• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.166-174
• /
• 2021

A large volume of patient data is generated from various devices used in healthcare applications. With increase in the volume of data generated in the healthcare industry, more wellness monitoring is required. A cloud-enabled analysis of healthcare data that predicts patient risk factors is required. Machine learning techniques have been developed to address these medical care problems. A novel technique called the radix-trie-based Tanimoto kernel regressive infomax boost classification (RT-TKRIBC) technique is introduced to analyze the heterogeneous health data in the cloud to predict the health risks and send alerts. The infomax boost ensemble technique improves the prediction accuracy by finding the maximum mutual information, thereby minimizing the mean square error. The performance evaluation of the proposed RT-TKRIBC technique is realized through extensive simulations in the cloud environment, which provides better prediction accuracy and less prediction time than those provided by the state-of-the-art methods.

• East Asian Economic Review
• /
• v.25 no.4
• /
• pp.403-424
• /
• 2021

AdaBoost tweaks the sample weight for each training set used in the iterative process, however, it is demonstrated that it provides more correlated errors as the boosting iteration proceeds if models' accuracy is high enough. Therefore, in this study, we propose a novel way to improve the performance of the existing AdaBoost algorithm by employing heterogeneous models and a stochastic twist. By employing the heterogeneous ensemble, it ensures different models that have a different initial assumption about the data are used to improve on diversity. Also, by using a stochastic algorithm with a decaying convergence rate, the model is designed to balance out the trade-off between model prediction performance and model convergence. The result showed that the stochastic algorithm with decaying convergence rate's did have a improving effect and outperformed other existing boosting techniques.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.789-816
• /
• 2019

Text classification is a challenging task, especially when dealing with a huge amount of text data. The performance of a classification model can be varied depending on what type of words contained in the document corpus and what type of features generated for classification. Aside from proposing a new modified version of the existing algorithm or creating a new algorithm, we attempt to modify the use of data. The classifier performance is usually affected by the quality of learning data as the classifier is built based on these training data. We assume that the data from different domains might have different characteristics of noise, which can be utilized in the process of learning the classifier. Therefore, we attempt to enhance the robustness of the classifier by injecting the heterogeneous data artificially into the learning process in order to improve the classification accuracy. Semi-supervised approach was applied for utilizing the heterogeneous data in the process of learning the document classifier. However, the performance of document classifier might be degraded by the unlabeled data. Therefore, we further proposed an algorithm to extract only the documents that contribute to the accuracy improvement of the classifier.

• The Korean Journal of Applied Statistics
• /
• v.35 no.1
• /
• pp.49-62
• /
• 2022

Realized volatility is well known to have long memory, strong association with other global financial markets and interdependences among macroeconomic indices such as exchange rate, oil price and interest rates. This paper proposes autoencoder factor-augmented heterogeneous autoregressive (AE-FAHAR) model for realized volatility forecasting. AE-FAHAR incorporates long memory using HAR structure, and exogenous variables into few factors summarized by autoencoder. Autoencoder requires intensive calculation due to its nonlinear structure, however, it is more suitable to summarize complex, possibly nonstationary high-dimensional time series. Our AE-FAHAR model is shown to have smaller out-of-sample forecasting error in empirical analysis. We also discuss pre-training, ensemble in autoencoder to reduce computational cost and estimation errors.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.64-69
• /
• 2015

Place awareness is an essential for location-based services that are widely provided to smartphone users. However, traditional GPS-based methods are only valid outdoors where the GPS signal is strong and also require symbolic place information of the physical location. In this paper, environmental sounds and images are used to recognize important aspects of each place. The proposed method extracts feature vectors from visual, auditory and location data recorded by a smartphone with built-in camera, microphone and GPS sensors modules. The heterogeneous feature vectors were then learned by an ensemble learning method that learns each group of feature vectors for each classifier respectively and votes to produce the highest weighted result. The proposed method is evaluated for place recognition using a data group of 3000 samples in six places and the experimental results show a remarkably improved recognition accuracy when using all kinds of sensory data comparing to results using data from a single sensor or audio-visual integrated data only.

• Bulletin of the Korean Chemical Society
• /
• v.33 no.8
• /
• pp.2553-2559
• /
• 2012

The adsorption properties of benzene, toluene, p-xylene in MCM-41 with heterogeneous and cylindrical pore were studied using grand canonical ensemble Monte Carlo simulation. The simulated isotherms were compared with experimental ones, and the different adsorption behaviors in MCM-41 with pore diameters of 2.2 and 3.2 nm were investigated. The simulated adsorption amounts above the capillary-condensation pressure agreed with the experimental ones. The simulation results showed that most molecular planes were nearly parallel to the pore axis. This orientation was not affected by the molecular position in the pore. The molecular planes were nearly parallel to the pore surface for the adsorbate molecules close to the pore wall, and the molecules in the MCM-41 with the pore diameter of 3.2 nm were ordered along the pore axis.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.19-29
• /
• 2003

This paper presents a novel hybrid classifier for face recognition with artificially generated virtual training samples. We utilize both the nearest neighbor approach in feature angle space and a connectionist model to obtain a synergy effect by combining the results of two heterogeneous classifiers. First, a classifier called the nearest feature angle (NFA), based on angular information, finds the most similar feature to the query from a given training set. Second, a classifier has been developed based on the recall of stored frontal projection of the query feature. It uses a frontal recall network (FRN) that finds the most similar frontal one among the stored frontal feature set. For FRN, we used an ensemble neural network consisting of multiple multiplayer perceptrons (MLPs), each of which is trained independently to enhance generalization capability. Further, both classifiers used the virtual training set generated adaptively, according to the spatial distribution of each person's training samples. Finally, the results of the two classifiers are combined to comprise the best matching class, and a corresponding similarit measure is used to make the final decision. The proposed classifier achieved an average classification rate of 96.33% against a large group of different test sets of images, and its average error rate is 61.5% that of the nearest feature line (NFL) method, and achieves a more robust classification performance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.16-18
• /
• 2006

데이터마이닝 기법의 클러스터링 알고리즘은 생물정보학에서 데이터 셋의 사전 정보를 고려하지 않고 중요한 유전적, 생물학적 상호작용을 찾기 위하여 적용되고 있다. 그러나 다양한 형식의 수많은 알고리즘들은 바이오데이터의 다양한 특성들과 실험의 가정 때문에 다른 클러스터링 결과들을 만들 수 있다. 본 논문에서는 바이오 데이터 셋의 특성에도 적합하면서 양질의 클러스터링 결과를 만들기 위한 새로운 방법을 제안한다. 이 방법은 여러 가지 클러스터링 알고리즘의 결과들을 유전자 알고리즘의 기본 개념인 진화적 환경에서 가장 적합한 형질을 선택하는 문제와 결합하였다. 그리고 실제 데이터 셋을 이용하여 우리의 제안하는 방법을 증명하고 실험 결과로 최적의 클러스터 결과를 보인다.

• The Journal of Engineering Geology
• /
• v.15 no.3
• /
• pp.245-255
• /
• 2005

Three dimensional Monte-Carlo simulations of non-ergodic transport of a non-reactive solute plume by steady-state groundwater flow under a uniform mean velocity in isotropic heterogeneous aquifers were conducted. The log-normally distributed hydraulic conductivity, K(x), is modeled as a random field. Significant efforts are made to reduce the simulation uncertainties. Ensemble averages of the second spatial moments of the plume, $$lt;S_{ij}'(t',l')$gt;$ and plume centroid variances, $$lt;R_{ij}'(t',l')$gt;$ were simulated with 3200 Monte Carlo runs for three variances of log K, $\omega^2_y1.0,,2.5,$ and 5.0, and three dimensionless lengths of line plume sources ( l=,5 and 10) normal to the mean velocity. The simulated second spatial moment and the plume centroid variance in longitudinal direction fit well to the first order theoretical results while the simulated transverse moments are not fit well with the first order results. The first order theoretical results definitely underestimated the simulated transverse second spatial moments for the aquifers of large u: and small initial plume sources. The ergodic condition for the second spatial moments is far from reaching, and the first order theoretical results of the transverse second spatial moment of the ergodic plume slightly underestimated the simulated moments.

• Journal of Soil and Groundwater Environment
• /
• v.10 no.6
• /
• pp.20-31
• /
• 2005

Three dimensional Monte-Carlo simulations of non-ergodic transport of a lion-reactive solute plume by steady-state groundwater flow under a uniform mean velocity in isotropic heterogeneous aquifers were conducted. The log-normally distributed hydraulic conductivity, K(x), is modeled as a random field. Significant efforts are made to reduce tile simulation uncertainties. Ensemble averages of the second spatial moments of the plume and plume centroid variances were simulated with 1600 Monte Carlo runs for three variances of log K, ${\sigma}_Y^2=0.09,\;0.23$, and 0.46, and three dimensionless lengths of line plume sources normal to the mean velocity. The simulated second spatial moment and the plume centroid variance in longitudinal direction fit well to the first order theoretical results while the simulated transverse moments are generally larger than the first order results. The first order theoretical results significantly underestimated the simulated dimensionless transverse moments for the aquifers of large ${\sigma}_Y^2$ and large dimensionless time. The ergodic condition for the second spatial moments is far from reaching in all cases simulated, and transport In transverse directions may reach ergodic condition much slower than that in longitudinal direction. The evolution of the contaminant transported in a heterogeneous aquifer is not affected by the shape of the initial plume but affected mainly by the degree of the heterogeneity and the size of the initial plume.