• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3820-3841
• /
• 2018

Most of the accidents occur due to drowsiness while driving, avoiding road signs and due to driver's distraction. Driver's distraction depends on various factors which include talking with passengers while driving, mood disorder, nervousness, anger, over-excitement, anxiety, loud music, illness, fatigue and different driver's head rotations due to change in yaw, pitch and roll angle. The contribution of this paper is two-fold. Firstly, a data set is generated for conducting different experiments on driver's distraction. Secondly, novel approaches are presented that use features based on facial points; especially the features computed using motion vectors and interpolation to detect a special type of driver's distraction, i.e., driver's head rotation due to change in yaw angle. These facial points are detected by Active Shape Model (ASM) and Boosted Regression with Markov Networks (BoRMaN). Various types of classifiers are trained and tested on different frames to decide about a driver's distraction. These approaches are also scale invariant. The results show that the approach that uses the novel ideas of motion vectors and interpolation outperforms other approaches in detection of driver's head rotation. We are able to achieve a percentage accuracy of 98.45 using Neural Network.

• 한국구조물진단유지관리공학회 논문집
• /
• 제7권1호
• /
• pp.267-277
• /
• 2003

The purpose of this study makes a retrofit and rehabilitation practice trough the analysis and the improvement for the underlying problem of current retrofit and rehabilitation methods. Therefore, the deterioration process, the damage cause, the condition classification, the fatigue mechanism and the applied quantity of strengthening methods for slab bridge decks were analysed. Artificial neural networks are efficient computing techniqures that are widely used to solve complex problems in many fields. In this study, a back-propagation neural network model for estimating a management on existing slab bridge decks from damage cause, damage type, and integrity assessment at the initial stsge is need. The training and testing of the network were based on a database of 36. Four different network models werw used to study the ability of the neural network to predict the desirable output of increasing degree of accuracy. The neural networks is trained by modifying the weights of the neurons in response to the errors between the actual output values and the target output value. Training was done iteratively until the average sum squared errors over all the training patterms were minimized. This generally occurred after about 5,000 cycles of training.

• 한국유체기계학회 논문집
• /
• 제10권5호
• /
• pp.9-19
• /
• 2007

Fluid temperature fluctuations in a mixing tee pipe were numerically analyzed by LES model in order to clarify internal turbulent flows and to develope an evaluation method for high-cycle thermal fatigue. Hot and cold water with an temperature difference $40^{\circ}C$ were supplied to the mixing tee. Fluid temperature fluctuations in a mixing tee pipe is analysed by using the computational fluid dynamics code, FLUENT, Temperature fluctuations of the fluid and pipe wall measured as the velocity ratio of the flow in the branch pipe to that in the main pipe was varied from 0.05 to 5.0. The power spectrum method was used to evaluate the heat transfer coefficient. The fluid temperature characteristics were dependent on the velocity ratio, rather than the absolute value of the flow velocity. Large fluid temperature fluctuations were occurred near the mixing tee, and the fluctuation temperature frequency was random. The ratios of the measured heat transfer coefficient to that evaluated by Dittus-Boelter's empirical equation were independent of the velocity ratio, The multiplier ratios were about from 4 to 6.

• 대한조선학회논문집
• /
• 제33권3호
• /
• pp.1-7
• /
• 1996

용접이음부재에서 피로강도에 큰 영향을 미치는 용접부의 응력집중계수를 추정하였다. 여기서는 하중전달형 십자필렛용접이음부를 그 대상으로 하였다. 필렛용접이음부에서 토우파괴를 일으키는 피로균열발생부인 용접토우부의 응력집중계수를 구하기 위해 인장하중하에서 토우부의 적정 요소 크기를 검토하고 여러 파라메타들의 값을 변화시켜 유한요소 응력해석을 수행하였다. 즉 용접토우부의 형상인 토우각 및 곡률반경의 영향과 용입부족부 길이의 변화를 동시에 고려한 응력집중계수를 정량적으로 구하였다. 그리고 그 결과를 이용하여 응력집중계수 추정식을 유도하였다.

• 대한조선학회 특별논문집
• /
• 대한조선학회 2008년도 특별논문집
• /
• pp.96-105
• /
• 2008

Turbulent flow-induced vibrations generate the structural fatigue and noise problems. In this paper, using Corcos, Smol' yakov-Tkachenko, Ffowcs Williams and Chase models, the input power generated by distributed fluid force is predicted for power flow analysis (PFA) of turbulent flow-induced vibration. Additionally, the Fast Fourier Transform (FFT) is used to raise the calculation efficiency PFA results obtained are compared with the classical modal solutions for verifications. Analytic results using the fluid models show good agreements with those of modal analysis, respectively.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제6권4호
• /
• pp.983-999
• /
• 2014

The structural design of the ships includes two main issues which should be checked carefully, namely the extreme structural response (yielding & buckling) and the fatigue structural response. Even if the corresponding failure modes are fundamentally different, the overall methodologies for their evaluation have many common points. Both issues require application of two main steps: deterministic calculations of hydro-structure interactions for given operating conditions on one side and the statistical post-processing in order to take into account the lifetime operational profile, on the other side. In the case of ultra large ships such as the container ships and in addition to the classical quasi-static type of structural responses the hydroelastic structural response becomes important. This is due to several reasons among which the following are the most important: the increase of the flexibility due to their large dimensions (Lpp close to 400 m) which leads to the lower structural natural frequencies, very large operational speed (> 20 knots) and large bow flare (increased slamming loads). The correct modeling of the hydroelastic ship structural response, and its inclusion into the overall design procedure, is significantly more complex than the evaluation of the quasi static structural response. The present paper gives an overview of the different tools and methods which are used in nowadays practice.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2002년도 가을 학술발표회 논문집
• /
• pp.227-236
• /
• 2002

The purpose of this study makes a retrofit and rehabilitation practice trough the analysis and the improvement for the underlying problem of current retrofit and rehabilitation methods. Therefore, the deterioration process, the damage cause, the condition classification, the fatigue mechanism and the applied quantity of strengthening methods for RC deck slabs were analyzed. Artificial neural networks are efficient computing techniques that are widely used to solve complex problems in many fields. In this study, a back-propagation neural network model for estimating a management on existing reinforced concrete bridge decks from damage cause, damage type, and integrity assessment at the initial stage is need. The training and testing of the network were based on a database of 36. Four different network models were used to study the ability of the neural network to predict the desirable output of increasing degree of accuracy. The neural networks is trained by modifying the weights of the neurons in response to the errors between the actual output values and the target output value. Training was done iteratively until the average sum squared errors over all the training patterns were minimized. This generally occurred after about 5,000 cycles of training.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2001년도 봄 학술발표회 논문집
• /
• pp.481-488
• /
• 2001

The HANARO in-chimney bracket was proposed as a structure which supports the guide tubes of irradiation facilities at the irradiation sites of CT, IR and OR4/5 in HANARO core for the reduction of flow-induced vibration and seismic response of the irradiation facilities. For the evaluation of the structural integrity of the in-chimney bracket, its finite element model is developed. The seismic response analysis was performed for the in-chimney bracket and related reactor structures, under the response spectrum of OBE and SSE. The analysis results show that stress values of the in-chimney bracket and reactor structures for the seismic loads are within the ASME code limits. It is also confirmed that its fatigue usage factor is much less than 1.0. For the verification of the implementation effects of the in-chimney bracket, the vibration level of the guide tube of the instrumented fuel assembly, which is subjected to fluid-induced vibration, was measured and analyzed. The vibration analysis results demonstrate that the vibration level of the instrumented fuel assembly has been remarkably reduced after installing the in-chimney bracket. Therefore, when the in-chimney bracket is installed at the reactor chimney, any damage on the structural integrity is not expected.

• International Journal of Railway
• /
• 제1권3호
• /
• pp.106-112
• /
• 2008

Rolling-sliding, cyclic contact of wheel and rail progressively alters the microstructure of the contacting steels, eventually leading to micro-scale crack initiation, wear and macro-scale crack growth in the railhead. Relating the microstructural changes to subsequent wear and cracking is being accomplished through modelling at three spatial scales: (i) bulk material (ii) multi-grain and (iii) sub-grain. The models incorporate detailed information from metallurgical examinations of used rails and tested rail material. The initial 2-dimensional models representing the rail material are being further developed into 3-dimensional models. Modelling is taking account of thermal effects, and traffic patterns to which the rails are exposed.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2004년도 추계 학술발표회 제16권2호
• /
• pp.49-52
• /
• 2004

In this studies, Dapped End Beams(DEB) having disturbed regions were designed by using strut tie model, and the main purpose of this paper is that whether T-headed bars and Steel fibers will be present or not. The ability of DEB with T-headed bars have a superior performance rather than others, such as improved ductility, larger energy adsorption and enhanced post-peak load carrying capability. The capacity of DEB with steel fibers also show increase of ductility, shear strength, fatigue strength and crack. Each DEB with both headed bars and steel fibers, headed bars, and steel fibers as a substitute reinforced steel in the disturbed regions and a DEB with only stirrup and tie reinforced steel were comparable. In contrast, the headed bar stirrups, the tie headed bars and the reinforced steel fibers did not lose their anchorage and hence were able to develop strain hardening and also served to delay buckling of the flexural compression steel. Excellent load-deflection predictions were obtained by increasing the tension stiffening effect to account for high load effects.