• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권6호
• /
• pp.1562-1582
• /
• 2024

The prediction of pedestrian trajectory is conducive to reducing traffic accidents and protecting pedestrian safety, which is crucial to the task of intelligent driving. The existing methods mainly use the past pedestrian trajectory to predict the future deterministic pedestrian trajectory, ignoring pedestrian intention and trajectory diversity. This paper proposes a multi-modal trajectory prediction model that introduces pedestrian intention. Unlike previous work, our model makes multi-modal goal-conditioned trajectory pedestrian prediction based on the past pedestrian trajectory and pedestrian intention. At the same time, we propose a novel Gate Recurrent Unit (GRU) to process intention information dynamically. Compared with traditional GRU, our GRU adds an intention unit and an intention gate, in which the intention unit is used to dynamically process pedestrian intention, and the intention gate is used to control the intensity of intention information. The experimental results on two first-person traffic datasets (JAAD and PIE) show that our model is superior to the most advanced methods (Improved by 30.4% on MSE_0.5s and 9.8% on MSE_1.5s for the PIE dataset; Improved by 15.8% on MSE_0.5s and 13.5% on MSE_1.5s for the JAAD dataset). Our multi-modal trajectory prediction model combines pedestrian intention that varies at each prediction time step and can more comprehensively consider the diversity of pedestrian trajectories. Our method, validated through experiments, proves to be highly effective in pedestrian trajectory prediction tasks, contributing to improving traffic safety and the reliability of intelligent driving systems.

• Journal of Mechanical Science and Technology
• /
• 제15권2호
• /
• pp.199-209
• /
• 2001

Modal analysis method (MAM) is introduced for the fully coupled structural dynamic problems. In this paper, the beam with active constrained layered damping (ACLD) treatment is considered as a representative problem. The ACLD beam consists of a viscoelastic layer that is sandwiched between the base beam structure and an active piezoelectric layer. The exact damped natural modes are spectrally formulated from a set of fully coupled dynamic equations of motion. The orthogonality property of the exact damped natural modes is then derived in a closed form to complete the modal analysis method. The accuracy of the present MAM is evaluated through some illustrative examples: the dynamic characteristics obtained by the present MAM are compared with the results by spectral element method (SEM) and finite element method (FEM). It is numerically proved that MAM solutions become identical to the accurate SEM solutions as the number of exact natural used in MAM is increased.

• 한국소음진동공학회논문집
• /
• 제19권12호
• /
• pp.1244-1251
• /
• 2009

In this paper the vibrational behavior of a multi-packet blade system having a cracked blade is investigated. Each blade is assumed as a slender cantilever beam. The coupling stiffness effect that originates from either disc flexibility or shroud is considered in the modeling. Hybrid deformation variables are employed to derive the equations of motion. The flexibility due to crack, which is assumed to be open during the vibration, is calculated basing on a fracture mechanics theory. In the paper, the results of the change in modal parameters due to crack appearance are presented. The influence of the crack parameters, especially of the changing location of the crack is examined.

• 한국정밀공학회지
• /
• 제30권11호
• /
• pp.1147-1151
• /
• 2013

A Crankshaft Multi Grinding Machine is developed for manufacturing of high precision crankshaft. The grinding head part of the developed machine should be moved precisely during grinding of work materials. In this paper, structural and modal analysis for the crankshaft multi grinding machine is carried out to check the design criteria of the machine.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1990년도 가을 학술발표회 논문집
• /
• pp.79-84
• /
• 1990

The modal parameter estimations of linear multi-degree-of-freedom structural dynamic systems are carried out in time domain. For this purpose, the equation of motion is transformed into the autoregressive and moving average model with auxiliary stochastic input (ARMAX) model. The parameters of the ARMAX model are estimated by using the sequential prediction error method. Then, the modal parameters of the system are obtained thereafter. Experimental results are given for a 3-story building model subject to ground exitations.

• 대한교통학회:학술대회논문집
• /
• 대한교통학회 2007년도 제56회 학술발표회논문집
• /
• pp.469-476
• /
• 2007

• 대한인간공학회지
• /
• 제32권6호
• /
• pp.517-528
• /
• 2013

Objective: The objective of this study was to suggest a multi-modal controller type for Smart TV Control. Background: Recently, many issues regarding the Smart TV are arising due to the rising complexity of features in a Smart TV. One of the specific issues involves what type of controller must be utilized in order to perform regulated tasks. This study examines the ongoing trend of the controller. Method: The selected participants had experiences with the Smart TV and were 20 to 30 years of age. A pre-survey determined the first independent variable of five tasks(Live TV, Record, Share, Web, App Store). The second independent variable was the type of controllers(Conventional, Mouse, Voice-Based Remote Controllers). The dependent variables were preference, task completion time, and error rate. The experiment consist a series of three experiments. The first experiment utilized a uni-modal Controller for tasks; the second experiment utilized a dual-modal Controller, while the third experiment utilized a triple-modal Controller. Results: The first experiment revealed that the uni-modal Controller (Conventional, Voice Controller) showed the best results for the Live TV task. The second experiment revealed that the dual-modal Controller(Conventional-Voice, Conventional-Mouse combinations) showed the best results for the Share, Web, App Store tasks. The third experiment revealed that the triple-modal Controller among all the level had not effective compared with dual-modal Controller. Conclusion: In order to control simple tasks in a smart TV, our results showed that a uni-modal Controller was more effective than a dual-modal controller. However, the control of complex tasks was better suited to the dual-modal Controller. User preference for a controller differs according the Smart TV functions. For instance, there was a high user preference for the uni-Controller for simple functions while high user preference appeared for Dual-Controllers when the task was complex. Additionally, in accordance with task characteristics, there was a high user preference for the Voice Controller for channel and volume adjustment. Furthermore, there was a high user preference for the Conventional Controller for menu selection. In situations where the user had to input text, the Voice Controller had the highest preference among users while the Mouse Type, Voice Controller had the highest user preference for performing a search or selecting items on the menu. Application: The results of this study may be utilized in the design of a controller which can effectively carry out the various tasks of the Smart TV.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2009년도 춘계학술대회 논문집
• /
• pp.266-271
• /
• 2009

A modeling method for the modal analysis of a multi-packet blade system having a crack undergoing rotational motion is presented in this paper. Each blade is assumed as a slender cantilever beam. The stiffness coupling effects between blades due to the flexibilities of the disc and the shroud are modeled with discrete springs. Hybrid deformation variables are employed to derive the equations of motion. The flexibility due to crack, which is assumed to be open during the vibration, is calculated basing on a fracture mechanics theory. To obtain more general information, the equations of motion are transformed into dimensionless forms in which dimensionless parameters are identified. The effects of the dimensionless parameters related to the angular speed, the depth and location of a crack on the modal characteristics of the system are investigated with some numerical examples.

• 대한인간공학회지
• /
• 제25권3호
• /
• pp.67-75
• /
• 2006

HVIMs consists of simulated driver models implemented with series of mathematical functions and computerized vehicle dynamic models. To effectively model the perception process, as a part of driver models, psychophysical nonlinearity should be considered not only for the single-modal stimulus but for the stimulus of multiple modalities and interactions among them. A series of human factors experiments were conducted using the primary sensory of visual and auditory modalities to find out the effects of auditory cues in visual velocity estimation tasks. The variations of auditory cues were found to enhance/reduce the perceived intensity of velocity as the level changed. These results indicate that the conventional psychophysical power functions could not applied for the perception process of the HVIMs with multi-modal stimuli. 'Ruled surfaces' in a 3-D coordinate system(with the intensities of both kinds of stimuli and the ratio of enhancement, respectively for each coordinate) were suggested to model the realistic perception process of multi-modal HVIMs.

• Journal of Power Electronics
• /
• 제18권1호
• /
• pp.185-194
• /
• 2018

Interaction among multiple grid-connected inverters has a negative impact on the stable operations and power quality of a power grid. The interrelated influences of inverter inductor-capacitor-inductor filters constitute a high-order power network, and consequently, excite complex resonances at various frequencies. This study first establishes a micro-grid admittance matrix, in which inverters use deadbeat control. Multiple resonances can then be evaluated via modal analysis. For the active damping method applied to deadbeat control, the sampling frequency and the stable domain of the virtual damping ratio are also presented by analyzing system stability in the discrete domain. Simulation and experimental results confirm the efficiency of modal analysis and stable domain calculation in multi-inverter grid-connected systems.