• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.1-7
• /
• 2019

With the in-depth development of machine learning, the deep learning method has made great progress, especially with the Convolution Neural Network(CNN). Compared with traditional text sentiment classification methods, deep learning based CNNs have made great progress in text classification and processing of complex multi-label and multi-classification experiments. However, there are also problems with the neural network for text sentiment classification. In this paper, we propose a fusion model based on Long-Short Term Memory networks(LSTM) and CNN deep learning methods, and applied to multi-category news datasets, and achieved good results. Experiments show that the fusion model based on deep learning has greatly improved the precision and accuracy of text sentiment classification. This method will become an important way to optimize the model and improve the performance of the model.

• Journal of Korean Society of Transportation
• /
• v.22 no.2 s.73
• /
• pp.121-130
• /
• 2004

In these days, multiple-path generation method is highly demanded in practice and research areas, which can represents realistically travelers behavior in choosing possible alternative paths. The multiple-path generation algorithm is one of the key components for policy analysis related to ATIS, DRGS and ATMS in ITS. This study suggested a method to generate multiple Possible paths from an origin to a destination. The approach of the suggested method is different from an other existing methods(K-shortest path algorithm) such as link elimination approach, link penalty approach and simulation approach. The result of the multi-label vine-building shortest path algorithm(MVA) by Kim (1998) and Kim(2001) was used to generate multiple reasonable possible paths with the concept of the rational upper boundary. Because the MVA algorithm records the cost, back-node and back-back node of the minimum path from the origin to the concerned node(intersection) for each direction to the node, many potential possible paths can be generated by tracing back. Among such large number of the potential possible paths, the algorithm distinguishes reasonable alternative paths from the unrealistic potential possible paths by using the concept of the rational upper boundary. The study also shows the very simple network examples to help the concept of the suggested path generation algorithm.

• Anxiety and mood
• /
• v.13 no.2
• /
• pp.66-73
• /
• 2017

Objective : The purpose of this study was to examine the effects of adjunctive aripiprazole versus bupropion on specific symptoms of depression. Methods : Data were from 6-week, randomized, prospective, open-label multi-center study in 103 patients with major depressive disorders. Participants were randomized to receive aripiprazole (2.5-10 mg/day) or bupropion (150-300 mg/day) for 6 weeks. Change in four subscales of the 17-item Hamilton Depression Rating Scale (HAM-D17) that capture core depression symptoms was determined, and change in individual HAM-D17 items was also assessed. Changes in three composite subscales-anxiety, insomnia, and drive were also examined. Results : Within-group change in the four core subscales was large [effect size (ES)=1.30-1.47] and it was similar to that in the HAM-D17 total score. Differences between aripiprazole and bupropion were significant for each of the four core subscales and the HAM-D17 total score favored aripiprazole (p<0.001). On three composite scales, both treatments caused substantial changes in anxiety (within-group ES=1.10 (aripiprazole) vs. 1.00 (bupropion)], insomnia (ES=0.75 vs 0.50), and drive (ES=1.17 vs 1.15). Conclusion : This results suggested that both aripiprazole and bupropion adjunctive therapies with selective serotonin reuptake inhibitors resulted in significant and clinically meaningful changes in core symptom subscales for depression.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2B
• /
• pp.250-262
• /
• 2004

In IPv6 environment, the Internet Telephony, VoD(Video on Demand) and high capacity file exchange service will be more increased than IPv4. Therefore, the strict guarantee of QoS based on End-to-End and differentiated quality control schemes are simultaneously required. This paper proposes the flow control schemes on IPv6 network that the traffic is identified by flow and the QoS of multi-service is improved by QoS information in IPv6 hop-by-hop option header. The object of flow control includes not only non-default QoS traffic, which uses the flow label, but also best-effort or encrypted traffic. Therefore, the guarantee of real-time service is strengthened and the flow, which abuses unnecessarily the network resources, is effectively controlled. Also, this paper proposes the mapping scheme between the flow and MPLS by reflecting the minimum change of the existed network resource and the status of backbone network of ISP(Internet Service Provider). In the simulation result, It is shown that the proposed scheme is effective in the side of QoS on real-time services and utilization of backbone resources.

• The KIPS Transactions:PartC
• /
• v.9C no.1
• /
• pp.123-134
• /
• 2002

The requirement for QoS (Quality of Service) has become an important Issue as real-time or high bandwidth services are increasing, such as Internet Telephony, Internet broadcasting, and multimedia service etc. In order to guarantee the QoS of Internet application services, several approaches are being sought including IntServ (Integrated Service) DiffServ(Differentiated Srvices), and MPLS(Multi-Protocol Label Switching). In this paper, we describe the performance analysis of QoS guarantee mechanism using the DiffServ. To analyze how the DiffServ performance was affected by diverse input traffic models and the weight value in WFQ(Weighted Fair Queueing), we simulated and performed performance evaluation under a random, bursty, and self-similar input traffic models and for diverse input parameters. leased on the results of performance analysis, it was confirmed that significant difference exist in packet delay and loss depending on the input traffic models used. However, it was revealed that QoS guarantee is possible to the EF (expedited Forwarding) class and the service separation between RF and BE (Best Effort) classes may also be achieved. Next, we discussed the performance synthesis problem. (i. e. derived the conservation laws for a DiffServ networks, and analysed the performance variation and dynamic behavior based on the resource allocation (i.e., weight value) in WFQ.

• Mood & Emotion
• /
• v.16 no.3
• /
• pp.140-151
• /
• 2018

Objectives : The purpose of this study was to examine effects of adjunctive aripiprazole versus bupropion, on depressive symptoms of female depression. Methods : Sixty six female patients with major depressive disorders were enrolled from a six-week, randomized prospective open-label multi-center study. Participants were randomized to receive aripiprazole (2.5-10 mg/day) or bupropion (150-300 mg/day). Montgomery Asberg Depression Rating Scale, 17-item Hamilton Depression Rating scale (HAM-D17), Iowa Fatigue Scale, Drug-Induced Extrapyramidal Symptoms Scale, Psychotropic-Related Sexual Dysfunction Questionnaire scores, and Clinical Global Impression-Severity (CGI-S) were obtained at baseline and after one, two, four, and six weeks. Changes on individual items of HAM-D17 were assessed as well as on composite scales (anxiety, insomnia and drive), and on four core subscales that capture core depression symptoms. Results : Overall, both treatments improved depressive symptoms, without causing serious adverse events. There were significant differences in the HAM-D17 total score (p=0.046) and CGI-S (p=0.004), between aripiprazole and bupropion augmentation, favoring aripiprazole over bupropion. Aripiprazole revealed significantly greater effect size in depressed mood (p=0.006), retardation (p=0.005), anxiety psychic (p=0.032), and general somatic symptom (p=0.01). Conclusion : While both treatments were effective, results of this study suggested that aripiprazole may be preferable, in treating general and core symptoms of female depression.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.505-518
• /
• 2023

3D point cloud semantic segmentation is a computer vision task that involves dividing the point cloud into different objects and regions by predicting the class label of each point. Existing 3D semantic segmentation models have some limitations in performing sufficient fusion of multi-modal features while ensuring both characteristics of 2D visual features extracted from RGB images and 3D geometric features extracted from point cloud. Therefore, in this paper, we propose MMCA-Net, a novel 3D semantic segmentation model using 2D-3D multi-modal features. The proposed model effectively fuses two heterogeneous 2D visual features and 3D geometric features by using an intermediate fusion strategy and a multi-modal cross attention-based fusion operation. Also, the proposed model extracts context-rich 3D geometric features from input point cloud consisting of irregularly distributed points by adopting PTv2 as 3D geometric encoder. In this paper, we conducted both quantitative and qualitative experiments with the benchmark dataset, ScanNetv2 in order to analyze the performance of the proposed model. In terms of the metric mIoU, the proposed model showed a 9.2% performance improvement over the PTv2 model using only 3D geometric features, and a 12.12% performance improvement over the MVPNet model using 2D-3D multi-modal features. As a result, we proved the effectiveness and usefulness of the proposed model.

• Applied Microscopy
• /
• v.34 no.2
• /
• pp.121-130
• /
• 2004

In this study, ultrastructural change of the bile duct fibroblast at infected rat with Clonorchis sinensis, and the distribution of lectin receptors and actin protein in cultured bile duct infected with Clonorchis sinensis. It explored using colloidal gold label complex with lectin WGA purified from wheat germ (Triticum vulgaris) and anti actin antibody purified actin (43 kDa) isolated from chicken back muscle. The lectin WGA with protein A gold complex labeled sections of the cultured fibroblast revealed gold particles specifically distributed on the multi vesicular form Golgi complex and cell surface of the fibroblast. The actin antibody with protein A gold complex labeled sections of the cultured fibroblast revealed gold particles specifically distributed on the cytoplasm of the fibroblast. Labeling of cultured fibroblast in rat bile duct infected with Clonorchis sinensis was then quantified and compared to that of cultured Fibroblast in Rat Bile duct. These results indicate that lectin WGA receptors are located in the multi vesicular form Golgi complex in the cytoplasm to the cytoplasmic process of the Rat bile duct fibroblast infected with Clonorchis sinensis. Therefore, the GlcNAc and NeuNac regions on the cell surface and cytoplasmic process appear to be functionally associated with cell-recognition and protection from other cell of the tissue, and linked with secretion and exocytosis of the fibroblst cytoplasm. GlcNAc and NeuNAc product in the multi vesicular form Golgi complex then it is transported to cell surface. Actin protein is many appears that infected fibroblast rather than normal fibroblast. The fibroblast of infected with Clonorchis sinensis are against of the physical and chemical stimulation. Then development of cytoplasmic process is relative some stimulation.

• Journal of the Korean Society of Costume
• /
• v.50 no.7
• /
• pp.97-111
• /
• 2000

The purpose of this study were to segment the hair care cosmetics market according to the benefits sought, to categorize the information sources on the hair care cosmetics, and to characterize the profiles of the segmentized groups of university students. Self-administered questionnaires were distributed to 457 university students in Chonbuk province from Jul. 10 to Jul. 21, 1999. Frequencies and percentages were calculated, and factor analysis, cluster analysis, one-way ANOVA, and $\chi$$^2$-test were used. The results were: 1. University student's benefit variables on hair care cosmetics were classified into special function, fashion, practicality, brand, fragrance, styling, nutritional reinforcement, and economy. And they were segmentized into the feeling pursuit, the multi-benefit pursuit, the practicality pursuit, the benefit unconscious, and the function pursuit. The information sources were classified into marketer-dominated sources, neutral sources and consumer -dominated sources. 2. The feeling pursuit strongly sought for fashion, brand and fragrance pursuit, but considered economy less, chiefly used the marketer-dominated and neutral information sources, and showed much interests in hair care cosmetics, and were consisted of women dominantly. The multi-benefits pursuit sought for various kinds of benefits from hair care cosmetics, depended heavily on various kinds of information sources, were well aware of their hair types and instructions on the hair care cosmetics label, and were consisted of women dominantly. The practicality pursuit highly sought for practicality, but low on the fashion, were not aware of their hair style, haler care, hair health status and hair type, and almost half of them are men. The benefit unconscious showed low concern about, all kinds of benefits and hair care cosmetics, and were consisted of more men than women. The function pursuit highly sought for special function and nutritional reinforcement, mainly depended on the consumer-dominated sources. and showed low concern about their hair style and hair care.

• Journal of Advanced Navigation Technology
• /
• v.14 no.2
• /
• pp.191-197
• /
• 2010

Many does an application and application but the image analysis of face detection considerably is difficult. In order for with effect of the illumination which is irregular in the present paper America the illumination to range evenly in the face which is detected, detects a face territory, Complemented the result which detects only the front face of existing. With LAB color illumination revisions compared in Adaboost face detection of existing and 32% was visible the face detection result which improves. Bought two images which are input and executed Glassfire label rings. Compared Area critical price and became the area of above critical value and revised from RGB smooth anger and LAB images with LCFD system algorithm. The operational conversion image which is extracted like this executed a face territory detection in the object. In order to extract the feature which is necessary to a face detection used AdaBoost algorithms. The face territory remote login with the face territory which tilts in the present paper, until Multi-view face territory detections was possible. Also relationship without high detection rate seems in direction of illumination, With only the public PC application is possible was given proof user authentication field etc.