• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.27-65
• /
• 2020

Many companies on information and communication technology make public their own developed AI technology, for example, Google's TensorFlow, Facebook's PyTorch, Microsoft's CNTK. By releasing deep learning open source software to the public, the relationship with the developer community and the artificial intelligence (AI) ecosystem can be strengthened, and users can perform experiment, implementation and improvement of it. Accordingly, the field of machine learning is growing rapidly, and developers are using and reproducing various learning algorithms in each field. Although various analysis of open source software has been made, there is a lack of studies to help develop or use deep learning open source software in the industry. This study thus attempts to derive a strategy for adopting the framework through case studies of a deep learning open source framework. Based on the technology-organization-environment (TOE) framework and literature review related to the adoption of open source software, we employed the case study framework that includes technological factors as perceived relative advantage, perceived compatibility, perceived complexity, and perceived trialability, organizational factors as management support and knowledge & expertise, and environmental factors as availability of technology skills and services, and platform long term viability. We conducted a case study analysis of three companies' adoption cases (two cases of success and one case of failure) and revealed that seven out of eight TOE factors and several factors regarding company, team and resource are significant for the adoption of deep learning open source framework. By organizing the case study analysis results, we provided five important success factors for adopting deep learning framework: the knowledge and expertise of developers in the team, hardware (GPU) environment, data enterprise cooperation system, deep learning framework platform, deep learning framework work tool service. In order for an organization to successfully adopt a deep learning open source framework, at the stage of using the framework, first, the hardware (GPU) environment for AI R&D group must support the knowledge and expertise of the developers in the team. Second, it is necessary to support the use of deep learning frameworks by research developers through collecting and managing data inside and outside the company with a data enterprise cooperation system. Third, deep learning research expertise must be supplemented through cooperation with researchers from academic institutions such as universities and research institutes. Satisfying three procedures in the stage of using the deep learning framework, companies will increase the number of deep learning research developers, the ability to use the deep learning framework, and the support of GPU resource. In the proliferation stage of the deep learning framework, fourth, a company makes the deep learning framework platform that improves the research efficiency and effectiveness of the developers, for example, the optimization of the hardware (GPU) environment automatically. Fifth, the deep learning framework tool service team complements the developers' expertise through sharing the information of the external deep learning open source framework community to the in-house community and activating developer retraining and seminars. To implement the identified five success factors, a step-by-step enterprise procedure for adoption of the deep learning framework was proposed: defining the project problem, confirming whether the deep learning methodology is the right method, confirming whether the deep learning framework is the right tool, using the deep learning framework by the enterprise, spreading the framework of the enterprise. The first three steps (i.e. defining the project problem, confirming whether the deep learning methodology is the right method, and confirming whether the deep learning framework is the right tool) are pre-considerations to adopt a deep learning open source framework. After the three pre-considerations steps are clear, next two steps (i.e. using the deep learning framework by the enterprise and spreading the framework of the enterprise) can be processed. In the fourth step, the knowledge and expertise of developers in the team are important in addition to hardware (GPU) environment and data enterprise cooperation system. In final step, five important factors are realized for a successful adoption of the deep learning open source framework. This study provides strategic implications for companies adopting or using deep learning framework according to the needs of each industry and business.

• Journal of Digital Convergence
• /
• v.19 no.8
• /
• pp.319-325
• /
• 2021

With the advancement of wireless technology and the rapid growth of the infrastructure of mobile communication technology, systems applying AI-based platforms are drawing attention from users. In particular, the system that understands users' tastes and interests and recommends preferred items is applied to advanced e-commerce customized services and smart homes. However, there is a problem that these recommendation systems are difficult to reflect in real time the preferences of various users for tastes and interests. In this research, we propose a Fuzzy-AHP-based movies recommendation system using the Gated Recurrent Unit (GRU) language model to address a problem. In this system, we apply Fuzzy-AHP to reflect users' tastes or interests in real time. We also apply GRU language model-based models to analyze the public interest and the content of the film to recommend movies similar to the user's preferred factors. To validate the performance of this recommendation system, we measured the suitability of the learning model using scraping data used in the learning module, and measured the rate of learning performance by comparing the Long Short-Term Memory (LSTM) language model with the learning time per epoch. The results show that the average cross-validation index of the learning model in this work is suitable at 94.8% and that the learning performance rate outperforms the LSTM language model.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.1
• /
• pp.13-24
• /
• 2021

Tunnel boring machine (TBM) is widely used for tunnel excavation in hard rock and soft ground. In the perspective of TBM-based tunneling, one of the main challenges is to drive the machine optimally according to varying geological conditions, which could significantly lead to saving highly expensive costs by reducing the total operation time. Generally, drilling investigations are conducted to survey the geological ground before the TBM tunneling. However, it is difficult to provide the precise ground information over the whole tunnel path to operators because it acquires insufficient samples around the path sparsely and irregularly. To overcome this issue, in this study, we proposed a geological type classification system using the TBM operating data recorded in a 5 s sampling rate. We first categorized the various geological conditions (here, we limit to granite) as three geological types (i.e., rock, soil, and mixed type). Then, we applied the preprocessing methods including outlier rejection, normalization, and extracting input features, etc. We adopted a deep neural network (DNN), which has 6 hidden layers, to classify the geological types based on TBM operating data. We evaluated the classification system using the 10-fold cross-validation. Average classification accuracy presents the 75.4% (here, the total number of data were 388,639 samples). Our experimental results still need to improve accuracy but show that geology information classification technique based on TBM operating data could be utilized in the real environment to complement the sparse ground information.

• Cartoon and Animation Studies
• /
• s.49
• /
• pp.425-464
• /
• 2017

The Knowledge of the Channel (e) is often used as educational materials; it delivers very short but compelling message of strong or interesting timeliness. However, as the media environment changes, expectations and demands for The Knowledge The Knowledge of the Channel (e) is used in school education and what should be improved upon to increase utilization of educational resources. We surveyed 361 elementary, middle and high school teachers and analyzed the frequency of using, approach and learning activities of The Knowledge of the Channel (e) in school education. We also analyzed difficulties in using it in the school and what improvements should be made. Result show that the frequency of using The Knowledge of the Channel (e) in school is highest in elementary schools, followed by middle school, and then high school. Teachers strongly consider curricular relevance when selecting broadcasting contents for education, and among programs of EBS(Educational Broadcasting System), most frequently use The Knowledge of the Channel (e). The The Knowledge of the Channel (e) is mainly used as an incentive for increasing motivation. When examined by elementary school curriculum, this material is highly utilized in subjects with content such as society, morality, and science, or with approaches that require various perspectives. However, it is difficult for teachers to find materials directly related to their classes, and since other media content similar to The Knowledge of the Channel (e) is abundant, the utilization of The Knowledge of the Channel (e) is decreasing. To improve this, The Knowledge of the Channel (e) needs to improve its platform and transformed the type of The Knowledge of the Channel (e) content being provided on social media.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.532-534
• /
• 2022

At a time when the 5G era is advancing beyond commercialization, places that used to handle simple logistics warehouse tasks are transforming into smart logistics warehouses by combining IT convergence technology and platforms. Smart logistics warehouses can accurately predict demand and inventory of products with AI, deep learning, and robot technologies based on 5G, and provide information on warehousing and warehousing status in real time. As the e-commerce market grows, the smart logistics sector is also growing rapidly. This paper implements a smart logistics warehouse system and studies and proposes a method of establishing a fast and accurate logistics system by utilizing 5G-based Logistics Automation Robot.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.5
• /
• pp.345-349
• /
• 2009

Social bookmarking systems are a typical web 2.0 service based on folksonomy, providing the platform for storing and sharing bookmarking information. Spammers in social bookmarking systems denote the users who abuse the system for their own interests in an improper way. They can make the entire resources in social bookmarking systems useless by posting lots of wrong information. Hence, it is important to detect spammers as early as possible and protect social bookmarking systems from their attack. In this paper, we applied a diverse set of machine learning approaches, i.e., decision tables, decision trees (ID3), $na{\ddot{i}}ve$ Bayes classifiers, TAN (tree-augment $na{\ddot{i}}ve$ Bayes) classifiers, and artificial neural networks to this task. In our experiments, $na{\ddot{i}}ve$ Bayes classifiers performed significantly better than other methods with respect to the AUC (area under the ROC curve) score as veil as the model building time. Plausible explanations for this result are as follows. First, $na{\ddot{i}}ve$> Bayes classifiers art known to usually perform better than decision trees in terms of the AUC score. Second, the spammer detection problem in our experiments is likely to be linearly separable.

• Information Systems Review
• /
• v.23 no.3
• /
• pp.51-75
• /
• 2021

Global e-commerce websites offer personalized recommendation services to gain sustainable competitiveness. Existing studies have offered personalized recommendation services using quantitative preferences such as ratings. However, offering personalized recommendation services using only quantitative data has raised the problem of decreasing recommendation performance. For example, a user gave a five-star rating but wrote a review that the user was unsatisfied with hotel service and cleanliness. In such cases, has problems where quantitative and qualitative preferences are inconsistent. Recently, a growing number of studies have considered review data simultaneously to improve the limitations of existing personalized recommendation service studies. Therefore, in this study, we identify review and rating mismatches and build a new user profile to offer personalized recommendation services. To this end, we use deep learning algorithms such as CNN, LSTM, CNN + LSTM, which have been widely used in sentiment analysis studies. And extract sentiment features from reviews and compare with quantitative preferences. To evaluate the performance of the proposed methodology in this study, we collect user preference information using real-world hotel data from the world's largest travel platform TripAdvisor. Experiments show that the proposed methodology in this study outperforms the existing other methodologies, using only existing quantitative preferences.

• Journal of Appropriate Technology
• /
• v.6 no.2
• /
• pp.151-162
• /
• 2020

Education is one of the priority sectors specified in Tanzania, and it has committed to provide 11 years of compulsory free basic education for all from pre-primary to lower secondary level. Despite the Government's efforts to provide free basic education to all children, there are 2.0 million (23.2 per cent) out of 8.5 million children at the primary school age of 7-13, who are out of school in Tanzania. The ICT class should be offered as a regular class in all secondary schools in Tanzania, recommended by the ministry of education. However, many schools are struggling to implement this mandate. Most of schools offer the ICT class with theory without any real hardware. Some schools were given with computers but they were not maintained for operation. There is a huge task to make ICT education universal. Main issues include: remoteness (off-grid area), lack of ICT teachers, lack of resources such as hardware, infrastructure, and lack of practical lessons or projects to be used at schools. An innovative blended ICT/STEM education program is being conducted not only for Tanzanian public and private/international schools, but also for out-of-school adolescents through institutions, NGO centers, home visits and at the E3 Empower academy center. For effective STEM education to take place and remain sustainable, more practical curriculum, and close-up teacher support need to be accompanied concurrently. Practical, project-based simple coding lessons have been developed and employed that students experience true learning. The effectiveness of the curriculum has been demonstrated in various project centers, and it showed that students are showing new interests in exploring new discovery, even though this was a totally new area for them. It has been designed for an easy replication, thus students who learned can repeat the lessons themselves to other students. The ultimate purpose of this project is to have IT education offered as universally as possible throughout the whole Tanzania. Quality education for all children is a key for better future for all. Previously it was hoped that education with discipline will improve the active learning. But now more than ever, we believe that children have the ability to learn on their own with given proper STEM education tools, guidelines and environment. This gives promising hope to all of us, including those in the developing countries.

• Journal of Service Research and Studies
• /
• v.12 no.2
• /
• pp.65-79
• /
• 2022

Non-face-to-face classes continue due to Covid-19. There have been e-learning classes since the past, but the difference is that the current non-face-to-face classes are blended classes that combine real-time and recording classes or combine face-to-face and non-face classes. It is also characterized by being able to self-filmed or choose various lecture platforms in a place other than a dedicated studio. The advantages of non-face-to-face classes can be learned beyond time and space, and repetitive viewing and learning speed can be adjusted. Greening classes have no time and place constraints, and real-time classes have the advantage of high communication effects with learners. Evaluating whether non-face-to-face classes provide sufficient quality compared to face-to-face classes or e-learning will be necessary if branded classes are considered for post Covid. In this paper, for the evaluation of the service quality of non-face-to-face classes, the essential attributes desired by the instructors were derived from the viewpoint of Kano quality attributes and a quality improvement plan was proposed. After expressing the degree of functions that non-face-to-face classes should have on the X-axis and the satisfaction of learners on the Y-axis, 23 quality attributes were classified into 6 quality dimensions. In addition, satisfaction coefficient, dissatisfaction coefficient, and customer satisfaction improvement index were derived. As a result, 50% of learners were satisfied with non-face-to-face classes, but the preference was slightly higher than satisfaction, suggesting the sustainability of non-face-to-face classes. In terms of the customer satisfaction improvement index, the ranking of attributes with the largest increase in satisfaction when improving class quality was as follows. Professors' quick answers to learners' questions, content that can fully explain the subject, what the professor explains easily, develop high-quality content that can be learned on mobile phones, fairness of attendance checks, and real-time classes should start on time.

• 한국HCI학회:학술대회논문집
• /
• 2007.02b
• /
• pp.213-218
• /
• 2007

정보생산을 촉진하는 새로운 형태의 사이버공간이 나타나면서 지식의 창출과 지식을 얻는 형태가 변화하고 있다. 최종사용자에게 웹 애플리케이션을 제공하는 컴퓨팅 플랫폼인 web 2.0의 도입으로 손쉽게 자신이 필요한 정보를 분류할 수 있는 웹 컨텐츠가 활발히 제공되고 있으며 제공된 컨텐츠를 활용하여 수많은 정보 속에서 자신만의 보석을 찾아 손쉽게 지식을 쌓아 관리를 하고 있다. 이러한 지식공유서비스는 무분별한 정보, 중복된 지식, 그리고 단순한 관리로 인해 자신이 원하는 지식을 얻기란 쉽지 않은 것이 사실이다. 본 논문에서는 온라인상의 정보를 탐색하기 위해서 인터넷을 이용하던 네티즌들이 정보생산자로서 참여하는 공간으로 등장한 '지식공유서비스'를 기반으로 지식 창출 및 관리자로서 시니어를 활용하여 지식의 수용자로서 유아들을 위한 NIE (News In Education) 활용 교육 체계를 제안한다. 뉴스는 유아부터 성인까지 활용될 수 있는 좋은 교육 자료로서 NIE를 통하여 사고력, 논리력, 표현력, 창의력 등 여러 영역에 걸친 능력을 향상시킬 수 있다. 특히 유치원이나 학교의 교과과정에 맞추어 이러한 능력들을 더욱 배가 시킬 수 있다는 점에서 NIE가 더욱 각광받고 있다. 본 연구는 미디어 융합의 결과로 인터넷 뉴스를 활용해 생활과 분리되지 않은 통합교육을 할 수 있는 SCORM 기반의 유아용 콘텐츠를 생성하여 유아 교육에 활용하고자 한다. 또한, 유아용 NIE 교육 콘텐츠는 시니어들을 NIE 강사로 양성하였을 때 학습 자료로도 활용된다. 시니어들을 NIE 강사로 양성함으로써 시니어의 일자리 창출 및 지역사회 통합과 1세대인 여성시니어와 3세대인 아동 간의 세대통합을 이끌어 낼 수 있도록 하는 것에 목적을 두고 시니어 NIE 콘텐츠를 생성하고자 한다. NIE에 생성되는 지식을 생성하고 관리하기 위한 지식 솔루션으로 위키의 기능을 추가하여 개발하고자 한다. 위키를 사용하므로 개별적으로 존재하던 지식을 공동의 지식으로 공유할 수 있으며 의견을 하나로 통합하는 과정에서도 유용하게 사용될 수 있을 것이다. 위키를 이용한 시니어 NIE 콘텐츠에서는 교수 학습 계획안 및 NIE 아이디어를 공동 작업을 통하여 효율적으로 지식을 생성할 수 있으며 여러 사람들이 여러 단계를 거치면서 하나의 정제된 지식을 생성하게 되므로 양질의 교수 학습 계획안이나 NIE 아이디어를 창출할 수 있을 것이다.