• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• The Korean Journal of Nuclear Medicine
• /
• v.39 no.1
• /
• pp.57-68
• /
• 2005

Purpose: The objective of this study was to assess attenuation correction algorithms with the $^{137}Cs$ point source for the brain positron omission tomography (PET) imaging process. Materials & Methods: Four different types of phantoms were used in this study for testing various types of the attenuation correction techniques. Transmission data of a $^{137}Cs$ point source were acquired after infusing the emission source into phantoms and then the emission data were subsequently acquired in 3D acquisition mode. Scatter corrections were performed with a background tail-fitting algorithm. Emission data were then reconstructed using iterative reconstruction method with a measured (MAC), elliptical (ELAC), segmented (SAC) and remapping (RAC) attenuation correction, respectively. Reconstructed images were then both qualitatively and quantitatively assessed. In addition, reconstructed images of a normal subject were assessed by nuclear medicine physicians. Subtracted images were also compared. Results: ELEC, SAC, and RAC provided a uniform phantom image with less noise for a cylindrical phantom. In contrast, a decrease in intensity at the central portion of the attenuation map was noticed at the result of the MAC. Reconstructed images of Jaszack and Hoffan phantoms presented better quality with RAC and SAC. The attenuation of a skull on images of the normal subject was clearly noticed and the attenuation correction without considering the attenuation of the skull resulted in artificial defects on images of the brain. Conclusion: the complicated and improved attenuation correction methods were needed to obtain the better accuracy of the quantitative brain PET images.

• Korean Journal of Remote Sensing
• /
• v.21 no.6
• /
• pp.445-456
• /
• 2005

The land surface parameters should be determined with sufficient accuracy, because these play an important role in climate change near the ground. As the surface reflectance presents strong anisotropy, off-nadir viewing results a strong dependency of observations on the Sun - target - sensor geometry. They contribute to the random noise which is produced by surface angular effects. The principal objective of the study is to provide a database of accurate surface reflectance eliminated the angular effects from MODIS 250m reflective channel data over Korea. The MODIS (Moderate Resolution Imaging Spectroradiometer) sensor has provided visible and near infrared channel reflectance at 250m resolution on a daily basis. The successive analytic processing steps were firstly performed on a per-pixel basis to remove cloudy pixels. And for the geometric distortion, the correction process were performed by the nearest neighbor resampling using 2nd-order polynomial obtained from the geolocation information of MODIS Data set. In order to correct the surface anisotropy effects, this paper attempted the semiempirical kernel-driven Bi- directional Reflectance Distribution Function(BRDF) model. The algorithm yields an inversion of the kernel-driven model to the angular components, such as viewing zenith angle, solar zenith angle, viewing azimuth angle, solar azimuth angle from reflectance observed by satellite. First we consider sets of the model observations comprised with a 31-day period to perform the BRDF model. In the next step, Nadir view reflectance normalization is carried out through the modification of the angular components, separated by BRDF model for each spectral band and each pixel. Modeled reflectance values show a good agreement with measured reflectance values and their RMSE(Root Mean Square Error) was totally about 0.01(maximum=0.03). Finally, we provide a normalized surface reflectance database consisted of 36 images for 2001 over Korea.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.1
• /
• pp.61-77
• /
• 2019

If a new utility tunnel is planned for high density existing urban areas in Korea, a rational decision-making process such as the determination of optimum design capacity by using the feasibility evaluation system based on quantitative evaluation indexes and the economic evaluation is needed. Thus, the previous study presented the important weight of individual higher-level indexes (3 items) and sub-indexes (16 items) through a hierarchy analysis (AHP) for quantitative evaluation index items, considering the characteristics of each urban type. In addition, an economic evaluation method was proposed considering 10 benefit items and 8 cost items by adding 3 new items, including the effects of traffic accidents, noise reduction and socio-economic losses, to the existing items for the benefit cost analysis suitable for urban utility tunnels. This study presented a quantitative feasibility evaluation method using the important weight of 16 sub-index items such as the road management sector, public facilities sector and urban environment sector. Afterwards, the results of quantitative feasibility and economic evaluation were compared and analyzed in 123 main road sections of the Seoul. In addition, a comprehensive evaluation method was proposed by the combination of the two evaluation results. The design capacity optimization program, which will be developed by programming the logic of the quantitative feasibility and economic evaluation system presented in this study, will be utilized in the planning and design phases of urban community zones and will ultimately contribute to the vitalization of urban utility tunnels.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.47-67
• /
• 2017

Steel plate faults is one of important factors to affect the quality and price of the steel plates. So far many steelmakers generally have used visual inspection method that could be based on an inspector's intuition or experience. Specifically, the inspector checks the steel plate faults by looking the surface of the steel plates. However, the accuracy of this method is critically low that it can cause errors above 30% in judgment. Therefore, accurate steel plate faults diagnosis system has been continuously required in the industry. In order to meet the needs, this study proposed a new steel plate faults diagnosis system using Simultaneous MTS (S-MTS), which is an advanced Mahalanobis Taguchi System (MTS) algorithm, to classify various surface defects of the steel plates. MTS has generally been used to solve binary classification problems in various fields, but MTS was not used for multiclass classification due to its low accuracy. The reason is that only one mahalanobis space is established in the MTS. In contrast, S-MTS is suitable for multi-class classification. That is, S-MTS establishes individual mahalanobis space for each class. 'Simultaneous' implies comparing mahalanobis distances at the same time. The proposed steel plate faults diagnosis system was developed in four main stages. In the first stage, after various reference groups and related variables are defined, data of the steel plate faults is collected and used to establish the individual mahalanobis space per the reference groups and construct the full measurement scale. In the second stage, the mahalanobis distances of test groups is calculated based on the established mahalanobis spaces of the reference groups. Then, appropriateness of the spaces is verified by examining the separability of the mahalanobis diatances. In the third stage, orthogonal arrays and Signal-to-Noise (SN) ratio of dynamic type are applied for variable optimization. Also, Overall SN ratio gain is derived from the SN ratio and SN ratio gain. If the derived overall SN ratio gain is negative, it means that the variable should be removed. However, the variable with the positive gain may be considered as worth keeping. Finally, in the fourth stage, the measurement scale that is composed of selected useful variables is reconstructed. Next, an experimental test should be implemented to verify the ability of multi-class classification and thus the accuracy of the classification is acquired. If the accuracy is acceptable, this diagnosis system can be used for future applications. Also, this study compared the accuracy of the proposed steel plate faults diagnosis system with that of other popular classification algorithms including Decision Tree, Multi Perception Neural Network (MLPNN), Logistic Regression (LR), Support Vector Machine (SVM), Tree Bagger Random Forest, Grid Search (GS), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The steel plates faults dataset used in the study is taken from the University of California at Irvine (UCI) machine learning repository. As a result, the proposed steel plate faults diagnosis system based on S-MTS shows 90.79% of classification accuracy. The accuracy of the proposed diagnosis system is 6-27% higher than MLPNN, LR, GS, GA and PSO. Based on the fact that the accuracy of commercial systems is only about 75-80%, it means that the proposed system has enough classification performance to be applied in the industry. In addition, the proposed system can reduce the number of measurement sensors that are installed in the fields because of variable optimization process. These results show that the proposed system not only can have a good ability on the steel plate faults diagnosis but also reduce operation and maintenance cost. For our future work, it will be applied in the fields to validate actual effectiveness of the proposed system and plan to improve the accuracy based on the results.