• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.904-911
• /
• 2022

Occlusion is one of the most challenging problems for computer vision-based construction monitoring. Due to the intrinsic dynamics of construction scenes, vision-based technologies inevitably suffer from occlusions. Previous researchers have proposed the occlusion handling methods by leveraging the prior information from the sequential images. However, these methods cannot be employed for construction object detection in non-sequential images. As an alternative occlusion handling method, this study proposes a data augmentation-based framework that can enhance the detection performance under occlusions. The proposed approach is specially designed for rebar occlusions, the distinctive type of occlusions frequently happen during construction worker detection. In the proposed method, the artificial rebars are synthetically generated to emulate possible rebar occlusions in construction sites. In this regard, the proposed method enables the model to train a variety of occluded images, thereby improving the detection performance without requiring sequential information. The effectiveness of the proposed method is validated by showing that the proposed method outperforms the baseline model without augmentation. The outcomes demonstrate the great potential of the data augmentation techniques for occlusion handling that can be readily applied to typical object detectors without changing their model architecture.

• Structural Engineering and Mechanics
• /
• v.60 no.6
• /
• pp.1021-1038
• /
• 2016

Considerable part of reinforced concrete building has suffered from destructive earthquakes in Turkey. This situation makes necessary to determine nonlinear behavior and seismic performance of existing RC buildings. Inelastic response of buildings to static and dynamic actions should be determined by considering both flexural plastic hinges and brittle shear hinges. However, shear capacities of members are generally neglected due to time saving issues and convergence problems and only flexural response of buildings are considered in performance assessment studies. On the other hand, recent earthquakes showed that the performance of older buildings is mostly controlled by shear capacities of members rather than flexure. Demand estimation is as important as capacity estimation for the reliable performance prediction in existing RC buildings. Demand estimation methods based on strength reduction factor (R), ductility (${\mu}$), and period (T) parameters ($R-{\mu}-T$) and damping dependent demand formulations are widely discussed and studied by various researchers. Adopted form of $R-{\mu}-T$ based demand estimation method presented in Eurocode 8 and Turkish Earthquake Code-2007 and damping based Capacity Spectrum Method presented in ATC-40 document are the typical examples of these two different approaches. In this study, eight different existing RC buildings, constructed before and after Turkish Earthquake Code-1998, are selected. Capacity curves of selected buildings are obtained with and without considering the brittle shear capacities of members. Seismic drift demands occurred in buildings are determined by using both $R-{\mu}-T$ and damping based estimation methods. Results have shown that not only capacity estimation methods but also demand estimation approaches affect the performance of buildings notably. It is concluded that including or excluding the shear capacity of members in nonlinear modeling of existing buildings significantly affects the strength and deformation capacities and hence the performance of buildings.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.3
• /
• pp.285-292
• /
• 2020

This paper introduces a new computational efficient Dilution of Precision (DOP)-based landmark exclusion method while ensuring the safety of the LiDAR-based navigation system that uses an innovation-based Nearest-Neighbor (NN) Data Association (DA) process. The NN DA process finds a correct landmark association hypothesis among all potential landmark permutations using Kalman filter innovation vectors. This makes the computational load increases exponentially as the number of landmarks increases. In this paper, we thus exclude landmarks by introducing DOP that quantifies the geometric distribution of landmarks as a way to minimize the loss of integrity performance that can occur by reducing landmarks. The number of landmarks to be excluded is set as the maximum number that can satisfy the integrity risk requirement. For the verification of the method, we developed a simulator that can analyze integrity risk according to the landmark number and its geometric distribution. Based on the simulation, we analyzed the relationship between DOP and integrity risk of the DA process by excluding each landmark. The results showed a tendency to minimize the loss of integrity performance when excluding landmarks with poor DOP. The developed method opens the possibility of assuring the safety risk of the Lidar-based navigation system in real-time applications by reducing a substantial amount of computational load.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.6 no.2
• /
• pp.1-7
• /
• 2002

A procedure for determination of performance point was developed based on the concept of the direct displacement-based design method. Using the proposed procedure, parametric study has been performed for various natural periods of the structure, yield strength, and the stiffness after the first yield. The proposed method was also applied to a 10-story steel frame, and the results were compared to those from the capacity spectrum method and the time history analysis. It was found from the comparison that there were good agreement between the results.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.57-62
• /
• 1998

This paper presents an auto tuning method of PID controller based on the application of fuzzy logic. The proposed method combined the principles of PID control with fuzzy control, which cam considerably improve the performance index of PID controller. Simulation results show that higher performance and accuracy of overall system for desired value is achieved with our manner when compared to widely-used conventional tuning method.

• International Journal of Highway Engineering
• /
• v.19 no.6
• /
• pp.165-173
• /
• 2017

PURPOSES : The current practice in car headlight visibility performance evaluation is based on the luminous intensity and illuminance of headlight. Such practice can be inappropriate from a visibility point of view where visibility indicates abilities to perceive an object ahead on the road. This study aimed at evaluating the appropriateness of current headlight evaluation method. METHODS : This study measured the luminance of object and road surface at unlit roadways. The variables were measured by vehicle type and by headlight lamp type. Based on the measurements, the distance where drivers can perceive an object ahead was calculated and then compared against such distance obtained by conventional visibility performance evaluation. RESULTS : The evaluation method based on illuminance of headlight is not appropriate when viewed from the visibility concept that is based on object-perceivable distance. Further, the results indicated a shorter object-perceiving distance even when road surface luminance is higher, thereby suggesting that illuminance of headlight and luminance of road surface are not the representative indices of nighttime visibility. CONCLUSIONS : Considering that this study utilized limited vehicle types and that road surface (background) luminance can vary depending on the characteristics of the given road surface, it would likely go too far to argue that this study's visibility performance evaluation results can get generalized to other conditions. Regardless, there is little doubt that the current performance evaluation criterion which is based on illuminance, is unreasonable. There should be future endeavors on the current subject which will need to explore study conditions further, under which more experiments should be conducted and effective methodologies developed for evaluating automotive headlight visibility performance. Needs are recognized particularly in the development of headlight visibility performance evaluation methodology which will take into account road surface (background) luminance and luminance contrast from various perspectives as the former indicates the driver's perception of the front road alignment and the latter being indicative of object perception performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.4
• /
• pp.1110-1127
• /
• 2022

To improve the training efficiency and generalization performance of a support vector machine (SVM) in a large-scale set, an optimal SVM learning method based on adaptive sparse sampling and the granularity shift factor is presented. The proposed method combines sampling optimization with learner optimization. First, an adaptive sparse sampling method based on the potential function density clustering is designed to adaptively obtain sparse sampling samples, which can achieve a reduction in the training sample set and effectively approximate the spatial structure distribution of the original sample set. A granularity shift factor method is then constructed to optimize the SVM decision hyperplane, which fully considers the neighborhood information of each granularity region in the sparse sampling set. Experiments on an artificial dataset and three benchmark datasets show that the proposed method can achieve a relatively higher training efficiency, as well as ensure a good generalization performance of the learner. Finally, the effectiveness of the proposed method is verified.

• Journal of Power Electronics
• /
• v.19 no.5
• /
• pp.1235-1247
• /
• 2019

Zero-Voltage-Switching (ZVS) operation for a Wireless Power Transfer (WPT) system can be achieved by designing a ZVS controller. However, the performance of the controller in some industrial applications needs to be designed tightly. This paper introduces a ZVS controller design method for WPT systems. The parameters of the controller are designed according to the desired performance based on the closed loop dominant pole placement method. To describe the dynamic characteristics of the system ZVS angle, a nonlinear dynamic model is deduced and linearized using the small signal linearization method. By analyzing the zero-pole distribution, a low-order equivalent model that facilitates the controller design is obtained. The parameters of the controller are designed by calculating the time constant of the closed-loop dominant poles. A prototype of a WPT system with the designed controller and a five-stage multistage series variable capacitor (MSVC) is built and tested to verify the performance of the controller. The recorded response curves and waveforms show that the designed controller can maintain the ZVS angle at the reference angle with satisfactory control performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.649-655
• /
• 2022

In this paper, a determinant-based two-channel noise reduction method which utilizes speech presence probability (SPP) is proposed. The proposed method improves noise reduction performance from the conventional determinant-based two-channel noise reduction method in [7] by applying SPP to the Wiener filter gain. Consequently, the proposed method adaptively controls the amount of noise reduction depending on the SPP. For performance evaluation, the segmental signal-to-noise ratio (SNR), the perceptual evaluation of speech quality, the short time objective intelligibility, and the log spectral distance were measured in the simulated noisy environments considered various types of noise, reverberation, SNR, and the direction and number of noise sources. The experimental results presented that determinant-based methods outperform phase difference-based methods in most cases. In particular, the proposed method achieved the best noise reduction performance maintaining minimum speech distortion.

• Journal of electromagnetic engineering and science
• /
• v.18 no.3
• /
• pp.206-211
• /
• 2018

In this paper, we proposed a two-level feature vector fusion technique to improve the performance of target classification. The proposed method combines feature vectors of the early-time region and late-time region in the first-level fusion. In the second-level fusion, we combine the monostatic and bistatic features obtained in the first level. The radar cross section (RCS) of the 3D full-scale model is obtained using the electromagnetic analysis tool FEKO, and then, the feature vector of the target is extracted from it. The feature vector based on the waveform structure is used as the feature vector of the early-time region, while the resonance frequency extracted using the evolutionary programming-based CLEAN algorithm is used as the feature vector of the late-time region. The study results show that the two-level fusion method is better than the one-level fusion method.