• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.81-83
• /
• 2024

본 논문에서는 mask R-CNN의 이미지 세그먼테이션(Image Segmentation) 기법을 이용하여 철도의 선로를 식별하고 분류하는 방법을 제안한다. mask R-CNN의 이미지 세그먼테이션은 바운딩 박스(Bounding Box)를 통해 이미지에서 객체를 식별하는 R-CNN 알고리즘과는 달리 픽셀 단위로 관심 있는 객체를 검출하고 분류하는 기법으로서 오브젝트 디텍션(Object Detection)보다 더욱 정교한 객체 식별이 가능하다. 본 연구에서는 Pascal VOC 형태의 고속철도 데이터 24,205셋의 데이터를 전처리하고 MS COCO 데이터셋으로 변환하여, MMDetection의 mask R-CNN을 통해 픽셀 단위로 철도선로를 식별하고 정상/불량 상태를 분류하는 연구를 수행하였다. 선행연구에서는 YOLO를 활용하여 Polygon형태의 좌표를 바운딩 박스로 분류하였는데, 본 연구에서는 mask R-CNN을 활용함으로써 철도 선로를 더욱 정교하게 식별하였으며 정상/불량의 상태 분류는 YOLO와 유사한 성능을 보였다.

• Journal of Web Engineering
• /
• v.20 no.8
• /
• pp.2335-2360
• /
• 2021

A folksonomy is a classification system in which volunteers collaboratively create and manage tags to annotate and categorize content. The folksonomy has several problems in retrieving music using tags, including problems related to synonyms, different tagging levels, and neologisms. To solve the problem posed by synonyms, we introduced a mood vector with 12 possible moods, each represented by a numeric value, as an internal tag. This allows moods in music pieces and mood tags to be represented internally by numeric values, which can be used to retrieve music pieces. To determine the mood vector of a music piece, 12 regressors predicting the possibility of each mood based on acoustic features were built using Support Vector Regression. To map a tag to its mood vector, the relationship between moods in a piece of music and mood tags was investigated based on tagging data retrieved from Last.fm, a website that allows users to search for and stream music. To evaluate retrieval performance, music pieces on Last.fm annotated with at least one mood tag were used as a test set. When calculating precision and recall, music pieces annotated with synonyms of a given query tag were treated as relevant. These experiments on a real-world data set illustrate the utility of the internal tagging of music. Our approach offers a practical solution to the problem caused by synonyms.

• Journal of Forest and Environmental Science
• /
• v.40 no.3
• /
• pp.250-258
• /
• 2024

Forests are crucial for ecosystem stability, societal advancement, and subsistence; however, environmental changes since the 1970s, including shifting agriculture, deforestation, urbanization, increasing human population, and drought, have significantly impacted the region. The purpose of this study was to investigate the status of temporal forest cover changes in the Benchi-Sheko zone in Southwestern Ethiopia. Two types of data were collected: spatial data from satellite images of 1973, 1988, 2003, and 2017, and GPS point data. GIS software, ERDAS version 2015 software, and a handheld GPS were used for data analysis. The data of both GIS from image classification and ERDAS quantification revealed that forest cover decreased from 46,306.17 (92.67%) hectares in 1973 to 27,937.89 (55.91%) hectares in 2017; therefore 18,368.28 hectares (36.76%) decrease in forest cover was detected in the last 44 years by an average annual change of 417.46 hectares and. Based on this, it is recommended that partners working on forest conservation in the locality should enhance local people's awareness to protect forests and forest products in their day-to-day activities.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.5
• /
• pp.323-330
• /
• 2020

This paper proposes the road roughness based Braking Pressure Calculation System(BPCS) for an Autonomous Vehicle Stability. The system consists of an image normalization module that processes the front image of a vehicle to fit the input of the random forest, a Random Forest based Road Roughness Classification Module that distinguish the roughness of the road on which the vehicle is travelling by using the weather information and the front image of a vehicle as an input, and a brake pressure control module that modifies a friction coefficient applied to the vehicle according to the road roughness and determines the braking strength to maintain optimal driving according to a vehicle ahead. To verify the efficiency of the BPCS experiment was conducted with a random forest model. The result of the experiment shows that the accuracy of the random forest model was about 2% higher than that of the SVM, and that 7 features should be bagged to make an accurate random forest model. Therefore, the BPCS satisfies both real-time and accuracy in situations where the vehicle needs to brake.

• Clinical and Experimental Pediatrics
• /
• v.64 no.9
• /
• pp.480-488
• /
• 2021

Background: An adequate large-scale pediatric cohort based on nationwide administrative data is lacking in Korea. Purpose: This study established the National Investigation of Birth Cohort in Korea study 2008 (NICKs-2008) based on data from a nationwide population-based health screening program and data on healthcare utilization for children. Methods: The NICKs-2008 study consisted of the Korean National Health Insurance System (NHIS) and the National Health Screening Program for Infants and Children (NHSPIC) databases comprising children born in 2008 (n=469,248) and 2009 (n=448,459) in the Republic of Korea. The NHIS database contains data on age, sex, residential area, income, healthcare utilization (International Classification of Diseases10 codes, procedure codes, and drug classification codes), and healthcare providers. The NHSPIC consists of 7 screening rounds. These screening sessions comprised physical examination, developmental screening (rounds 2-7), a general health questionnaire, and age-specific anticipatory guidance. Results: During the 10-year follow-up, 2,718 children (0.3%) died, including more boys than girls (hazard ratio, 1.145; P<0.001). A total of 848,048 children participated in at least 1 of the 7 rounds of the NHSPIC, while 96,046 participated in all 7 screening programs. A total of 823 infants (0.1%) weighed less than 1,000 g, 3,177 (0.4%) weighed 1,000-1,499 g, 37,166 (4.4%) weighed 1,500-2,499 g, 773,081 (91.4%) weighed 2,500-4,000 g, and 32,016 (5.1%) weighed over 4,000 g. There were 23,404 premature babies (5.5%) in 2008 compared to 23,368 (5.6%) in 2009. The developmental screening test indicated appropriate development in 95%-98% of children, follow-up requirements for 1%-4% of children, and recommendations for further evaluation for 1% of children. Conclusion: The NICKs-2008, which integrates data from the NHIS and NHSPIC databases, can be used to analyze disease onset prior to hospitalization based on information such as lifestyle, eating habits, and risk factors.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2022

Non-small cell lung cancer (NSCLC) accounts for a high proportion of 85% among all lung cancer and has a significantly higher mortality rate (22.7%) compared to other cancers. Therefore, it is very important to predict the prognosis after surgery in patients with non-small cell lung cancer. In this study, the types of preoperative chest CT image patches for non-small cell lung cancer patients with tumor as a region of interest are diversified into five types according to tumor-related information, and performance of single classifier model, ensemble classifier model with soft-voting method, and ensemble classifier model using 3 input channels for combination of three different patches using pre-trained ResNet and EfficientNet CNN networks are analyzed through misclassification cases and Grad-CAM visualization. As a result of the experiment, the ResNet152 single model and the EfficientNet-b7 single model trained on the peritumoral patch showed accuracy of 87.93% and 81.03%, respectively. In addition, ResNet152 ensemble model using the image, peritumoral, and shape-focused intratumoral patches which were placed in each input channels showed stable performance with an accuracy of 87.93%. Also, EfficientNet-b7 ensemble classifier model with soft-voting method using the image and peritumoral patches showed accuracy of 84.48%.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.664-672
• /
• 2009

Recently, studies on utilizing tensor expression on image data analysis and processing have been attracting much interest. The purpose of this study is to develop an efficient system for classifying image patterns by using second order tensor expression. To achieve the goal, we propose a data generation model expressed by class factors and environment factors with second order tensor representation. Based on the data generation model, we define a function for measuring similarities between two images. The similarity function is obtained by estimating the probability density of environment factors using a matrix normal distribution. Through computational experiments on a number of benchmark data sets, we confirm that we can make improvement in classification rates by using second order tensor, and that the proposed similarity function is more appropriate for image data compared to conventional similarity measures.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.633-641
• /
• 2009

In this paper, we proposed a new pattern classifier which can be incrementally learned, be added new class in learning time, and handle with analog data. Proposed pattern classifier has hierarchical structure and the classification rate is improved by using different metric for each levels. Proposed model is based on the Gaussian ARTMAP which is an artificial neural network model for the pattern classification. We hierarchically constructed the Gaussian ARTMAP and proposed the Principal Component Emphasis(P.C.E) method to be learned different features in each levels. And we defined new metric based on the P.C.E. P.C.E is a method that discards dimensions whose variation are small, that represents common attributes in the class. And remains dimensions whose variation are large. In the learning process, if input pattern is misclassified, P.C.E are performed and the modified pattern is learned in sub network. Experimental results indicate that Hierarchical Gaussian ARTMAP yield better classification result than the other pattern recognition algorithms on variable data set including real applicable problem.

• Journal of KIISE:Software and Applications
• /
• v.36 no.6
• /
• pp.491-497
• /
• 2009

This paper proposes a new feature weighting method for document sentiment classification. The proposed method considers the difference of sentiment intensities among sentences in a document. Sentiment features consist of sentiment vocabulary words and the sentiment intensity scores of them are estimated by the chi-square statistics. Sentiment intensity of each sentence can be measured by using the obtained chi-square statistics value of each sentiment feature. The calculated intensity values of each sentence are finally applied to the TF-IDF weighting method for whole features in the document. In this paper, we evaluate the proposed method using support vector machine. Our experimental results show that the proposed method performs about 2.0% better than the baseline which doesn't consider the sentiment intensity of a sentence.

• Journal of Korean Society of Rural Planning
• /
• v.18 no.4
• /
• pp.117-127
• /
• 2012

The demand of rural tourism industry has increased among the urbanites in South Korea, in due to the increase of leisure activity and the emergence of ageing society. Rural amenity resources are gaining various interests, in the value creation and promotion of tourism. In this study, the propensities of city dwellers were separated by life-style classification, and each affinity to the rural amenity resources was examined in accordance with the separation. A questionnaire survey of urbanites in the southern area of Gyeonggi-do, the most populous province in South Korea, was conducted to analyze the preference of city dwellers about rural amenity resource and life-style of themselves. For statistical verification, $IBM^{(R)}$ $SPSS^{(R)}$ Statistics 20 software was used for frequency, reliability, factor and multiple regression analysis of this research. The results of the statistical analyses found a noticeable characteristic in life-style classification. The affinities of urbanites can be classified into four congregations of life-style factors in this statistical model. Each congregation of the factors was named as 'Self-development-oriented', 'Leisure-oriented', 'Achievement-oriented', and 'Culture-oriented' life-style, to represent the characteristics for convenience' sake. Among these styles, only 'Self-development-oriented' and 'Achievement-oriented' showed the positive correlation with rural amenity resources in the multiple regression analysis. In addition, the rural amenity resources were also analyzed in accordance with the life-styles classification of urbanites. City dwellers showed the highest interest to the 'natural resource management facility resource' in natural resources, the 'traditional heritage resource' in cultural resources, and the 'community resource' in social resources. Meanwhile, they showed less interest to 'agricultural and scenery resources' in natural resources, 'specialty production resource' in cultural resources, and 'cooperative farming' in social resources. These characteristics can be constructed as meaning that the urbanites who concern self-development and achievement of their lives have high interest in rural amenity resources, and the main interest of them is not 'return-to-the-farm'(歸農) but 'return-to-the-home'(歸村).