• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.133-140
• /
• 2018

Accurate sentiment classification is an important research topic in sentiment analysis. This study suggests an efficient classification method of Korean sentiment using word2vec and ensemble methods which have been recently studied variously. For the 200,000 Korean movie review texts, we generate a POS-based BOW feature and a feature using word2vec, and integrated features of two feature representation. We used a single classifier of Logistic Regression, Decision Tree, Naive Bayes, and Support Vector Machine and an ensemble classifier of Adaptive Boost, Bagging, Gradient Boosting, and Random Forest for sentiment classification. As a result of this study, the integrated feature representation composed of BOW feature including adjective and adverb and word2vec feature showed the highest sentiment classification accuracy. Empirical results show that SVM, a single classifier, has the highest performance but ensemble classifiers show similar or slightly lower performance than the single classifier.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.293-296
• /
• 2021

K-water에서는 다목적댐의 관리를 위해 실시간으로 댐수위, 하천 수위 및 강우량 등을 계측하고 있으며, 계측된 값들은 댐을 효과적으로 운영하는데 필요한 데이터로 활용되고 있다. 특히 댐수위 이상 데이터를 탐지하지 못한 채 그대로 사용할 경우 댐의 방류 시기와 방류량 등을 결정하는 중요한 의사결정을 그르칠 수 있으므로 이를 신속히 탐지하는 것이 매우 중요하다. 현재의 자동화된 이상 데이터 탐지방법 중 하나는 현재 데이터가 최댓값과 최솟값을 초과할 때, 다른 하나는 현재 데이터와 일정 시간 동안의 평균값 간의 차이가 관리자가 정한 특정 값을 벗어났을 때를 기준으로 삼고 있다. 전자는 상한과 하한의 초과 여부만 판단하므로 탐지가 쉬우나 정상범위 내에서 발생한 이상 데이터는 탐지가 불가하다. 후자는 관리자의 경험을 통해 판단 조건을 정하기 때문에 객관성이 결여되는 문제가 있다. 특히 방류와 강우가 복합적으로 댐수위에 영향을 미치는 홍수기에 관리자의 경험에 기초한 이상 데이터 판별은 신뢰성의 문제가 있을 수 있다. 따라서 본 연구에서는 기계학습을 최초로 적용하여 이상 데이터를 탐지하고자 하였다. 댐수위, 누적강우량 및 누적방류량 데이터와 댐수위데이터를 가공하여 생성한 댐수위차, 댐수위차평균, 댐수위평균 등 자질들의 다양한 조합을 만든 후 이를 Random Forest, SVM, AdaptiveBoost 및 다층퍼셉트론(MLP) 등과 같은 여러 가지 기계학습모델 등을 통해 이상 데이터를 판별하는 실험(분류)을 하였다. 실험결과 댐수위, 댐수위차, 댐수위-댐수위평균, 누적강우량, 누적방류량 및 댐수위차평균을 사용하였을 때 MLP에서 가장 우수한 성능을 보였다. 이 연구를 통해서 댐수위 이상 데이터를 기계학습의 분류기능을 통해 효과적으로 탐지할 수 있다는 것과 모델의 성능은 실험에 사용한 자질의 수뿐 아니라 자질의 종류에도 큰 영향을 받는다는 것을 알 수 있었다.

• Steel and Composite Structures
• /
• v.46 no.2
• /
• pp.153-173
• /
• 2023

Rectangular concrete-filled steel tubular (RCFST) column, a type of concrete-filled steel tubular (CFST), is widely used in compression members of structures because of its advantages. This paper proposes a robust machine learning-based framework for predicting the ultimate compressive strength of RCFST columns under both concentric and eccentric loading. The gradient boosting neural network (GBNN), an efficient and up-to-date ML algorithm, is utilized for developing a predictive model in the proposed framework. A total of 890 experimental data of RCFST columns, which is categorized into two datasets of concentric and eccentric compression, is carefully collected to serve as training and testing purposes. The accuracy of the proposed model is demonstrated by comparing its performance with seven state-of-the-art machine learning methods including decision tree (DT), random forest (RF), support vector machines (SVM), deep learning (DL), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and categorical gradient boosting (CatBoost). Four available design codes, including the European (EC4), American concrete institute (ACI), American institute of steel construction (AISC), and Australian/New Zealand (AS/NZS) are refereed in another comparison. The results demonstrate that the proposed GBNN method is a robust and powerful approach to obtain the ultimate strength of RCFST columns.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.10
• /
• pp.955-961
• /
• 2010

In this paper, we describe a study of a vehicle detection method based on a Boosting Classifier which uses Histogram of Oriented Gradient (HOG) features and Image Segmentation techniques. An input image is segmented by means of a split and merge algorithm. Then, the two largest segmented regions are removed in order to reduce the search region and speed up processing time. The HOG features are then calculated for each pixel in the search region. In order to detect the vehicle region we used the AdaBoost (adaptive boost) method, which is well known for classifying samples with two classes. To evaluate the performance of the proposed method, 537 training images were used to train and learn the classifier, followed by 500 non-training images to provide the recognition rate. From these experiments we were able to detect the proper image 98.34% of the time for the 500 non-training images. In conclusion, the proposed method can be used for detecting the location of a vehicle in an intelligent vehicle control system.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.39-46
• /
• 2022

As the link between traffic accidents and social and economic losses has been confirmed, there is a growing interest in developing safety policies based on crash data and a need for countermeasures to reduce severe crash outcomes such as severe injuries and fatalities. In this study, we select Daejeon city where the relative proportion of fatal crashes is high, as a case study region and focus on the severity of pedestrian crashes. After a series of data manipulation process, we run machine learning algorithms for the optimal model selection and variable identification. Of nine algorithms applied, AdaBoost and Random Forest (ensemble based ones) outperform others in terms of performance metrics. Based on the results, we identify major influential factors (i.e., the age of pedestrian as 70s or 20s, pedestrian crossing) on pedestrian crashes in Daejeon, and suggest them as measures for reducing severe outcomes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5489-5511
• /
• 2019

The performance of evolutionary algorithms can be seriously weakened when constraints limit the feasible region of the search space. In this paper we present a constrained multi-objective optimization algorithm based on adaptive ε-truncation (ε-T-CMOA) to further improve distribution and convergence of the obtained solutions. First of all, as a novel constraint handling technique, ε-truncation technique keeps an effective balance between feasible solutions and infeasible solutions by permitting some excellent infeasible solutions with good objective value and low constraint violation to take part in the evolution, so diversity is improved, and convergence is also coordinated. Next, an exponential variation is introduced after differential mutation and crossover to boost the local exploitation ability. At last, the improved crowding density method only selects some Pareto solutions and near solutions to join in calculation, thus it can evaluate the distribution more accurately. The comparative results with other state-of-the-art algorithms show that ε-T-CMOA is more diverse than the other algorithms and it gains better in terms of convergence in some extent.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.570-595
• /
• 2017

Robust and perceptually-adaptive image watermarking algorithms have mainly targeted gray-scale images either at the modeling or embedding levels despite the widespread availability of color images. Only few of the existing algorithms are specifically designed for color images where color correlation and perception are constructively exploited. In this paper, a new perceptual and high-capacity color image watermarking solution is proposed based on the extension of Tsui et al. algorithm. The $CIEL^*a^*b^*$ space and the spatio-chromatic Fourier transform (SCFT) are combined along with a perceptual model to hide watermarks in color images where the embedding process reconciles between the conflicting requirements of digital watermarking. The perceptual model, based on an emerging color image model, exploits the non-uniform just-noticeable color difference (NUJNCD) thresholds of the $CIEL^*a^*b^*$ space. Also, spread-spectrum techniques and semi-random low-density parity check codes (SR-LDPC) are used to boost the watermark robustness and capacity. Unlike, existing color-based models, the data hiding capacity of our scheme relies on a game-theoretic model where upper bounds for watermark embedding are derived. Finally, the proposed watermarking solution outperforms existing color-based watermarking schemes in terms of robustness to standard image/color attacks, hiding capacity and imperceptibility.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4347-4366
• /
• 2015

Distinguished with traditional strategies which offload an application's computation to a single server, parallel computation offloading can promote the performance by simultaneously delivering the computation to multiple computing resources around the mobile terminal. However, due to the variability of communication and computation environments, static application component multi-partitioning algorithms are difficult to maintain the optimality of their solutions in time-varying scenarios, whereas, over-frequent algorithm executions triggered by changes of environments may bring excessive algorithm costs. To this end, an adaptive application component mapping algorithm for parallel computation offloading in variable environments is proposed in this paper, which aims at minimizing computation costs and inter-resource communication costs. It can provide the terminal a suitable solution for the current environment with a low incremental algorithm cost. We represent the application component multi-partitioning problem as a graph mapping model, then convert it into a pathfinding problem. A genetic algorithm enhanced by an elite-based immigrants mechanism is designed to obtain the solution adaptively, which can dynamically adjust the precision of the solution and boost the searching speed as transmission and processing speeds change. Simulation results demonstrate that our algorithm can promote the performance efficiently, and it is superior to the traditional approaches under variable environments to a large extent.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.32-38
• /
• 2020

The deployment of geographically distributed wireless sensors has greatly elevated the capability of monitoring structural health in social-overhead capital (SOC) public infrastructures. This paper deals with the utilization of a distributed mobility management (DMM) approach for the deployment of wireless sensing devices in a structural health monitoring system (SHM). Then, a wireless sensing mechanism utilizing low-energy adaptive clustering hierarchy (LEACH)-based clustering algorithm for smart sensors has been analyzed to support the seamless data transmission of structural health information which is essentially important to guarantee public safety. The clustering of smart sensors will be able to provide real-time monitoring of structural health and a filtering algorithm to boost the transmission of critical information over heterogeneous wireless and mobile networks.

• Radiation Oncology Journal
• /
• v.36 no.4
• /
• pp.254-264
• /
• 2018

This article reviewed new trends and controversial issues, including the intensification of chemotherapy and recent brachytherapy (BT) advances, and also reviewed recent consensuses from different societies on the management of locally advanced cervical cancer (LACC). Intensive chemotherapy during and after radiation therapy (RT) was not recommended as a standard treatment due to severe toxicities reported by several studies. The use of positron emission tomography-computed tomography (PET-CT) and magnetic resonance imaging (MRI) for pelvic RT planning has increased the clinical utilization of intensity-modulated radiation therapy (IMRT) for the evaluation of pelvic lymph node metastasis and pelvic bone marrow. Recent RT techniques for LACC patients mainly aim to minimize toxicities by sparing the normal bladder and rectum tissues and shortening the overall treatment time by administering a simultaneous integrated boost for metastatic pelvic lymph node in pelvic IMRT followed by MRI-based image guided adaptive BT.