• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.687-696
• /
• 2014

This paper presents a semantic object extraction method using user's stroke input, color, and depth information. It is supposed that a semantically meaningful object is surrounded with a few strokes from a user, and has similar depths all over the object. In the proposed method, deciding the region of interest (ROI) is based on the stroke input, and the semantically meaningful object is extracted by using color and depth information. Specifically, the proposed method consists of two steps. The first step is over-segmentation inside the ROI using color and depth information. The second step is semantically meaningful object extraction where over-segmented regions are classified into the object region and the background region according to the depth of each region. In the over-segmentation step, we propose a new marker extraction method where there are two propositions, i.e. an adaptive thresholding scheme to maximize the number of the segmented regions and an adaptive weighting scheme for color and depth components in computation of the morphological gradients that is required in the marker extraction. In the semantically meaningful object extraction, we classify over-segmented regions into the object region and the background region in order of the boundary regions to the inner regions, the average depth of each region being compared to the average depth of all regions classified into the object region. In experimental results, we demonstrate that the proposed method yields reasonable object extraction results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.7
• /
• pp.1728-1736
• /
• 2015

Several algorithms have been developed to classify arrhythmia which either rely on specific ECG(Electrocardiogram) database. Nevertheless personalized difference of ECG signal exist, performance degradation occurs because of carrying out diagnosis by general classification rule. Most methods require accurate detection of P-QRS-T point, higher computational cost and larger processing time. But it is difficult to detect the P and T wave signal because of person's individual difference. Therefore it is necessary to design efficient algorithm that classifies different arrhythmia in realtime and decreases computational cost by extracting minimal feature. In this paper, we propose arrhythmia classification method using QRS Pattern of ECG signal according to personalized type. For this purpose, we detected R wave through the preprocessing method and define QRS pattern of ECG signal by QRS feature Also, we detect and modify by pattern classification, classified arrhythmia duplicated QRS pattern in realtime. Normal, PVC, PAC, LBBB, RBBB, Paced beat classification is evaluated by using 43 record of MIT-BIH arrhythmia database. The achieved scores indicate the average of 99.98%, 97.22%, 95.14%, 91.47%, 94.85%, 97.48% in PVC, PAC, Normal, BBB, Paced beat classification.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1037-1052
• /
• 2019

We had developed in preceding study a classification model for the Korean pine and Larch with an accuracy of 98 percent using Hyperion and Sentinel-2 satellite images, texture information, and geometric information as the first step for tree species mapping in the inaccessible North Korea. Considering a share of major tree species in North Korea, the classification model needs to be expanded as it has a large share of Oak(29.5%), Pine (12.7%), Fir (8.2%), and as well as Larch (17.5%) and Korean pine (5.8%). In order to classify 5 major tree species, national forest type map of South Korea was used to build 11,039 training and 2,330 validation data. Sentinel-2 data was used to derive spectral information, and PlanetScope data was used to generate texture information. Geometric information was built from SRTM DEM data. As a machine learning algorithm, Random forest was used. As a result, the overall accuracy of classification was 80% with 0.80 kappa statistics. Based on the training data and the classification model constructed through this study, we will extend the application to Mt. Baekdu and North and South Goseong areas to confirm the applicability of tree species classification on the Korean Peninsula.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.713-722
• /
• 2013

This paper proposes a method of using depth information to detect the hand region in real-time based on the cascade method. In order to ensure stable and speedy detection of the hand region even under conditions of lighting changes in the test environment, this study uses only features based on depth information, and proposes a method of detecting the hand region by means of a classifier that uses boosting and cascading methods. First, in order to extract features using only depth information, we calculate the difference between the depth value at the center of the input image and the average of depth value within the segmented block, and to ensure that hand regions of all sizes will be detected, we use the central depth value and the second order linear model to predict the size of the hand region. The cascade method is applied to implement training and recognition by extracting features from the hand region. The classifier proposed in this paper maintains accuracy and enhances speed by composing each stage into a single weak classifier and obtaining the threshold value that satisfies the detection rate while exhibiting the lowest error rate to perform over-fitting training. The trained classifier is used to classify the hand region, and detects the final hand region in the final merger stage. Lastly, to verify performance, we perform quantitative and qualitative comparative analyses with various conventional AdaBoost algorithms to confirm the efficiency of the hand region detection algorithm proposed in this paper.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.1
• /
• pp.48-63
• /
• 2015

In this study, we introduce various hyperspectral data processing techniques for the monitoring of shallow and coastal waters to enlarge the application range and to improve the accuracy of the end results in Korea. Unlike land, more accurate atmospheric correction is needed in coastal region showing relatively low reflectance in visible wavelengths. Sun-glint which occurs due to a geometry of sun-sea surface-sensor is another issue for the data processing in the ocean application of hyperspectal imagery. After the preprocessing of the hyperspectral data, a semi-analytical algorithm based on a radiative transfer model and a spectral library can be used for bathymetry mapping in coastal area, type classification and status monitoring of benthos or substrate classification. In general, semi-analytical algorithms using spectral information obtained from hyperspectral imagey shows higher accuracy than an empirical method using multispectral data. The water depth and quality are constraint factors in the ocean application of optical data. Although a radiative transfer model suggests the theoretical limit of about 25m in depth for bathymetry and bottom classification, hyperspectral data have been used practically at depths of up to 10 m in shallow and coastal waters. It means we have to focus on the maximum depth of water and water quality conditions that affect the coastal applicability of hyperspectral data, and to define the spectral library of coastal waters to classify the types of benthos and substrates.

• Korean Journal of Remote Sensing
• /
• v.12 no.2
• /
• pp.169-198
• /
• 1996

The objectives of this investigation are : 1. To analyze spectral signature and the associated vegetation index for geometric illumination conditions inf1uenced by low solar elevation and high slope orientations in mountainous forest. 2. To assess the accuracy of the spectral angle mapper classification for the a winter land cover in comparison with the maximum likelihood classification. 3. To produce the image of water quality and water properties that could be used to estimate the water pollution sources and the tide-included by turbid water in estuarine and coastal areas. These objectives are to characterize environmental and ecological monitoring applications of the Nak-Dong River Basin by using Fuyo-1 OPS VNIR data acquired on December 26, 1992. The results of this paper are as follows : 1. The spectral digital numbers and vegetation indexes (NDVI and TVI) of mountainous forest are higher on the slope facing the sun than on the slope hidden the sun under low sun elevation condition. 2. The spectral angle mapper algorithm produces a more accurate land cover classification of areas with steep slope, various aspects and low solar elevation than the maximum likelihood classifier. 3. The maximum likelihood classification images can be used for identifying the location and movement of both freshwater and salt water, regardless of geometric illumination conditions. 4. The color-coded density sliced image of selected water bodies by using the near-infrared band 3 can provide distribution of the water quality of the Lower Nak-Dong River. 5. The color-coded normalized difference vegetation index image of the selected mountain forest is suitable to classify winter vegetation cover types, i.e., forest canopy densities for slope orientations.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.871-884
• /
• 2021

The purpose of this study was to determine ways to increase efficiency in constructing and verifying artificial intelligence learning data on land cover using aerial and satellite images, and in applying the data to AI learning algorithms. To this end, multi-resolution datasets of 0.51 m and 10 m each for 8 categories of land cover were constructed using high-resolution aerial images and satellite images obtained from Sentinel-2 satellites. Furthermore, fine data (a total of 17,000 pieces) and coarse data (a total of 33,000 pieces) were simultaneously constructed to achieve the following two goals: precise detection of land cover changes and the establishment of large-scale learning datasets. To secure the accuracy of the learning data, the verification was performed in three steps, which included data refining, annotation, and sampling. The learning data that wasfinally verified was applied to the semantic segmentation algorithms U-Net and DeeplabV3+, and the results were analyzed. Based on the analysis, the average accuracy for land cover based on aerial imagery was 77.8% for U-Net and 76.3% for Deeplab V3+, while for land cover based on satellite imagery it was 91.4% for U-Net and 85.8% for Deeplab V3+. The artificial intelligence learning datasets on land cover constructed using high-resolution aerial and satellite images in this study can be used as reference data to help classify land cover and identify relevant changes. Therefore, it is expected that this study's findings can be used in the future in various fields of artificial intelligence studying land cover in constructing an artificial intelligence learning dataset on land cover of the whole of Korea.

• Journal of Advanced Navigation Technology
• /
• v.25 no.5
• /
• pp.426-432
• /
• 2021

Continuous wave (CW) Doppler radar has the advantage of being able to solve the privacy problem unlike camera and obtains signals in a non-contact manner. Therefore, this paper proposes a human activity recognition (HAR) system using CW Doppler radar, and presents the hardware design and implementation results for acceleration. CW Doppler radar measures signals for continuous operation of human. In order to obtain a single motion spectrogram from continuous signals, an algorithm for counting the number of movements is proposed. In addition, in order to minimize the computational complexity and memory usage, binarized neural network (BNN) was used to classify human motions, and the accuracy of 94% was shown. To accelerate the complex operations of BNN, the FPGA-based BNN accelerator was designed and implemented. The proposed HAR system was implemented using 7,673 logics, 12,105 registers, 10,211 combinational ALUTs, and 18.7 Kb of block memory. As a result of performance evaluation, the operation speed was improved by 99.97% compared to the software implementation.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.1-9
• /
• 2021

3D-NAND flash memory provides high capacity per unit area by stacking 2D-NAND cells having a planar structure. However, due to the nature of the lamination process, there is a problem that the frequency of error occurrence may vary depending on each layer or physical cell location. This phenomenon becomes more pronounced as the number of write/erase(P/E) operations of the flash memory increases. Most flash-based storage devices such as SSDs use ECC for error correction. Since this method provides a fixed strength of data protection for all flash memory pages, it has limitations in 3D NAND flash memory, where the error rate varies depending on the physical location. Therefore, in this paper, pages and layers with different error rates are classified into clusters through the K-means machine learning algorithm, and differentiated data protection strength is applied to each cluster. We classify pages and layers based on the number of errors measured after endurance test, where the error rate varies significantly for each page and layer, and add parity data to stripes for areas vulnerable to errors to provides differentiate data protection strength. We show the possibility that this differentiated data protection policy can contribute to the improvement of reliability and lifespan of 3D NAND flash memory compared to the protection techniques using RAID-like or ECC alone.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.93-103
• /
• 2021

Despite the efforts of financial authorities in conducting the direct management and supervision of collection agents and bond-collecting guideline, the illegal and unfair collection of debts still exist. To effectively prevent such illegal and unfair debt collection activities, we need a method for strengthening the monitoring of illegal collection activities even with little manpower using technologies such as unstructured data machine learning. In this study, we propose a classification model for illegal debt collection that combine machine learning such as Support Vector Machine (SVM) with a rule-based technique that obtains the collection transcript of loan companies and converts them into text data to identify illegal activities. Moreover, the study also compares how accurate identification was made in accordance with the machine learning algorithm. The study shows that a case of using the combination of the rule-based illegal rules and machine learning for classification has higher accuracy than the classification model of the previous study that applied only machine learning. This study is the first attempt to classify illegalities by combining rule-based illegal detection rules with machine learning. If further research will be conducted to improve the model's completeness, it will greatly contribute in preventing consumer damage from illegal debt collection activities.