies for the proposed lines. The teams performed trend, color, fabrication and target market research; developed sketches for a line; edited the sketches and presented their line plans; wrote specifications; fitted prototypes on fit models, and developed final production samples for presentation to industry. The branding students developed a SWOT analysis, a Brand Measurement report, a mind-map for the brands and a fully integrated Marketing Report which was presented alongside the ideas for the new lines. In future if the opportunity arises to work in this collaborative way with an existing company who wishes to look both at branding and product development strategies, classes will be scheduled at the same time so that students have more time to meet and discuss timelines and assigned tasks. As it was, student groups had to meet outside of each class time and this proved to be a challenging though not uncommon part of teamwork (Pfaff and Huddleston, 2003). Although the logistics of this exercise were time-consuming to set up and administer, professors felt that the benefits to students were multiple. The most important benefit, according to student feedback from both classes, was the opportunity to work with industry professionals, follow their process, and see the results of their work evaluated by the people who made the decisions at the company level. Faculty members were grateful to have a "real-world" case to work with in the classroom to provide focus. Creative ideas and strategies were traded as plans were made, extending and strengthening the departmental links be tween the branding and product development areas. By working not only with students coming from a different knowledge base, but also having to keep in contact with the industry partner and follow the framework and timeline of industry practice, student teams were challenged to produce excellent and innovative work under new circumstances. Working on the product development and branding for "real-life" brands that are struggling gave students an opportunity to see how closely their coursework ties in with the real-world and how creativity, collaboration and flexibility are necessary components of both the design and business aspects of company operations. Industry personnel were impressed by (a) the level and depth of knowledge and execution in the student projects, and (b) the creativity of new ideas for the brands.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.61-73
• /
• 2014

This study reviewed an application of water quality estimation using an Airborne Hyperspectral Imagery (A-HSI) and tested a part of Han River water quality (especially suspended solid) estimation with available in-situ data. The estimation of water quality was processed two methods. One is using observation data as downwelling radiance to water surface and as scattering and reflectance into water body. Other is linear regression analysis with water quality in-situ measurement and upwelling data as at-sensor radiance (or reflectance). Both methods drive meaningful results of RS estimation. However it has more effects on the auxiliary dataset as water quality in-situ measurement and water body scattering measurement. The test processed a part of Han River located Paldang-dam downstream. We applied linear regression analysis with AISA eagle hyperspectral sensor data and water quality measurement in-situ data. The result of linear regression for a meaningful band combination shows $-24.847+0.013L_{560}$ as 560 nm in radiance (L) with 0.985 R-square. To comparison with Multispectral Imagery (MSI) case, we make simulated Landsat TM by spectral resampling. The regression using MSI shows -55.932 + 33.881 (TM1/TM3) as radiance with 0.968 R-square. Suspended Solid (SS) concentration was about 3.75 mg/l at in-situ data and estimated SS concentration by A-HIS was about 3.65 mg/l, and about 5.85mg/l with MSI with same location. It shows overestimation trends case of estimating using MSI. In order to upgrade value for practical use and to estimate more precisely, it needs that minimizing sun glint effect into whole image, constructing elaborate flight plan considering solar altitude angle, and making good pre-processing and calibration system. We found some limitations and restrictions such as precise atmospheric correction, sample count of water quality measurement, retrieve spectral bands into A-HSI, adequate linear regression model selection, and quantitative calibration/validation method through the literature review and test adopted general methods.

• Publications of The Korean Astronomical Society
• /
• v.34 no.3
• /
• pp.31-40
• /
• 2019

We study the internal structure under the artificial mountain of Heumkyeonggak-nu, a Korean water-powered clock in the early Joseon dynasty. All the puppets on the artificial mountain are driven by the rotational force generated by the water wheel at their designated time. We design a model that work with three parts of the artificial mountain. At the upper part of the artificial mountain to the east, west, north and south, there are four puppets called the Four Mystical Animal Divinity and four ladies called the Jade Lady respectively. The former rotates a quarter every double hour and the latter rings the bell every hour. In the middle part of this mountain is the timekeeping platform with four puppets; the Timekeeping Official (Hour Jack), the Bell-, Drum-, and Gong-Warriors. The Hour Jack controls time with three warriors each hitting his own bell, drum, and gong, respectively. In the plain there are 12 Jade Lady puppets (the lower ladies) combined with 12 Oriental Animal Deity puppets. In his own time a lady doll pops out of the hole and her animal doll gets up. Two hours later, the animal deity lies down and his lady hides in the artificial plain. These puppets are regularly moved by the signal such as iron balls, bumps, levers, and so on. We can use balls and bumps to explain the concept of the Jujeon system. Iron balls were used to manipulate puppets of the timekeeping mechanism in Borugak-nu, another Korean water-powered clock in Joseon dynasty, which was developed earlier than Heumgyeonggak-nu. According to the North Korea's previous study (Choi, 1974), it is obvious that bumps were used in the internal structure of Heumgyeonggak-nu. In 1669, The armillary clock made by Song, I-young was also utilized bumps. Finally we presented mock-ups of three timekeeping systems.

• The Korean Journal of Food And Nutrition
• /
• v.15 no.2
• /
• pp.112-118
• /
• 2002

Sporulation in the fission yeast Schizosaccharomyces pombe has been regarded as an important model of cellular development and differentiation. S. pombe cells proliferate by mitosis and binary fission on growth medium. Deprivation of nutrients especially nitrogen sources, causes the cessation of mitosis and initiates sexual reproduction by matting between two sexually compatible cell types. Meiosis is then followed in a diploid cell in the absence of nitrogen source. DNA fragment complemented with the mutations of sporulation gene was isolated from the S. pombe gene library constructed in the vector, pDB 248' and designated as pDB(spo5)1. We futher analyzed six recombinant plasmids, pDB(spo5)2, pDB(spo5)3, pDB(spo5)4, pDB(spo5)5, pDB (spo5)6, pDB(spo5)7 and found each of these plasmids is able to rescue the spo5-2, spo5-3, spo5-4, spo5-5, spo5-6, spo5-7 mutations, respectively. Mapping of the integrated plasmid into the homologous site of the S. pombe chromosomes demonstrated that pDB(spo5)1, and pDB(spu5)Rl contained the spo5 gene. Transcripts of spo5 gene were analyzed by Northern hybridization. Two transcripts of 3.2 kb and 2.5kb were detected with 5kb Hind Ⅲ fragment containing a part of the spo5 gene as a probe. The small mRNA(2.5kb) appeared only when a wild-type strain was cultured in the absence of nitrogen source in which condition the large mRNA (3.2kb) was produced constitutively. Appearance of a 2.5kb spo5-mRNA depends upon the function of the meil, mei2 and mei3 genes.

• Korean Journal of Culture and Social Issue
• /
• v.9 no.spc
• /
• pp.107-122
• /
• 2003

The object of this study is to evaluate the prevailing physical and psychosocial conditions regarding occupational low back injury. This study consists of two parts. In the first part of the study, analytic biomechanical model and NIOSH guidelines are applied to evaluate risk levels of low back injury for automobile assembly jobs. Total of 246 workers are analysed. There are 20 jobs having greater back compressive forces than 300kg at L5/S1. Also, there are 44 jobs over Action Limit with respect to 1981 NIOSH guidelines. The relationship between psychosocial factors and low back injury was examined in the second part of the study. A battery of questionnaires concerning the psychosocial stress based on PWI (Psychosocial Well-being Index) and musculoskeletal pain symptoms at low back was completed by 246 workers at the same plant. Results showed that 207 out 246 workers experienced the symptoms and 27 workers were diagnosed as patients. Two groups(low stressed, high stressed) based on PWI score had no significant relationships with both symptoms and results of diagnosis. The relationships between physical work load and psychosocial stress were also analysed. Specifically, some postural factors(vertical deviation angle of forearm, horizontal deviation angle of upperarm, vertical deviation angle of thigh, etc) were highly correlated with psychosocial stress. The results illustrated that PWI scores were associated with some physical workloads. However, psychosocial stress levels couldn't be well related with the pain symptom as well as the actual incidence of low back injury since pain or discomfort regarding low back injury were more complex than that of other musculoskeletal disorders.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2004.04a
• /
• pp.3-4
• /
• 2004

Results will be presented from two field studies that evaluated the in-situ treatment of chlorinated aliphatic hydrocarbons (CAHs) using aerobic cometabolism. In the first study, a cometabolic air sparging (CAS) demonstration was conducted at McClellan Air Force Base (AFB), California, to treat chlorinated aliphatic hydrocarbons (CAHs) in groundwater using propane as the cometabolic substrate. A propane-biostimulated zone was sparged with a propane/air mixture and a control zone was sparged with air alone. Propane-utilizers were effectively stimulated in the saturated zone with repeated intermediate sparging of propane and air. Propane delivery, however, was not uniform, with propane mainly observed in down-gradient observation wells. Trichloroethene (TCE), cis-1, 2-dichloroethene (c-DCE), and dissolved oxygen (DO) concentration levels decreased in proportion with propane usage, with c-DCE decreasing more rapidly than TCE. The more rapid removal of c-DCE indicated biotransformation and not just physical removal by stripping. Propane utilization rates and rates of CAH removal slowed after three to four months of repeated propane additions, which coincided with tile depletion of nitrogen (as nitrate). Ammonia was then added to the propane/air mixture as a nitrogen source. After a six-month period between propane additions, rapid propane-utilization was observed. Nitrate was present due to groundwater flow into the treatment zone and/or by the oxidation of tile previously injected ammonia. In the propane-stimulated zone, c-DCE concentrations decreased below tile detection limit (1 $\mu$g/L), and TCE concentrations ranged from less than 5 $\mu$g/L to 30 $\mu$g/L, representing removals of 90 to 97%. In the air sparged control zone, TCE was removed at only two monitoring locations nearest the sparge-well, to concentrations of 15 $\mu$g/L and 60 $\mu$g/L. The responses indicate that stripping as well as biological treatment were responsible for the removal of contaminants in the biostimulated zone, with biostimulation enhancing removals to lower contaminant levels. As part of that study bacterial population shifts that occurred in the groundwater during CAS and air sparging control were evaluated by length heterogeneity polymerase chain reaction (LH-PCR) fragment analysis. The results showed that an organism(5) that had a fragment size of 385 base pairs (385 bp) was positively correlated with propane removal rates. The 385 bp fragment consisted of up to 83% of the total fragments in the analysis when propane removal rates peaked. A 16S rRNA clone library made from the bacteria sampled in propane sparged groundwater included clones of a TM7 division bacterium that had a 385bp LH-PCR fragment; no other bacterial species with this fragment size were detected. Both propane removal rates and the 385bp LH-PCR fragment decreased as nitrate levels in the groundwater decreased. In the second study the potential for bioaugmentation of a butane culture was evaluated in a series of field tests conducted at the Moffett Field Air Station in California. A butane-utilizing mixed culture that was effective in transforming 1, 1-dichloroethene (1, 1-DCE), 1, 1, 1-trichloroethane (1, 1, 1-TCA), and 1, 1-dichloroethane (1, 1-DCA) was added to the saturated zone at the test site. This mixture of contaminants was evaluated since they are often present as together as the result of 1, 1, 1-TCA contamination and the abiotic and biotic transformation of 1, 1, 1-TCA to 1, 1-DCE and 1, 1-DCA. Model simulations were performed prior to the initiation of the field study. The simulations were performed with a transport code that included processes for in-situ cometabolism, including microbial growth and decay, substrate and oxygen utilization, and the cometabolism of dual contaminants (1, 1-DCE and 1, 1, 1-TCA). Based on the results of detailed kinetic studies with the culture, cometabolic transformation kinetics were incorporated that butane mixed-inhibition on 1, 1-DCE and 1, 1, 1-TCA transformation, and competitive inhibition of 1, 1-DCE and 1, 1, 1-TCA on butane utilization. A transformation capacity term was also included in the model formation that results in cell loss due to contaminant transformation. Parameters for the model simulations were determined independently in kinetic studies with the butane-utilizing culture and through batch microcosm tests with groundwater and aquifer solids from the field test zone with the butane-utilizing culture added. In microcosm tests, the model simulated well the repetitive utilization of butane and cometabolism of 1.1, 1-TCA and 1, 1-DCE, as well as the transformation of 1, 1-DCE as it was repeatedly transformed at increased aqueous concentrations. Model simulations were then performed under the transport conditions of the field test to explore the effects of the bioaugmentation dose and the response of the system to tile biostimulation with alternating pulses of dissolved butane and oxygen in the presence of 1, 1-DCE (50 $\mu$g/L) and 1, 1, 1-TCA (250 $\mu$g/L). A uniform aquifer bioaugmentation dose of 0.5 mg/L of cells resulted in complete utilization of the butane 2-meters downgradient of the injection well within 200-hrs of bioaugmentation and butane addition. 1, 1-DCE was much more rapidly transformed than 1, 1, 1-TCA, and efficient 1, 1, 1-TCA removal occurred only after 1, 1-DCE and butane were decreased in concentration. The simulations demonstrated the strong inhibition of both 1, 1-DCE and butane on 1, 1, 1-TCA transformation, and the more rapid 1, 1-DCE transformation kinetics. Results of tile field demonstration indicated that bioaugmentation was successfully implemented; however it was difficult to maintain effective treatment for long periods of time (50 days or more). The demonstration showed that the bioaugmented experimental leg effectively transformed 1, 1-DCE and 1, 1-DCA, and was somewhat effective in transforming 1, 1, 1-TCA. The indigenous experimental leg treated in the same way as the bioaugmented leg was much less effective in treating the contaminant mixture. The best operating performance was achieved in the bioaugmented leg with about over 90%, 80%, 60 % removal for 1, 1-DCE, 1, 1-DCA, and 1, 1, 1-TCA, respectively. Molecular methods were used to track and enumerate the bioaugmented culture in the test zone. Real Time PCR analysis was used to on enumerate the bioaugmented culture. The results show higher numbers of the bioaugmented microorganisms were present in the treatment zone groundwater when the contaminants were being effective transformed. A decrease in these numbers was associated with a reduction in treatment performance. The results of the field tests indicated that although bioaugmentation can be successfully implemented, competition for the growth substrate (butane) by the indigenous microorganisms likely lead to the decrease in long-term performance.

• Asia pacific journal of information systems
• /
• v.20 no.3
• /
• pp.167-190
• /
• 2010

The research conducted here focuses on the effect of factors that affect the behavior of UCC (User Created Content) website users, other than user's rational recognition of how useful a UCC website can be. Most discussions in the existing literature on information systems have focused on users' evaluation how a UCC website can help to attain the users' own goals. However, there are other factors and this research pays attention to an individual's 'personality,' which is stable and biological in nature. Specifically, I have noted here that 'extroversion' and 'neuroticism,' the two common personality factors presented in Eysenck's most representative 'EPQ Model' and 'Big Five Model,' are the two personality factors that affect a site's 'usefulness,' by this I mean how useful does the user consider the website and its content. How useful a site is considered by the user is the other factor that has been regarded as the antecedent factor that influences the adoption of information systems in the existing MIS (Management Information System) research. Secondly, as using or creating a UCC website does not guarantee the user's or the creator's extrinsic motivation, unlike when using the information system within an organization, there is a greater likelihood that the increase in user's activities in relation to a UCC website is motivated by emotional factors rather than rational factors. Thus, I have decided to include the relationship between an individual's personality and what they find pleasurable in the research model. Thirdly, when based on the S-O-R Paradigm of Mehrabian and Russell, the two cognitive factors and emotional factors are finally affected by stimulus, and thus these factors ultimately have an effect on an individual's respondent behavior. Therefore, this research has presented an assumption that the recognition of how useful the site and content is and what emotional pleasure it provides will finally affect the behavior of the UCC website users. Finally, the relationship between the recognition of how useful a site is and how pleasurable it is to useand UCC usage may differ depending on certain situational conditions. In other words, the relationship between the three factors may vary according to how much users are involved in the creation of the website content. Creation thus emerges as the keyword of UCC. I analyzed the above relationships through the moderating variable of the user's involvement in the creation of the site. The research result shows the following: When it comes to the relationship between an individual's personality and what they find pleasurable it is extroverted users who have a greater likelihood to feel pleasure when using a UCC website, as was expected in this research. This in turn leads to a more active usage of the UCC web site because a person who is an extrovert likes to spend time on activities with other people, is sensitive to new experiences and stimuli and thus actively responds to these. An extroverted person accepts new UCC activities as part of his/her social life, rather than getting away from this new UCC environment. This is represented by the term 'Foxonomy' where the users meet a variety of users from all over the world and contact new types of content created by these users. However, neuroticism creates the opposite situation to that created by extroversion. The representative symptoms of neuroticism are instability, stress, and tension. These dispositions are more closely related to stress caused by a new environment rather than this creatingcuriosity or pleasure. Thus, neurotic persons have an uneasy feeling and will eventually avoid the situation where their own or others' daily lives are frequently exposed to the open web environment, this eventually makes them have a negative attitude towards the web environment. When it comes to an individual's personality and how useful site is, the two personality factors of extroversion and neuroticism both have a positive relationship with the recognition of how useful the site and its content is. The positive, curious, and social dispositions of extroverted persons tend to make them consider the future usefulness and possibilities of a new type of information system, or website, based on their positive attitude, which has a significant influence on the recognition of how useful these UCC sites are. Neuroticism also favorably affects how useful a UCC website can be through a different mechanism from that of extroversion. As the neurotic persons tend to feel uneasy and have much doubt about a new type of information system, they actively explore its usefulness in order to relieve their uncomfortable feelings. In other words, neurotic persons seek out how useful a site can be in order to secure their own stable feelings. Meanwhile, extroverted persons explore how useful a site can be because of their positive attitude and curiosity. As a lot of MIS research has revealed that the recognition of how useful a site can be and how pleasurable it can be to use have been proven to have a significant effect on UCC activity. However, the relationship between these factors reveals different aspects based on the user's involvement in creation. This factor of creationgauges the interest of users in the creation of UCC contents. Involvement is a variable that shows the level of an individual's mental effort in creating UCC contents. When a user is highly involved in the creation process and makes an enormous effort to create UCC content (classed a part of a high-involvement group), their own pleasure and recognition of how useful the site is have a significantly higher effect on the future usage of the UCC contents, more significantly than the users who sit back and just retrieve the UCC content created by others. The cognitive and emotional response of those in the low-involvement group is unlikely to last long,even if they recognize the contents of a UCC website is pleasurable and useful to them. However, the high-involvement group tends to participate in the creation and the usage of UCC more favorably, connecting the experience with their own goals. In this respect, this research presents an answer to the question; why so many people are participating in the usage of UCC, the representative form of the Web 2.0 that has drastically involved more and more people in the creation of UCC, even if they cannot gain any monetary or social compensation. Neither information system nor a website can succeed unless it secures a certain level of user base. Moreover, it cannot be further developed when the reasons, or problems, for people's participation are not suitably explored, even if it has a certain user base. Thus, what is significant in this research is that it has studied users' respondent behavior based on an individual's innate personality, emotion, and cognitive interaction, unlike the existing research that has focused on 'compensation' to explain users' participation with the UCC website. There are also limitations in this research. Firstly, I divided an individual's personality into extroversion and neuroticism; however, there are many other personal factors such as neuro-psychiatricism, which also needs to be analyzed for its influence on UCC activities. Secondly, as a UCC website comes in many types such as multimedia, Wikis, and podcasting, these types need to be included as a sub-category of the UCC websites and their relationship with personality, emotion, cognition, and behavior also needs to be analyzed.

• 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.19 no.3
• /
• pp.25-44
• /
• 2013

Accessing movie contents has become easier and increased with the advent of smart TV, IPTV and web services that are able to be used to search and watch movies. In this situation, there are increasing search for preference movie contents of users. However, since the amount of provided movie contents is too large, the user needs more effort and time for searching the movie contents. Hence, there are a lot of researches for recommendations of personalized item through analysis and clustering of the user preferences and user profiles. In this study, we propose recommendation system which uses ontology based knowledge base. Our ontology can represent not only relations between metadata of movies but also relations between metadata and profile of user. The relation of each metadata can show similarity between movies. In order to build, the knowledge base our ontology model is considered two aspects which are the movie metadata model and the user model. On the part of build the movie metadata model based on ontology, we decide main metadata that are genre, actor/actress, keywords and synopsis. Those affect that users choose the interested movie. And there are demographic information of user and relation between user and movie metadata in user model. In our model, movie ontology model consists of seven concepts (Movie, Genre, Keywords, Synopsis Keywords, Character, and Person), eight attributes (title, rating, limit, description, character name, character description, person job, person name) and ten relations between concepts. For our knowledge base, we input individual data of 14,374 movies for each concept in contents ontology model. This movie metadata knowledge base is used to search the movie that is related to interesting metadata of user. And it can search the similar movie through relations between concepts. We also propose the architecture for movie recommendation. The proposed architecture consists of four components. The first component search candidate movies based the demographic information of the user. In this component, we decide the group of users according to demographic information to recommend the movie for each group and define the rule to decide the group of users. We generate the query that be used to search the candidate movie for recommendation in this component. The second component search candidate movies based user preference. When users choose the movie, users consider metadata such as genre, actor/actress, synopsis, keywords. Users input their preference and then in this component, system search the movie based on users preferences. The proposed system can search the similar movie through relation between concepts, unlike existing movie recommendation systems. Each metadata of recommended candidate movies have weight that will be used for deciding recommendation order. The third component the merges results of first component and second component. In this step, we calculate the weight of movies using the weight value of metadata for each movie. Then we sort movies order by the weight value. The fourth component analyzes result of third component, and then it decides level of the contribution of metadata. And we apply contribution weight to metadata. Finally, we use the result of this step as recommendation for users. We test the usability of the proposed scheme by using web application. We implement that web application for experimental process by using JSP, Java Script and prot$\acute{e}$g$\acute{e}$ API. In our experiment, we collect results of 20 men and woman, ranging in age from 20 to 29. And we use 7,418 movies with rating that is not fewer than 7.0. In order to experiment, we provide Top-5, Top-10 and Top-20 recommended movies to user, and then users choose interested movies. The result of experiment is that average number of to choose interested movie are 2.1 in Top-5, 3.35 in Top-10, 6.35 in Top-20. It is better than results that are yielded by for each metadata.

• 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.