• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.637-639
• /
• 2003

As the number of spectral bands of high spectral resolution data increases, the capability to detect more detailed classes should also increase, and the classification accuracy should increase as well. Often, it is impossible to access enough training pixels for supervise classification. For this reason, the performance of traditional classification methods isn't useful. In this paper, we propose a new model for classification that operates based on decision fusion. In this classifier, learning is performed at two steps. In first step, only training samples are used and in second step, this classifier utilizes semilabeled samples in addition to original training samples. At the beginning of this method, spectral bands are categorized in several small groups. Information of each group is used as a new source and classified. Each of this primary classifier has special characteristics and discriminates the spectral space particularly. With using of the benefits of all primary classifiers, it is made sure that the results of the fused local decisions are accurate enough. In decision fusion center, some rules are used to determine the final class of pixels. This method is applied to real remote sensing data. Results show classification performance is improved, and this method may solve the limitation of training samples in the high dimensional data and the Hughes phenomenon may be mitigated.

• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.67-72
• /
• 2023

In the past decade, Autonomous Vehicle Systems (AVS) have advanced at an exponential rate, particularly due to improvements in artificial intelligence, which have had a significant impact on social as well as road safety and the future of transportation systems. The fusion of light detection and ranging (LiDAR) and camera data in real-time is known to be a crucial process in many applications, such as in autonomous driving, industrial automation and robotics. Especially in the case of autonomous vehicles, the efficient fusion of data from these two types of sensors is important to enabling the depth of objects as well as the classification of objects at short and long distances. This paper presents classification of objects using CNN based vision and Light Detection and Ranging (LIDAR) fusion in autonomous vehicles in the environment. This method is based on convolutional neural network (CNN) and image up sampling theory. By creating a point cloud of LIDAR data up sampling and converting into pixel-level depth information, depth information is connected with Red Green Blue data and fed into a deep CNN. The proposed method can obtain informative feature representation for object classification in autonomous vehicle environment using the integrated vision and LIDAR data. This method is adopted to guarantee both object classification accuracy and minimal loss. Experimental results show the effectiveness and efficiency of presented approach for objects classification.

• 한국도서관정보학회지
• /
• 제36권2호
• /
• pp.165-178
• /
• 2005

본 연구는 대학도서관의 단행본에 대한 분류검색 환경을 조사${\cdot}$분석함으로써, 그 실태를 파악하기 위한 것이다. 조사내용은 분류검색 제공여부, 접근방법, 검색수준 등에 중점을 두었다. 데이터 수집은 계통추출법에 의해 표집된 100개 도서관 중, 조사기간 동안 URL 연결이 가능한 97개 도서관을 대상으로 이루어졌다. 그 결과, 97개 도서관 중, $92.8\%$가 분류검색을 제공하고 있었으나, 이중 $52.2\%$가 분류기호만을 통해, $47.8\%$가 분류기호와 분류 디렉터리를 통해 접근이 가능한 것으로 나타났다. 따라서, 분류검색을 활성화하기 위해서는 분류기호만을 통해 접근이 가능한 도서관에 대한 검색환경 개선이 시급한 것으로 파악되었다.

• Journal of Information Technology Applications and Management
• /
• 제31권1호
• /
• pp.79-95
• /
• 2024

In modern society, as data plays a crucial role at the levels of businesses, industries, and nations, the utilization of data becomes increasingly important. Consequently, governments are prioritizing the development and implementation of plans to cultivate data workforce, viewing the data industry as a cornerstone of national strategy. To enhance domestic capabilities and nurture workforce in the data industry, it is deemed necessary to conduct an objective comparative analysis with major foreign countries. Therefore, this study aims to analyze cases of domestic and international data industries and explore methods for quantitatively comparing data industry workforce across nations. Initially, the study distinguishes between "data industry workforce" and "data job-related workforce," particularly focusing on professionals handling data-related tasks. Subsequently, it compares the workforce sizes of data job-related workforce across nations, utilizing standardized occupational classification codes based on the International Standard Classification of Occupations(ISCO). However, it should be noted that countries employing their own unique occupational classification systems often require matching job titles with similar meanings for accurate comparison. Through this study, it is anticipated that policymakers will be able to establish future directions for cultivating data workforce based on comparable status.

• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1035-1046
• /
• 2022

이 연구에서는 토지 피복 분류를 위한 다중 해상도 자료 융합의 적용성을 평가하였다. 여기서 다중 해상도 자료 융합 모델로는 spatial time-series geostatistical deconvolution/fusion model (STGDFM)을 적용하였다. 연구 지역은 미국 Iowa 주의 일부 농경 지역으로 선정하였으며, 대상 지역의 규모를 고려해 다중 해상도 자료 융합의 입력 자료로 Moderate Resolution Imaging Spectroradiometer (MODIS) 및 Landsat 영상을 사용하였다. 이를 바탕으로 STGDFM 적용해 Landsat 영상이 결측된 시기에서 가상의 Landsat 영상을 생성하였다. 그리고 획득한 Landsat 영상과 함께 STGDFM의 융합 결과를 입력 자료로 사용해 토지 피복 분류를 수행하였다. 특히 다중 해상도 자료 융합의 적용성 평가를 위해 획득한 Landsat 영상만을 이용한 분류 결과와 Landsat 영상 및 융합 결과를 모두 이용한 분류 결과를 비교 평가하였다. 그 결과, Landsat 영상만을 이용한 분류 결과에서는 대상 지역의 주요 토지 피복인 옥수수와 콩 재배지에서 혼재 양상이 두드러지게 나타났다. 또한 건초 및 곡물 지역과 초지 지역 등 식생 피복 간의 혼재 양상도 큰 것으로 나타났다. 반면 Landsat 영상 및 융합 결과를 이용한 분류 결과에서는 옥수수와 콩 재배지의 혼재 양상과 식생 피복 간의 혼재 양상이 크게 완화되었다. 이러한 영향으로 Landsat 영상 및 융합 결과를 이용한 분류 결과에서 분류 정확도가 약 20%p 향상되었다. 이는 STGDFM을 통해 MODIS 영상이 갖는 시계열 분광 정보를 융합 결과에 반영하면서 Landsat 영상의 결측을 보완할 수 있었고, 이러한 시계열 분광 정보가 분류 과정에 결합되면서 오분류를 크게 줄일 수 있었던 것으로 판단된다. 본 연구 결과를 통해 토지 피복 분류에 다중 해상도 자료 융합이 효과적으로 적용될 수 있음을 확인하였다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제27권2호
• /
• pp.175-196
• /
• 2018

Purpose The purpose of this study is to identify problems of current educational facility data management and recommend a standardized terminology classification system as a solution. In addition, the research aims to present a preemptive and integrated disaster and safety management framework for educational facilities by seeking efficient business processes through secured data quality, systematic data management, and external data linkage and analysis. Design/methodology/approach A terminology classification system has been established through various processes including filtering and analysis of related data including laws, manuals, educational facilities accidents, and historical records. Furthermore, the terminology classification system has been further reviewed through several consultations with experts and practitioners. In addition, the accumulated data was refined according to the established standard terminology and an Excel database was developed. Based on the data, accident patterns occurred in educational facilities over the past 10 years were analyzed. Findings In the study, a template was developed to collect consistent data for the standardized disaster and safety management terminology classification system in educational facilities. In addition, the standardized data utilization methods are presented from the viewpoint of 'education facility disaster safety data management', 'data analysis and insight', 'business management through data', and 'leaping into big data management'.

• 인터넷정보학회논문지
• /
• 제1권1호
• /
• pp.63-72
• /
• 2000

데이터마이닝은 방대한 데이터 자료로부터 숨어있는 지식이나 유용한 정보를 추출하는 과정이다. 이러한 데이터 마이닝 알고리즘은 통계학, 전자계산학, 그리고 기계학습 분야에서의 오랜 기간동안 이루어진 연구 결과의 산물이다. 어느 특정한 상황에 적용하는 특정한 기술들의 선택은 구현되어야 하는 데이터 마이닝 임무의 성격과 가용한 데이터의 성격에 의존한다. 데이터 마이닝에는 여러 임무가 있으며, 그 중에서 가장 대표적인 임무가 분류라고 (classification) 볼 수 있다. 분류는 인간 사고의 기본적인 요소이기 때문에 여러 응용 분야에서 많은 연구가 진행되어 왔으며, 문제 분석의 첫 단계라고 볼 수 있다. 본 논문에서는 학습문제에서 강건성(robust)을 갖는 유전자 알고리즘 기반의 분류시스템을 제안하고, 데이터 마이닝에서 중요한 분류기능에 관련된 문제인 nDmC에 응용해서 그 유효성을 검증한다.

• Industrial Engineering and Management Systems
• /
• 제13권4호
• /
• pp.421-431
• /
• 2014

The market basket data in the form of a binary user-item matrix or a binary item-user matrix can be modelled as a binary classification problem. The binary logistic regression approach tackles the binary classification problem, where principal components are predictor variables. If users or items are sparse in the training data, the binary classification problem can be considered as a cold-start problem. The binary logistic regression approach may not function appropriately if the principal components are inefficient for the cold-start problem. Assuming that the market basket data can also be considered as a special regression problem whose response is either 0 or 1, we propose three supervised learning approaches: random forest regression, random forest classification, and elastic net to tackle the cold-start problem, comparing the performance in a variety of experimental settings. The experimental results show that the proposed supervised learning approaches outperform the conventional approaches.

• Genomics & Informatics
• /
• 제9권3호
• /
• pp.134-135
• /
• 2011

DNA chips are used for experiments on genes and provide useful information that could be further analyzed. Using the data extracted from the DNA chips to find useful patterns or information has become a very important issue. In this paper, we explain the application developed for classifying DNA chip data using a classification method based on the Particle Swarm Optimization (PSO) algorithm. Considering that DNA chip data is extremely large and has a fuzzy characteristic, an algorithm that imitates the ecosystem such as the PSO algorithm is suitable to be used for analyzing such data. The application enables researchers to customize the PSO algorithm parameters and see detail results of the classification rules.

• 산업경영시스템학회지
• /
• 제29권2호
• /
• pp.13-19
• /
• 2006

The instance-based learning is a machine learning technique that has proven to be successful over a wide range of classification problems. Despite its high classification accuracy, however, it has a relatively high storage requirement and because it must search through all instances to classify unseen cases, it is slow to perform classification. In this paper, we have presented a new data reduction method for instance-based learning that integrates the strength of instance partitioning and attribute selection. Experimental results show that reducing the amount of data for instance-based learning reduces data storage requirements, lowers computational costs, minimizes noise, and can facilitates a more rapid search.