• Corrosion Science and Technology
• /
• v.20 no.2
• /
• pp.62-68
• /
• 2021

Artificial neural network techniques show an excellent ability to predict the data (output) for various complex characteristics (input). It is primarily specialized to solve nonlinear relationship problems. This study is an experimental investigation that applies artificial neural network techniques and an experimental design to predict the cyclic polarization curves of the super-austenitic stainless steel AL-6XN alloy with sensitization. A cyclic polarization test was conducted in a 3.5% NaCl solution based on an experimental design matrix with various factors (degree of sensitization, temperature, pH) and their levels, and a total of 36 cyclic polarization data were acquired. The 36 cyclic polarization patterns were used as training data for the artificial neural network model. As a result, the supervised learning algorithms with back-propagation showed high learning and prediction performances. The model showed an excellent training performance (R²=0.998) and a considerable prediction performance (R²=0.812) for the conditions that were not included in the training data.

• Journal of Electrochemical Science and Technology
• /
• v.10 no.3
• /
• pp.276-283
• /
• 2019

Nitinol is an alloy of nickel and titanium. Nitinol is one of the shape memory alloys(SMA) that are restored to a remembered form, changing the crystal structure at a given temperature. Because of these unique features, it is used in medical devices, high precision sensors, and aerospace industries. However, the conventional method of mechanical machining for nitinol has problems of thermal and residual stress after processing. Therefore, the electrochemical machining(ECM), which does not produce residual stress and thermal deformation, has emerged as an alternative processing technique. In addition, to replace the existing experimental planning methods, this study used deep neural network(DNN), which is the basis for AI. This method was shown to be more useful than conventional method of design of experiments(RSM, Taguchi, Regression) by applying deep neural network(DNN) to electrochemical machining(ECM) and comparing root mean square errors(RMSE). Comparison with actual experimental values has shown that DNN is a more useful method than conventional method. (DOE - RSM, Taguchi, Regression). The result of the machining was accurately and efficiently predicted by applying electrochemical machining(ECM) and deep neural network(DNN) to the shape memory alloy(SMA), which is a hard-mechinability material.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.6
• /
• pp.289-296
• /
• 2018

Drone detection in FMCW radar system needs complex techniques because a drone beat frequency is highly dynamic and unpredictable. Therefore, the current static signal processing algorithms cannot show appropriate detection accuracy. With dynamic signal fluctuation and environmental clutters, it can fail to detect a drone or make false detection. It affects to the radar system integrity and safety. Constant false alarm rate (CFAR), one of famous static signal process algorithm is effective for static environment. But for drone detection, it shows low detection accuracy. In this paper, we suggest neural network based FMCW radar system for detecting a drone. We use recurrent neural network (RNN) because it is the effective neural network for signal processing. In our FMCW radar system, one transmitter emits FMCW signal and four-way fixed receivers detect reflected drone beat frequency. The coordinate of the drone can be calculated with four receivers information by triangulation. Therefore, RNN only learns and inferences reflected drone beat frequency. It helps higher learning and detection accuracy. With several drone flight experiments, RNN shows false detection rate and detection accuracy as 21.1% and 96.4%, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.475-482
• /
• 2018

In this paper, we present a study on data augmentation methods for DNN (Deep Neural Network)-based audio tagging. In this system, an audio signal is converted into a mel-spectrogram and used as an input to the DNN for audio tagging. To cope with the problem associated with a small number of training data, we augment the training samples using time stretching, pitch shifting, dynamic range compression, and block mixing. In this paper, we derive optimal parameters and combinations for the augmentation methods through audio tagging simulations.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.227-233
• /
• 2019

In this paper, we propose a deep neural network-based sound interpolation method for realizing virtual reality sound. Through this method, sound between two points is generated by using acoustic signals obtained from two points. Sound interpolation can be performed by statistical methods such as arithmetic mean or geometric mean, but this is insufficient to reflect actual nonlinear acoustic characteristics. In order to solve this problem, in this study, the sound interpolation is performed by training the deep neural network based on the acoustic signals of the two points and the target point, and the experimental results show that the deep neural network-based sound interpolation method is superior to the statistical methods.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.33-38
• /
• 2021

This paper presents a comparative study between the parameter-optimized Pacejka model and artificial neural network model for the tire force estimation. The two different approaches are investigated and compared in this study. First, offline optimization is conducted based on Pacejka Magic Formula model to determine the proper parameter set for the minimization of tire force error between the model and test data set. Second, deep neural network model is used to fit the model to the tire test data set. The actual tire forces are measured using MTS Flat-Track test platform and the measurements are used as the reference tire data set. The focus of this study is on the applicability of machine learning technique to tire force estimation. It is shown via the regression results that the deep neural network model is more effective in describing the tire force than the parameter-optimized Pacejka model.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.6
• /
• pp.89-97
• /
• 2022

Ultrasonic metal welding has been widely used for joining lithium-ion battery tabs. Weld quality monitoring has been an important issue in lithium-ion battery manufacturing. This study focuses on the weld quality monitoring in ultrasonic metal welding with the longitudinal-torsional vibration mode horn developed newly. As the quality of ultrasonic welding depends on welding parameters like pressure, time, and amplitude, the suitable values of these parameters were selected for experimentation. The welds were tested via tensile testing machine and weld strengths were investigated. The dataset collected for performance test was used to train the multi-layer perceptron neural network. The three layer neural network was used for the study and the optimum number of neurons in the first and second hidden layers were selected based on performances of each models. The best models were selected for the horn and then tested to see their performances on an unseen dataset. The neural network models for the longitudinal-torsional mode horn attained test accuracy of 90%. This result implies that proposed models has potential for the weld quality monitoring.

• Journal of Information Processing Systems
• /
• v.18 no.1
• /
• pp.75-88
• /
• 2022

With the development of the sharing economy, existing recommender services are changing from user-item recommendations to user-user recommendations. The most important consideration is that all users should have the best possible satisfaction. To achieve this outcome, the matching service adds information between users and items necessary for the existing recommender service and information between users, so higher-level data mining is required. To this end, this paper proposes a user-to-user matching service (UTU-MS) employing the prediction of mutual satisfaction based on learning. Users were divided into consumers and suppliers, and the properties considered for recommendations were set by filtering and weighting. Based on this process, we implemented a convolutional neural network (CNN)-deep neural network (DNN)-based model that can predict each supplier's satisfaction from the consumer perspective and each consumer's satisfaction from the supplier perspective. After deriving the final mutual satisfaction using the predicted satisfaction, a top recommendation list is recommended to all users. The proposed model was applied to match guests with hosts using Airbnb data, which is a representative sharing economy platform. The proposed model is meaningful in that it has been optimized for the sharing economy and recommendations that reflect user-specific priorities.

• Electronics and Telecommunications Trends
• /
• v.38 no.5
• /
• pp.34-50
• /
• 2023

Quantum error correction is a key technology for achieving fault-tolerant quantum computation. Finding the best decoding solution to a single error syndrome pattern counteracting multiple errors is an NP-hard problem. Consequently, error decoding is one of the most expensive processes to protect the information in a logical qubit. Recent research on quantum error decoding has been focused on developing conventional and neural-network-based decoding algorithms to satisfy accuracy, speed, and scalability requirements. Although conventional decoding methods have notably improved accuracy in short codes, they face many challenges regarding speed and scalability in long codes. To overcome such problems, machine learning has been extensively applied to neural-network-based error decoding with meaningful results. Nevertheless, when using neural-network-based decoders alone, the learning cost grows exponentially with the code size. To prevent this problem, hierarchical error decoding has been devised by combining conventional and neural-network-based decoders. In addition, research on quantum error decoding is aimed at reducing the spacetime decoding cost and solving the backlog problem caused by decoding delays when using hardware-implemented decoders in cryogenic environments. We review the latest research trends in decoders for quantum error correction with high accuracy, neural-network-based quantum error decoders with high speed and scalability, and hardware-based quantum error decoders implemented in real qubit operating environments.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.7
• /
• pp.32-45
• /
• 1995

In this paper, we present a new method to tool path planning problem for rough cut of pocket milling operations. The key idea is to formulate the tool path problem into a TSP (Travelling Salesman Problem) so that the powerful neural network approach can be effectively applied. Specifically, our method is composed of three procedures: a) discretization of the pocket area into a finite number of tool points, b) neural network approach (called SOM-Self Organizing Map) for path finding, and c) postprocessing for path smoothing and feedrate adjustment. By the neural network procedure, an efficient tool path (in the sense of path length and tool retraction) can be robustly obtained for any arbitrary shaped pockets with many islands. In the postprocessing, a) the detailed shape of the path is fine tuned by eliminating sharp corners of the path segments, and b) any cross-overs between the path segments and islands. With the determined tool path, the feedrate adjustment is finally performed for legitimate motion without requiring excessive cutting forces. The validity and powerfulness of the algorithm is demonstrated through various computer simulations and real machining.