• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• Journal of the Korean Society for Heat Treatment
• /
• v.36 no.6
• /
• pp.396-401
• /
• 2023

Aus-tempering heat treatment is suitable for thin and small-sized in precision parts. However, the heat treatment process relies on the experience and skill of the operator, making it challenging to produce precision parts due to the cold forging process. The aims of this study is to explore suitable machine learning models using data from the aus-tempering heat treatment process and analyze the factors that significantly impact the mechanic properties (e.g. hardness). As a result, the study analyzed, from a machine learning perspective, how hardness prediction varies based on the quenching temperature, carbon (C), and copper (Cu) contents.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.7
• /
• pp.72-79
• /
• 2021

This study reports on the experiment of using deep learning algorithms to determine the machining process of aluminium and steel. A face cutting milling tool was used for machining and the cutting speed was set between 3 and 4 mm/s. Both materials were machined with a depth to 0.5mm and 1.0mm. To demonstrate the developed deep learning algorithm, simulation experiments were performed using the VGGish algorithm in MATLAB toobox. Downcutting was used to cut aluminum and steel as a machining process for high quality and precise learning. As a result of learning algorithms using audio data, 61%-99% accuracy was obtained in four categories: Al 0.5mm, Al 1.0mm, Steel 0.5mm and Steel 1.0mm. Audio discrimination using deep learning is derived as a probabilistic result.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.2
• /
• pp.301-307
• /
• 2021

After the spread of the data collection devices such as smart meters, energy data is increasingly collected in a variety of ways, and its importance continues to grow. However, due to technical or practical limitations, errors such as missing or outliers in the data occur during data collection process. Especially in the case of customer-related data, billing problems may occur, so energy companies are conducting various research to process such data. In addition, efforts are being made to create added value from data, which makes it difficult to provide such services unless reliability of data is guaranteed. In order to solve these challenges, this research analyzes prior research related to bad data processing specifically in the energy field, and propose new missing value processing methods to improve the reliability and field utilization of energy data.

• Journal of IKEEE
• /
• v.21 no.2
• /
• pp.136-141
• /
• 2017

In this paper, we propose an algorithm for memory optimization to apply deep learning to PC. The proposed algorithm minimizes the memory and computation processing time by reducing the amount of computation processing and data required in the conventional deep learning structure in a general PC. The algorithm proposed in this paper consists of three steps: a convolution layer configuration process using a random filter with discriminating power, a data reduction process using PCA, and a CNN structure creation using SVM. The learning process is not necessary in the convolution layer construction process using the discriminating random filter, thereby shortening the learning time of the overall deep learning. PCA reduces the amount of memory and computation throughput. The creation of the CNN structure using SVM maximizes the effect of reducing the amount of memory and computational throughput required. In order to evaluate the performance of the proposed algorithm, we experimented with Yale University's Extended Yale B face database. The results show that the algorithm proposed in this paper has a similar performance recognition rate compared with the existing CNN algorithm. And it was confirmed to be excellent. Based on the algorithm proposed in this paper, it is expected that a deep learning algorithm with many data and computation processes can be implemented in a general PC.

• International Journal of Advanced Culture Technology
• /
• v.10 no.4
• /
• pp.420-426
• /
• 2022

Developing a machine learning model and putting it into production goes through a number of steps. Automated Machine Learning(AutoML) appeared to increase productivity and efficiency by automating inefficient tasks that occur while repeating this process whenever machine learning is applied. The high degree of automation of AutoML models allows non-experts to use machine learning models and techniques without the need to become machine learning experts. Automating the process of applying machine learning end-to-end with AutoML models has the added benefit of creating simpler solutions, generating these solutions faster, and often generating models that outperform hand-designed models. In this paper, the AutoML data is collected and AutoML's Color Petri net model is created and analyzed based on it.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.2
• /
• pp.1-8
• /
• 2011

In this study, software products developed in the course of testing, software managers in the process of testing software test and test tools for effective learning effects perspective has been studied using the NHPP software. The finite failure non-homogeneous Poisson process models presented and the life distribution applied extreme distribution which used to find the minimum (or the maximum) of a number of samples of various distributions. Software error detection techniques known in advance, but influencing factors for considering the errors found automatically and learning factors, by prior experience, to find precisely the error factor setting up the testing manager are presented comparing the problem. As a result, the learning factor is greater than automatic error that is generally efficient model could be confirmed. This paper, a numerical example of applying using time between failures and parameter estimation using maximum likelihood estimation method, after the efficiency of the data through trend analysis model selection were efficient using the mean square error.

• Transactions of Materials Processing
• /
• v.30 no.4
• /
• pp.186-194
• /
• 2021

Finite element simulation is a widely applied method for practical purpose in various metal forming process. However, in the simulation of elasto-plastic behavior of porous material or in crystal plasticity coupled multi-scale simulation, it requires much calculation time, which is a limitation in its application in practical situations. A machine learning model that directly outputs the constitutive equation without iterative calculations would greatly reduce the calculation time of the simulation. In this study, we examined the possibility of artificial intelligence based constitutive equation with the input of existing state variables and current velocity filed. To introduce the methodology, we described the process of obtaining the training data, machine learning process and the coupling of machine learning model with commercial software DEFROM^TM, as a preliminary study, via rigid plastic finite element simulation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.4
• /
• pp.701-706
• /
• 2019

The advent of the AI(: Artificial Intelligence) has applied to many industrial and general applications have havingact on our lives these days. Various types of machine learning methods are supported in this field. The supervised learning method of the machine learning has features and targets as an input in the learning process. There are many supervised learning methods as well and their performance varies depends on the characteristics and states of the big data type as an input data. Therefore, in this paper, in order to compare the performance of the various supervised learning method with a specific big data set, the supervised learning methods supported in the Tensorflow and the Sckit-Learn are simulated and analyzed in the Jupyter Notebook environment with python.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.471-476
• /
• 2024

With the spread of various smart devices and computing devices, big data generation is occurring widely. Machine learning is an algorithm that performs reasoning by learning data patterns. Among the various machine learning algorithms, the algorithm that attracts attention is deep learning based on neural networks. Deep learning is achieving rapid performance improvement with the release of various applications. Recently, among deep learning algorithms, attempts to analyze data using graph structures are increasing. In this study, we present a graph generation method for transferring to a deep learning network. This paper proposes a method of generalizing node properties and edge weights in the graph generation process and converting them into a structure for deep learning input by presenting a matricization We present a method of applying a linear transformation matrix that can preserve attribute and weight information in the graph generation process. Finally, we present a deep learning input structure of a general graph and present an approach for performance analysis.