• 재활복지
• /
• v.22 no.2
• /
• pp.53-82
• /
• 2018

The purpose of this study was to understand the experience of persons with developmental disabilities participating in the Personalized Support Services. For case study, we conducted in-depth interviews with the persons with developmental disabilities and with the active supporters for them who were using the community welfare centers for the disabled. Through this, we have come up with three core categories: 'coming out into the community', 'experimenting with various choices in life', and 'living a subjective life'. This suggests the followings; First, it can be seen that persons with developmental disabilities who have limited communication and self-determination should be allowed to participate in the service through the participation process, and active support for the parties is needed in the process. Second, it is necessary to plan and support for them, centering on the parties, away from institution-centered services. Third, sufficient budget support should be provided for the self-determination, selection and control of the parties. Fourth, we should be able to enjoy everyday life by participating together in the local community, and change the perception of local residents to participate in the community. Fifth, continuous support is needed rather than temporary support. Finally it will be needed for us to listen to the voices of both parties and to represent their rights with all our efforts.

• International Area Studies Review
• /
• v.20 no.1
• /
• pp.277-295
• /
• 2016

It is undoubtedly true that national security in Korean peninsula is on the road to destabilization. The main factors are known to be North Korea's development and experiment on nuclear arms, especially the forth nuclear experiment on January 6th, ICBM launch February 7th, and encroachment upon the territory the NLL on the 8th along with the shutdown on Gaeseong Industrial Complex. Also, China's trouble with other nations over sovereignty over islands in the South China Sea and the fact that Japan's government is veering to the right side and having territorial dispute are making the case worse. Nations in Northeast Asia are striving to obtain the interest for the sake of their own country. In order to do so, they're walking the path to achieve national security. Until then, they are not so willing to participate foreign matters or economical race. Even in our perspective, these issues are many of the main problems which our country is currently facing. However, it is important for them to avoid making policies which may take away the citizen's happiness. The number one priority for the nation or any form of a group is to act in the best interest for the national security and the citizen's happiness. They are the main factors why a nation could exist. They are the symbols of a nation's sovereign authority. Countries outside are proving it by increasing their national defense budget even in this unprecedented economical crisis. If we are willing to stay the same as ever, the disparity in the military force will not be the same in the future. In conclusion, the study examines the problem which changes in Northeast Asia's defense environment could bring and the appropriate amount of national defense budget in order to support the nation's integration of its abilities to move toward South and North Korea's unification.

• 재활복지
• /
• v.21 no.3
• /
• pp.129-146
• /
• 2017

In an event of an emergency, such as fire in a building, visually impaired and blind people are prone to exposed to a level of danger that is greater than that of normal people, for they cannot be aware of it quickly. Current fire detection methods such as smoke detector is very slow and unreliable because it usually uses chemical sensor based technology to detect fire particles. But by using vision sensor instead, fire can be proven to be detected much faster as we show in our experiments. Previous studies have applied various image processing and machine learning techniques to detect fire, but they usually don't work very well because these techniques require hand-crafted features that do not generalize well to various scenarios. But with the help of recent advancement in the field of deep learning, this research can be conducted to help solve this problem by using deep learning-based object detector that can detect fire using images from security camera. Deep learning based approach can learn features automatically so they can usually generalize well to various scenes. In order to ensure maximum capacity, we applied the latest technologies in the field of computer vision such as YOLO detector in order to solve this task. Considering the trade-off between recall vs. complexity, we introduced two convolutional neural networks with slightly different model's complexity to detect fire at different recall rate. Both models can detect fire at 99% average precision, but one model has 76% recall at 30 FPS while another has 61% recall at 50 FPS. We also compare our model memory consumption with each other and show our models robustness by testing on various real-world scenarios.

• Journal of the Korean Applied Science and Technology
• /
• v.36 no.2
• /
• pp.668-675
• /
• 2019

Fine dust in air pollutants is recognized as one of the most serious social environmental problems. Most of the NOx is generated in a combustion process such as that of a coal-fired power plant, and therefore efficient elimination of the NOx from the coal-fired power plants is needed. This study investigates the removal efficiency of using $TiO_2$, a photocatalyst, to remove NOx by Selective Catalytic Reduction (SCR). To evaluate the NOx removal efficiency, $TiO_2$ catalyst and phosphate binder were mixed on the surface of the $Al_2O_3$ substrate with the exothermic agent, and the substrate was heat-treated. The NOx removal efficiency of the catalysts was evaluated according to the temperature, and XRD, SEM, TG-DTA and BET analyzes were performed to investigate the physicochemical properties of the catalysts. NOx removal efficiency was 58.7%~65.9% at 20min, 63.7~66.0% at 30min with temperature change according to time($250^{\circ}C{\sim}500^{\circ}C$). The $TiO_2$ used in the SCR for NOx removal is judged to have the most efficient removal efficiency at $300^{\circ}C$.

• Journal of the HCI Society of Korea
• /
• v.14 no.2
• /
• pp.71-81
• /
• 2019

As AI technology develops, its application has been extended to diverse fields. In particular, AI-enabled Chatbot services have garnered growing attention and such services are more important as a tool of communication in mobile shopping. However, research on chatbots is in its early stage and the understanding of chatbots in the context of mobile commerce is very limited. The purpose of this study is to empirically investigate consumer responses to a shopping chatbot with a focus on the effects of chatbot agent types and message types. Specifically, a $2{\times}2$ between-subjects experimental design, with the agent type (secretary/friend) and the message type (factual/evaluative) as the independent variables, was employed. The results show that although main effects of chatbot agent and message types are not found, interaction effects between chatbot agents and message types on consumer responses are significant. Specifically, when the agent type was a secretary, consumer responses to product recommendation with a factual message were more positive. On the other hand, in the case of the friend agent, the evaluative message led to more positive responses. The findings suggest that communication elements are important in the understanding of consumer responses to chatbots in mobile shopping and effective strategies for utilizing chatbots for mobile commerce should be considered.

• Management & Information Systems Review
• /
• v.38 no.3
• /
• pp.245-257
• /
• 2019

This study focused on the brand attitude of consumers toward social innovation companies so that they could have differentiated competitive advantage and secure competitive advantage with ordinary companies. To this end, the difference in consumer brand attitudes between products of social innovation entities and products of general enterprises was compared through blind testing. The blind test results of this study showed that there was no statistically significant difference in product properties or brand attitudes, but after the information of the after-sales product was disclosed, the information included that the soap product used as a laboratory was natural handmade soap, indicating that post-brand attitudes improved in both social innovation and general enterprise products. And after explaining the social values pursued by social innovators, the increased interest in social innovation firms compared to ordinary enterprises resulted in a statistically significant increase in brand attitudes toward social innovation enterprise products. Clear and unexaggerated information displays on product packaging can be a tool to improve brand attitudes. In addition, in order to raise consumer awareness of social innovation enterprise products, there will be a need to enhance education and promotion policies for social innovation companies at the government level, and developing self-help measures for social innovation companies to promote themselves by presenting the contents of their social values as advertising copy on their product packaging may also be another breakthrough for improving brand attitudes and increasing sales.

• Journal of the Society of Disaster Information
• /
• v.14 no.4
• /
• pp.458-465
• /
• 2018

Purpose: Concrete track that affects on railway safety can detect cracks using image processing technique. However, since a condition of concrete track and surface noisy are obstructed to detect cracks, there is a need for a way to remove them effectively. Method: In this study, we proposed an image processing to detect cracks effectively for Korean railway and verified its performance through experiment. We developed image acquisition system for capture a railway concrete track and acquired railway concrete track images, randomly selected 2000 images and detected cracks in the image process using proposed Gabor Filter Bank methods. Results: As a result, 94% of detection rate are matched to the actual cracks in same quality and format railway concrete track image. Conclution: The crack detection method using Garbor Filter Bank was confirmed to be effective for crack image including noise in the Korean railway concrete track. This system is expected to become an automated maintenance system in the existing human-centered railway industry.

• Journal of Internet Computing and Services
• /
• v.20 no.5
• /
• pp.105-111
• /
• 2019

Core technologies that lead the Fourth Industrial Revolution era, such as artificial intelligence, big data, and autonomous driving, are implemented and serviced through the rapid development of computing power and hyper-connected networks based on the Internet of Things. In this paper, we implement two different models for drivable area segmentation in various environment, and propose a better model by comparing the results. The models for drivable area segmentation are using DeepLab V3+ and Mask R-CNN, which have great performances in the field of image segmentation and are used in many studies in autonomous driving technology. For driving information in various environment, we use BDD dataset which provides driving videos and images in various weather conditions and day&night time. The result of two different models shows that Mask R-CNN has higher performance with 68.33% IoU than DeepLab V3+ with 48.97% IoU. In addition, the result of visual inspection of drivable area segmentation on driving image, the accuracy of Mask R-CNN is 83% and DeepLab V3+ is 69%. It indicates Mask R-CNN is more efficient than DeepLab V3+ in drivable area segmentation.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.39-47
• /
• 2020

In this paper, we proposed a deep learning-based detection method using Saliency Attention to detect salient objects in images. The salient object detection separates the object where the human eye is focused from the background, and determines the highly relevant part of the image. It is usefully used in various fields such as object tracking, detection, and recognition. Existing deep learning-based methods are mostly Autoencoder structures, and many feature losses occur in encoders that compress and extract features and decoders that decompress and extend the extracted features. These losses cause the salient object area to be lost or detect the background as an object. In the proposed method, Saliency Attention is proposed to reduce the feature loss and suppress the background region in the Autoencoder structure. The influence of the feature values was determined using the ELU activation function, and Attention was performed on the feature values in the normalized negative and positive regions, respectively. Through this Attention method, the background area was suppressed and the projected object area was emphasized. Experimental results showed improved detection results compared to existing deep learning methods.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.461-469
• /
• 2020

In this paper, we propose a PCA-based feature feedback method for extracting important areas of handwritten numeric data sets and face data sets. A PCA-based feature feedback method is proposed by extending the previous LDA-based feature feedback method. In the proposed method, the data is reduced to important feature dimensions by applying the PCA technique, one of the dimension reduction machine learning algorithms. Through the weights derived during the dimensional reduction process, the important points of data in each reduced dimensional axis are identified. Each dimension axis has a different weight in the total data according to the size of the eigenvalue of the axis. Accordingly, a weight proportional to the size of the eigenvalues of each dimension axis is given, and an operation process is performed to add important points of data in each dimension axis. The critical area of the data is calculated by applying a threshold to the data obtained through the calculation process. After that, induces reverse mapping to the original data in the important area of the derived data, and selects the important area in the original data space. The results of the experiment on the MNIST dataset are checked, and the effectiveness and possibility of the pattern recognition method based on PCA-based feature feedback are verified by comparing the results with the existing LDA-based feature feedback method.