• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.143-148
• /
• 2022

Brain tumor classification is an important process that allows doctors to plan treatment for patients based on the stages of the tumor. To improve classification performance, various CNN-based architectures are used for brain tumor classification. Existing methods for brain tumor segmentation suffer from overfitting and poor efficiency when dealing with large datasets. The enhanced CNN architecture proposed in this study is based on U-Net for brain tumor segmentation, RefineNet for pattern analysis, and SegNet architecture for brain tumor classification. The brain tumor benchmark dataset was used to evaluate the enhanced CNN model's efficiency. Based on the local and context information of the MRI image, the U-Net provides good segmentation. SegNet selects the most important features for classification while also reducing the trainable parameters. In the classification of brain tumors, the enhanced CNN method outperforms the existing methods. The enhanced CNN model has an accuracy of 96.85 percent, while the existing CNN with transfer learning has an accuracy of 94.82 percent.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.53-62
• /
• 2022

The deployment of advanced structural health monitoring (SHM) systems in large-scale civil structures collects large amounts of data. Note that these data may contain multiple types of anomalies (e.g., missing, minor, outlier, etc.) caused by harsh environment, sensor faults, transfer omission and other factors. These anomalies seriously affect the evaluation of structural performance. Therefore, the effective analysis and mining of SHM data is an extremely important task. Inspired by the deep learning paradigm, this study develops a novel generative adversarial network (GAN) and convolutional neural network (CNN)-based data anomaly detection approach for SHM. The framework of the proposed approach includes three modules : (a) A three-channel input is established based on fast Fourier transform (FFT) and Gramian angular field (GAF) method; (b) A GANomaly is introduced and trained to extract features from normal samples alone for class-imbalanced problems; (c) Based on the output of GANomaly, a CNN is employed to distinguish the types of anomalies. In addition, a dataset-oriented method (i.e., multistage sampling) is adopted to obtain the optimal sampling ratios between all different samples. The proposed approach is tested with acceleration data from an SHM system of a long-span bridge. The results show that the proposed approach has a higher accuracy in detecting the multi-pattern anomalies of SHM data.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.9-15
• /
• 2023

Single-Page Application(SPA) requires data transformation for communication with RESTful API. The Backend for Frontend(BFF) pattern handles this transformation in the server, but there is some problem that increases the number of communication and makes development and distribution difficult. In this study, we propose an architecture that maps the ViewModel of SPA and the model of RESTful API directly in SPA. The proposed architecture automatically generates a mapping model between the RESTful API model and the ViewModel using the OpenAPI specification, which is the document model of the RESTful API. The data transfer component of SPA automatically converts RESTful API data and ViewModel using the created model. As a result of comparison with the existing BFF method through case study, the proposed architecture showed higher development productivity than BFF, and as a result of load tests, it recorded about 6% lower server CPU occupancy compared to BFF.

• Steel and Composite Structures
• /
• v.48 no.3
• /
• pp.321-333
• /
• 2023

This paper proposes a comprehensive investigation on lateral stiffness of corner-supported steel modular frame using splice connection. A full-scale modular frame with two stacked steel modules under lateral load is tested. Ductile pattern in the transfer of lateral load is found in the final failure mode. Two types of lateral stiffness, including tangent stiffness and secant stiffness, are defined from the load-displacement due to the observed nonlinearity. The difference between these two types of stiffness is found around 20%. The comparisons between the experimental lateral stiffness and the predictions of classical methods are also conducted. The D-value method using hypothesis of independent case is a conservative option for predicting lateral stiffness, which is more recommended than method of contraflexural bending moment. Analyses on two classical short-rod models, including fix-rod model and pin-rod model, are further conducted. Results indicate that fix-rod model is more recommended than pin-rod model to simplify splice connection for simulation on lateral stiffness of modular frame in elastic design stage.

• Korean Journal of Materials Research
• /
• v.33 no.2
• /
• pp.71-76
• /
• 2023

The electroconvection generated on the surface of an ion exchange membrane (IEM) is closely related to the electrical/chemical characteristics or topology of the IEM. In particular, when non-conductive regions are mixed on the surface of the IEM, it can have a great influence on the transfer of ions and the formation of nonlinear electroconvective vortices, so more theoretical and experimental studies are necessary. Here, we present a novel method for creating microscale non-conductive patterns on the IEM surface by laser ablation, and successfully visualize microscale vortices on the surface modified IEM. Microscale (~300 ㎛) patterns were fabricated by applying UV nanosecond laser processing to the non-conductive film, and were transferred to the surface of the IEM. In addition, UV nanosecond laser process parameters were investigated for obvious micro-pattern production, and operating conditions were optimized, such as minimizing the heat-affected zone. Through this study, we found that non-conductive patterns on the IEM surface could affect the generation and growth of electroconvective vortices. The experimental results provided in our study are expected to be a good reference for research related to the surface modification of IEMs, and are expected to be helpful for new engineering applications of electroconvective vortices using a non-conductive patterned IEM.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.13 no.2 s.54
• /
• pp.137-144
• /
• 2009

This paper provides the results from evaluating the stiffness of Hi-Form joint by an experiment and the system identification method using the dynamic modal data, and the reasonable modeling method of Hi-Form joint which is proposed for improved stair construction recently. Based on the crack pattern and load-displacement relationship and the damage distribution, it can be judged that Hi-Form joint can't fully transfer the forces between the elements linked, and we propose that the joint is modeled as a element which have a stiffness with 50% decrease.

• Korean Journal of Applied Biomechanics
• /
• v.18 no.2
• /
• pp.95-104
• /
• 2008

The purpose of this study was to investigate kinematic coordination and control of lower segments in skill process. For the investigation, we examined the difference of resultant linear velocity of segments and angle vs angle graph. Novice subjects were 9 male middle school students who has never been experienced a taekwondo and expert subjects were 7 university taekwondo players. We analyzed kinematic variables of Dollyochagi motion through videographical analysis and the conclusion were as follows. 1. Examining the graph of novice subjects' maximal resultant linear velocity of the thigh, shank, and foot segment, as it gets closer to the end of the training, the maximal resultant linear velocity in each segment increased. Statistical analysis showed the following results; thigh segment caused the increase of speed, using the trunk segment's momentum in the latter term of learning, while the shank segment utilized the momentum of the adjacent proximal segment at the beginning of learning, and the foot segment in the middle of learning. 2. Until the point where the knee joint angle is minimum, as the novice group learn the skill, the flexion of knee and hip joints has changed into the form of coordination pattern in phase. On the other hand, the expert group showed continual coordination pattern in phase that the movement sequences were smooth. From the knee joint maximal flexion to impact timing, all novice and expert groups showed coordination pattern out of phase. 3. From the knee joint maximal flexion to impact timing, the ankle joint was fixed and the knee joint was extended to all the novice stages and expert subjects.

• Archives of design research
• /
• v.13 no.3
• /
• pp.123-134
• /
• 2000

Electronic commerce in digital environment is greatly different from the commerce in physical environment in the past (reality environment) in terms of marketing, distribution structure and, above an, comsumers'purchase pattern. The Old purchase pattern is that a consumer buys a product after s/he touches, tests, and feels it physically, while the purchase pattern in electronic commerce enables the comsumer to make a decision about whether to buy it or not through the information gleaned from the computer monitor screen. A number of products which appears in the market now are designed to use the reality environment setup without consideration of the digital environment, of which the intention is to appeal to consumers with a series of design process. However, taking under consideration the present situation in which lots of electronic commerce are made in the cyber space or digital environment, we are required to forward the product design which can gains the positive attraction for consumers in this environment. Factor analysis is made in order to understand how the subjects perceive the image of the design of the product both in reality situation and in digital environment. The result shows the first factor has different images in those environments. In the background of this conclusion rests the fact that the difference of the transfer of formative factors to consumers is made in the images which show themselves in those different environments.

• Reproductive and Developmental Biology
• /
• v.31 no.2
• /
• pp.83-90
• /
• 2007

Insulin-like growth factor II (IGF2) and H19 genes are mutually imprinted genes which may be responsible for abnormalities in the cloned fetuses and offspring. This study was performed to identify putative differentially methylated regions (DMRs) of porcine H19 locus and to explore its genomic imprinting in in vitro fertilized (IVF) and somatic cell nuclear transferred (SCNT) embryos. Based on mice genomic data, we identified DMRs on H19 and found porcine H19 DMRs that included three CTCF binding sites. Methylation patterns in IVF and SCNT embryos at the 2-, 4-, $8{\sim}16$-cells and blastocyst stages were analyzed by BS (Bisulfite Sequencing)-PCR. The CpGs in CTCF1 was significantly unmethylated in the 2-cell stage IVF embryos. However, the 4- (29.1%) and $8{\sim}16$-cell (68.2%) and blastocyst (48.2%) stages showed higher methylation levels (p<0.01). On the other hand, SCNT embryos were unmethylayted ($0{\sim}2%$) at all stages of development. The CpGs in CTCF2 showed almost unmethylation levels at the 2-,4- and $8{\sim}16$-cell and blastocyst stages of development in both IVF ($0{\sim}14.1%$) and SCNT ($0{\sim}6.4%$) embryos. At all stages of development, CTCF3 was unmethylated in IVF ($0{\sim}17.3%$) and SCNT ($0{\sim}1.2%$) embryos except at the blastocyst stage (54.5%) of IVF embryos. In conclusion, porcine SCNT embryos showed an aberrant methylation pattern comprised to IVF embryos. Therefore, we suggest that the aberrant methylation pattern of H19 loci may be a reason for increased abnormal fetus after embryo transfer of porcine SCNT embryos.

• The Journal of Korean Academy of Prosthodontics
• /
• v.42 no.4
• /
• pp.356-372
• /
• 2004

Statement of problom: In the internal connection system the loading transfer mechanism within the inner surface of the implant and also the stress distribution occuring to the mandible can be changed according to the abutment form. Therefore it is thought to be imperative to study the difference of the stress distribution occuring at the mandible according to the abutment form. Purpose: The purpose of this study was to assess the loading distributing characteristics of 3 implant systems with internal connection under vertical and inclined loading using finite element analysis. Material and method: Three finite element models were designed according to the type of internal connection of ITI(model 1), Friadent(model 2), and Bicon(model 3) respectively. This study simulated loads of 200N in a vertical direction (A), a $15^{\circ}$ inward inclined direction (B), and a $30^{\circ}$ outward inclined direction (C). Result: The following results have been made based on this numeric simulations. 1. The greatest stress showed in the loading condition C of the inclined load with outside point from the centric cusp tip. 2. Without regard to the loading condition, the magnitudes of the stresses taken at the supporting bone, the implant fixture, and the abutment were greater in the order of model 2, model 1, and model 3. 3. Without regard to the loading condition, greater stress was concentrated at the cortical bone contacting the upper part of the implant fixture, and lower stress was taken at the cancellous bone. 4. The stress of the implant fixture was usually widely distributed along the inner surface of the implant fixture contacting the abutment post. 5. The stress distribution pattern of the abutment showed that the great stress was usually concentrated at the neck of the abutment and the abutment post, and the stress was also distributed toward the lower part of the abutment post in case of the loading condition B, C of the inclined load. 6. In case of the loading condition B, C of the inclined load, the maximum von Misess stress at the whole was taken at the implant fixture both in the model 1 and model 2, and at the abutment in the model 3. 7. The stress was inclined to be distributed from abutment post to fixture in case of the internal connection system. Conclusion: The internal connection system of the implant and the abutment connection methods, the stress-induced pattern at the supporting bone, the implant fixture, and the abutment according to the abutment connection form had differenence among them, and the stress distribution pattern usually had a widely distributed tendency along the inner surface of the implant fixture contacting the a butment post.