• Korean Journal of Labor Studies
• /
• v.23 no.2
• /
• pp.277-306
• /
• 2017

This article empirically explores the impact of minijobs in the wake of the Hartz reform in Germany on women's employment relationship. Theoretically it is of great significance to examine whether the minijobs play an active role as a bridge in leading the minijobbers to regular, socially secured jobs or not. Several interviews as well as secondary data I could get during my sabbatical in 2015 were used to test the theory. One of the main findings was the fact that the minijob labor market opened doors wide for women in Germany, particularly for career-interrupted women, students or pensioners. However, the minijob can easily become a trap of lowest income and poverty for women. Most women minjobbers cannot go over to regular, socially secured jobs. Especially in terms of collective industrial relations, it considerably damages the power of industrial unions and the legal binding force of collective agreement. In conclusion, this study makes it clear that the labor market segmentation theory rather than the transitional labor market theory is valid in accounting for the reality of minijob in Germany. In other words, the minijob in Germany has a Toijan Horse Effect. It also suggests, from a practical viewpoint, that German industrial unions or works councils organize the minijobbers and that the coverage of collective agreements be extended to the minijobbers. Consequently, the time-selective part-timer model put into practice in Korea in 2014 is not only invalid but also undesirable.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1579-1590
• /
• 2020

In this paper, spatially-adaptive denormalization (SPADE) based U-Net is proposed to detect changes by using high-resolution satellite images. The proposed network is to preserve spatial information using SPADE. Change detection methods using high-resolution satellite images can be used to resolve various urban problems such as city planning and forecasting. For using pixel-based change detection, which is a conventional method such as Iteratively Reweighted-Multivariate Alteration Detection (IR-MAD), unchanged areas will be detected as changing areas because changes in pixels are sensitive to the state of the environment such as seasonal changes between images. Therefore, in this paper, to precisely detect the changes of the objects that consist of the city in time-series satellite images, the semantic spatial objects that consist of the city are defined, extracted through deep learning based image segmentation, and then analyzed the changes between areas to carry out change detection. The semantic objects for analyzing changes were defined as six classes: building, road, farmland, vinyl house, forest area, and waterside area. Each network model learned with KOMPSAT-3A satellite images performs a change detection for the time-series KOMPSAT-3 satellite images. For objective assessments for change detection, we use F1-score, kappa. We found that the proposed method gives a better performance compared to U-Net and UNet++ by achieving an average F1-score of 0.77, kappa of 77.29.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.679-684
• /
• 2023

Venous puncture is widely used to obtain blood samples for pathological examination. Because the invasive venipuncture method using a needle is repeatedly performed, the pain suffered by the patient increases, so our research team pre-developed a miniaturized near-infrared (NIR) imaging system in advance. To improve the image quality of the acquired NIR images, this study aims to model the non-local means (NLM) algorithm, which is well known to be efficient in noise reduction, and analyze its applicability in the system. The developed NIR imaging system is based on the principle that infrared rays pass through dichroic and long-pass filters and are detected by a CMOS sensor module. The proposed NLM algorithm is modeled based on the principle of replacing the pixel from which noise is to be removed with a value that reflects the distances between surrounding pixels. After acquiring an NIR image with a central wavelength of 850 nm, the NLM algorithm was applied to segment the final vein area through histogram equalization. As a result, the coefficient of variation of the NIR image of the vein using the NLM algorithm was 0.247 on average, which was an excellent result compared to conventional filtering methods. In addition, the dice similarity coefficient value of the NLM algorithm was improved by 62.91 and 9.40%, respectively, compared to the median filter and total variation methods. In conclusion, we demonstrated that the NLM algorithm can acquire accurate segmentation of veins acquired with a NIR imaging system.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.52 no.2
• /
• pp.39-50
• /
• 2024

Color is an essential visual element that has a significant impact on the formation of a city's image and people's perceptions. Quantitative analysis of color in urban environments is a complex process that has been difficult to implement in the past. However, with recent rapid advances in Machine Learning, it has become possible to analyze city colors using photos shared by tourists. This study selected Dali City, a popular tourist destination in China, as a case study. Photos of Dali City shared by tourists were collected, and a method to measure large-scale city colors was explored by combining machine learning techniques. Specifically, the DeepLabv3+ model was first applied to perform a semantic segmentation of tourist sharing photos based on the ADE20k dataset, thereby separating artificial elements in the photos. Next, the K-means clustering algorithm was used to extract colors from the artificial elements in Dali City, and an adjacency matrix was constructed to analyze the correlations between the dominant colors. The research results indicate that the main color of the artificial elements in Dali City has the highest percentage of orange-grey. Furthermore, gray tones are often used in combination with other colors. The results indicated that local ethnic and Buddhist cultures influence the color characteristics of artificial elements in Dali City. This research provides a new method of color analysis, and the results not only help Dali City to shape an urban color image that meets the expectations of tourists but also provide reference materials for future urban color planning in Dali City.

• Journal of the Korean Society for Railway
• /
• v.15 no.4
• /
• pp.370-375
• /
• 2012

In order to apply Interior Permanet Magnet Synchronous Motor(IPMSM) to the propulsion system of the railway transit, 110kW class IPMSMs with high-power density are designed as a concentrated winding model and a distributed winding model in this study. The concentrated winding model designed in this study is 6 poles/9 slots and the distributed winding model is 6 poles/36 slots. In general, the eddy current losses in the permanent magnets of IPMSM are caused by the slot harmonics. The thermal demagnetization of the magnet by the eddy current losses at high rotational speed often becomes one of the major problems in the IPMSM with a concentrated windings especially. A design to reduce eddy current losses in permanent magnet design is important in IPMSM for the railway vehicle propulsion system which requires high-speed operation. Therefore, a method to devide the permanent magnet is proposed to reduce the eddy current losses in permanent magnet in this study. Authors analyze the variation characteristics of the eddy current losses generated in permanent magnet of the concentrated winding model by changing the number of the division of the permanent magnets.

• Journal of KIISE:Software and Applications
• /
• v.31 no.3
• /
• pp.379-386
• /
• 2004

Video segmentation is a fundamental task in video indexing and it includes two kinds of shot change detections such as the abrupt transition and the gradual transition. The abrupt shot boundaries are detected by computing the image-based distance between adjacent frames and comparing this distance with a pre-determined threshold value. However, the gradual shot boundaries are difficult to detect with this approach. To overcome this difficulty, we propose the method that detects gradual transition in the MPEG compressed video using the HMM (Hidden Markov Model). We take two different HMMs such as a discrete HMM and a continuous HMM with a Gaussian mixture model. As image features for HMM's observations, we use two distinct features such as the difference of histogram of DC images between two adjacent frames and the difference of each individual macroblock's deviations at the corresponding macroblock's between two adjacent frames, where deviation means an arithmetic difference of each macroblock's DC value from the mean of DC values in the given frame. Furthermore, we obtain the DC sequences of P and B frame by the first order approximation for a fast and effective computation. Experiment results show that we obtain the best detection and classification performance of gradual transitions when a continuous HMM with one Gaussian model is taken and two image features are used together.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_1
• /
• pp.823-833
• /
• 2020

In order to stably produce crops, there is an increasing demand for effective crop monitoring techniques in domestic agricultural areas. In this manuscript, a cultivation area extraction method by using deep learning model is developed, and then, applied to satellite imagery. Training dataset for crop cultivation areas were generated using RapidEye satellite images that include blue, green, red, red-edge, and NIR bands useful for vegetation and environmental analysis, and using this, we tried to estimate the crop cultivation area of onion and garlic by deep learning model. In order to training the model, atmospheric-corrected RapidEye satellite images were used, and then, a deep learning model using FC-DenseNet, which is one of the representative deep learning models for semantic segmentation, was created. The final crop cultivation area was determined as object-based data through combination with cadastral maps. As a result of the experiment, it was confirmed that the FC-DenseNet model learned using atmospheric-corrected training data can effectively detect crop cultivation areas.

• Journal of Distribution Research
• /
• v.12 no.4
• /
• pp.1-25
• /
• 2007

The purpose of this study is to provide the strategic implication of the Korean open air market by examining the factors affecting customer loyalty for various market segments as their competitive environment becomes more turbulent. We have undertaken empirical research that uses the methodology of a mixture regression modeling, as a way to ascertain the determinants of customer loyalty toward the Korean open air market, which should form the base of strategy for each segment. We construct a mixture regression model which uses perceived the Korean open air market value dimensions as explanatory variables, an income as a covariate variable, and a customer loyalty as a dependent variable. The analysis of results show that customers are statistically divided into four segments: 'Accessibility'(33.7%), 'Price'(29.7%), 'Shopping environment,'(22.0%), and 'Merchandising,'(14.5%) groups. The findings also showed that parameter estimates are different for each group, which indicates that the sensitivity to changes in the Korean traditional market perceived value and the income variable affecting customer loyalty vary among segments.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.2
• /
• pp.147-156
• /
• 2024

The sustainable management and enhancement of marine resources are becoming increasingly important issues worldwide. This study was conducted in response to these challenges, focusing on the development and performance comparison of fish detection and classification models as part of a deep learning-based technique for assessing the effectiveness of marine resource enhancement projects initiated by the Korea Fisheries Resources Agency. The aim was to select the optimal model by training various sizes of YOLOv8-Seg models on a fish image dataset and comparing each performance metric. The dataset used for model construction consisted of 36,749 images and label files of 12 different species of fish, with data diversity enhanced through the application of augmentation techniques during training. When training and validating five different YOLOv8-Seg models under identical conditions, the medium-sized YOLOv8m-Seg model showed high learning efficiency and excellent detection and classification performance, with the shortest training time of 13 h and 12 min, an of 0.933, and an inference speed of 9.6 ms. Considering the balance between each performance metric, this was deemed the most efficient model for meeting real-time processing requirements. The use of such real-time fish detection and classification models could enable effective surveys of marine resource enhancement projects, suggesting the need for ongoing performance improvements and further research.