• Title/Summary/Keyword: Model-test

Search Result 20,591, Processing Time 0.059 seconds

A Study on Analyzing Sentiments on Movie Reviews by Multi-Level Sentiment Classifier (영화 리뷰 감성분석을 위한 텍스트 마이닝 기반 감성 분류기 구축)

  • Kim, Yuyoung;Song, Min
    • Journal of Intelligence and Information Systems
    • /
    • v.22 no.3
    • /
    • pp.71-89
    • /
    • 2016
  • Sentiment analysis is used for identifying emotions or sentiments embedded in the user generated data such as customer reviews from blogs, social network services, and so on. Various research fields such as computer science and business management can take advantage of this feature to analyze customer-generated opinions. In previous studies, the star rating of a review is regarded as the same as sentiment embedded in the text. However, it does not always correspond to the sentiment polarity. Due to this supposition, previous studies have some limitations in their accuracy. To solve this issue, the present study uses a supervised sentiment classification model to measure a more accurate sentiment polarity. This study aims to propose an advanced sentiment classifier and to discover the correlation between movie reviews and box-office success. The advanced sentiment classifier is based on two supervised machine learning techniques, the Support Vector Machines (SVM) and Feedforward Neural Network (FNN). The sentiment scores of the movie reviews are measured by the sentiment classifier and are analyzed by statistical correlations between movie reviews and box-office success. Movie reviews are collected along with a star-rate. The dataset used in this study consists of 1,258,538 reviews from 175 films gathered from Naver Movie website (movie.naver.com). The results show that the proposed sentiment classifier outperforms Naive Bayes (NB) classifier as its accuracy is about 6% higher than NB. Furthermore, the results indicate that there are positive correlations between the star-rate and the number of audiences, which can be regarded as the box-office success of a movie. The study also shows that there is the mild, positive correlation between the sentiment scores estimated by the classifier and the number of audiences. To verify the applicability of the sentiment scores, an independent sample t-test was conducted. For this, the movies were divided into two groups using the average of sentiment scores. The two groups are significantly different in terms of the star-rated scores.

A Comparative Study on the Effective Deep Learning for Fingerprint Recognition with Scar and Wrinkle (상처와 주름이 있는 지문 판별에 효율적인 심층 학습 비교연구)

  • Kim, JunSeob;Rim, BeanBonyka;Sung, Nak-Jun;Hong, Min
    • Journal of Internet Computing and Services
    • /
    • v.21 no.4
    • /
    • pp.17-23
    • /
    • 2020
  • Biometric information indicating measurement items related to human characteristics has attracted great attention as security technology with high reliability since there is no fear of theft or loss. Among these biometric information, fingerprints are mainly used in fields such as identity verification and identification. If there is a problem such as a wound, wrinkle, or moisture that is difficult to authenticate to the fingerprint image when identifying the identity, the fingerprint expert can identify the problem with the fingerprint directly through the preprocessing step, and apply the image processing algorithm appropriate to the problem. Solve the problem. In this case, by implementing artificial intelligence software that distinguishes fingerprint images with cuts and wrinkles on the fingerprint, it is easy to check whether there are cuts or wrinkles, and by selecting an appropriate algorithm, the fingerprint image can be easily improved. In this study, we developed a total of 17,080 fingerprint databases by acquiring all finger prints of 1,010 students from the Royal University of Cambodia, 600 Sokoto open data sets, and 98 Korean students. In order to determine if there are any injuries or wrinkles in the built database, criteria were established, and the data were validated by experts. The training and test datasets consisted of Cambodian data and Sokoto data, and the ratio was set to 8: 2. The data of 98 Korean students were set up as a validation data set. Using the constructed data set, five CNN-based architectures such as Classic CNN, AlexNet, VGG-16, Resnet50, and Yolo v3 were implemented. A study was conducted to find the model that performed best on the readings. Among the five architectures, ResNet50 showed the best performance with 81.51%.

Experimental Study for Confirmation of Relaxation Zone in the Underground Cavity Expansion (지중 내 공동 확장에 따른 이완영역 확인을 위한 실험적 연구)

  • Kim, Youngho;Kim, Hoyeon;Kim, Yeonsam;You, Seung-Kyong;Han, Jung-Geun
    • Journal of the Korean Geosynthetics Society
    • /
    • v.16 no.4
    • /
    • pp.231-240
    • /
    • 2017
  • Recently, there have been frequent occurrences of ground sink in the urban area, which have resulted in human and material damage and are accompanied by economic losses. This is caused by artificial factors such as soil loss, poor compaction, horizontal excavation due to the breakage of the aged sewage pipe, and lack of water proof at vertical excavation. The ground sink can be prevented by preliminary restoration and reinforcement through exploration, but it can be considered that it is not suitable for urgent restoration by the existing method. In this study, a model experiment was carried out to simulate the in-ground cavities caused by groundwater flow for developing non-excavation urgent restoration in underground cavity and the range of the relaxation zone was estimated by detecting the around the cavity using a relaxation zone detector. In addition, disturbance region and relaxation region were separated by injecting gypsum into cavity formed in simulated ground. The shape of the underground cavity due to the groundwater flow was similar to that of the failure mode III formed in the dense relative density ground due to water pipe breakage in the previous study. It was confirmed that the relaxed region detected using the relaxation zone detector is formed in an arch shape in the cavity top. The length ratio of the relaxation region to the disturbance region in the upper part of the cavity center is 2: 1, and it can be distinguished by the difference in the decrease of the shear resistance against the external force. In other words, it was confirmed that the secondary damage should not occur in consideration of the expandability of the material used as the injecting material in the pre-repair and reinforcement, and various ground deformation states will be additionally performed through additional experiments.

Analysis of volatile compounds and metals in essential oil and solvent extracts of Amomi Fructus (사인으로부터 추출한 정유와 용매 추출물의 휘발성 물질 및 금속성분 분석)

  • Lee, Sam-Keun;Eum, Chul Hun;Son, Chang-Gue
    • Analytical Science and Technology
    • /
    • v.28 no.6
    • /
    • pp.436-445
    • /
    • 2015
  • Amomi Fructus with anti-oxidative activity was chosen and essential oil was obtained by SDE (simultaneous distillation extraction), and 39 constituents were determined by GC-MS (gas chromatography-mass spectrometry). Major components were camphor, borneol acetate, borneol, D-limonene and camphene. Three solvent extracts such as hexanes, diethyl ether and methylene chloride from Amomi Fructus were obtained. These were analyzed by GC-MS and 4 more constituents were identified in addition to 39 components discovered in essential oil. Five major components such as camphor, borneol acetate, borneol, D-limonene and camphene were also detected, however the relative peak percents of those components were different from those of constituents in essential oil. To estimate the kind and the amount of materials evaporated at certain temperature and conditions from essential oil and solvent extracts, dynamic headspace apparatus was used and materials evaporated and trapped at certain conditions were analyzed by GC-MS. Recovery yield of SDE method from Amomi Fructus was measured by using camphor and standard calibration solution of camphor methanol solution and, the yield was 82.0%. Content of Hg was measured by mercury analyzer and contents of Cd, Pb, Cr, Mn, Co, Ni, Cu and Zn in Amomi Fructus, essential oils and solvent extracts were determined by ICP-MS (Inductively coupled plasma-mass spectrometer). Pb, Cd and Hg were measured in the concentration of 0.72 mg/kg, <0.10 mg/kg and 0.0023 mg/kg, respectively and these were below permission level of purity test. Contents of Mn, Cu and Zn in Amomi Fructus were 213 mg/kg, 8.29 mg/kg and 31.0 mg/kg, respectively and which were relatively higher than other metals such as Cr, Co and Ni. Metals such as Mn (0.65 ~ 9.08 mg/kg), Cu (1.16 ~ 4.40 mg/kg) and Zn (1.10 ~ 3.80 mg/kg) in essential oil and solvent extracts were detected. At this point it is not clear that the metals were cross-contaminated in the course of treating Amomi Fructus or metals were contained in Amomi Fructus. The influence evaluation toward biological model study of these metals in essential oil and solvent extracts will be needed.

Modeling of Sensorineural Hearing Loss for the Evaluation of Digital Hearing Aid Algorithms (디지털 보청기 알고리즘 평가를 위한 감음신경성 난청의 모델링)

  • 김동욱;박영철
    • Journal of Biomedical Engineering Research
    • /
    • v.19 no.1
    • /
    • pp.59-68
    • /
    • 1998
  • Digital hearing aids offer many advantages over conventional analog hearing aids. With the advent of high speed digital signal processing chips, new digital techniques have been introduced to digital hearing aids. In addition, the evaluation of new ideas in hearing aids is necessarily accompanied by intensive subject-based clinical tests which requires much time and cost. In this paper, we present an objective method to evaluate and predict the performance of hearing aid systems without the help of such subject-based tests. In the hearing impairment simulation(HIS) algorithm, a sensorineural hearing impairment medel is established from auditory test data of the impaired subject being simulated. Also, the nonlinear behavior of the loudness recruitment is defined using hearing loss functions generated from the measurements. To transform the natural input sound into the impaired one, a frequency sampling filter is designed. The filter is continuously refreshed with the level-dependent frequency response function provided by the impairment model. To assess the performance, the HIS algorithm was implemented in real-time using a floating-point DSP. Signals processed with the real-time system were presented to normal subjects and their auditory data modified by the system was measured. The sensorineural hearing impairment was simulated and tested. The threshold of hearing and the speech discrimination tests exhibited the efficiency of the system in its use for the hearing impairment simulation. Using the HIS system we evaluated three typical hearing aid algorithms.

  • PDF

THE EXPRESSION OF OSTEONECTIN AND OSTEOCALCIN IN THE EXPERIMENTAL TOOTH MOVEMENT IN RAT (백서의 실험적 치아이동시 osteonectin 및 osteocalcin의 발현)

  • Bae, Sung-Real;Kim, Sang-Cheol
    • The korean journal of orthodontics
    • /
    • v.28 no.5 s.70
    • /
    • pp.699-716
    • /
    • 1998
  • This study was designed to evaluate the expression of non-collagenous protein in periodontal tissue during the experimental movement of rat incisors, by LSAB(labelled streptavidine biotin) immunohistochemical staining for osteonectin and osteocalcin. Twenty seven Sprague-Dawley rats were divided into a control group(3 rats) and 6 experimental groups(24 rats) where 75g of force was applied from helical springs across the maxillary incisors. Rats of experimental groups were sacrificed at 12 hours, 1, 4, 7, 14 and 28 days after force application, respectively. And the tissues of a control group and experimental groups were studied immunohistochemically and histologically. The results were as follows : 1. Until 28 days after force application, periodontal fibers had been strectched on tension side and compressed in pressure side of all the experimental groups, and the arrangement of periodontal fibers had not been recovered yet. 2. The expression of osteonectin in control group was rare in dentin, cementum and osteocyte, and was mild in odontoblasts and matrix of alveolar bone. 3. The expression of osteocalcin in control group was negative in gingiva, osteoblasts, osteocyte and cementum, and was rare in predentin, capillaries in pulp and periodontal ligament and the matrix of alveolar bone. 4. There was no difference in the expression of osteocalcin or osteonectin in dentin, cementum, pulp, odontoblasts, between of control and of experimental groups. 5. The expression of osteonectin in intermaxillary suture got the peak in 7-day and was declined after 14-day. The expression of osteocalcin remained in a same degree since it became mild in 14-day. 6. The expression of osteonectin in pressure side of periodontal ligament of experimental group was rare, which was similar to control group. But in tension side, it was increased until 14-day aftrer which it was declined. 7. The expression of osteocalcin in periodntal ligament was rare in 12-hour to 14-day, but became severe in 28-day, which was greater in tension side than in pressure side, and in the periodontal fiber next to alveolar bone than to tooth surface. 8. The expression of osteocalcin in alveolar bone was rare until 14-day in pressure side, but became moderate in 28-day. The expression of osteonectin was increased from 7-day by time dependency, which was greater in tension side than in pressure side.

  • PDF

The Effect of Home economic education teaching plans for students in academic and those in vocational high schools' 'Preparation for Successful aging' in the 'Family life in old age' unit -A comparative study between practical problem-teaching lesson plans and instructor-led teaching and learning plans- (인문계와 가사.실업 전문계 고등학생의 '성공적인 노후생활 준비교육'을 위한 가정과 수업의 적용과 효과 -실천적 문제 중심 수업과 강의식 수업을 중심으로-)

  • Lee, Jong-Hui;Cho, Byung-Eun
    • Journal of Korean Home Economics Education Association
    • /
    • v.23 no.4
    • /
    • pp.105-124
    • /
    • 2011
  • To achieve this objective, practical problem-teaching lesson plans and instructor-led teaching and learning plans were developed and integrated into the Technology Home Economics, and Human Development curricula at both academic and vocational high schools. The impact of these plans was examined, as were connections between the teaching methods and types of schools. As part of this study, a survey was conducted on 1,263 students in 46 classes at 6 randomly selected high schools: 4 academic and 2 vocational. A total of 9 teachers conducted classes for both experimental and comparative groups between October 2009 and November 2010. Pre- and post-tests were used to study the impact of the lessons on the experimental and comparative groups. In terms of data analysis and statistics processing, this study implemented mean and standard deviations, t-test, and analysis of covariance using the SPSS 12.0 program. The results of this study are as follows. The practical problem-teaching lessons produced more positive results in the students than the instructor-led lessons, in terms of their image of the elderly, their level of knowledge about them, their understanding of their need for welfare services, and preparation for Successful aging. When comparing the results by type of school, the experimental groups at academic high schools appeared to have a more positive image and better understanding of the elderly and their need for welfare services, and were better prepared for Successful aging than during their previous lessons. They also showed an increase in independence from their children in aging. As for the comparative groups, students at academic high schools showed an increase in preparation for Successful aging compared to the previous lessons. Finally, as for future research on preparation for aging in high schools, more schools should include this subject in their regular curriculum for Technology Home Economics, Human Development and Home Economics in order to generalize the results, and they need to evaluate the content. Additionally, this study suggests that new high school curricula should include lessons on preparation for aging so that students can deal successfully with our aging society.

  • PDF

Long-term Prognostic Value of Dipyridamole Stress Myocardial SPECT (디피리다몰 부하 심근관류 SPECT의 장기예후 예측능)

  • Lee, Dong-Soo;Cheon, Gi-Jeong;Jang, Myung-Jin;Kang, Won-Jun;Chung, June-Key;Lee, Myoung-Mook;Lee, Myung-Chul;Kang, Wee-Chang;Lee, Young-Jo
    • The Korean Journal of Nuclear Medicine
    • /
    • v.34 no.1
    • /
    • pp.39-54
    • /
    • 2000
  • Purpose: Dipyridamole stress myocardial perfusion SPECT could predict prognosis, however, long-term follow-up showed change of hazard ratio in patients with suspected coronary artery disease. We investigated how long normal SPECT could predict the benign prognosis on the long-term follow-up. Materials and Methods: We followed up 1169 patients and divided these patients into groups in whom coronary angiography were performed and were not. Total cardiac event rate and hard event rate were predicted using clinical, angiographic and SPECT findings. Predictive values of normal and abnormal SPECT were examined using survival analysis with Mantel-Haenszel method, multivariate Cox proportional hazard model analysis and newly developed statistical method to test time-invariance of hazard rate and changing point of this rate. Results: Reversible perfusion decrease on myocardial perfusion SPECT predicted higher total cardiac event rate independently and further to angiographic findings. However, myocardial SPECT showed independent but not incremental prognostic values for hard event rate. Hazard ratio of normal perfusion SPECT was changed significantly (p<0.001) and the changing point of hazard rate was 4.4 years of follows up. However, the ratio of abnormal SPECT was not. Conclusion: Dipyridamole stress myocardial perfusion SPECT provided independent prognostic information in patients with known and suspected coronary artery disease. Normal perfusion SPECT predicted least event rate for 4.4 years.

  • PDF

Effect of the Solvent Fractions of Zingiber officinale Roscoe against Thrombintreated Tumor Invasion in Human Oral Squamous Carcinoma YD-10B Cells (YD-10B 인간구강암세포주에서 생강 유기용매 분획물의 항산화, 트롬빈억제 및 thrombin에 의해 처리된 암 침윤 및 전이 억제 효과)

  • Kim, Eun-Jung;Kim, Jun-Ho
    • Journal of Life Science
    • /
    • v.26 no.11
    • /
    • pp.1289-1297
    • /
    • 2016
  • Oral squamous cell carcinoma (OSCC) is a common malignant tumor in the oral cavity, comprising up to 90% of oral cancer. Oral cancer is characterized by a marked tendency of local invasiveness and is good for early detection and treatment; therefore, it is recognized as a good model for cancer prevention. The present study investigated the antioxidant, thrombin inhibitory, and anti-invasive activities of the solvent fractions of Zingiber officinale Roscoe. Samples were fractionated into hexane, chloroform, ethyl acetate, butanol, and water fractions, and each of these was assayed individually. The water fraction showed the highest extraction yield at 9.79%(w/w). Anti-oxidative activity was analyzed by DPPH assay. Thrombin inhibitory activity was used to analyze thrombin inhibitor assay. Cell viability was detected by the MTS assay. The activity and mRNA expression of MMP-2 and MMP-9 in human oral squamous carcinoma YD-10B cells were examined by zymography and RT-PCR. The antioxidative activities of hexane and water fractions were 92.38% and 92.96%, respectively. In the thrombin inhibitory activity test, water fraction was the highest, with a value of 65.86%. MMP-2/-9 activation was increased in phorbol 12-myristate 13-acetate (PMA)-induced YD-10B cells. MMP-9 activation was increased in thrombin-treated YD-10B cells. In PMA- or thrombin-treated YD-10B cells, the increased mRNA expression and protein activation of MMP-2/-9 were significantly inhibited in the hexane fraction. Therefore, the hexane fraction obtained from a Zingiber officinale Roscoe water extract is a promising therapeutic anti-invasive agent in oral cancer.

Evaluation of Maternal Behavior between Normal Parturition and Expected Cesarean Section in Rats (자연 분만 및 예정된 제왕절개 수술 랫드에 있어서 모성 행동의 차이에 대한 검토)

  • Lee, S.K.;Kang, H.G.;Kim, I.W.;Jeong, J.M.;Hwang, D.Y.;Kim, C.K.;Chae, K.R.;Cho, J.S.
    • Journal of Embryo Transfer
    • /
    • v.22 no.3
    • /
    • pp.161-165
    • /
    • 2007
  • Oxytocin is a neurohypophyseal hormone which has multiple functions in mammals. Mainly, oxytocin regulates milk ejection and has an effect on uterine contraction and is related to maternal behavior. Maternal behavior is believed to be suppressed by stress and facilitated by oxytocin. In the cesarean section, oxytocin may be administrated into uterus to promote uterine involution. The present study aimed to test the effect of oxytocin into uterus on maternal behavior of rats with cesarean section. It was measured the effects on maternal behavior of oxytocin infused into uterus in rats with cesarean section as a stressor. In the first experiment, pup survival rate of between a control group and a group with laparotomy as a stress in natural parturition rats was compared. In the second experiment, survival rate for 2 weeks and maternal pup searching behavior (MPSV) were observed in one cesarean sectioned group without oxytocin and the other cesarean sectioned group with oxytocin. Infanticide was observed in stressed group in the first experiment while a normal maternal behavior was observed in a control one. In the second experiment, MPSV was only observed in a cesarean sectioned group with oxytocin and infanticide was observed in two groups except one rat which is thought to be affected by oxytocin as operated relatively late. This is the first study to show that the administration of oxytocin into uterus in the cesarean section is not involved in the regulation of maternal behavior in rats. In conclusion, this study proves the needs of oxytocin into brain in cesarean section related rats model and further study of maternal behavior list, like MPSV.