• 한국진공학회지
• /
• 제6권S1호
• /
• pp.1-15
• /
• 1997

Titanium oxide films were prepared by ion beam enhanced deposition where the films were synthesized by deposition titianium atoms and simultaneously bombarding with xenon ion beam at an energy of 40 keV in an $O_2$ environ,ent. Structure and composition of titanium oxide films were investigated by X-ray Doffractopm (XRD) Ritjerfprd Backscattering Spectroscopy (RBS) and X-ray Diffraction(XRD) Rutherford Backscattering Spectroscopy (RBS) and X-ray photoelectron spectroscopy (XPS) The results show that thestructure of the prepared films exhibit a rutile phase structure wit high(200) orientation and the O/Ti ratio of the titanium oxide films was about 2:1 XPS anlysis shows that $Ti^{2+},Ti^{3+}\;and\;Ti^{4+}$ chemical states exist on the titanium oxide films. the blood compatibility of the titanium oxide films was studied by measurements of blood clotting time and platelet adhesion. The results show that the anticoagulation property of titanium oxide films improved significantly and better than that of LTI-carbon which was widely used to fabricate artificial heart valve.

• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Clinical Endoscopy
• /
• 제56권5호
• /
• pp.553-562
• /
• 2023

Colonoscopy plays an important role in reducing the incidence and mortality of colorectal cancer by detecting adenomas and other precancerous lesions. Image-enhanced endoscopy (IEE) increases lesion visibility by enhancing the microstructure, blood vessels, and mucosal surface color, resulting in the detection of colorectal lesions. In recent years, various IEE techniques have been used in clinical practice, each with its unique characteristics. Numerous studies have reported the effectiveness of IEE in the detection of colorectal lesions. IEEs can be divided into two broad categories according to the nature of the image: images constructed using narrow-band wavelength light, such as narrow-band imaging and blue laser imaging/blue light imaging, or color images based on white light, such as linked color imaging, texture and color enhancement imaging, and i-scan. Conversely, artificial intelligence (AI) systems, such as computer-aided diagnosis systems, have recently been developed to assist endoscopists in detecting colorectal lesions during colonoscopy. To gain a better understanding of the features of each IEE, this review presents the effectiveness of each type of IEE and their combination with AI for colorectal lesion detection by referencing the latest research data.

• Journal of the Korean Institute of Landscape Architecture International Edition
• /
• 제2호
• /
• pp.109-113
• /
• 2004

It is important to consider urban parks and greenery not only from the viewpoint of amenity or aesthetics but also from the viewpoint of biodiversity. In this study, we focused on bryophytes (mosses), and analyzed how existence of artificial structures in urban greeney, such as concrete curbs and stone walls, affect species diversity of bryophytes. Kyoto Gyoen in Kyoto City, western Japan, was selected as the study site. In consideration of kinds of substrates on which bryophytes grow, microhabitats of Kyoto Gyoen were divided into ten types including concrete curbs and stone walls. In each type of microhabitats, we selected the area where bryophyte diversity was highest, and established a quadrat for bryophyte flora survey. Our results showed that the number of bryophyte species and growth forms and the value of diversity indices on concrete curbs or stone walls were higher than the averages of those. The bryophyte species were divided into the four groups by TWINSPAN as follows: Group A (epiphyte species), Group B (rocky species), Group C (roadsides, grassland or forest species), and Group D (waterside species). Bryophytes classified into Group B (rocky species) were mainly recorded on concrete curbs or stone walls. It was considered that the existence of artificial structures (concrete curbs and stone walls) provided favorite habitats for the bryophytes classified into Group B (rocky species), which mainly grows on concrete or rocks, and enhanced species diversity of bryophytes in Kyoto Gyoen.

• 한국물환경학회지
• /
• 제28권3호
• /
• pp.418-425
• /
• 2012

Dam construction in a river can change its hydrological pattern and trap sediments, which results in ecological changes in the downstream. It is a common phenomenon in the downstream of dams to have decreased sediment flow and increased periphyton. Artificial floods and sediment application are suggested as mitigation practices in order to simulate natural process of flood; transporting sediment and sloughing periphyton off. In this study the effects of artificial floods on periphyton were examined by applying sand artificially and discharging water from a dam (Yangyang Dam, Korea). The study area has been suffering from turbidity problems caused by shore erosion of the dam. The accumulation of inorganic sediments and increase of periphyton on the river bottom are the major factors of habitat deterioration in the downstream reaches. Artificial flood and artificial addition of sand was performed in summer and the effects were measured. Piles of applied sands were washed off easily by discharge and it enhanced the periphyton sloughing effect. The removal efficiency of periphyton was 50 ~ 80% within the 2 km reach from the dam. In conclusion artificial floods and sand application can be a good mitigation measure for the habitat rehabilitation after a dam construction in streams.

• 한국게임학회 논문지
• /
• 제16권6호
• /
• pp.59-68
• /
• 2016

다양한 이유로 콘텐츠 생성에 대한 연구는 최근 게임 인공 지능분야에서 활발히 연구되고 있다. 디자이너의 개입과 관계없이 자동적으로 콘텐츠를 생성하려는 시도가 계속 되고 있으며, 여러 게임 장르에서 다양한 형태의 게임 콘텐츠를 생성하는데 사용되어 왔다. 본 논문은 다양한 콘텐츠 생성 연구 중, 고립 동굴이 없는 맵을 자동으로 생성하기 위해 이진 공간 분할을 활용하여 보강된 셀 오토마타 방법을 제안한다. 이진 공간 분할을 이용하면 원하는 공간의 수를 지정할 수 있으며, 셀 오토마타를 이용하여 자동 생성된 맵의 통로를 탐색하는데 걸리는 시간도 줄일 수 있다. 본 논문에서는 이진 공간 분할로 보강된 셀 오토마타를 이용하여 자동 생성된 맵을 게임에 적용하여 그 유용성을 보인다.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2009년도 추계학술대회 논문집
• /
• pp.76-79
• /
• 2009

The current understanding for phase/grain boundary sliding and low-temperature/high-strain rate superplasticity of two-phase titanium alloys is summarized. The quantitative analysis on boundary sliding revealed increased sliding resistance on the order of $\alpha/\beta\;\ll\;\alpha/\alpha\;\approx\;\beta/\beta$ boundary, hence, led to the conclusion that approximately 50% alpha(or beta) volume fraction and/or grain refinement is beneficial for obtaining large superplastic elongation at low temperature and/or high strain rate. To predict the temperature for 50% alpha volume in various alpha/beta Ti, artificial neural network was applied. Finally, much enhanced superplasticity was achieved through grain refinement utilizing dynamic globularization.

• 유체기계공업학회:학술대회논문집
• /
• 유체기계공업학회 2002년도 유체기계 연구개발 발표회 논문집
• /
• pp.346-353
• /
• 2002

The steam generator feedwater flow rate in a nuclear power plant was estimated by means of artificial neural networks with the wavelet analysis for enhanced information extraction. The fouling of venturi meters, used for steam generator feedwater flow rate in pressurized water reactors, may result in unnecessary plant power derating. The backpropagation network was used to generate models of signals for a pressurized water reactor. Multiple-input single-output heteroassociative networks were used for evaluating the feedwater flow rate as a function of a set of related variables. The wavelet was used as a low pass filter eliminating the noise from the raw signals. The results have shown that possible fouling of venturi can be detected by neural networks, and the feedwater flow rate can be predicted as an alternative to existing methods. The research has also indicated that the decomposition of signals by wavelet transform is a powerful approach to signal analysis for denoising.

• 한국염색가공학회지
• /
• 제18권4호
• /
• pp.28-36
• /
• 2006

The polyurethane prepolymers, which were previously synthesized from 2,4-toluene disocyanate(2,4-TDI) and polypropylene glycol(PPG), were chain extended by ethylene diamine or hydroxyl terminated polydimethylsiloxane(HTPMS) having hydroxy group at both ends of the chain, giving polyurethaneurea(PU) and polyurethane containing HTPMS segment(SiPU), respectively. In thermal gravimetric analysis, PU was almost completely degraded at $500^{circ}$ but SiPU showed about 11% residue at the same temperature. Suspension of SiPU and pigment showed more good compatibility than that of PU and pigment. The crocking fastness, migration fastness and solvent wicking were enhanced to 4.5 grades, 4 grades and 4 grades, respectively.

• 한국정보시스템학회지:정보시스템연구
• /
• 제25권4호
• /
• pp.23-36
• /
• 2016

Purpose Recently, many researchers have paid much attention to the Artificial Intelligence fields of GVGP, PCG. The paper suggests that the improved MCTS algorithm to apply for the framework can generate better AI agent. Design/methodology/approach As noted, the MCTS generate magnificent performance without an advanced training and in turn, fit applying to the field of GVGP which does not need prior knowledge. The improved and modified MCTS shows that the survival rate is increased interestingly and the search can be done in a significant way. The study was done with 2 different sets. Findings The results showed that the 10 training set which was not given any prior knowledge and the other training set which played a role as validation set generated better performance than the existed MCTS algorithm. Besed upon the results, the further study was suggested.