• 한국지리정보학회지
• /
• 제24권3호
• /
• pp.1-9
• /
• 2021

본 연구에서는 드론으로 취득한 고해상도 정사영상 자료를 이용하여, 컨볼루션 신경망(Convolution Neural Network, CNN)을 이용한 딥러닝 기법을 통해 수종에 대한 자동분류 가능성을 분석해 보고자 하였다. 수종판독을 위한 분류항목을 소나무, 자작나무, 낙엽송, 잣나무 그리고 신갈나무 5개 수종으로 선정하였다. 고해상도 정사영상과 임상도를 이용하여 총 5,000개의 데이터셋을 구축하였다. 수종분류를 위한 학습모델로 CNN 기법을 적용하였고, 데이터셋을 5:3:2의 비율로 훈련데이터, 검증테이터, 테스트데이터를 구분하여 모델의 학습 및 평가에 사용하였다. 모델의 전체 정확도는 89%로 나타났으며, 수종별 정확도는 소나무 95%, 자작나무 89%, 낙엽송 80%, 잣나무 86%, 신갈나무 98%로 나타났다.

• Nuclear Engineering and Technology
• /
• 제53권2호
• /
• pp.522-531
• /
• 2021

We describe a new deep learning model - Convolutional eXtreme Gradient Boosting (ConvXGB) for classification problems based on convolutional neural nets and Chen et al.'s XGBoost. As well as image data, ConvXGB also supports the general classification problems, with a data preprocessing module. ConvXGB consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by XGBoost in the last layer for predicting the class labels. The ConvXGB model is simplified by reducing the number of parameters under appropriate conditions, since it is not necessary re-adjust the weight values in a back propagation cycle. Experiments on several data sets from UCL Repository, including images and general data sets, showed that our model handled the classification problems, for all the tested data sets, slightly better than CNN and XGBoost alone and was sometimes significantly better.

• 한국콘텐츠학회논문지
• /
• 제22권3호
• /
• pp.354-360
• /
• 2022

대사성 질환은 국내의 경우 유병률이 26%에 이르는 질환으로 복부비만, 고혈압, 공복혈당장애, 고중성지방, 낮은 HDL 콜레스테롤 5가지 상태 중 3가지를 동시에 가진 상태를 말한다. 본 논문은 농촌진흥청의 소비자패널 데이터와 건강보험공단의 진료 데이터를 연계하여 식품 소비 특성을 통해 대사성 질환자군과 대조군으로 나누는 분류 모델을 생성하고 차이를 비교하고자 한다. 기존의 국내외에서 연구된 많은 대사성 질환과 식품 소비 특성 관련 연구는 특정 식품군이나 특정 성분의 질환 상관성 연구이며, 본 논문은 일반 식사에서 포함하는 모든 식품군을 고려한 로지스틱 회귀를 이용한 분류 모델, 의사결정나무 기반 분류 모델, XGBoost를 활용한 분류 모델을 생성하였다. 세 가지 모델 중 정확도가 높은 모델은 XGBoost 분류 모델이지만, 정확도가 0.7 미만으로 높지 않았다. 향후 연구로 환자군의 식품 소비 관찰 기간을 5년 이상으로 확대하고 섭취한 식품을 영양적 특성으로 변환한 후 대사성 질환 분류 모델 연구가 필요하다.

• 한국비블리아학회지
• /
• 제8권1호
• /
• pp.197-227
• /
• 1997

The main purpose of this study is ① to settle and to analyze the classification of the Internet Search Engine comparitively, and ② to build the compatible model of Internet Search Engine classification in order to seek information on the Internet resources. specially in the branch of the Computers and Internet areas. For this study, four Internet Search Engine (Excite, 1-Detect, Simmany, Yahoo Korea!), Inspec Classification and two distionaries were used. The major findings and result of analysis are summarized as follows : 1. The basis of the classification is the scope of topics, the system logic, the clearness, the efficiency. 2. The scope of topics is analyzed comparitively by the number of items from each Search Engine. In the result, Excite is the most superior of the four 3. The system logic is analyzed comparitively by the casuality balance and consistency of the items from each Search Engine. In the result, Excite is the most superior of the four 4. The clearness is analyzed comparitively by the clearness and accuracy of items, the recognition of the searchers. In the result, Excite is the most superior of the four. 5 The efficiency is analyzed comparitively by the exactness of indexing and decreasing the effort of the searchers. In the result, Yahoo Korea！ is the most superior of the four. 6 The compatible model of Internet Search Engine classification is estavlished to uplift the scope of topics, the system logic, the clearness, and the efficiency. The model divides the area mainly based upon the topics and resources using‘bookmark’and‘shadow’concept.

• 한국비블리아학회지
• /
• 제24권4호
• /
• pp.23-51
• /
• 2013

이 연구는 정부기능분류체계가 기록분류에 어떻게 적용되고 있는지, 그 가능성과 한계는 무엇인지 밝히기 위한 것이다. 자료 수집을 위해 6개 중앙행정기관의 기록관리전문직 6명을 대상으로 3회에 걸친 집단면담을 실시하였다. 우선 공공기록물관리법률 분석을 통해 기록물분류제도를 살펴본 후, 정부기능분류체계를 기록분류에 적용함으로써 얻을 수 있는 편익의 유형을 조사하였다. 면담 자료를 토대로 단위과제를 활용한 기록물철 분류의 실태와 문제점을 구조 및 운용 측면에서 분석하였다.

• 인지과학
• /
• 제18권1호
• /
• pp.1-14
• /
• 2007

목적 지향 대화에서 사용자의 의도는 화행과 개념열의 쌍으로 구성된 영역 행위로 표현될 수 있다. 그러므로 지능적인 대화 시스템을 구성하기 위해서는 영역 행위를 정확히 파악하는 것이 매우 중요하다. 본 논문에서는 CRFs (Conditional Random Fields)를 이용하여 화행과 개념열을 동시에 결정하는 통계 모델을 제안한다. 편향 학습 문제를 피하기 위하여 제안한 모델은 어휘와 품사 같은 낮은 수준의 언어 자질을 입력 자질로 사용하며, 카이 제곱 통계량을 이용하여 불필요한 자질들을 제거한다. 일정 관리 영역에서 실험을 수행한 결과, 제안한 모델은 화행 분류 정착률에서 93.0%, 개념열 분류 정확률에서 90.2%의 좋은 성능을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권1호
• /
• pp.364-380
• /
• 2016

The most popular approach in object classification is based on the bag of visual-words model, which has several fundamental problems that restricting the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification based on weakly supervised E2LSH and saliency map weighting is proposed. Firstly, E2LSH (Exact Euclidean Locality Sensitive Hashing) is employed to generate a group of weakly randomized visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, graph-based visual saliency (GBVS) algorithm is applied to detect the saliency map of different images and weight the visual words according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results datasets of Pascal 2007 and Caltech-256 indicate that the distinguishability of objects is effectively improved and our method is superior to the state-of-the-art object classification methods.

• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.329-342
• /
• 2020

In recent years, emotional text classification is one of the essential research contents in the field of natural language processing. It has been widely used in the sentiment analysis of commodities like hotels, and other commentary corpus. This paper proposes an improved W-LDA (weighted latent Dirichlet allocation) topic model to improve the shortcomings of traditional LDA topic models. In the process of the topic of word sampling and its word distribution expectation calculation of the Gibbs of the W-LDA topic model. An average weighted value is adopted to avoid topic-related words from being submerged by high-frequency words, to improve the distinction of the topic. It further integrates the highest classification of the algorithm of support vector machine based on the extracted high-quality document-topic distribution and topic-word vectors. Finally, an efficient integration method is constructed for the analysis and extraction of emotional words, topic distribution calculations, and sentiment classification. Through tests on real teaching evaluation data and test set of public comment set, the results show that the method proposed in the paper has distinct advantages compared with other two typical algorithms in terms of subject differentiation, classification precision, and F1-measure.

• 품질경영학회지
• /
• 제48권4호
• /
• pp.553-566
• /
• 2020

Purpose: The purpose of this study was to design a framework for generating one-class classification algorithm based on Hyper-Rectangle(H-RTGL) in a distributed environment connected by network. Methods: At first, we devised one-class classifier based on H-RTGL which can be performed by distributed computing nodes considering model and data parallelism. Then, we also designed facilitating components for execution of distributed processing. In the end, we validate both effectiveness and efficiency of the classifier obtained from the proposed framework by a numerical experiment using data set obtained from UCI machine learning repository. Results: We designed distributed processing framework capable of one-class classification based on H-RTGL in distributed environment consisting of physically separated computing nodes. It includes components for implementation of model and data parallelism, which enables distributed generation of classifier. From a numerical experiment, we could observe that there was no significant change of classification performance assessed by statistical test and elapsed time was reduced due to application of distributed processing in dataset with considerable size. Conclusion: Based on such result, we can conclude that application of distributed processing for generating classifier can preserve classification performance and it can improve the efficiency of classification algorithms. In addition, we suggested an idea for future research directions of this paper as well as limitation of our work.

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.205-211
• /
• 2021

Plants are important for humanity. They intervene in several areas of human life: medicine, nutrition, cosmetics, decoration, etc. The large number of varieties of these plants requires an efficient solution to identify them for proper use. The ease of recognition of these plants undoubtedly depends on the classification of these species into family; however, finding the relevant characteristics to achieve better automatic classification is still a huge challenge for researchers in the field. In this paper, we have developed a new automatic plant classification technique based on artificial neural networks. Our model uses leaf texture characteristics as parameters for plant family identification. The results of our model gave a perfect classification of three plant families of the Ivorian flora, with a determination coefficient (R2) of 0.99; an error rate (RMSE) of 1.348e-14, a sensitivity of 84.85%, a specificity of 100%, a precision of 100% and an accuracy (Accuracy) of 100%. The same technique was applied on Flavia: the international basis of plants and showed a perfect identification regression (R2) of 0.98, an error rate (RMSE) of 1.136e-14, a sensitivity of 84.85%, a specificity of 100%, a precision of 100% and a trueness (Accuracy) of 100%. These results show that our technique is efficient and can guide the botanist to establish a model for many plants to avoid identification problems.