• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.109-122
• /
• 2014

People are nowadays creating a tremendous amount of data on Social Network Service (SNS). In particular, the incorporation of SNS into mobile devices has resulted in massive amounts of data generation, thereby greatly influencing society. This is an unmatched phenomenon in history, and now we live in the Age of Big Data. SNS Data is defined as a condition of Big Data where the amount of data (volume), data input and output speeds (velocity), and the variety of data types (variety) are satisfied. If someone intends to discover the trend of an issue in SNS Big Data, this information can be used as a new important source for the creation of new values because this information covers the whole of society. In this study, a Twitter Issue Tracking System (TITS) is designed and established to meet the needs of analyzing SNS Big Data. TITS extracts issues from Twitter texts and visualizes them on the web. The proposed system provides the following four functions: (1) Provide the topic keyword set that corresponds to daily ranking; (2) Visualize the daily time series graph of a topic for the duration of a month; (3) Provide the importance of a topic through a treemap based on the score system and frequency; (4) Visualize the daily time-series graph of keywords by searching the keyword; The present study analyzes the Big Data generated by SNS in real time. SNS Big Data analysis requires various natural language processing techniques, including the removal of stop words, and noun extraction for processing various unrefined forms of unstructured data. In addition, such analysis requires the latest big data technology to process rapidly a large amount of real-time data, such as the Hadoop distributed system or NoSQL, which is an alternative to relational database. We built TITS based on Hadoop to optimize the processing of big data because Hadoop is designed to scale up from single node computing to thousands of machines. Furthermore, we use MongoDB, which is classified as a NoSQL database. In addition, MongoDB is an open source platform, document-oriented database that provides high performance, high availability, and automatic scaling. Unlike existing relational database, there are no schema or tables with MongoDB, and its most important goal is that of data accessibility and data processing performance. In the Age of Big Data, the visualization of Big Data is more attractive to the Big Data community because it helps analysts to examine such data easily and clearly. Therefore, TITS uses the d3.js library as a visualization tool. This library is designed for the purpose of creating Data Driven Documents that bind document object model (DOM) and any data; the interaction between data is easy and useful for managing real-time data stream with smooth animation. In addition, TITS uses a bootstrap made of pre-configured plug-in style sheets and JavaScript libraries to build a web system. The TITS Graphical User Interface (GUI) is designed using these libraries, and it is capable of detecting issues on Twitter in an easy and intuitive manner. The proposed work demonstrates the superiority of our issue detection techniques by matching detected issues with corresponding online news articles. The contributions of the present study are threefold. First, we suggest an alternative approach to real-time big data analysis, which has become an extremely important issue. Second, we apply a topic modeling technique that is used in various research areas, including Library and Information Science (LIS). Based on this, we can confirm the utility of storytelling and time series analysis. Third, we develop a web-based system, and make the system available for the real-time discovery of topics. The present study conducted experiments with nearly 150 million tweets in Korea during March 2013.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.95-112
• /
• 2021

In university education, the choice of major class plays an important role in students' careers. However, in line with the changes in the industry, the fields of major subjects by department are diversifying and increasing in number in university education. As a result, students have difficulty to choose and take classes according to their career paths. In general, students choose classes based on experiences such as choices of peers or advice from seniors. This has the advantage of being able to take into account the general situation, but it does not reflect individual tendencies and considerations of existing courses, and has a problem that leads to information inequality that is shared only among specific students. In addition, as non-face-to-face classes have recently been conducted and exchanges between students have decreased, even experience-based decisions have not been made as well. Therefore, this study proposes a recommendation system model that can recommend college major classes suitable for individual characteristics based on data rather than experience. The recommendation system recommends information and content (music, movies, books, images, etc.) that a specific user may be interested in. It is already widely used in services where it is important to consider individual tendencies such as YouTube and Facebook, and you can experience it familiarly in providing personalized services in content services such as over-the-top media services (OTT). Classes are also a kind of content consumption in terms of selecting classes suitable for individuals from a set content list. However, unlike other content consumption, it is characterized by a large influence of selection results. For example, in the case of music and movies, it is usually consumed once and the time required to consume content is short. Therefore, the importance of each item is relatively low, and there is no deep concern in selecting. Major classes usually have a long consumption time because they have to be taken for one semester, and each item has a high importance and requires greater caution in choice because it affects many things such as career and graduation requirements depending on the composition of the selected classes. Depending on the unique characteristics of these major classes, the recommendation system in the education field supports decision-making that reflects individual characteristics that are meaningful and cannot be reflected in experience-based decision-making, even though it has a relatively small number of item ranges. This study aims to realize personalized education and enhance students' educational satisfaction by presenting a recommendation model for university major class. In the model study, class history data of undergraduate students at University from 2015 to 2017 were used, and students and their major names were used as metadata. The class history data is implicit feedback data that only indicates whether content is consumed, not reflecting preferences for classes. Therefore, when we derive embedding vectors that characterize students and classes, their expressive power is low. With these issues in mind, this study proposes a Net-NeuMF model that generates vectors of students, classes through network analysis and utilizes them as input values of the model. The model was based on the structure of NeuMF using one-hot vectors, a representative model using data with implicit feedback. The input vectors of the model are generated to represent the characteristic of students and classes through network analysis. To generate a vector representing a student, each student is set to a node and the edge is designed to connect with a weight if the two students take the same class. Similarly, to generate a vector representing the class, each class was set as a node, and the edge connected if any students had taken the classes in common. Thus, we utilize Node2Vec, a representation learning methodology that quantifies the characteristics of each node. For the evaluation of the model, we used four indicators that are mainly utilized by recommendation systems, and experiments were conducted on three different dimensions to analyze the impact of embedding dimensions on the model. The results show better performance on evaluation metrics regardless of dimension than when using one-hot vectors in existing NeuMF structures. Thus, this work contributes to a network of students (users) and classes (items) to increase expressiveness over existing one-hot embeddings, to match the characteristics of each structure that constitutes the model, and to show better performance on various kinds of evaluation metrics compared to existing methodologies.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.149-171
• /
• 2020

The period at university is to make decision about getting an actual job. As our society develops rapidly and highly, jobs are diversified, subdivided, and specialized, and students' job preparation period is also getting longer and longer. This study analyzed the log data of college students to see how the various activities that college students experience inside and outside of school might have influences on employment. For this experiment, students' various activities were systematically classified, recorded as an activity data and were divided into six core competencies (Job reinforcement competency, Leadership & teamwork competency, Globalization competency, Organizational commitment competency, Job exploration competency, and Autonomous implementation competency). The effect of the six competency levels on the employment status (employed group, unemployed group) was analyzed. As a result of the analysis, it was confirmed that the difference in level between the employed group and the unemployed group was significant for all of the six competencies, so it was possible to infer that the activities at the school are significant for employment. Next, in order to analyze the impact of the six competencies on the qualitative performance of employment, we had ANOVA analysis after dividing the each competency level into 2 groups (low and high group), and creating 6 groups by the range of first annual salary. Students with high levels of globalization capability, job search capability, and autonomous implementation capability were also found to belong to a higher annual salary group. The theoretical contributions of this study are as follows. First, it connects the competencies that can be extracted from the school experience with the competencies in the Human Resource Management field and adds job search competencies and autonomous implementation competencies which are required for university students to have their own successful career & life. Second, we have conducted this analysis with the competency data measured form actual activity and result data collected from the interview and research. Third, it analyzed not only quantitative performance (employment rate) but also qualitative performance (annual salary level). The practical use of this study is as follows. First, it can be a guide when establishing career development plans for college students. It is necessary to prepare for a job that can express one's strengths based on an analysis of the world of work and job, rather than having a no-strategy, unbalanced, or accumulating excessive specifications competition. Second, the person in charge of experience design for college students, at an organizations such as schools, businesses, local governments, and governments, can refer to the six competencies suggested in this study to for the user-useful experiences design that may motivate more participation. By doing so, one event may bring mutual benefits for both event designers and students. Third, in the era of digital transformation, the government's policy manager who envisions the balanced development of the country can make a policy in the direction of achieving the curiosity and energy of college students together with the balanced development of the country. A lot of manpower is required to start up novel platform services that have not existed before or to digitize existing analog products, services and corporate culture. The activities of current digital-generation-college-students are not only catalysts in all industries, but also for very benefit and necessary for college students by themselves for their own successful career development.

• Journal of Distribution Research
• /
• v.15 no.3
• /
• pp.111-137
• /
• 2010

The basic purpose of this study is to investigate perceived quality and service personal value affecting the result of long-term relationship between service buyers and suppliers. This research presented a constructive model(perceived quality affecting the service personal value and the moderate effect of NFC) in the on off line and then propose the research model base on prior researches and studies about relationships among components of service. Data were gathered from respondents who visit at the education service market. For this study, Data were analyzed by AMOS 7.0. We integrate the literature on services marketing with researches on personal values and perceived quality. The SERPVAL scale presented here allows for the creation of a common ground for assessing service personal values, giving a clear understanding of the key value dimensions behind service choice and usage. It will lead to a focus of future research in services marketing, extending knowledge in the field and stimulating further empirical research on service personal values. At the managerial level, as a tool the SERPVAL scale should allow practitioners to evaluate and improve the value of a service, and consequently, to define strategies and actions to address services for customers based on their fundamental personal values. Through qualitative and empirical research, we find that the service quality construct conforms to the structure of a second-order factor model that ties service quality perceptions to distinct and actionable dimensions: outcome, interaction, and environmental quality. In turn, each has two subdimensions that define the basis of service quality perceptions. The authors further suggest that for each of these subdimensions to contribute to improved service quality perceptions, the quality received by consumers must be perceived to be reliable, responsive, and empathetic. Although the service personal value may be found in researches that explore individual values and their consequences for consumer behavior, there is no established operationalization of a SERPVAL scale. The inexistence of an established scale, duly adapted in order to understand and analyze personal values behind services usage, exposes the need of a measurement scale with such a purpose. This need has to be rooted, however, in a conceptualization of the construct being scaled. Service personal values can be defined as a customer's overall assessment of the use of a service based on the perception of what is achieved in terms of his own personal values. As consumer behaviors serve to show an individual's values, the use of a service can also be a way to fulfill and demonstrate consumers'personal values. In this sense, a service can provide more to the customer than its concrete and abstract attributes at both the attribute and the quality levels, and more than its functional consequences at the value level. Both values and services literatures agree, that personal value is the highest-level concept, followed by instrumental values, attitudes and finally by product attributes. Purchasing behaviors are agreed to be the end result of these concepts' interaction, with personal values taking a major role in the final decision process. From both consumers' and practitioners' perspectives, values are extremely relevant, as they are desirable goals that serve as guiding principles in people's lives. While building on previous research, we propose to assess service personal values through three broad groups of individual dimensions; at the self-oriented level, we use (1) service value to peaceful life (SVPL) and, at the social-oriented level, we use (2) service value to social recognition (SVSR), and (3) service value to social integration (SVSI). Service value to peaceful life is our first dimension. This dimension emerged as a combination of values coming from the RVS scale, a scale built specifically to assess general individual values. If a service promotes a pleasurable life, brings or improves tranquility, safety and harmony, then its user recognizes the value of this service. Generally, this service can improve the user's pleasure of life, since it protects or defends the consumer from threats to life or pressures on it. While building upon both the LOV scale, a scale built specifically to assess consumer values, and the RVS scale for individual values, we develop the other two dimensions: SVSR and SVSI. The roles of social recognition and social integration to improve service personal value have been seriously neglected. Social recognition derives its outcome utility from its predictive utility. When applying this underlying belief to our second dimension, SVSR, we assume that people use a service while taking into consideration the content of what is delivered. Individuals consider whether the service aids in gaining respect from others, social recognition and status, as well as whether it allows achieving a more fulfilled and stimulating life, which might then be revealed to others. People also tend to engage in behavior that receives social recognition and to avoid behavior that leads to social disapproval, and this contributes to an individual's social integration. This leads us to the third dimension, SVSI, which is based on the fact that if the consumer perceives that a service strengthens friendships, provides the possibility of becoming more integrated in the group, or promotes better relationships at the social, professional or family levels, then the service will contribute to social integration, and naturally the individual will recognize personal value in the service. Most of the research in business values deals with individual values. However, to our knowledge, no study has dealt with assessing overall personal values as well as their dimensions in a service context. Our final results show that the scales adapted from the Schwartz list were excluded. A possible explanation is that although Schwartz builds on Rokeach work in order to explore individual values, its dimensions might be especially focused on analyzing societal values. As we are looking for individual dimensions, this might explain why the values inspired by the Schwartz list were excluded from the model. The hierarchical structure of the final scale presented in this paper also presents theoretical implications. Although we cannot claim to definitively capture the dimensions of service personal values, we believe that we come close to capturing these overall evaluations because the second-order factor extracts the underlying commonality among dimensions. In addition to obtaining respondents' evaluations of the dimensions, the second-order factor model captures the common variance among these dimensions, reflecting the respondents' overall assessment of service personal values. Towards this fact, we expect that the service personal values conceptualization and measurement scale presented here contributes to both business values literature and the service marketing field, allowing for the delineation of strategies for adding value to services. This new scale also presents managerial implications. The SERPVAL dimensions give some guidance on how to better pursue a highly service-oriented business strategy. Indeed, the SERPVAL scale can be used for benchmarking purposes, as this scale can be used to identify whether or not a firms' marketing strategies are consistent with consumers' expectations. Managerial assessment of the personal values of a service might be extremely important because it allows managers to better understand what customers want or value. Thus, this scale allows us to identify what services are really valuable to the final consumer; providing knowledge for making choices regarding which services to include. Traditional approaches have focused their attention on service attributes (as quality) and service consequences(as service value), but personal values may be an important set of variables to be considered in understanding what attracts consumers to a certain service. By using the SERPVAL scale to assess the personal values associated with a services usage, managers may better understand the reasons behind services' usage, so that they may handle them more efficiently. While testing nomological validity, our empirical findings demonstrate that the three SERPVAL dimensions are positively and significantly associated with satisfaction. Additionally, while service value to social integration is related only with loyalty, service value to peaceful life is associated with both loyalty and repurchase intent. It is also interesting and surprising that service value to social recognition appears not to be significantly linked with loyalty and repurchase intent. A possible explanation is that no mobile service provider has yet emerged in the market as a luxury provider. All of the Portuguese providers are still trying to capture market share by means of low-end pricing. This research has implications for consumers as well. As more companies seek to build relationships with their customers, consumers are easily able to examine whether these relationships provide real value or not to their own lives. The selection of a strategy for a particular service depends on its customers' personal values. Being highly customer-oriented means having a strong commitment to customers, trying to create customer value and understanding customer needs. Enhancing service distinctiveness in order to provide a peaceful life, increase social recognition and gain a better social integration are all possible strategies that companies may pursue, but the one to pursue depends on the outstanding personal values held by the service customers. Data were gathered from 284 respondents in the korean discount store and online shopping mall market. This research proposed 3 hypotheses on 6 latent variables and tested through structural equation modeling. 6 alternative measurements were compared through statistical significance test of the 6 paths of research model and the overall fitting level of structural equation model. and the result was successful. and Perceived quality more positively influences service personal value when NFC is high than when no NFC is low in the off-line market. The results of the study indicate that service quality is properly modeled as an antecedent of service personal value. We consider the research and managerial implications of the study and its limitations. In sum, by knowing the dimensions a consumer takes into account when choosing a service, a better understanding of purchasing behaviors may be realized, guiding managers toward customers expectations. By defining strategies and actions that address potential problems with the service personal values, managers might ultimately influence their firm's performance. we expect to contribute to both business values and service marketing literatures through the development of the service personal value. At a time when marketing researchers are challenged to provide research with practical implications, it is also believed that this framework may be used by managers to pursue service-oriented business strategies while taking into consideration what customers value.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.127-148
• /
• 2020

The data center is a physical environment facility for accommodating computer systems and related components, and is an essential foundation technology for next-generation core industries such as big data, smart factories, wearables, and smart homes. In particular, with the growth of cloud computing, the proportional expansion of the data center infrastructure is inevitable. Monitoring the health of these data center facilities is a way to maintain and manage the system and prevent failure. If a failure occurs in some elements of the facility, it may affect not only the relevant equipment but also other connected equipment, and may cause enormous damage. In particular, IT facilities are irregular due to interdependence and it is difficult to know the cause. In the previous study predicting failure in data center, failure was predicted by looking at a single server as a single state without assuming that the devices were mixed. Therefore, in this study, data center failures were classified into failures occurring inside the server (Outage A) and failures occurring outside the server (Outage B), and focused on analyzing complex failures occurring within the server. Server external failures include power, cooling, user errors, etc. Since such failures can be prevented in the early stages of data center facility construction, various solutions are being developed. On the other hand, the cause of the failure occurring in the server is difficult to determine, and adequate prevention has not yet been achieved. In particular, this is the reason why server failures do not occur singularly, cause other server failures, or receive something that causes failures from other servers. In other words, while the existing studies assumed that it was a single server that did not affect the servers and analyzed the failure, in this study, the failure occurred on the assumption that it had an effect between servers. In order to define the complex failure situation in the data center, failure history data for each equipment existing in the data center was used. There are four major failures considered in this study: Network Node Down, Server Down, Windows Activation Services Down, and Database Management System Service Down. The failures that occur for each device are sorted in chronological order, and when a failure occurs in a specific equipment, if a failure occurs in a specific equipment within 5 minutes from the time of occurrence, it is defined that the failure occurs simultaneously. After configuring the sequence for the devices that have failed at the same time, 5 devices that frequently occur simultaneously within the configured sequence were selected, and the case where the selected devices failed at the same time was confirmed through visualization. Since the server resource information collected for failure analysis is in units of time series and has flow, we used Long Short-term Memory (LSTM), a deep learning algorithm that can predict the next state through the previous state. In addition, unlike a single server, the Hierarchical Attention Network deep learning model structure was used in consideration of the fact that the level of multiple failures for each server is different. This algorithm is a method of increasing the prediction accuracy by giving weight to the server as the impact on the failure increases. The study began with defining the type of failure and selecting the analysis target. In the first experiment, the same collected data was assumed as a single server state and a multiple server state, and compared and analyzed. The second experiment improved the prediction accuracy in the case of a complex server by optimizing each server threshold. In the first experiment, which assumed each of a single server and multiple servers, in the case of a single server, it was predicted that three of the five servers did not have a failure even though the actual failure occurred. However, assuming multiple servers, all five servers were predicted to have failed. As a result of the experiment, the hypothesis that there is an effect between servers is proven. As a result of this study, it was confirmed that the prediction performance was superior when the multiple servers were assumed than when the single server was assumed. In particular, applying the Hierarchical Attention Network algorithm, assuming that the effects of each server will be different, played a role in improving the analysis effect. In addition, by applying a different threshold for each server, the prediction accuracy could be improved. This study showed that failures that are difficult to determine the cause can be predicted through historical data, and a model that can predict failures occurring in servers in data centers is presented. It is expected that the occurrence of disability can be prevented in advance using the results of this study.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.8
• /
• pp.19-31
• /
• 2021

This study tried to identify the characteristics of college students' entrepreneurial intentions in the entertainment industry, focusing on existing literature studies. Based on this, it was intended to suggest realistic educational alternatives for university student start-ups and implications for start-up management to university start-up officials and those in charge of national start-up support policy. Therefore, the implications of this study are as follows. First, technology(item) for idea creation education, which is an essential element in the entertainment industry, how to connect ideas and products, technology methods that can increase content value, and user characteristics education within the entertainment industry will need to be continued. In addition, along with the idea education, it is necessary to increase the understanding of start-up business management such as financing, human resource management, marketing, and operation management, and furthermore, confidence education should be provided so that the possibility of success in an entertainment start-up and a sense of adventure in a new job can be developed. Second, the space and equipment necessary for start-up (club room, student start-up room, entertainment-related equipment, etc.) should be provided centering on the opinion survey of students who are interested in starting a business, and various regulations of universities and government for student start-up should be relaxed. will have to In addition, education for the formation of entrepreneurial knowledge inside and outside of the school, special lectures and consultations by experts, and on-the-spot education, etc., should be made to create more practical entrepreneurial knowledge. something to do. Third, for students wishing to start a business in the entertainment industry, it is necessary to inform their families about the field situation of the entertainment industry accurately so that their children can develop a positive perception rather than a negative perception when choosing a business field. In addition, by promoting various successful cases of college students to their families after starting a business, families should be encouraged so that their children can develop a challenging spirit about starting a business. Fourth, it should be possible to form continuous clubs or gatherings with friends who wish to start a business in the entertainment industry, and furthermore, an opportunity to listen to the opinions of friends who actually started a business through these meetings should be provided. In addition, the meeting and the formation of friends should create a place for discussion about writing a business plan, how to succeed in starting a business, and management of startups, and psychological stimulation activities should be conducted so that each other's will to start a business arises. Fifth, various knowledge related to start-up (methods for securing funds, management of start-up organizations, grasping information about the market in which they want to start a business, etc.) should be cultivated, and how to write a business plan for the various entertainment industry fields they want to start up. You will also need to train them to be practical. Also, based on this knowledge formation, students themselves should be able to respond to risks and changes that may occur in entrepreneurship. Lastly, it is necessary to increase the understanding of business start-up management, and various psychological stimulation activities are needed to make the confidence and fear of starting a business disappear.

• Cartoon and Animation Studies
• /
• s.33
• /
• pp.153-172
• /
• 2013

There are many cases that messages of boring contents of most contents with public interests appear on the surface. Audiences don't think these contents are interesting. It is true that animations cannot be generally boring when delivering messages of public interests. was produced to focus on making audiences experience that a global warming story, the boring and textbook contents is interesting. And it was composed by the multiform story to realize narration through audiences' participation by utilizing the characteristics of live windows, not just watching the animation. This paper examines the differences between theaters and live window through the case that was produced and examples which utilized interaction for audiences' participation based on this. It analyzes the differences between environments according to characteristics of places and audiences in the differences between the theaters and live window, examines the examples to utilize interaction focusing on the process that narration is gradually changed as response to user environment design and interaction for unspecified individuals, and suggests direction that animation should move forward as public art based on the results to show the animation in Millano Piazza. According to the characteristics of live windows, the audiences of are people in the streets who are heading for different destinations, not the ones who come to theaters to watch the animation. Showing the animation with narration to them was a new attempt. When it began to show it in Millano Piazza, the audiences were very satisfied with the experiences that the stories were changed as they participated in it by themselves and naturally thought of global warming problems. You cannot know how the message of change people's habits and thoughts for the present, but this attempt was an opportunity that animations play the social role. Many animations are being produced in the world. Most of them are being done to aim at theaters, TVs, and film festivals. They should meet audiences through more various methods. One of them is animations as public art. And can be the new attempt in this sense. And in the future, animations as public art should make efforts to show you interesting experiences that you can share thoughts to be able to live together. As art of various media is changing to the one which considers public interests, animations can be new types of public art by integrating them with various technologies.

• Korean Journal of Environment and Ecology
• /
• v.28 no.1
• /
• pp.90-98
• /
• 2014

This study was carried out to provide basic data. his research conducted the survey using face to face survey and board survey during about 2 months from Oct. to Nov. in 2009 for users of Bongje Mt., a small-sized mountain at downtown, and Acha Mt., a big-sized mountain at outskirt so as to compare the differences of using behavior by forms and size of urban forest in living area of Seoul. Characteristics of urban forest users, using behavior, demands and satisfaction of facilities and management and pass pattern were set as research items. The thing in common for using behavior is that both genders of main users were in more than 40s~60s. They showed the highest using rate from 7 a.m. to 12 p.m. and high rate for using nearly everyday or visiting two or three times per a week. In addition, it's judged that the accessibility from dwelling area to entrance of urban forest in living area is good and satisfaction for the standard of facilities and their management in forest way was relatively low. For the complement and essential facilities, 'sanitary facilities' showed the highest rate. For the differences of using behavior, most of Bongje Mt. users were residents living within a 2km radius (under the standard of walking) and they moved by average 1.3km. And, they preferred short-time activities of about 24 minutes. On the other hand, main users of Acha Mt. were residents living within a 4km radius (under the standard of walking) and people of other regions. and 60% of them preferred the passage route taking 3hours half over 6km. Through the survey on using behavior of urban forest in living area of Seoul, with different using form and forest size, introduction of using program for main users or managing method of differentiations for introduced facility's management should be properly applied. Especially, urban forest should be systematically managed like park green as expected that residents's using of urban forest will be increased with the increase of leisure time.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.1-17
• /
• 2017

The deep learning framework is software designed to help develop deep learning models. Some of its important functions include "automatic differentiation" and "utilization of GPU". The list of popular deep learning framework includes Caffe (BVLC) and Theano (University of Montreal). And recently, Microsoft's deep learning framework, Microsoft Cognitive Toolkit, was released as open-source license, following Google's Tensorflow a year earlier. The early deep learning frameworks have been developed mainly for research at universities. Beginning with the inception of Tensorflow, however, it seems that companies such as Microsoft and Facebook have started to join the competition of framework development. Given the trend, Google and other companies are expected to continue investing in the deep learning framework to bring forward the initiative in the artificial intelligence business. From this point of view, we think it is a good time to compare some of deep learning frameworks. So we compare three deep learning frameworks which can be used as a Python library. Those are Google's Tensorflow, Microsoft's CNTK, and Theano which is sort of a predecessor of the preceding two. The most common and important function of deep learning frameworks is the ability to perform automatic differentiation. Basically all the mathematical expressions of deep learning models can be represented as computational graphs, which consist of nodes and edges. Partial derivatives on each edge of a computational graph can then be obtained. With the partial derivatives, we can let software compute differentiation of any node with respect to any variable by utilizing chain rule of Calculus. First of all, the convenience of coding is in the order of CNTK, Tensorflow, and Theano. The criterion is simply based on the lengths of the codes and the learning curve and the ease of coding are not the main concern. According to the criteria, Theano was the most difficult to implement with, and CNTK and Tensorflow were somewhat easier. With Tensorflow, we need to define weight variables and biases explicitly. The reason that CNTK and Tensorflow are easier to implement with is that those frameworks provide us with more abstraction than Theano. We, however, need to mention that low-level coding is not always bad. It gives us flexibility of coding. With the low-level coding such as in Theano, we can implement and test any new deep learning models or any new search methods that we can think of. The assessment of the execution speed of each framework is that there is not meaningful difference. According to the experiment, execution speeds of Theano and Tensorflow are very similar, although the experiment was limited to a CNN model. In the case of CNTK, the experimental environment was not maintained as the same. The code written in CNTK has to be run in PC environment without GPU where codes execute as much as 50 times slower than with GPU. But we concluded that the difference of execution speed was within the range of variation caused by the different hardware setup. In this study, we compared three types of deep learning framework: Theano, Tensorflow, and CNTK. According to Wikipedia, there are 12 available deep learning frameworks. And 15 different attributes differentiate each framework. Some of the important attributes would include interface language (Python, C ++, Java, etc.) and the availability of libraries on various deep learning models such as CNN, RNN, DBN, and etc. And if a user implements a large scale deep learning model, it will also be important to support multiple GPU or multiple servers. Also, if you are learning the deep learning model, it would also be important if there are enough examples and references.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.19-29
• /
• 2006

As the security of personal information is becoming more important in mobile phones, we are starting to apply iris recognition technology to these devices. In conventional iris recognition, magnified iris images are required. For that, it has been necessary to use large magnified zoom & focus lens camera to capture images, but due to the requirement about low size and cost of mobile phones, the zoom & focus lens are difficult to be used. However, with rapid developments and multimedia convergence trends in mobile phones, more and more companies have built mega-pixel cameras into their mobile phones. These devices make it possible to capture a magnified iris image without zoom & focus lens. Although facial images are captured far away from the user using a mega-pixel camera, the captured iris region possesses sufficient pixel information for iris recognition. However, in this case, the eye region should be detected for accurate iris recognition in facial images. So, we propose a new fast iris detection method, which is appropriate for mobile phones based on corneal specular reflection. To detect specular reflection robustly, we propose the theoretical background of estimating the size and brightness of specular reflection based on eye, camera and illuminator models. In addition, we use the successive On/Off scheme of the illuminator to detect the optical/motion blurring and sunlight effect on input image. Experimental results show that total processing time(detecting iris region) is on average 65ms on a Samsung SCH-S2300 (with 150MHz ARM 9 CPU) mobile phone. The rate of correct iris detection is 99% (about indoor images) and 98.5% (about outdoor images).