• Journal of Drive and Control
• /
• v.16 no.3
• /
• pp.59-66
• /
• 2019

Hydraulic systems are essential for most of the construction equipments due to their various advantages, such as very powerful, quick response speed, precision control and remote control. Moreover, they are necessary to apply the electro hydraulic systems for precise and remote controls. Operating the small electronic joystick of the remote controller for the control of a multipurpose work machine with remote control technology increases the possibility of a sudden operation compared to the use of a conventional hydraulic joystick. When a joystick is suddenly operated, the peak pressure is generated in the system due to the quick response of the system. Then a vibration is generated due to the peak pressure, which causes instability to the operation of the construction equipment. Therefore, in this study, we confirmed the level of reduction of peak pressure occurring in the electro hydraulic system by using AMESim, when the output signal of the step shape generated by the sudden operation of the electronic joystick was changed by using the convolution operation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4285-4299
• /
• 2019

Adversarial attack is a technique that causes a malfunction of classification models by adding noise that cannot be distinguished by humans, which poses a threat to a deep learning model. In this paper, we propose an efficient method to detect adversarial images using Gaussian process regression. Existing deep learning-based adversarial detection methods require numerous adversarial images for their training. The proposed method overcomes this problem by performing classification based on the statistical features of adversarial images and clean images that are extracted by Gaussian process regression with a small number of images. This technique can determine whether the input image is an adversarial image by applying Gaussian process regression based on the intermediate output value of the classification model. Experimental results show that the proposed method achieves higher detection performance than the other deep learning-based adversarial detection methods for powerful attacks. In particular, the Gaussian process regression-based detector shows better detection performance than the baseline models for most attacks in the case with fewer adversarial examples.

• Journal of Integrative Natural Science
• /
• v.11 no.4
• /
• pp.167-183
• /
• 2018

Electroencephalogram (EEG) recording provides a new way to support human-machine communication. It gives us an opportunity to analyze the neuro-dynamics of human cognition. Machine learning is a powerful for the EEG classification. In addition, machine learning can compensate for high variability of EEG when analyzing data in real time. However, the optimal EEG electrode location must be prioritized in order to extract the most relevant features from brain wave data. In this paper, we propose an intelligent system model for the extraction of EEG data by training the optimal electrode location of EEG in a specific problem. The proposed system is basically a fuzzy system and uses a neural network structurally. The fuzzy clustering method is used to determine the optimal number of fuzzy rules using the features extracted from the EEG data. The parameters and weight values found in the process of determining the number of rules determined here must be tuned for optimization in the learning process. Genetic algorithms are used to obtain optimized parameters. We present useful results by using optimal rule numbers and non - symmetric membership function using EEG data for four movements with the right arm through various experiments.

• Geomechanics and Engineering
• /
• v.17 no.6
• /
• pp.583-595
• /
• 2019

In this paper, a comprehensive investigation of the dynamic response of a long-bridge subjected to spatially varying earthquake ground motions (SVEGM) is performed based on a proposed analytical model which includes the effect of soil-structure interaction (SSI). The spatial variability of ground motions is simulated by the powerful record generator, SIMQKE II. Modeling of the SSI in the system is simplified by replacing the pile foundations and soil with sets of independent equivalent linear springs and dashpots along the pile groups. One of the most fundamental objectives of this study is to examine how well the proposed model simulates the dynamic response of a bridge system. For this purpose, the baseline data required for the evaluation process is derived from analyzing a 3D numerical model of the bridge system which is validated in this paper. To emphasize the importance of the SVEGM and SSI, bridge responses are also determined for the uniform ground motion and fixed base cases. This study proposing a compatible analytical model concerns the relative importance of the SSI and SVEGM and shows that these effects cannot be neglected in the seismic analysis of long-bridges.

• Journal of Yeungnam Medical Science
• /
• v.36 no.2
• /
• pp.124-135
• /
• 2019

Background: We aimed to establish robust histoprognostic predictors on residual rectal cancer after preoperative chemoradiotherapy (CRT). Methods: Analyzing known histoprognostic factors in 146 patients with residual disease allows associations with patient outcome to be evaluated. Results: The median follow-up time was 77.8 months, during which 59 patients (40.4%) experienced recurrence and 41 (28.1%) died of rectal cancer. On univariate analysis, residual tumor size, ypT category, ypN category, ypTNM stage, downstage, tumor regression grade, lymphatic invasion, perineural invasion, venous invasion, and circumferential resection margin (CRM) were significantly associated with recurrence free survival (RFS) or/and cancer-specific survival (CSS) (all p<0.005). On multivariate analysis, higher ypTNM stage and CRM positivity were identified as independent prognostic factors for RFS (ypTNM stage, p=0.024; CRM positivity, p<0.001) and CSS (p=0.022, p=0.017, respectively). Furthermore, CRM positivity was an independent predictor of reduced RFS and CSS, irrespective of subgrouping according to downstage (non-downstage, p<0.001 and p<0.001; downstage, p=0.002 and p=0.002) or lymph node metastasis (non-metastasis, p<0.001 and p=0.001; metastasis, p<0.001 and p<0.001). Conclusion: CRM status may be as powerful as ypTNM stage as a prognostic indicator for patient outcome in patients with residual rectal cancer after preoperative CRT.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.222-224
• /
• 2019

Light Field (LF) camera captures not only the light intensity but also the light direction coming to camera. While the rich information captured by LF camera enables many interesting applications such as digital refocusing, viewpoint changing, and 3D reconstruction, but it also requires powerful coding tools to reduce its large volume of data. In this paper, we investigate using the intra prediction scheme of the versatile video coding (VVC), which is the most recent video coding technology currently under developing, to compress the LF image. The Intra Block Copy (IBC) technique in VVC is exploited considering special LF image structure. The experimental result shows that VVC intra predict ion outperforms the H.265/HEVC intra coding technique in encoding LF data irrespective of using the IBC mode or not.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.439-441
• /
• 2019

Deep learning has become a powerful and robust algorithm in Artificial Intelligence. One of the most impressive forms of Deep learning tools is that of the Convolutional Neural Networks (CNN). CNN is a state-of-the-art solution for object recognition. For instance when we utilize CNN with MNIST handwritten digital dataset, mostly the result is well. Because, in MNIST dataset, all digits are centralized. Unfortunately, the real world is different from our imagination. If digits are shifted from the center, it becomes a big issue for CNN to recognize and provide result like before. To solve that issue, we have created frequency images from spatial images by a Fast Fourier Transform (FFT).

• Mass Spectrometry Letters
• /
• v.12 no.3
• /
• pp.93-105
• /
• 2021

Exosomes have gained the attention of the scientific community because of their role in facilitating intercellular communication, which is critical in disease monitoring and drug delivery research. Exosome research has grown significantly in recent decades, with a focus on the development of various technologies for isolating and characterizing exosomes. Among these efforts is the use of matrix-assisted laser desorption ionization (MALDI) mass spectrometry (MS), which offers high-throughput direct analysis while also being cost and time effective. MALDI is used less frequently in exosome research than electrospray ionization due to the diverse population of extracellular vesicles and the impurity of isolated products, both of which necessitate chromatographic separation prior to MS analysis. However, MALDI-MS is a more appropriate instrument for the analytical approach to patient therapy, given it allows for fast and label-free analysis. There is a huge drive to explore MALDI-MS in exosome research because the technology holds great potential, most notably in biomarker discovery. With methods such as fingerprint analysis, OMICs profiling, and statistical analysis, the search for biomarkers could be much more efficient. In this review, we highlight the potential of MALDI-MS as a tool for investigating exosomes and some of the possible strategies that can be implemented based on prior research.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.33 no.12
• /
• pp.53-62
• /
• 2017

Many gradient-based mathematical methods have been developed and are in use for structural size optimization problems, in which the cross-sectional areas or sizing variables are usually assumed to be continuous. In most practical structural engineering design problems, however, the design variables are discrete. The main objective of this paper is to propose an efficient optimization method for structures with discrete-sized variables based on the harmony search (HS) meta-heuristic algorithm that is derived using penalty function. The recently developed HS algorithm was conceptualized using the musical process of searching for a perfect state of harmony. It uses a stochastic random search instead of a gradient search so that derivative information is unnecessary. In this paper, a discrete search strategy using the HS algorithm with a static penalty function is presented in detail and its applicability using several standard truss examples is discussed. The numerical results reveal that the HS algorithm with the static penalty function proposed in this study is a powerful search and design optimization technique for structures with discrete-sized members.

• Geomechanics and Engineering
• /
• v.24 no.3
• /
• pp.237-251
• /
• 2021

The main purpose of this study is to investigate the performance of the proposed hybrid teaching-learning based optimization algorithm on the optimum design of reinforced concrete (RC) cantilever retaining walls. For this purpose, three different design examples are optimized with 100 independent runs considering continuous and discrete variables. In order to determine the algorithm performance, the optimization results were compared with the outcomes of the nine powerful meta-heuristic algorithms applied to this problem, previously: the big bang-big crunch (BB-BC), the biogeography based optimization (BBO), the flower pollination (FPA), the grey wolf optimization (GWO), the harmony search (HS), the particle swarm optimization (PSO), the teaching-learning based optimization (TLBO), the jaya (JA), and Rao-3 algorithms. Moreover, Rao-1 and Rao-2 algorithms are applied to this design problem for the first time. The objective function is defined as minimizing the total material and labor costs including concrete, steel, and formwork per unit length of the cantilever retaining walls subjected to the requirements of the American Concrete Institute (ACI 318-05). Furthermore, the effects of peak ground acceleration value on minimum total cost is investigated using various stem height, surcharge loads, and backfill slope angle. Finally, the most robust results were obtained by HTLBO with 50 populations. Consequently the optimization results show that, depending on the increase in PGA value, the optimum cost of RC cantilever retaining walls increases smoothly with the stem height but increases rapidly with the surcharge loads and backfill slope angle.