• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.10
• /
• pp.239-246
• /
• 2020

In the medical field where artificial intelligence technology is introduced, research related to clinical decision support system(CDSS) in relation to diagnosis and prediction is actively being conducted. In particular, medical imaging-based disease diagnosis area applied AI technologies at various products. However, medical imaging data consists of inconsistent data, and it is a reality that it takes considerable time to prepare and use it for research. This paper describes a one-stop AI learning platform for converting to medical image standard R_CDM(Radiology Common Data Model) and supporting AI algorithm development research based on the dataset. To this, the focus is on linking with the existing CDM(common data model) and model the system, including the schema of the medical imaging standard model and report information for multi-center research based on DICOM(Digital Imaging and Communications in Medicine) tag information. And also, we show the execution results based on generated datasets through the AI learning platform. As a proposed platform, it is expected to be used for various image-based artificial intelligence researches.

• Structural Engineering and Mechanics
• /
• v.44 no.3
• /
• pp.325-337
• /
• 2012

In this article, the multi-objective optimization of cylindrical aluminum tubes under axial impact load is presented. The specific absorbed energy and the maximum crushing force are considered as objective functions. The geometric dimensions of tubes including diameter, length and thickness are chosen as design variables. D/t and L/D ratios are constricted in the range of which collapsing of tubes occurs in concertina or diamond mode. The Non-dominated Sorting Genetic Algorithm-II is applied to obtain the Pareto optimal solutions. A back-propagation neural network is constructed as the surrogate model to formulate the mapping between the design variables and the objective functions. The finite element software ABAQUS/Explicit is used to generate the training and test sets for the artificial neural networks. To validate the results of finite element model, several impact tests are carried out using drop hammer testing machine.

• Structural Engineering and Mechanics
• /
• v.62 no.2
• /
• pp.237-246
• /
• 2017

In the present paper a new Neuro-Wavelet control algorithm is proposed based on a cost function to actively control the vibrations of structures under earthquake loads. A wavelet neural network (WNN) was developed to train the control algorithm. This algorithm is designed to control multi-degree-of-freedom (MDOF) structures which consider the geometric and material non-linearity, structural irregularity, and the incident direction of an earthquake load. The training process of the algorithm was performed by using the El-Centro 1940 earthquake record. A numerical model of a three dimensional (3D) three story building was used to accredit the control algorithm under three different seismic loads. Displacement responses and hysteretic behavior of the structure before and after the application of the controller showed that the proposed strategy can be applied effectively to suppress the structural vibrations.

• International Journal of Aerospace System Engineering
• /
• v.2 no.2
• /
• pp.44-49
• /
• 2015

A gust response analyses method based on Reduced Order Models (ROMs) was developed in the paper. Firstly, taken random signal as the input signal and adopt Single Input-Multi-Output (SIMO) training fashion, a ROM based on Auto-Regressive and Moving Average model (ARMA) was established and validated with the comparison of CFD/CSD and experiment. Then, by introducing control surface deflection and control laws, flutter active suppress was studied. Lastly, through filtering and transferring function, the gust temporal signal is obtained based on Dryden gust model, and gust response and suppress were simulated.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.12
• /
• pp.27-37
• /
• 1991

In this paper, the novel PLD (Preceding Layer Driven) MLP (Multi Layer Perceptron) neural network model and its learning algorithm is described. This learning algorithm is different from the conventional. This integer weights and hard limit function are used for synaptic weight values and activation function, respectively. The entire learning process is performed by layer-by-layer method. the number of layers can be varied with difficulty of training data. Since the synaptic weight values are integers, the synapse circuit can be easily implemented with CMOS. PLD MLP neural network was applied to English Characters, arbitrary waveform generation and spiral problem.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.288-298
• /
• 2021

Abstractive text summarization is a process of making a summary of a given text by paraphrasing the facts of the text while keeping the meaning intact. The manmade summary generation process is laborious and time-consuming. We present here a summary generation model that is based on multilayered attentional peephole convolutional long short-term memory (MAPCoL; LSTM) in order to extract abstractive summaries of large text in an automated manner. We added the concept of attention in a peephole convolutional LSTM to improve the overall quality of a summary by giving weights to important parts of the source text during training. We evaluated the performance with regard to semantic coherence of our MAPCoL model over a popular dataset named CNN/Daily Mail, and found that MAPCoL outperformed other traditional LSTM-based models. We found improvements in the performance of MAPCoL in different internal settings when compared to state-of-the-art models of abstractive text summarization.

• Advances in nano research
• /
• v.12 no.3
• /
• pp.263-279
• /
• 2022

In this research, the physical education training quality was investigated using the entropy model to compute variance associated with a random value (a strong tool). The entropy and undefined estimation principles are used to extract the greatest entropy of information dependent on the index system. In the study of tennis motion tracking from a dynamic viewpoint, such stages are utilized to improve the perception of the players' achievement (Lv et al. 2020). Six female tennis players served on the right side (50 cm from the T point). The initial flat serve from T point was the movement under consideration, and the entropy was utilized to weigh all indications. As a result, a multi-index measurement vector is stabilized, followed by the confidence level to determine the structural plane establishment range. As a result, the use of the unascertained measuring technique of information entropy showed an excellent approach to assessing athlete performance more accurately than traditional ways, enabling coaches and athletes to enhance their movements successfully.

• Journal of Sensor Science and Technology
• /
• v.33 no.2
• /
• pp.78-85
• /
• 2024

We proposed a method for visual place recognition that represents images using objects as visual words. Visual words represent the various objects present in urban environments. To detect various objects within the images, we implemented and used a zero-shot detector based on a large-scale image language model. This zero-shot detector enables the detection of various objects in urban environments without additional training. In the process of creating histograms using the proposed method, frequency-based weighting was applied to consider the importance of each object. Through experiments with open datasets, the potential of the proposed method was demonstrated by comparing it with another method, even in situations involving environmental or viewpoint changes.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.56-62
• /
• 2024

To enhance energy efficiency and reduce emissions in prefabricated construction, optimizing the production scheduling of precast concrete is considered an effective approach. Due to the unique characteristics of precast concrete during production, traditional scheduling models are no longer applicable. This present study introduces practical considerations, such as a limited number of molds, buffers, uncertainty of order arrivals and vehicles. Furthermore, to meet the requirements of contemporary industrial development, a mulit-objective optimization scheduling model is formulated by integrating total processing time, on-time delivery rate and work station idle time. A solution based on reinforcement learning algorithm is devised. Results indicate that this method can effectively undergo training and achieve outstanding performance in addressing such issues. The model has the potential to significantly reduce decision-making time in precast production, thereby contributing to the sustainable development of prefabricated construction.

• The KIPS Transactions:PartA
• /
• v.11A no.4
• /
• pp.243-250
• /
• 2004

Monitoring is used to see if a real-time system provides a service on time. Generally, monitoring for real-time focuses on investigating the current status of a real-time system. To support a stable performance of a real-time system, it should have not only a function to see the current status of real-time process but also a function to predict executions of real-time processes, however. The legacy prediction model has some limitation to apply it to a real-time monitoring. First, it performs a static prediction after a real-time process finished. Second, it needs a statistical pre-analysis before a prediction. Third, transition probability and data about clustering is not based on the current data. We propose the execution prediction model based on learning algorithm to solve these problems and apply it to real-time monitoring. This model gets rid of unnecessary pre-processing and supports a precise prediction based on current data. In addition, this supports multi-level prediction by a trend analysis of past execution data. Most of all, We designed the model to support dynamic prediction which is performed within a real-time process' execution. The results from some experiments show that the judgment accuracy is greater than 80% if the size of a training set is set to over 10, and, in the case of the multi-level prediction, that the prediction difference of the multi-level prediction is minimized if the number of execution is bigger than the size of a training set. The execution prediction model proposed in this model has some limitation that the model used the most simplest learning algorithm and that it didn't consider the multi-regional space model managing CPU, memory and I/O data. The execution prediction model based on a learning algorithm proposed in this paper is used in some areas related to real-time monitoring and control.