• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.171-183
• /
• 2020

Capsule endoscopy is one of the increasingly demanded diagnostic methods among patients in recent years because of its ability to observe small intestine difficulties. It is often conducted for 12 to 14 hours, but significant frames constitute only 10% of whole frames. Thus, it has been designed to automatically acquire significant frames through deep learning. For example, studies to track the position of the capsule (stomach, small intestine, etc.) or to extract lesion-related information (polyps, etc.) have been conducted. However, although grouping or labeling the training images according to similar features can improve the performance of a learning model, various attributes (such as degree of wrinkles, presence of valves, etc.) are not considered in conventional approaches. Therefore, we propose a class-labeling method that can be used to design a learning model by constructing a knowledge model focused on main lesions defined in standard terminologies for capsule endoscopy (minimal standard terminology, capsule endoscopy structured terminology). This method enables the designing of a systematic learning model by labeling detailed classes through differentiation of similar characteristics.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.5
• /
• pp.325-333
• /
• 2015

Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.83-88
• /
• 2024

In this research, we propose a Semi-Supervised learning based railroad surface defect detection method. The Resnet50 model, pretrained on ImageNet, was employed for the training. Data without labels are randomly selected, and then labeled to train the ResNet50 model. The trained model is used to predict the results of the remaining unlabeled training data. The predicted values exceeding a certain threshold are selected, sorted in descending order, and added to the training data. Pseudo-labeling is performed based on the class with the highest probability during this process. An experiment was conducted to assess the overall class classification performance based on the initial number of labeled data. The results showed an accuracy of 98% at best with less than 10% labeled training data compared to the overall training data.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.65-75
• /
• 2017

The Detection Model is the model to find the result of a certain purpose using artificial intelligent, data mining, intelligent algorithms In Cyber Security, it usually uses to detect intrusion, malwares, cyber incident, and attacks etc. There are an amount of unlabeled data that are collected in a real environment such as security data. Since the most of data are not defined the class labels, it is difficult to know type of data. Therefore, the label determination process is required to detect and analysis with accuracy. In this paper, we proposed a KDFL(K-means and D-S Fusion based Labeling) method using D-S inference and k-means(unsupervised) algorithms to decide label of data records by fusion, and a detection model architecture using a proposed labeling method. A proposed method has shown better performance on detection rate, accuracy, F1-measure index than other methods. In addition, since it has shown the improved results in error rate, we have verified good performance of our proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.4
• /
• pp.313-321
• /
• 2014

In the current era of data-intensive services, the handling of big data is a crucial issue that affects almost every discipline and industry. In this study, we propose a classification method for large volumes of numeric data, which is implemented in a distributed programming framework, i.e., MapReduce. The proposed method partitions the data space into a grid structure and it then models the probability distributions of classes for grid cells by collecting sufficient statistics using distributed MapReduce tasks. The class labeling of new data is achieved by k-nearest neighbor classification based on Bayesian inference.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.696-701
• /
• 2002

This paper describes some results of change detection in Tokyo metropolitan area, Japan , using the Landsat TM data, and methods to quantify the ground cover classes. The changes are analyzed using the measures of not only conventional spectral classes but also a set of landscape indices to describe spatial properties of ground cove types using fractal dimension of objects, entropy in the specific windows defining the neighbors of focusing locations. In order eliminate the seasonal radiometric effects on TM data, an automated class labeling method is also attempted. Urban areas are also delineated automatically by defining the boundaries of the urban area. These procedures for urban change detection were implemented by the unified image computing methods proposed by the author, they can be automated in coherent and systematic ways, and it is anticipated to automate the whole procedures. The results of this analysis suggest that Tokyo metropolitan area was extended to the suburban areas along the new transportation networks and the high density area of Tokyo were also very much extended during the period between 1985 and 1995.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.749-752
• /
• 2017

캡슐내시경 검사는 일반내시경으로는 관찰하기 힘든 소장 기관을 관찰할 수 있어 최근 환자들 사이에서 수요가 늘고 있는 검사 방법 중 하나이다. 이와 같은 캡슐내시경으로부터 병변에 대한 의료 정보가 획득될 수 있는데, 최근에는 캡슐내시경 영상의 학습을 통해 이를 자동으로 획득하려는 시도들이 이루어지고 있다. 예를 들면, 캡슐의 위치를 추적하기 위해 위장관의 개략적인 위치(위, 소장 등)를 파악하거나, 캡슐내시경 영상으로부터 관찰될 수 있는 병변(폴립 등)을 검출하기 위해 영상의 학습이 수행되고 있는 상황이다. 그러나 캡슐내시경의 방대한 영상 프레임 중에서 병변에 대한 영상은 극히 일부분이기 때문에, 기존 학습 영상의 클래스(레이블)는 다양한 병변에 대한 정의나 영상에서 확인될 수 있는 구체적인 속성이 고려되지 않는다. 따라서 본 논문에서는 캡슐내시경 관련 표준(MST, CEST)에서 정의하고 있는 주요 병변 정보에 대한 색상 유사도 분석을 통해, 출력층에서 활용될 수 있는 클래스 레이블링 기법을 제안한다. 제안하는 기법은 유사한 특성을 보이는 영상의 구분을 통해 세부적인 클래스 레이블링을 수행하여 체계적인 학습 모델의 설계를 가능케한다.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.439-442
• /
• 1999

It is important to analyze the seasonal change profiles of land cover type in large scale for establishing preservation strategy and environmental monitoring. Because the NOAA-AVHRR data sets provide global data with high temporal resolution, it is suitable for the land cover classification of the large area. The objectives of this study were to classify land cover of Korea, to investigate the phenological profiles of land cover. The NOAA-AVHRR data from Jan. 1998 to Dec. 1998 were received by Korea Ocean Research & Development Institute(KORDI) and were used for this study. The NDVI data were produced from this data. And monthly maximum value composite data were made for reducing cloud effect and temporal classification. And the data were classified using the method of supervised classification. To label the land cover classes, they were classified again using generalized vegetation map and Landsat-TM classified image. And the profiles of each class was analyzed according to each month. Results of this study can be summarized as follows. First, it was verified that the use of vegetation map and TM classified map was available to obtain the temporal class labeling with NOAA-AVHRR. Second, phenological characteristics of plant communities of Korea using NOAA-AVHRR was identified. Third, NDVI of North Korea is lower on Summer than that of South Korea. And finally, Forest cover is higher than another cover types. Broadleaf forest is highest on may. Outline of covertype profiles was investigated.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.91-98
• /
• 2023

Recently, according to development of artificial intelligence, a wide range of industry being automatic and optimized. Also we can find out some research of using supervised learning for deteceting defect of railway in domestic rail industry. However, there are structures other than rails on the track, and the fastener is a device that binds the rail to other structures, and periodic inspections are required to prevent safety accidents. In this paper, we present a method of reducing cost for labeling using semi-supervised and transfer model trained on rail fastener data. We use Resnet50 as the backbone network pretrained on ImageNet. At first we randomly take training data from unlabeled data and then labeled that data to train model. After predict unlabeled data by trained model, we adopted a method of adding the data with the highest probability for each class to the training data by a predetermined size. Futhermore, we also conducted some experiments to investigate the influence of the number of initially labeled data. As a result of the experiment, model reaches 92% accuracy which has a performance difference of around 5% compared to supervised learning. This is expected to improve the performance of the classifier by using relatively few labels without additional labeling processes through the proposed method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.75-81
• /
• 2012

Road identification is the important task for extracting a road region from the high-resolution satellite images, when the road candidates is extracted by the pre-processing tasks using a binarization, noise removal, and color processing. Therefore, we propose a noble approach for identifying a road using the orientation-selective spatial filters, which is motivated by a computational model of neuron cells found in the primary visual cortex. In our approach, after the neuron cell typed spatial filters is applied to the isolated connected-labeling road candidate regions, proposed method identifies the region of perceiving the strong orientation feature with the real road region. To evaluate the effectiveness of the proposed method, the accuracy&error ratio in the confusion matrix was measured from road candidates including road and non-road class. As a result, the proposed method shows the more than 92% accuracy.