• Journal of the Korean Institute of Gas
• /
• v.27 no.3
• /
• pp.52-58
• /
• 2023

With the increasing awareness of the importance of carbon neutrality in response to global climate change, the utilization of hydrogen as a carbon-free fuel source is also growing. Hydrogen is commonly used in fuel cells (FC), but it can also be utilized in internal combustion engines (ICE) that are based on combustion. Particularly, ICEs that already have established infrastructure for production and supply can greatly contribute to the expansion of hydrogen energy utilization when it becomes difficult to rely solely on fuel cells or expand their infrastructure. However, a disadvantage of utilizing hydrogen through combustion is the potential generation of nitrogen oxides (NOx), which are harmful emissions formed when nitrogen in the air reacts with oxygen at high temperatures. In particular, for the EURO-7 exhaust regulation, which includes cold start operation, efforts to reduce exhaust emissions during the warm-up process are required. Therefore, in this study, the characteristics of nitrogen oxides and fuel consumption were investigated during the warm-up process of cooling water from room temperature to 88℃ using a 2-liter direct injection spark ignition (SI) engine fueled with hydrogen. One advantage of hydrogen, compared to conventional fuels like gasoline, natural gas, and liquefied petroleum gas (LPG), is its wide flammable range, which allows for sparser control of the excessive air ratio. In this study, the excessive air ratio was varied as 1.6/1.8/2.0 during the warm-up process, and the results were analyzed. The experimental results show that as the excessive air ratio becomes sparser during warm-up, the emission of nitrogen oxides per unit time decreases, and the thermal efficiency relatively increases. However, as the time required to reach the final temperature becomes longer, the cumulative emissions and fuel consumption may worsen.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.1-23
• /
• 2013

To discover significant social issues such as unemployment, economy crisis, social welfare etc. that are urgent issues to be solved in a modern society, in the existing approach, researchers usually collect opinions from professional experts and scholars through either online or offline surveys. However, such a method does not seem to be effective from time to time. As usual, due to the problem of expense, a large number of survey replies are seldom gathered. In some cases, it is also hard to find out professional persons dealing with specific social issues. Thus, the sample set is often small and may have some bias. Furthermore, regarding a social issue, several experts may make totally different conclusions because each expert has his subjective point of view and different background. In this case, it is considerably hard to figure out what current social issues are and which social issues are really important. To surmount the shortcomings of the current approach, in this paper, we develop a prototype system that semi-automatically detects social issue keywords representing social issues and problems from about 1.3 million news articles issued by about 10 major domestic presses in Korea from June 2009 until July 2012. Our proposed system consists of (1) collecting and extracting texts from the collected news articles, (2) identifying only news articles related to social issues, (3) analyzing the lexical items of Korean sentences, (4) finding a set of topics regarding social keywords over time based on probabilistic topic modeling, (5) matching relevant paragraphs to a given topic, and (6) visualizing social keywords for easy understanding. In particular, we propose a novel matching algorithm relying on generative models. The goal of our proposed matching algorithm is to best match paragraphs to each topic. Technically, using a topic model such as Latent Dirichlet Allocation (LDA), we can obtain a set of topics, each of which has relevant terms and their probability values. In our problem, given a set of text documents (e.g., news articles), LDA shows a set of topic clusters, and then each topic cluster is labeled by human annotators, where each topic label stands for a social keyword. For example, suppose there is a topic (e.g., Topic1 = {(unemployment, 0.4), (layoff, 0.3), (business, 0.3)}) and then a human annotator labels "Unemployment Problem" on Topic1. In this example, it is non-trivial to understand what happened to the unemployment problem in our society. In other words, taking a look at only social keywords, we have no idea of the detailed events occurring in our society. To tackle this matter, we develop the matching algorithm that computes the probability value of a paragraph given a topic, relying on (i) topic terms and (ii) their probability values. For instance, given a set of text documents, we segment each text document to paragraphs. In the meantime, using LDA, we can extract a set of topics from the text documents. Based on our matching process, each paragraph is assigned to a topic, indicating that the paragraph best matches the topic. Finally, each topic has several best matched paragraphs. Furthermore, assuming there are a topic (e.g., Unemployment Problem) and the best matched paragraph (e.g., Up to 300 workers lost their jobs in XXX company at Seoul). In this case, we can grasp the detailed information of the social keyword such as "300 workers", "unemployment", "XXX company", and "Seoul". In addition, our system visualizes social keywords over time. Therefore, through our matching process and keyword visualization, most researchers will be able to detect social issues easily and quickly. Through this prototype system, we have detected various social issues appearing in our society and also showed effectiveness of our proposed methods according to our experimental results. Note that you can also use our proof-of-concept system in http://dslab.snu.ac.kr/demo.html.

• Economic and Environmental Geology
• /
• v.8 no.3
• /
• pp.117-124
• /
• 1975

Wet chemical analysis (for $MnO_2$, MnO, and $H_2O$(+)) and electron microprobe analysis (for $Fe_2O_3$ and PbO) give $MnO_2$ 74.91, MnO 11.33, $Fe_2O_3$ (total Fe) 4.19, PbO 0.03, $H_2O$ (+) 9.46, sum 99.92%. 'Available oxygen determined by oxalate titration method is allotted to $MnO_2$ from total Mn, and the remaining Mn is calculated as MnO. Traces of Ba, Ca, Mg, K, Cu, Zn, and Al were found. Li and Na were not found. The existence of (OH) is verified from the infrared absorption spectra. The analysis corresponds to the formula $Mn^{4+}{_{4.85}}(Mn^{2+}{_{0.90}}Fe^{3+}{_{0.30}})_{1.20}O_{8.09}(OH)_{5.91}$, on the basis of O=14, 'or ideally $Mn^{4+}{_{5-x}}(Mn^{2+},Fe^{3+})_{1+x}O_{8}(OH)_{6}$ ($x{\approx}0.2$). X-ray single crystal study could not be made because of the distortion of single crystals. But the x-ray powder pattern is satisfactorily indexed by an orthorhombic cell with a 9.324, b 14.05, c $7.956{\AA}$., Z=4. The indexed powder diffraction lines are 9.34(s) (100), 7.09(s) (020), 4.62(m) (200, 121), 4.17(m) (130), 3.547(s) (112), 3.212(vw) (041), 3.101(s) (300), 2.597(w) (013), 2.469(m) (331), 2.214(vw)(420), 2.098(vw) (260), 2.014 (vw) (402), 1.863(w) (500), 1.664(w) (314), 1.554(vw) (600), 1.525(m) (601), 1.405(m) (0.10.0). DTA curve shows the endothermic peaks at $250-370^{\circ}C$ and $955^{\circ}C$. The former is due to the dehydration: and oxidation forming$(Mn,\;Fe)_2O_3$(cubic, a $9.417{\AA}$), and the latter is interpreted as the formation of a hausmannite-type oxide (tetragonal, a 5.76, c $9.51{\AA}$) from $(Mn,\;Fe)_2O_3$. Infrared absorption spectral curve shows Mn-O stretching vibrations at $515cm^{-1}$ and $545cm^{-1}$, O-H bending vibration at $1025cm^{-1}$ and O-H stretching vibration at $3225cm^{-1}$. Opaque. Reflectance 13-15%. Bireflectance distinct in air and strong in oil. Reflection pleochroism changes from whitish to light grey. Between crossed nicols, color changes from yellowish brown with bluish tint to grey in air and yellowish brown to grey through bluish brown in oil. No internal reflections. Etching reactions: HCl(conc.) and $H_2SO_4+H_2O_2$-grey tarnish; $SnCl_2$(sat.)-dark color; $HNO_3$(conc.)-grey color; $H_2O_2$-tarnish with effervescence. It is black in color. Luster dull. Cleavage one direction perfect. Streak brownish black to dark brown. H. (Mohs) 2-3, very fragile. Specific gravity 3.59(obs.), 3.57(calc.). It occurs as radiating groups of flakes, flower-like aggregates, colloform bands, dendritic or arborescent masses composed of fine grains in the cementation zone of the supergene manganese oxide deposits of the Janggun mine, Bonghwa-gun, southeastern Korea. Associated minerals are calcite, nsutite, todorokite, and some undetermined manganese dioxide minerals. The name is for the mine, the first locality. The mineral and name were approved before publication by the Commission on New Minerals and Mineral Names, I.M.A.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.69-92
• /
• 2015

The explosion of social media data has led to apply text-mining techniques to analyze big social media data in a more rigorous manner. Even if social media text analysis algorithms were improved, previous approaches to social media text analysis have some limitations. In the field of sentiment analysis of social media written in Korean, there are two typical approaches. One is the linguistic approach using machine learning, which is the most common approach. Some studies have been conducted by adding grammatical factors to feature sets for training classification model. The other approach adopts the semantic analysis method to sentiment analysis, but this approach is mainly applied to English texts. To overcome these limitations, this study applies the Word2Vec algorithm which is an extension of the neural network algorithms to deal with more extensive semantic features that were underestimated in existing sentiment analysis. The result from adopting the Word2Vec algorithm is compared to the result from co-occurrence analysis to identify the difference between two approaches. The results show that the distribution related word extracted by Word2Vec algorithm in that the words represent some emotion about the keyword used are three times more than extracted by co-occurrence analysis. The reason of the difference between two results comes from Word2Vec's semantic features vectorization. Therefore, it is possible to say that Word2Vec algorithm is able to catch the hidden related words which have not been found in traditional analysis. In addition, Part Of Speech (POS) tagging for Korean is used to detect adjective as "emotional word" in Korean. In addition, the emotion words extracted from the text are converted into word vector by the Word2Vec algorithm to find related words. Among these related words, noun words are selected because each word of them would have causal relationship with "emotional word" in the sentence. The process of extracting these trigger factor of emotional word is named "Emotion Trigger" in this study. As a case study, the datasets used in the study are collected by searching using three keywords: professor, prosecutor, and doctor in that these keywords contain rich public emotion and opinion. Advanced data collecting was conducted to select secondary keywords for data gathering. The secondary keywords for each keyword used to gather the data to be used in actual analysis are followed: Professor (sexual assault, misappropriation of research money, recruitment irregularities, polifessor), Doctor (Shin hae-chul sky hospital, drinking and plastic surgery, rebate) Prosecutor (lewd behavior, sponsor). The size of the text data is about to 100,000(Professor: 25720, Doctor: 35110, Prosecutor: 43225) and the data are gathered from news, blog, and twitter to reflect various level of public emotion into text data analysis. As a visualization method, Gephi (http://gephi.github.io) was used and every program used in text processing and analysis are java coding. The contributions of this study are as follows: First, different approaches for sentiment analysis are integrated to overcome the limitations of existing approaches. Secondly, finding Emotion Trigger can detect the hidden connections to public emotion which existing method cannot detect. Finally, the approach used in this study could be generalized regardless of types of text data. The limitation of this study is that it is hard to say the word extracted by Emotion Trigger processing has significantly causal relationship with emotional word in a sentence. The future study will be conducted to clarify the causal relationship between emotional words and the words extracted by Emotion Trigger by comparing with the relationships manually tagged. Furthermore, the text data used in Emotion Trigger are twitter, so the data have a number of distinct features which we did not deal with in this study. These features will be considered in further study.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.

• Tuberculosis and Respiratory Diseases
• /
• v.55 no.5
• /
• pp.449-458
• /
• 2003

Background : The poor prognostic factors of far-advanced pulmonary tuberculosis(FAPTB) are lymphocytopenia in the peripheral blood(PB)(< $1,000/mm^3$) and $T_4$-cell count ${\leq}500/mm^3$. However, the cause of PB lymphocytopenia in FAPTB is unclear. The aim of this study was to analyze the lymphocyte proportion and cytokines of the bone marrow(BM) in FAPTB patients with peripheral lymphocytopenia in order to clarify whether the limiting step of the lymphocytopenia occurs in production, differentiation, or circulation. Methods : This study included patients with FAPTB between August 1999 and August 2002 who visited Gachon Medical School Gil Medical Center. The exclusion criteria were old age(${\geq}65years$), cachexia or a low body weight, shock, hematologic diseases, or BM involvement of tuberculosis. The distributions of cells in PB and BM were analyzed and compared to the control group. The interleukin(IL)-2, IL-7, IL-10, TNF-${\alpha}$, Interferon-${\gamma}$, and TGF-${\beta}$ levels in the BM were measured by ELISA. Result : Thirteen patients(male : female=9:4) were included and the mean age was $42{\pm}12$years. The proportion and count of the lymphocytes in the PB were significantly lower in the FAPTB group ($7.4{\pm}3.0%$, $694{\pm}255/mm^3$ vs. $17.5{\pm}5.8%$, $1,377{\pm}436/mm^3$, each p=0.0001 and 0.002). The proportion of immature lymphocyte in the BM showed a decreasing trend in the FAPTB group($9{\pm}4%$ vs. $12{\pm}3%$, p=0.138). The IL-2($26.0{\pm}29.1$ vs. $112.2{\pm}42.4pg/mL$, p=0.001) and IL-10($3.4{\pm}4.7$ vs. $12.0{\pm}8.0pg/mL$, p=0.031) levels in the BM were significantly lower in the FAPTB group than those in control. The levels of the other cytokines in FAPTB group and control were similar. Conclusion : These results suggest that the cause of lymphocytopenia in PB is associated with a abnormality IL-2 and IL-10 production in the BM. More study will be needed to define the mechanism of a decreased reservoir in BM.