• Journal of the Korean Institute of Intelligent Systems
• /
• 제26권6호
• /
• pp.477-484
• /
• 2016

Small industrial appliances such as fan, audio, electric rice cooker mostly consist of ABS, PP, PS materials. In colored plastics, it is possible to classify by near infrared(NIR) spectroscopy, while in black plastics, it is very difficult to classify black plastic because of the characteristic of black material that absorbs the light. So the RBFNNs pattern classifier is introduced for sorting electrical and electronic waste plastics through LIBS(Laser Induced Breakdown Spectroscopy) spectrometer. At the preprocessing part, PCA(Principle Component Analysis), as a kind of dimension reduction algorithms, is used to improve processing speed as well as to extract the effective data characteristics. In the condition part, FCM(Fuzzy C-Means) clustering is exploited. In the conclusion part, the coefficients of linear function of being polynomial type are used as connection weights. PSO and 5-fold cross validation are used to improve the reliability of performance as well as to enhance classification rate. The performance of the proposed classifier is described based on both optimization and no optimization.

• Journal of the Korea Society of Computer and Information
• /
• 제24권11호
• /
• pp.79-86
• /
• 2019

It is very important to analyze and provide information resources for research output produced in the computer field, the core science of the 4th Industrial Revolution. In this paper, SCI journals cited from domestic journals in the computer field were identified and the citation rankings and their co-citation networks were generated, analyzed, mapped and visualized. For this, the bibliographic and citation index information from 2015 to 2017 in the KSCD were used as the basis data, and the co-citation method and network centrality analysis were used. As a result of this study, the number of citations and the citation ranks of SCI journals and papers cited by korean journals in the computer field were analyzed, and peak time(2 years), half-life(6.6 years), and immediacy citation rate(2.4%) were measured by citation age analysis. As a result of network centrality analysis, Three network centralities(degree, betweenness, closeness) of the cited SCI journals were calculated, and the ranking of journals by each network centrality was measured, and the relationship between the subject classifications of the cited SCI journals was visualized through the mapping of the network.

• Journal of the Korea Society of Computer and Information
• /
• 제26권12호
• /
• pp.151-158
• /
• 2021

Internet of Things (IoT) technology, which provides services by connecting various objects in the real world and objects in the virtual world based on the Internet, is emerging as a technology that enables a hyper-connected society in the era of the 4th industrial revolution. Since IoT technology is a convergence technology that encompasses devices, networks, platforms, and services, various studies are being conducted. Among these studies, studies on measures that can measure service quality provided by IoT software are still insufficient. IoT software has hardware parts of the Internet of Things, technologies based on them, features of embedded software, and network features. These features are used as elements defining IoT software quality measurement metrics. However, these features are considered in the metrics related to IoT software quality measurement so far. Therefore, this paper presents a metric for reusability measurement among various quality factors of IoT software in consideration of these factors. In particular, since IoT software is used through IoT devices, services in IoT software must be designed to be changed, replaced, or expanded, and metrics that can measure this are very necessary. In this paper, we propose three metrics: changeability, replaceability, and scalability that can measure and evaluate the reusability of IoT software services were presented, and the metrics presented through case studies were verified. It is expected that the service quality verification of IoT software will be carried out through the metrics presented in this paper, thereby contributing to the improvement of users' service satisfaction.

• KIPS Transactions on Computer and Communication Systems
• /
• 제7권12호
• /
• pp.301-312
• /
• 2018

In industrial wireless sensor networks, the continuous object detection such as fire or toxic gas detection is one of major applications. A continuous object occurs at a specific point and then diffuses over a wide area. Therefore, many studies have focused on accurately detecting a continuous object and delivering data to a static sink with an energy-efficient way. Recently, some applications such as fire suppression require mobile sinks to provide real-time response. However, the sink mobility support in continuous object detection brings challenging issues. The existing approaches supporting sink mobility are designed for individual object detection, so they establish one-to-one communication between a source and a mobile sink for location update. But these approaches are not appropriate for a continuous object detection since a mobile sink should establish one-to-many communication with all sources. The one-to-many communication increases energy consumption and thus shortens the network lifetime. In this paper, we propose the origin-centric communication scheme to support sink mobility in a continuous object detection. Simulation results verify that the proposed scheme surpasses all the other work in terms of energy consumption.

• Korean Chemical Engineering Research
• /
• 제57권2호
• /
• pp.274-282
• /
• 2019

In recent years, big data analysis has been expanded to include automatic control through reinforcement learning as well as prediction through modeling. Research on the utilization of image data is actively carried out in various industrial fields such as chemical, manufacturing, agriculture, and bio-industry. In this paper, we applied NASNet, which is an AutoML reinforced learning algorithm, to DeepU-Net neural network that modified U-Net to improve image semantic segmentation performance. We used BRATS2015 MRI data for performance verification. Simulation results show that DeepU-Net has more performance than the U-Net neural network. In order to improve the image segmentation performance, remove dropouts that are typically applied to neural networks, when the number of kernels and filters obtained through reinforcement learning in DeepU-Net was selected as a hyperparameter of neural network. The results show that the training accuracy is 0.5% and the verification accuracy is 0.3% better than DeepU-Net. The results of this study can be applied to various fields such as MRI brain imaging diagnosis, thermal imaging camera abnormality diagnosis, Nondestructive inspection diagnosis, chemical leakage monitoring, and monitoring forest fire through CCTV.

• The Journal of the Korea Contents Association
• /
• 제19권6호
• /
• pp.168-178
• /
• 2019

This study takes a close look at the recent success of independent documentaries to find its implications and a way to invigorate Korean documentary ecosystems. To this aim, this study performed in-depth interviews with independent documentary film makers and television documentary directors. Also, it analyzed the case of POV (Point Of View), which is television's longest-running showcase for independent documentary films in the USA. The results display that independent documentaries convey competitive edge of contents and expansion of distribution and funding through film industry systems, based on the producer systems, global distribution networks of overseas pitching and film festivals, marketing and audience strategy of film industry. Although this shows its molding of documentary industry ecosystems, there are great needs for various platforms other than film industrial outlet in order to make an advancement of the ecosystems under the digital environment. POV works on the basis of 'open sourcing' form when collaborating with independent film makers. Independent documentaries picked up by POV are aired on PBS, streamed via its online service, and distributed through community screenings; this three-outlet strategy makes POV a unique platform and has a relevance and feasibility to apply for Korean documentary ecosystems. Therefore, this study suggests to create a platform adopting POV system hoping that more studies and efforts would come for various and novel platform building so to make more advanced and invigorated ecosystems of Korean documentary.

• Journal of the Economic Geographical Society of Korea
• /
• 제22권2호
• /
• pp.214-235
• /
• 2019

This study adopts the concept of social innovation cluster in which social economy organizations as one of the emerging axes of economic systems operate in collaboration with government agencies, investment institutions, intermediate supporting organizations and non-profit organizations, and investigates how the clusters of this kind grow in the context of the Korean socio-economic situation for the cases of Seongdong-gu and Eunpyeong-gu in Seoul, Korea. For this purpose, it has identified the actors of the clusters and their internal relations, and analyzed the process of cluster formation. A social network analysis of the partnerships between the actors has shown that Seongdong-gu has more diversified types of the network participation of universities, global networks and investment institutions than Eunpyeong-gu. It is interpreted that this pattern has resulted from the domination of private organizations in the former area, which is also confirmed by in-depth interviews with persons involved in the clusters. Although the facets of social innovation clusters are manifested in both areas, even in their initial stage, such factors as linkages between industrial actors and convergence with other clusters, which appear in the maturing stage of cluster formation, has yet to be found. It is suggested that the sustainable growth of social innovation clusters should be accompanied by information sharing and cooperation between the two areas on the future orientation of development.

• Management & Information Systems Review
• /
• 제38권3호
• /
• pp.55-80
• /
• 2019

Recently, many companies improving their management performance by building a powerful brand value which is recognized for trademark rights. However, as growing up the size of online commerce market, the infringement of trademark rights is increasing. According to various studies and reports, cases of foreign and domestic companies infringing on their trademark rights are increased. As the manpower and the cost required for the protection of trademark are enormous, small and medium enterprises(SMEs) could not conduct preliminary investigations to protect their trademark rights. Besides, due to the trademark image search service does not exist, many domestic companies have a problem that investigating huge amounts of trademarks manually when conducting preliminary investigations to protect their rights of trademark. Therefore, we develop an intelligent similar trademark search model to reduce the manpower and cost for preliminary investigation. To measure the performance of the model which is developed in this study, test data selected by intellectual property experts was used, and the performance of ResNet V1 101 was the highest. The significance of this study is as follows. The experimental results empirically demonstrate that the image classification algorithm shows high performance not only object recognition but also image retrieval. Since the model that developed in this study was learned through actual trademark image data, it is expected that it can be applied in the real industrial environment.

• Journal of the Korean Association of Geographic Information Studies
• /
• 제22권3호
• /
• pp.51-64
• /
• 2019

Mt. Geumgang has been a scenic spot representing the Korean peninsula since the Joseon Dynasty, and became a symbol of inter-Korean exchanges with the Gaesong Industrial Complex after the division of the South and North. Mt. Geumgang Tour Course is divided into the Inner-Geumgang (Naegeumgang) and the Outer-Geumgang (Oegeumgang). It was common for the Mt. Geumgang tour route during the Joseon Dynasty and the Japanese Imperialization period to enter the Inner-Geumgang, near Seoul, and come to the East Sea through the Outer-Geumgang. However, the tour route starting from Goseong was utilized for the Mt. Geumgang tour course operated by Hyundai. Because North Korea opened only the Outer-Geumgang area. North Korea has only opened some of its tour courses to Hyundai, but if Geumgang tourism is resumed in the future, there is a high possibility that it will be opened further, such as opening some sections of the Inner-Geumgang in 2007. In this case, it is necessary to connect additional transportation networks to access Inner-Geumgang from South Korea. The best alternative was the restoration of the Mt. Geumgang Railway. However, considering the fact that the reconstruction of the Mt. Geumgang Railway can not be completed due to the construction of the Imnam Dam, it is the most realistic alternative to restore Route 31 connecting Yanggu and Geumgang-eup. As a result of the analysis of road connecting Inner-Geumgang, three routes were confirmed. All of which were adjacent to the existing National Route 31. These routes passing through Dutayeon and Mundeung-ri and joining the Route 31 from Inje. Considering road length, topography characteristics, and military facility layout, it seems that the connection of 'Dutaeyun - Mundeung - Geumgang' is a realistic alternative connecting from South Korea to Inner-Geumgang.

• Food Engineering Progress
• /
• 제21권2호
• /
• pp.167-173
• /
• 2017

Purple-fleshed potato powder (PFPP) was investigated to determine optimal mixing ratio with milk powder and dextrin to produce a ready-to-eat mashed potato powder. The rheological characteristics, color, and anthocyanin contents were studied at a different concentration of ingredients. The power-law model was applied to explain the mechanical spectra of mashed potatoes which represented the change in structure induced by different mixing ratios. Mixture design was used to obtain the experimental points used to establish the empirical models to describe the effects of each ingredient on the characteristic of the mashed potato. The results of mechanical spectra showed that both storage and loss moduli (G' and G'') were significantly influenced by PFPP and milk powder concentration. The power law parameters n' and n'' showed higher values for the mashed potato with a lower concentration of PFPP and a higher concentration of milk powder, which showed that the gel networks involved in the mashed potato were weaker. The optimum mixing ratio with the highest redness and anthocyanin content, while maintaining the rheological properties similar to the commercial mashed potato, was determined as PFPP:milk powder:dextrin = 90.49:4.86:4.65 (w/w). The proportions of PFPP and milk powder in the formulation significantly changed the characteristics of mashed potato, whereas no significant effect of dextrin was observed in this formulation.