• Title/Summary/Keyword: Size

Search Result 66,253, Processing Time 0.092 seconds

Taxonomical Classification and Genesis of Jeju Series in Jeju Island (제주도 토양인 제주통의 분류 및 생성)

  • Song, Kwan-Cheol;Hyun, Byung-Geun;Moon, Kyung-Hwan;Jeon, Seung-Jong;Lim, Han-Cheol;Lee, Shin-Chan
    • Korean Journal of Soil Science and Fertilizer
    • /
    • v.43 no.2
    • /
    • pp.230-236
    • /
    • 2010
  • Jeju Island is a volanic island which is located about 96 km south of Korean Peninsula. Volcanic ejecta, and volcaniclastic materials are widespread as soil parent materials throughout the island. Soils on the island have the characteristics of typical volcanic ash soils. This study was conducted to reclassify Jeju series based on the second edition of Soil Taxonomy and to discuss the formation of Jeju series in Jeju Island. Morphological properties of typifying pedon of Jeju series were investigated, and physico-chemical properties were analyzed according to Soil survey laboratory methods manual. The typifying pedon has dark brown (10YR 3/3) silt clay loam A horizon (0~22 cm), strong brown (7.5YR 4/6) silty clay BAt horizon (22~43 cm), brown (7.5YR 4/4) silty clay Bt1 horizon (43~80 cm), brown (7.5YR 4/6) silty clay loamBt2 horizon (80~105 cm), and brown (10YR 5/4) silty clay loam Bt3 horizon (105~150 cm). It is developed in elevated lava plain, and are derived from basalt, and pyroclastic materials. The typifying pedon contains 1.3~2.1% oxalate extractable (Al + 1/2 Fe), less than 85%phosphate retention, and higher bulk density than 0.90 Mg $m^{-3}$. That can not be classified as Andisol. But it has an argillic horizon from a depth of 22 to 150 cm, and a base saturation (sum of cations) of less than 35% at 125 cm below the upper boundary of the argillic horizon. That can be classified as Ultisol, not as Andisol. Its has 0.9% or more organic carbon in the upper 15 cm of the argillic horizon, and can be classified as Humult. It dose not have fragipan, kandic horizon, sombric horizon, plinthite, etc. in the given depths, and key out as Haplohumult. A hoizon (0~22 cm) has a fine-earth fraction with both a bulk density of 1.0 Mg $cm^{-3}$ or less, and Al plus 1/2 Fe percentages (by ammonium oxalate) totaling more than 1.0. Thus, it keys out as Andic Haplohumult. It has 35% or more clay at the particle-size control section, and has thermic soil temperature regime. Jeju series can be classified as fine, mixed, themic family of Andic Haplohumults, not as ashy, thermic family of Typic Hapludands. In the western, and northern coastal areas which have a relatively dry climate in Jeju Island, non Andisols are widely distributed. Mean annual precipitation increase 110 mm, and mean annual temperature decrease $0.8^{\circ}C$ with increasing elevation of 100m. In the western, and northern mid-mountaineous areas Andisols, and non Andisols are distributed simultaneously. Jeju series distributed mainly in the western and northern mid-mountaineous areas are developed as Ultisols with Andic subgroup.

Taxonomical Classification and Genesis of Dongsong Series Distributed on the Lava Plain in Cheolweon (철원 용암류대지 토양인 동송통의 분류 및 생성)

  • Song, Kwan-Cheol;Hyun, Byung-Geun;Sonn, Yeon-Kyu;Zhang, Yong-Seon;Park, Chan-Won;Jang, Byoung-Choon
    • Korean Journal of Soil Science and Fertilizer
    • /
    • v.43 no.2
    • /
    • pp.217-223
    • /
    • 2010
  • This study was conducted to reclassify Dongsong series based on the second edition of Soil Taxonomy and to discuss the formation of Dongsong series distributed on the lava plain at Cheolweon in Korea. Morphological properties of typifying pedon of Dongsong series were investigated, and physico-chemical properties were analyzed according to Soil Survey Laboratory Methods Manual. The typifying pedon of Dongsong series has brown (7.5YR 4/2) silty clay loam Ap horizon (0-16 cm), brown (7.5YR 4/2) silty clay loam BA horizon (16-22 cm), brown (7.5YR 4/2) silty clay Bt1 horizon (22-50 cm), reddish brown (5YR 5/4) silty clay Bt2 horizon (50-92 cm), and brown (7.5YR 4/3) silty clay loam Bt3 horizon (92-120 cm). It occurs on lava plain derived from baslt materials. The typifying pedon has higher bulk density than 0.90 Mg $m^{-3}$. That can not be classified as Andisol. But it has an argillic horizon from a depth of 22 to more than 120 cm, and a base saturation (sum of cations) of less than 35% at 125 cm below the upper boundary of the argillic horizon. It can be classified as Ultisol, not as Andisol or Alfisol. It has aquic conditions for some time in normal years in one or more horizons within 50 cm of the mineral soil surface, redoximorphic features between a depth of 25 cm, and a depth of 40 cm from the mineral soil surface, and redox concentrations, and 50%or more redox depletions with chroma of 2 or less in the matrix within the upper 12.5 cm of the argillic horizon. Therefore it can be classified as Aquult. It has episaturation, and keys out as Epiaquult. It has 50% or more chroma of 3 or more in one or more horizons between a depth of 25 cm from the mineral soil surface, and a depth of 75 cm. It can be classified as Aeric Aquult. Dongsong series have 35%or more clay at the particle-size control section, and have mesic soil temperature regime. Therefore they can be classified as fine, mesic family of Aeric Epiaquults, not as fine, mesic family of Typic Epiaqualfs. The Quarternary volcanic activities occurred in Jeju Island, Ulrung Island, Baekryeong Island, Cheolweon area, and Mt. Paekdu et al. in the Korean Penninsula. Most of them belong to the central eruption type, but Cheolweon area may be of the fissure eruption type. Dongsong series occur on Cheolweon lava plains derived from basaltic materials. Most soils distributed in Jeju Island, and derived from mainly pyroclastics are developed as Andisols. But Dongsong series distributed in Cheolweon lava plains which have a relatively dry climate and derived from basaltic materials are developed as Ultisols.

The Effect of a Bypass Operation for Atherosclerotic Arterial Obstructive Disease at the Lower Extremity (동맥경화성 하지 동맥 폐색증에 대한 우회로 수술의 효과)

  • Choi, Won-Suk;Park, Jae-Min;Lee, Yang-Haeng;Han, Il-Yong;Jun, Hee-Jae;Yoon, Young-Chul;Hwang, Youn-Ho;Cho, Kwang-Hyun
    • Journal of Chest Surgery
    • /
    • v.41 no.5
    • /
    • pp.610-618
    • /
    • 2008
  • Background: There are various treatment modalities for atherosclerotic arterial obstructive disease at the lower limbs, for example, conservative physical therapy, medication, operation etc. Yet it has been established that an arterial bypass operation is the most effective treatment. The aim of this study is to evaluate the effect of arterial bypass operation within our experience and to determine the indicators of treatment. Material and Method: Ninety six patients received arterial bypass operation for atherosclerotic arterial obstructive disease from June 2002 to April 2006. We evaluated the feasibility of arterial bypass operation based on the improvement of symptoms and the ankle-brachial index (ABI) and the surgical outcomes, as based on the complications, the amputation rates and the patency rates. We also assessed the possible risk factors such as gender, age, a smoking history, co-morbidities, the anastomotic sites, the graft size and the graft type. We retrospectively reviewed the medical records of the patients. The total mean follow-up period was $29.4{\pm}13.1$ months. Result: The mean age was $65.95{\pm}9.61$ and there were 88 male patients. The most common clinical manifestation was ischemic resting pain in the lower extremities. The underlying combined diseases were hypertension (61%), diabetes (43%), cardiac problems (35%) and smoking (91.7%). The most frequent site of arterial obstruction was the superficial femoral artery (44 cases, 40%). A femoropopliteal artery bypass operation with a Polytetrafluoroethylene(PTFE) synthetic graft was done in 44 cases (40%) and the great saphenous vein graft was used in 11 cases. The postoperative ABI increased significantly from $0.30{\pm}0.11$ preoperatively to $0.63{\pm}0.11$ (p<0.001) postoperatively. In 8 cases, amputations above the ankle level were necessary. The graft patency rates were 86.4% and 68.0% after 1 and 3 years, respectively. There were 29 cases (30.21%) of patency failure; the male gender, smokers and hypertension were significantly more frequent in the failure group. Of these, hypertension was the most powerful risk factor (p=0.042). Conclusion: The arterial bypass operation is an effective treatment modality for controlling the symptoms such as pain and claudication, and for preventing major amputations for the patients with atherosclerotic arterial obstructive disease. This study suggests quitting smoking, strict blood pressure control, selection of an appropriate graft, regular outpatient follow up and proper medication would offer higher patency rates and more favorable outcomes.

The Hardness Water Production By RO/NF/ED Linking Process From Deep Seawater (RO/NF/ED 연계 공정에 의한 고경도 담수 제조)

  • Moon, Deok-Soo;Kim, Kwang Soo;Gi, Ho;Choi, Mi Yeon;Jung, Hyun Ji;Kim, Hyun Ju
    • Journal of the Korean Society for Marine Environment & Energy
    • /
    • v.16 no.4
    • /
    • pp.227-238
    • /
    • 2013
  • The purpose of this study is to develop a process technology to produce high hardness drinking water which meet drinking water standard, remaining useful minerals like magnesium and calcium in the seawater desalination process while removing the sulfate ions and chloride ions. Seawater have been separated the concentrated seawater and desalted seawater by passing on Reverse Osmosis membrane (RO). Using Nano-filtration membrane (NF), We were prepared primary mineral concentrated water that sodium chloride were not removed. By the operation of electro-dialysis (ED) having ion exchange membrane, we were prepared concentrated mineral water (Mineral enriched desalted water) which the sodium chloride is removed. We have produced the high hardness water to meet the drinking water quality standards by diluting the mineral enriched desalted water with deionized water by RO. Reverse osmosis membranes (RO) can separate dissolved material and freshwater from seawater (deep seawater). The desalination water throughout the second reverse osmosis membrane was completely removed dissolved substances, which dissolved components was removed more than 99.9%, its the hardness concentration was 1 mg/L or less and its chloride concentration was 2.3 mg/L. Since the nano-filtration membrane pore size is $10^{-9}$ m, 50% of magnesium ions and calcium ions can not pass through the nano-filtration membrane, while more than 95% of sodium ions and chloride ions can pass through NF membrane. Nano-filtration membrane could be separated salt components like sodium ion and chloride ions and hardness ingredients like magnesium ions and calcium ions, but their separation was not perfect. Electric dialysis membrane system can be separated single charged ions (like sodium and chloride ions) and double charged ions (like magnesium and calcium ions) depending on its electrical conductivity. Above electrical conductivity 20mS/cm, hardness components (like magnesium and calcium ions) did not removed, on the other hand salt ingredients like sodium and chloride ions was removed continuously. Thus, we were able to concentrate hardness components (like magnesium and calcium ions) using nano-filtration membrane, also could be separated salts ingredients from the hardness concentration water using electrical dialysis membrane system. Finally, we were able to produce a highly concentrated mineral water removed chloride ions, which hardness concentration was 12,600 mg/L and chloride concentration was 2,446 mg/L. By diluting 10 times these high mineral water with secondary RO (Reverse Osmosis) desalination water, we could produce high mineral water suitable for drinking water standards, which chloride concentration was 244 mg/L at the same time hardness concentration 1,260 mg/L. Using the linked process with reverse osmosis (RO)/nano filteration (NF)/electric dialysis (ED), it could be concentrated hardness components like magnesium ions and calcium ions while at the same time removing salt ingredients like chloride ions and sodium ion without heating seawater. Thus, using only membrane as RO, NF and ED without heating seawater, it was possible to produce drinking water containing high hardness suitable for drinking water standard while reducing the energy required to evaporation.

Development of a split beam transducer for measuring fish size distribution (어체 크기의 자동 식별을 위한 split beam 음향 변환기의 재발)

  • 이대재;신형일
    • Journal of the Korean Society of Fisheries and Ocean Technology
    • /
    • v.37 no.3
    • /
    • pp.196-213
    • /
    • 2001
  • A split beam ultrasonic transducer operating at a frequency of 70 kHz to use in the fish sizing echo sounder was developed and the acoustic radiation characteristics were experimentally analyzed. The amplitude shading method utilizing the properties of the Chebyshev polynomials was used to obtain side lobe levels below -20 dB and to optimize the relationship between main beam width and side lobe level of the transducer, and the amplitude shading coefficient to each of the elements was achieved by changing the amplitude contribution of elements with 4 weighting transformers embodied in the planar array transducer assembly. The planar array split beam transducer assembly was composed of 36 piezoelectric ceramics (NEPEC N-21, Tokin) of rod type of 10 mm in diameter and 18.7 mm in length of 70 kHz arranged in the rectangular configuration, and the 4 electrical inputs were supplied to the beamformer. A series of impedance measurements were conducted to check the uniformity of the individual quadrants, and also in the configurations of reception and transmission, resonant frequency, and the transmitting and receiving characteristics were measured in the water tank and analyzed, respectively. The results obtained are summarized as follows : 1. Average resonant and antiresonant frequencies of electrical impedance for four quadrants of the split beam transducer in water were 69.8 kHz and 83.0 kHz, respectively. Average electrical impedance for each individual transducer quadrant was 49.2$\Omega$ at resonant frequency and 704.7$\Omega$ at antiresonant frequency. 2. The resonance peak in the transmitting voltage response (TVR) for four quadrants of the split beam transducer was observed all at 70.0 kHz and the value of TVR was all about 165.5 dB re 1 $\mu$Pa/V at 1 m at 70.0 kHz with bandwidth of 10.0 kHz between -3 dB down points. The resonance peak in the receiving sensitivity (SRT) for four combined quadrants (quad LU+LL, quad RU+RL, quad LU+RU, quad LL+RL) of the split beam transducer was observed all at 75.0 kHz and the value of SRT was all about -177.7 dB re 1 V/$\mu$Pa at 75.0 kHz with bandwidth of 10.0 kHz between -3 dB down points. The sum beam transmitting voltage response and receiving senstivity was 175.0 dB re 1$\mu$Pa/V at 1 m at 75.0 kHz with bandwidth of 10.0 kHz, respectively. 3. The sum beam of split beam transducer was approximately circular with a half beam angle of $9.0^\circ$ at -3 dB points all in both axis of the horizontal plane and the vertical plane. The first measured side lobe levels for the sum beam of split beam transducer were -19.7 dB at $22^\circ$ and -19.4 dB at $-26^\circ$ in the horizontal plane, respectively and -20.1 dB at $22^\circ$ and -22.0 dB at $-26^\circ$ in the vertical plane, respectively. 4. The developed split beam transducer was tested to estimate the angular position of the target in the beam through split beam phase measurements, and the beam pattern loss for target strength corrections was measured and analyzed.

  • PDF

The study of thermal change by chemoport in radiofrequency hyperthermia (고주파 온열치료시 케모포트의 열적 변화 연구)

  • Lee, seung hoon;Lee, sun young;Gim, yang soo;Kwak, Keun tak;Yang, myung sik;Cha, seok yong
    • The Journal of Korean Society for Radiation Therapy
    • /
    • v.27 no.2
    • /
    • pp.97-106
    • /
    • 2015
  • Purpose : This study evaluate the thermal changes caused by use of the chemoport for drug administration and blood sampling during radiofrequency hyperthermia. Materials and Methods : 20cm size of the electrode radio frequency hyperthermia (EHY-2000, Oncotherm KFT, Hungary) was used. The materials of the chemoport in our hospital from currently being used therapy are plastics, metal-containing epoxy and titanium that were made of the diameter 20 cm, height 20 cm insertion of the self-made cylindrical Agar phantom to measure the temperature. Thermoscope(TM-100, Oncotherm Kft, Hungary) and Sim4Life (Ver2.0, Zurich, Switzerland) was compared to the actual measured temperature. Each of the electrode measurement position is the central axis and the central axis side 1.5 cm, 0 cm(surface), 0.5 cm, 1.8 cm, 2.8 cm in depth was respectively measured. The measured temperature is $24.5{\sim}25.5^{\circ}C$, humidity is 30% ~ 32%. In five-minute intervals to measure the output power of 100W, 60 min. Results : In the electrode central axis 2.8 cm depth, the maximum temperature of the case with the unused of the chemoport, plastic, epoxy and titanium were respectively $39.51^{\circ}C$, $39.11^{\circ}C$, $38.81^{\circ}C$, $40.64^{\circ}C$, simulated experimental data were $42.20^{\circ}C$, $41.50^{\circ}C$, $40.70^{\circ}C$, $42.50^{\circ}C$. And in the central axis electrode side 1.5 cm depth 2.8 cm, mesured data were $39.37^{\circ}C$, $39.32^{\circ}C$, $39.20^{\circ}C$, $39.46^{\circ}C$, the simulated experimental data were $42.00^{\circ}C$, $41.80^{\circ}C$, $41.20^{\circ}C$, $42.30^{\circ}C$. Conclusion : The thermal variations were caused by radiofrequency electromagnetic field surrounding the chemoport showed lower than in the case of unused in non-conductive plastic material and epoxy material, the titanum chemoport that made of conductor materials showed a slight differences. This is due to the metal contents in the chemoport and the geometry of the chemoport. And because it uses a low radio frequency bandwidth of the used equipment. That is, although use of the chemoport in this study do not significantly affect the surrounding tissue. That is, because the thermal change is insignificant, it is suggested that the hazard of the chemoport used in this study doesn't need to be considered.

  • PDF

A study of usefulness for the plan based on only MRI using ViewRay MRIdian system (ViewRay MRIdian System을 이용한 MRI only based plan의 유용성 고찰)

  • Jeon, Chang Woo;Lee, Ho Jin;An, Beom Seok;Kim, Chan young;Lee, Je hee
    • The Journal of Korean Society for Radiation Therapy
    • /
    • v.27 no.2
    • /
    • pp.131-143
    • /
    • 2015
  • Purpose : By comparing a CT fusion plan based on MRI with a plan based on only MRI without CT, we intended to study usefulness of a plan based on only MRI. And furthermore, we intended to realize a realtime MR-IGRT by MRI image without CT scan during the course of simulation, treatment planning, and radiation treatment. Materials and Methods : BBB CT (Brilliance Big Bore CT, 16slice, Philips), Viewray MRIdian system (Viewray, USA) were used for CT & MR simulation and Treatment plan of 11 patients (1 Head and Neck, 5 Breast, 1 Lung, 3 Liver, 1 Prostate). When scanning for treatment, Free Breathing was enacted for Head&Neck, Breast, Prostate and Inhalation Breathing Holding for Lung and Liver. Considering the difference of size between CT and Viewray, the patient's position and devices were in the same condition. Using Viewray MRIdian system, two treatment plans were established. The one was CT fusion treatment plan based on MR image. Another was MR treatment plan including electron density that [ICRU 46] recommend for Lung, Air and Bone. For Head&Neck, Breast and Prostate, IMRT was established and for Lung and Liver, Gating treatment plan was established. PTV's Homogeneity Index(HI) and Conformity Index(CI) were use to estimate the treatment plan. And DVH and dose difference of each PTV and OAR were compared to estimate the treatment plan. Results : Between the two treatment plan, each difference of PTV's HI value is 0.089% (Head&Neck), 0.26% (Breast), 0.67% (Lung), 0.2% (Liver), 0.4% (Prostate) and in case of CI, 0.043% (Head&Neck), 0.84% (Breast), 0.68% (Lung), 0.46% (Liver), 0.3% (Prostate). As showed above, it is on Head&Neck that HI and CI's difference value is smallest. Each difference of average dose on PTV is 0.07 Gy (Head&Neck), 0.29 Gy (Breast), 0.18 Gy (Lung), 0.3 Gy (Liver), 0.18 Gy (Prostate). And by percentage, it is 0.06% (Head&Neck), 0.7% (Breast), 0.29% (Lung), 0.69% (Liver), 0.44% (Prostate). Likewise, All is under 1%. In Head&Neck, average dose difference of each OAR is 0.01~0.12 Gy, 0.04~0.06 Gy in Breast, 0.01~0.21 Gy in Lung, 0.06~0.27 Gy in Liver and 0.02~0.23 Gy in Prostate. Conclusion : PTV's HI, CI dose difference on the Treatment plan using MR image is under 1% and OAR's dose difference is maximum 0.89 Gy as heterogeneous tissue increases when comparing with that fused CT image. Besides, It characterizes excellent contrast in soft tissue. So, radiation therapy using only MR image without CT scan is useful in the part like Head&Neck, partial breast and prostate cancer which has a little difference of heterogeneity.

  • PDF

The Effect of Retailer-Self Image Congruence on Retailer Equity and Repatronage Intention (자아이미지 일치성이 소매점자산과 고객의 재이용의도에 미치는 영향)

  • Han, Sang-Lin;Hong, Sung-Tai;Lee, Seong-Ho
    • Journal of Distribution Research
    • /
    • v.17 no.2
    • /
    • pp.29-62
    • /
    • 2012
  • As distribution environment is changing rapidly and competition is more intensive in the channel of distribution, the importance of retailer image and retailer equity is increasing as a different competitive advantages. Also, consumers are not functionally oriented and that their behavior is significantly affected by the symbols such as retailer image which identify retailer in the market place. That is, consumers do not choose products or retailers for their material utilities but consume the symbolic meaning of those products or retailers as expressed in their self images. The concept of self-image congruence has been utilized by marketers and researchers as an aid in better understanding how consumers identify themselves with the brands they buy and the retailer they patronize. Although self-image congruity theory has been tested across many product categories, the theory has not been tested extensively in the retailing. Therefore, this study attempts to investigate the impact of self image congruence between retailer image and self image of consumer on retailer equity such as retailer awareness, retailer association, perceived retailer quality, and retailer loyalty. The purpose of this study is to find out whether retailer-self image congruence can be a new antecedent of retailer equity. In addition, this study tries to examine how four-dimensional retailer equity constructs (retailer awareness, retailer association, perceived retailer quality, and retailer loyalty) affect customers' repatronage intention. For this study, data were gathered by survey and analyzed by structural equation modeling. The sample size in the present study was 254. The reliability of the all seven dimensions was estimated with Cronbach's alpha, composite reliability values and average variance extracted values. We determined whether the measurement model supports the convergent validity and discriminant validity by Exploratory factor analysis and Confirmatory Factor Analysis. For each pair of constructs, the square root of the average variance extracted values exceeded their correlations, thus supporting the discriminant validity of the constructs. Hypotheses were tested using the AMOS 18.0. As expected, the image congruence hypotheses were supported. The greater the degree of congruence between retailer image and self-image, the more favorable were consumers' retailer evaluations. The all two retailer-self image congruence (actual self-image congruence and ideal self-image congruence) affected customer based retailer equity. This result means that retailer-self image congruence is important cue for customers to estimate retailer equity. In other words, consumers are often more likely to prefer products and retail stores that have images similar to their own self-image. Especially, it appeared that effect for the ideal self-image congruence was consistently larger than the actual self-image congruence on the retailer equity. The results mean that consumers prefer or search for stores that have images compatible with consumer's perception of ideal-self. In addition, this study revealed that customers' estimations toward customer based retailer equity affected the repatronage intention. The results showed that all four dimensions (retailer awareness, retailer association, perceived retailer quality, and retailer loyalty) had positive effect on the repatronage intention. That is, management and investment to improve image congruence between retailer and consumers' self make customers' positive evaluation of retailer equity, and then the positive customer based retailer equity can enhance the repatonage intention. And to conclude, retailer's image management is an important part of successful retailer performance management, and the retailer-self image congruence is an important antecedent of retailer equity. Therefore, it is more important to develop and improve retailer's image similar to consumers' image. Given the pressure to provide increased image congruence, it is not surprising that retailers have made significant investments in enhancing the fit between retailer image and self image of consumer. The enhancing such self-image congruence may allow marketers to target customers who may be influenced by image appeals in advertising.

  • PDF

A Study of 'Emotion Trigger' by Text Mining Techniques (텍스트 마이닝을 이용한 감정 유발 요인 'Emotion Trigger'에 관한 연구)

  • An, Juyoung;Bae, Junghwan;Han, Namgi;Song, Min
    • 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.

A Time Series Graph based Convolutional Neural Network Model for Effective Input Variable Pattern Learning : Application to the Prediction of Stock Market (효과적인 입력변수 패턴 학습을 위한 시계열 그래프 기반 합성곱 신경망 모형: 주식시장 예측에의 응용)

  • Lee, Mo-Se;Ahn, Hyunchul
    • 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.