• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1730-1747
• /
• 2018

Multi-view video plus depth (MVD) is a mainstream format of 3D scene representation in free viewpoint video systems. The advanced 3D extension of the high efficiency video coding (3D-HEVC) standard introduces new prediction tools to improve the coding performance of depth video. However, the depth video in 3D-HEVC is time consuming. To reduce the complexity of the depth video inter coding, we propose a fast coding unit (CU) size and mode decision algorithm. First, an off-line trained Bayesian model is built which the feature vector contains the depth levels of the corresponding spatial, temporal, and inter-component (texture-depth) neighboring largest CUs (LCUs). Then, the model is used to predict the depth level of the current LCU, and terminate the CU recursive splitting process. Finally, the CU mode search process is early terminated by making use of the mode correlation of spatial, inter-component (texture-depth), and inter-view neighboring CUs. Compared to the 3D-HEVC reference software HTM-10.0, the proposed algorithm reduces the encoding time of depth video and the total encoding time by 65.03% and 41.04% on average, respectively, with negligible quality degradation of the synthesized virtual view.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.83-89
• /
• 2012

Natural Vegetation cover, which is very important earth resource, has been significantly altered by humans in some manner. Since this has currently resulted in a significant effect on global climate, various studies on vegetation environment including forest have been performed and the results are utilized in policy decision making. Remotely sensed data can detect, identify and map vegetation cover change based on the analysis of spectral characteristics and thus are vigorously utilized for monitoring vegetation resources. Among various vegetation indices extracted from spectral reponses of remotely sensed data, NDVI is the most popular index which provides a measure of how much photosynthetically active vegetation is present in the scene. In this study, for change detection in vegetation cover, a Multi-layer Perceptron Network (MLPN) as a nonparametric approach has been designed and applied to MODIS/Aqua vegetation indices 16-day L3 global 250m SIN Grid(v005) (MYD13Q1) data. The feature vector for change detection is constructed with the direct NDVI diffenrence at a pixel as well as the differences in some subset of NDVI series data. The research covered 5 years (2006-20110) over Korean peninsular.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.123-132
• /
• 2013

As the smartphones are equipped with various sensors such as the accelerometer, GPS, gravity sensor, gyros, ambient light sensor, proximity sensor, and so on, there have been many research works on making use of these sensors to create valuable applications. Human activity recognition is one such application that is motivated by various welfare applications such as the support for the elderly, measurement of calorie consumption, analysis of lifestyles, analysis of exercise patterns, and so on. One of the challenges faced when using the smartphone sensors for activity recognition is that the number of sensors used should be minimized to save the battery power. When the number of sensors used are restricted, it is difficult to realize a highly accurate activity recognizer or a classifier because it is hard to distinguish between subtly different activities relying on only limited information. The difficulty gets especially severe when the number of different activity classes to be distinguished is very large. In this paper, we show that a fairly accurate classifier can be built that can distinguish ten different activities by using only a single sensor data, i.e., the smartphone accelerometer data. The approach that we take to dealing with this ten-class problem is to use the ensemble of nested dichotomy (END) method that transforms a multi-class problem into multiple two-class problems. END builds a committee of binary classifiers in a nested fashion using a binary tree. At the root of the binary tree, the set of all the classes are split into two subsets of classes by using a binary classifier. At a child node of the tree, a subset of classes is again split into two smaller subsets by using another binary classifier. Continuing in this way, we can obtain a binary tree where each leaf node contains a single class. This binary tree can be viewed as a nested dichotomy that can make multi-class predictions. Depending on how a set of classes are split into two subsets at each node, the final tree that we obtain can be different. Since there can be some classes that are correlated, a particular tree may perform better than the others. However, we can hardly identify the best tree without deep domain knowledge. The END method copes with this problem by building multiple dichotomy trees randomly during learning, and then combining the predictions made by each tree during classification. The END method is generally known to perform well even when the base learner is unable to model complex decision boundaries As the base classifier at each node of the dichotomy, we have used another ensemble classifier called the random forest. A random forest is built by repeatedly generating a decision tree each time with a different random subset of features using a bootstrap sample. By combining bagging with random feature subset selection, a random forest enjoys the advantage of having more diverse ensemble members than a simple bagging. As an overall result, our ensemble of nested dichotomy can actually be seen as a committee of committees of decision trees that can deal with a multi-class problem with high accuracy. The ten classes of activities that we distinguish in this paper are 'Sitting', 'Standing', 'Walking', 'Running', 'Walking Uphill', 'Walking Downhill', 'Running Uphill', 'Running Downhill', 'Falling', and 'Hobbling'. The features used for classifying these activities include not only the magnitude of acceleration vector at each time point but also the maximum, the minimum, and the standard deviation of vector magnitude within a time window of the last 2 seconds, etc. For experiments to compare the performance of END with those of other methods, the accelerometer data has been collected at every 0.1 second for 2 minutes for each activity from 5 volunteers. Among these 5,900 ($=5{\times}(60{\times}2-2)/0.1$) data collected for each activity (the data for the first 2 seconds are trashed because they do not have time window data), 4,700 have been used for training and the rest for testing. Although 'Walking Uphill' is often confused with some other similar activities, END has been found to classify all of the ten activities with a fairly high accuracy of 98.4%. On the other hand, the accuracies achieved by a decision tree, a k-nearest neighbor, and a one-versus-rest support vector machine have been observed as 97.6%, 96.5%, and 97.6%, respectively.

• Journal of the Korean Geographical Society
• /
• v.50 no.3
• /
• pp.255-276
• /
• 2015

This paper presents a multi-agent system model of land-use and cover changes, which is developed and applied to the Gariwang-san and its vicinity, located in Pyeongchang and Jeongseon-gun, Gangwon province, Korea. The Land Use Dynamics Simulator (LUDAS) framework of this study is well suited for representing the spatial heterogeneity and dynamic interactions between human and natural environment, and capturing the impacts of forest-opening policy interventions to future socio-economic and natural environment changes. The model consists of four components: (1) a system of human population, (2) a system of landscape environment, (3) decision-making procedures integrating human(or household), environmental and policy information into forest land-use decisions, and (4) a set of policy scenarios that are related to the forest-opening. The results of model simulation by different combination of various forest management scenarios are assessed by the levels of household income, ecosystem service value and income inequality in the study region. As a result, the optimal scenario of forest-opening policies in the study region is to open the forest to local residential community for the purpose of recreation, considering the distinctive topographical feature. The model developed in this research is expected to contribute to a decision support system for sustainable forest management and various land-use policies in Korea.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.135-144
• /
• 2021

Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

• Korean Journal of Environment and Ecology
• /
• v.33 no.4
• /
• pp.472-480
• /
• 2019

Selection of the plant material for planting to reduce fine dust should comprehensively consider the visual characteristics, such as the shape and texture of the plant leaves and form of bark, which affect the adsorption function of the plant. However, previous studies on reduction of fine dust through plants have focused on the absorption function rather than the adsorption function of plants and on foliage plants, which are indoor plants, rather than the outdoor plants. In particular, the criterion for selection of fine dust reduction species is not specific, so research on the selection criteria for plant materials for fine dust reduction in urban areas is needed. The purpose of this study is to identify the priorities of eight indicators that affect the fine dust reduction by using the fuzzy multi-criteria decision-making model (MCDM) and establish the tree selection criteria for the urban planting to reduce fine dust. For the purpose, we conducted a questionnaire survey of those who majored in fine dust-related academic fields and those with experience of researching fine dust. A result of the survey showed that the area of leaf and the tree species received the highest score as the factors that affect the fine dust reduction. They were followed by the surface roughness of leaves, tree height, growth rate, complexity of leaves, edge shape of leaves, and bark feature in that order. When selecting the species that have leaves with the coarse surface, it is better to select the trees with wooly, glossy, and waxy layers on the leaves. When considering the shape of the leaves, it is better to select the two-type or three-type leaves and palm-shaped leaves than the single-type leaves and to select the serrated leaves than the smooth edged leaves to increase the surface area for adsorbing fine dust in the air on the surface of the leaves. When considering the characteristics of the bark, it is better to select trees that have cork layers or show or are likely to show the bark loosening or cracks than to select those with lenticel or patterned barks. This study is significant in that it presents the priorities of the selection criteria of plant material based on the visual characteristics that affect the adsorption of fine dust for the planning of planting to reduce fine dust in the urban area. The results of this study can be used as basic data for the selection of trees for plantation planning in the urban area.