• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.95-110
• /
• 2013

Recently, the amount of unstructured data being generated through a variety of social media has been increasing rapidly, resulting in the increasing need to collect, store, search for, analyze, and visualize this data. This kind of data cannot be handled appropriately by using the traditional methodologies usually used for analyzing structured data because of its vast volume and unstructured nature. In this situation, many attempts are being made to analyze unstructured data such as text files and log files through various commercial or noncommercial analytical tools. Among the various contemporary issues dealt with in the literature of unstructured text data analysis, the concepts and techniques of opinion mining have been attracting much attention from pioneer researchers and business practitioners. Opinion mining or sentiment analysis refers to a series of processes that analyze participants' opinions, sentiments, evaluations, attitudes, and emotions about selected products, services, organizations, social issues, and so on. In other words, many attempts based on various opinion mining techniques are being made to resolve complicated issues that could not have otherwise been solved by existing traditional approaches. One of the most representative attempts using the opinion mining technique may be the recent research that proposed an intelligent model for predicting the direction of the stock index. This model works mainly on the basis of opinions extracted from an overwhelming number of economic news repots. News content published on various media is obviously a traditional example of unstructured text data. Every day, a large volume of new content is created, digitalized, and subsequently distributed to us via online or offline channels. Many studies have revealed that we make better decisions on political, economic, and social issues by analyzing news and other related information. In this sense, we expect to predict the fluctuation of stock markets partly by analyzing the relationship between economic news reports and the pattern of stock prices. So far, in the literature on opinion mining, most studies including ours have utilized a sentiment dictionary to elicit sentiment polarity or sentiment value from a large number of documents. A sentiment dictionary consists of pairs of selected words and their sentiment values. Sentiment classifiers refer to the dictionary to formulate the sentiment polarity of words, sentences in a document, and the whole document. However, most traditional approaches have common limitations in that they do not consider the flexibility of sentiment polarity, that is, the sentiment polarity or sentiment value of a word is fixed and cannot be changed in a traditional sentiment dictionary. In the real world, however, the sentiment polarity of a word can vary depending on the time, situation, and purpose of the analysis. It can also be contradictory in nature. The flexibility of sentiment polarity motivated us to conduct this study. In this paper, we have stated that sentiment polarity should be assigned, not merely on the basis of the inherent meaning of a word but on the basis of its ad hoc meaning within a particular context. To implement our idea, we presented an intelligent investment decision-support model based on opinion mining that performs the scrapping and parsing of massive volumes of economic news on the web, tags sentiment words, classifies sentiment polarity of the news, and finally predicts the direction of the next day's stock index. In addition, we applied a domain-specific sentiment dictionary instead of a general purpose one to classify each piece of news as either positive or negative. For the purpose of performance evaluation, we performed intensive experiments and investigated the prediction accuracy of our model. For the experiments to predict the direction of the stock index, we gathered and analyzed 1,072 articles about stock markets published by "M" and "E" media between July 2011 and September 2011.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

• Journal of Korean Society of Forest Science
• /
• v.33 no.1
• /
• pp.33-58
• /
• 1977

A bark comprises about 10 to 20 percents of a typical log by volume, and is generally considered as an unwanted residue rather than a potentially valuable resourses. As the world has been confronted with decreasing forest resources, natural resources pressure dictate that a bark should be a raw material instead of a waste. The utilization of the largely wasted bark of genus Pinus, Quercus, and Populus grown in Korea can be enhanced by learning its physical and mechanical properties. However, the study of tree bark grown in Korea have never been undertaken. In the present paper, an investigative study is carried out on the bark of three genus, eleven species representing not only the major bark trees but major species currently grown in Korea. For each species 20 trees were selected, at Suweon and Kwang-neung areas, on the same basis of the diameter class at the proper harvesting age. One $200cm^2$ segment of bark was obtained from each tree at brest height. Physical properties of bark studied are: bark density, moisture content of green bark (inner-, outer-, and total-bark), fiber saturation point, hysteresis loop, shrinkage, water absorption, specific heat, heat of wetting, thermal conductivity, thermal diffusivity, heat of combustion, and differential thermal analysis. The mechanical properties are studied on bending and compression strength (radial, longitudinal, and tangential). The results may be summarized as follows: 1. The oven-dry specific gravities differ between wood and bark, further more even for a given bark sample, the difference is obersved between inner and outer bark. 2. The oven-dry specific gravity of bark is higher than that of wood. This fact is attributed to the anatomical structure whose characters are manifested by higher content of sieve fiber and sclereids. 3. Except Pinus koraiensis, the oven-dry specific gravity of inner bark is higher than that of outer bark, which results from higher shrinkage of inner bark. 4. The moisture content of bark increases with direct proportion to the composition ratio of sieve components and decreases with higher percent of sclerenchyma and periderm tissues. 5. The possibility of determining fiber saturation point is suggested by the measuring the heat of wetting. With the proposed method, the fiber saturation point of Pinus densiflora lies between 26 and 28%, that of Quercus accutissima ranges from 24 to 28%. These results need be further examined by other methods. 6. Contrary to the behavior of wood, the bark shrinkage is the highest in radial direction and the lowest in longitudinal direction. Quercus serrata and Q. variabilis do not fall in this category. 7. Bark shows the same specific heat as wood, but the heat of wetting of bark is higher than that of wood. In heat conductivity, bark is lower than wood. From the measures of oven-dry specific gravity (${\rho}d$) and moisture fraction specific gravity (${\rho}m$) is devised the following regression equation upon which heat conductivity can be calculated. The calculated heat conductivity of bark is between $0.8{\times}10^{-4}$ and $1.6{\times}10^{-4}cal/cm-sec-deg$. $$K=4.631+11.408{\rho}d+7.628{\rho}m$$ 8. The bark heat diffusivity varies from $8.03{\times}10^{-4}$ to $4.46{\times}10^{-4}cm^2/sec$. From differential thermal analysis, wood shows a higher thermogram than bark under ignition point, but the tendency is reversed above ignition point. 9. The modulus of rupture for static bending strength of bark is proportional to the density of bark which in turn gives the following regression equation. M=243.78X-12.02 The compressive strength of bark is the highest in radial direction, contrary to the behavior of wood, and the compressive strength of longitudinal direction follows the tangential one in decreasing order.

• Radiation Oncology Journal
• /
• v.22 no.4
• /
• pp.237-246
• /
• 2004

Purpose: To investigate the effects of radiation dose-escalation on the treatment outcome, complications and the other prognostic variables for glioblastoma patients treated with 3D-conformal radiotherapy (3D-CRT). Materials and Methods: Between Jan 1997 and July 2002, a total of 75 patients with histologically proven diagnosis of glioblastoma were analyzed. The patients who had a Karnofsky Performance Score (KPS) of 60 or higher, and received at least 50 Gy of radiation to the tumor bed were eligible. All the patients were divided into two arms; Arm 1, the high-dose group was enrolled prospectively, and Arm 2, the low-dose group served as a retrospective control. Arm 1 patients received $63\~70$ Gy (Median 66 Gy, fraction size $1.8\~2$ Gy) with 3D-conformal radiotherapy, and Arm 2 received 59.4 Gy or less (Median 59.4 Gy, fraction size 1.8 Gy) with 2D-conventional radiotherapy. The Gross Tumor Volume (GTV) was defined by the surgical margin and the residual gross tumor on a contrast enhanced MRI. Surrounding edema was not included in the Clinical Target Volume (CTV) in Arm 1, so as to reduce the risk of late radiation associated complications; whereas as in Arm 2 it was included. The overall survival and progression free survival times were calculated from the date of surgery using the Kaplan-Meier method. The time to progression was measured with serial neurologic examinations and MRI or CT scans after RT completion. Acute and late toxicities were evaluated using the Radiation Therapy Oncology Group neurotoxicity scores. Results: During the relatively short follow up period of 14 months, the median overall survival and progression free survival times were $15{\pm}1.65$ and $11{\pm}0.95$ months, respectively. The was a significantly longer survival time for the Arm 1 patients compared to those in Arm 2 (p=0.028). For Arm 1 patients, the median survival and progression free survival times were $21{\pm}5.03$ and $12{\pm}1.59$ months, respectively, while for Arm 2 patients they were $14{\pm}0.94$ and $10{\pm}1.63$ months, respectively. Especially in terms of the 2-year survival rate, the high-dose group showed a much better survival time than the low-dose group; $44.7\%$ versus $19.2\%$. Upon univariate analyses, age, performance status, location of tumor, extent of surgery, tumor volume and radiation dose group were significant factors for survival. Multivariate analyses confirmed that the impact of radiation dose on survival was independent of age, performance status, extent of surgery and target volume. During the follow-up period, complications related directly with radiation, such as radionecrosis, has not been identified. Conclusion: Using 3D-conformal radiotherapy, which is able to reduce the radiation dose to normal tissues compared to 2D-conventional treatment, up to 70 Gy of radiation could be delivered to the GTV without significant toxicity. As an approach to intensify local treatment, the radiation dose escalation through 3D-CRT can be expected to increase the overall and progression free survival times for patients with glioblastomas.