• Journal of Advanced Navigation Technology
• /
• v.14 no.6
• /
• pp.874-881
• /
• 2010

A automatic flight control system(AFCS) of UAS needs to control its flight path along target path exactly as adjusts flight coefficient itself depending on static or dynamic changes of airplane's features such as type, size or weight. In this paper, we propose system which tunes control gain autonomously depending on change of airplane's feature in flight as adding MLM(Machine Learning Module) on AFCS. MLM is designed with Linear Regression algorithm and Reinforcement Learning and it includes EvM(Evaluation Module) which evaluates learned control gain from MLM and verified system. This system is tested on beaver FDC simulator and we present its analysed result.

• Journal of KIISE:Software and Applications
• /
• v.32 no.9
• /
• pp.920-926
• /
• 2005

Nearest neighbor algorithms classify an unseen input instance by selecting similar cases and use the discovered membership to make predictions about the unknown features of the input instance. The usefulness of the nearest neighbor algorithms have been demonstrated sufficiently in many real-world domains. In nearest neighbor algorithms, it is an important issue to assign proper weights to the attributes. Therefore, in this paper, we propose a new method which can automatically assigns to each attribute a weight of its importance with respect to the target attribute. The method has been implemented as a computer program and its effectiveness has been tested on a number of machine learning databases publicly available.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.4
• /
• pp.186-191
• /
• 2018

As influence of the 4th industry is growing with development of information society more electronic devices and sensor are used in the field. As this is the case, importance of signal processing during data transfer is rising Furthermore, the need for technology to remove noise caused by various reasons and to stabilize sensor output is growing as well. This research suggests digital filter algorithm that efficiently remove noise by stabilizing output of accelerating sensor. The standard value of this algorithm is calculated by applying Gaussian coefficient. To maintain its feature, final output is obtained by subtracting weight depending on variance from standard value For its evaluation, it is compared with other protocols and its function is checked through output features.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.6
• /
• pp.1-9
• /
• 2019

Hard disks, which have long been used as secondary storage in computing systems, are increasingly being replaced by solid state drives (SSDs), due to their relatively fast data input / output speeds and small, light weight. SSDs that use NAND flash memory as a storage medium are significantly different from hard disks in terms of physical operation and internal operation. In particular, there is a feature that data overwrite can not be performed, which causes erase operation before writing. In order to solve this problem, a hot data for frequently updating a data for a specific page is distinguished from a cold data for a relatively non-hot data. Hot data identification helps to improve overall performance by identifying and managing hot data separately. Among the various hot data identification methods known so far, there is a technique of recording consecutive write requests by using a Bloom filter and judging the values by hot data. However, the Bloom filter technique has a problem that a new bit array must be generated every time a set of items is changed. In addition, since it is judged based on a continuous write request, it is possible to make a wrong judgment. In this paper, we propose a method using a counting filter for accurate hot data verification. The proposed method examines consecutive write requests. It also records the number of times consecutive write requests occur. The proposed method enables more accurate hot data verification.

• Computers and Concrete
• /
• v.23 no.6
• /
• pp.445-457
• /
• 2019

Cracks are an important distress of concrete bridges, and may reduce the life and safety of bridges. However, the traditional manual crack detection means highly depend on the experience of inspectors. Furthermore, it is time-consuming, expensive, and often unsafe when inaccessible position of bridge is to be assessed, such as viaduct pier. To solve this question, the real-time automatic crack detecting system with unmanned aerial vehicle (UAV) become a choice. This paper designs a new automatic detection system based on real-time comprehensive image processing for bridge crack. It has small size, light weight, low power consumption and can be carried on a small UAV for real-time data acquisition and processing. The real-time comprehensive image processing algorithm used in this detection system combines the advantage of connected domain area, shape extremum, morphology and support vector data description (SVDD). The performance and validity of the proposed algorithm and system are verified. Compared with other detection method, the proposed system can effectively detect cracks with high detection accuracy and high speed. The designed system in this paper is suitable for practical engineering applications.

• Journal of the Korean Institute of Educational Facilities
• /
• v.26 no.5
• /
• pp.25-36
• /
• 2019

School gymnasium is a multi-purpose large space building for various events and physical education activities, and is a facility that requires an approach to the desirable structural design, besides mechanical problems of structure against loads. For the integrated structure design concerning the architectural features, the major considerations of gymnasium planning that are the internal and external shape of the gymnasium, the space scale with structure members, the structural efficiency by members weight reduction and openness of the gymnasium space will have to take into account in the structural planning. From this point of view, the several cases of the school gymnasium were investigated and the parametric analyses were performed to the models using the various structural system. The parameters were the composition elements of structure system that are profile of structure, rigidity of member, connection and anchorage and stability. At the result, It was presented that the profile of structure member was the most influential factor to structural efficiency and the effect of the form and space of gymnasium. Also the design informations of structure design having the various feature of form and space were presented for the initial gymnasium planning.

• Structural Engineering and Mechanics
• /
• v.84 no.1
• /
• pp.1-16
• /
• 2022

An efficient and accurate classification method for failure modes of reinforced concrete (RC) columns was proposed based on key characteristic parameters. The weight coefficients of seven characteristic parameters for failure modes of RC columns were determined first based on the support vector machine-recursive feature elimination. Then key characteristic parameters for classifying flexure, flexure-shear and shear failure modes of RC columns were selected respectively. Subsequently, a support vector machine with key characteristic parameters (SVM-K) was proposed to classify three types of failure modes of RC columns. The optimal parameters of SVM-K were determined by using the ten-fold cross-validation and the grid-search algorithm based on 270 sets of available experimental data. Results indicate that the proposed SVM-K has high overall accuracy, recall and precision (e.g., accuracy>95%, recall>90%, precision>90%), which means that the proposed SVM-K has superior performance for classification of failure modes of RC columns. Based on the selected key characteristic parameters for different types of failure modes of RC columns, the accuracy of SVM-K is improved and the decision function of SVM-K is simplified by reducing the dimensions and number of support vectors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4326-4344
• /
• 2021

The SinGAN is one of generative adversarial networks that can be trained on a single nature image. It has poor ability to learn more global features from nature image, and losses much local detail information when it generates arbitrary size image sample. To solve the problem, a non-linear function is firstly proposed to control downsampling ratio that is ratio between the size of current image and the size of next downsampled image, to increase the ratio with increase of the number of downsampling. This makes the low-resolution images obtained by downsampling have higher proportion in all downsampled images. The low-resolution images usually contain much global information. Therefore, it can help the model to learn more global feature information from downsampled images. Secondly, the attention mechanism is introduced to the generative network to increase the weight of effective image information. This can make the network learn more local details. Besides, in order to make the output image more natural, the TVLoss function is introduced to the loss function of SinGAN, to reduce the difference between adjacent pixels and smear phenomenon for the output image. A large number of experimental results show that our proposed model has better performance than other methods in generating random samples with fixed size and arbitrary size, image harmonization and editing.