• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.43-52
• /
• 2023

Rubber produced by rubber companies is subjected to quality suitability inspection through rheometer test, followed by secondary processing for automobile parts. However, rheometer test is being conducted by humans and has the disadvantage of being very dependent on experts. In order to solve this problem, this paper proposes a deep learning-based rheometer quality inspection system. The proposed system combines LSTM(Long Short-Term Memory) and CNN(Convolutional Neural Network) to take advantage of temporal and spatial characteristics from the rheometer. Next, combination materials of each rubber was used as an auxiliary input to enable quality conformity inspection of various rubber products in one model. The proposed method examined its performance with 30,000 validation datasets. As a result, an F1-score of 0.9940 was achieved on average, and its excellence was proved.

• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1071-1082
• /
• 2021

Since the smart factory has been recently recognized as an industrial core requirement, various mechanisms to ensure efficient and stable operation have attracted much attention. This attention is based on the fact that in a smart factory environment where operating processes, such as facility control, data collection, and decision making are automated, the disruption of processes due to problems such as facility anomalies causes considerable losses. Although many studies have considered methods to prevent such losses, few have investigated how to effectively apply the solutions. This study proposes a Kubernetes based system applied in a smart factory providing effective operation and facility management. To develop the system, we employed a useful and popular open source project, and adopted deep learning based anomaly detection model for multi-sensor anomaly detection. This can be easily modified without interruption by changing the container image for inference. Through experiments, we have verified that the proposed method can provide system stability through nondisruptive maintenance, monitoring and non-disruptive updates for anomaly detection models.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.1
• /
• pp.58-65
• /
• 2019

The stability, reliability and efficiency of a smart ship are important issues as the interest in an autonomous ship has recently been high. An automatic collision avoidance system is an essential function of an autonomous ship. This system detects the possibility of collision and automatically takes avoidance actions in consideration of economy and safety. In order to construct an automatic collision avoidance system using reinforcement learning, in this work, the sequential decision problem of ship collision is mathematically formulated through a Markov Decision Process (MDP). A reinforcement learning environment is constructed based on the ship maneuvering equations, and then the three key components (state, action, and reward) of MDP are defined. The state uses parameters of the relationship between own-ship and target-ship, the action is the vertical distance away from the target course, and the reward is defined as a function considering safety and economics. In order to solve the sequential decision problem, the Deep Deterministic Policy Gradient (DDPG) algorithm which can express continuous action space and search an optimal action policy is utilized. The collision avoidance system is then tested assuming the $90^{\circ}$intersection encounter situation and yields a satisfactory result.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.39-47
• /
• 2020

In this paper, we proposed a deep learning-based detection method using Saliency Attention to detect salient objects in images. The salient object detection separates the object where the human eye is focused from the background, and determines the highly relevant part of the image. It is usefully used in various fields such as object tracking, detection, and recognition. Existing deep learning-based methods are mostly Autoencoder structures, and many feature losses occur in encoders that compress and extract features and decoders that decompress and extend the extracted features. These losses cause the salient object area to be lost or detect the background as an object. In the proposed method, Saliency Attention is proposed to reduce the feature loss and suppress the background region in the Autoencoder structure. The influence of the feature values was determined using the ELU activation function, and Attention was performed on the feature values in the normalized negative and positive regions, respectively. Through this Attention method, the background area was suppressed and the projected object area was emphasized. Experimental results showed improved detection results compared to existing deep learning methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.262-269
• /
• 2020

Recently, many attempts have been made to reduce the time required for payment in various shopping environments. In addition, for the Fourth Industrial Revolution era, artificial intelligence is advancing, and Internet of Things (IoT) devices are becoming more compact and cheaper. So, by integrating these two technologies, access to building an unmanned environment to save people time has become easier. In this paper, we propose a smart shopping cart system based on low-cost IoT equipment and deep-learning object-detection technology. The proposed smart cart system consists of a camera for real-time product detection, an ultrasonic sensor that acts as a trigger, a weight sensor to determine whether a product is put into or taken out of the shopping cart, an application for smartphones that provides a user interface for a virtual shopping cart, and a deep learning server where learned product data are stored. Communication between each module is through Transmission Control Protocol/Internet Protocol, a Hypertext Transmission Protocol network, a You Only Look Once darknet library, and an object detection system used by the server to recognize products. The user can check a list of items put into the smart cart via the smartphone app, and can automatically pay for them. The smart cart system proposed in this paper can be applied to unmanned stores with high cost-effectiveness.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.6
• /
• pp.375-380
• /
• 2022

High-speed railway bridges carry a risk of dynamic response amplification due to resonance caused by train loads, and running safety and riding comfort must therefore be reviewed through dynamic analysis in accordance with design codes. The running safety and ride comfort calculation procedure, however, is time consuming and expensive because dynamic analyses must be performed for every 10 km/h interval up to 110% of the design speed, including the critical speed for each train type. In this paper, a deep-learning-based prediction system that can predict the running safety and ride comfort in advance is proposed. The system does not use dynamic analysis but employs a deep learning algorithm. The proposed system is based on a neural network trained on the dynamic analysis results of each train and speed of the railway bridge and can predict the running safety and ride comfort according to input parameters such as train speed and bridge characteristics. To confirm the performance of the proposed system, running safety and riding comfort are predicted for a single span, straight simple beam bridge. Our results confirm that the deck vertical displacement and deck vertical acceleration for calculating running safety and riding comfort can be predicted with high accuracy.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.155-162
• /
• 2020

Recently, with the development of computer vision and deep learning technology, research on human action recognition has been actively conducted for video analysis, video surveillance, interactive multimedia, and human machine interaction applications. Diverse techniques have been introduced for human action understanding and classification by many researchers using RGB image, depth image, skeleton and inertial data. However, skeleton-based action discrimination is still a challenging research topic for human machine-interaction. In this paper, we propose an end-to-end skeleton joints mapping of action for generating spatio-temporal image so-called dynamic image. Then, an efficient deep convolution neural network is devised to perform the classification among the action classes. We use publicly accessible UTD-MHAD skeleton dataset for evaluating the performance of the proposed method. As a result of the experiment, the proposed system shows better performance than the existing methods with high accuracy of 97.45%.

• Structural Engineering and Mechanics
• /
• v.83 no.3
• /
• pp.401-413
• /
• 2022

The collapse of civil infrastructure due to natural disasters results in financial losses and many casualties. In particular, the recent increase in earthquake activities has highlighted on the importance of assessing the seismic performance and predicting the seismic risk of a structure. However, the nonlinear behavior of a structure and the uncertainty in ground motion complicate the accurate seismic response prediction of a structure. Artificial intelligence can overcome these limitations to reasonably predict the nonlinear behavior of structures. In this study, a deep learning-based algorithm was developed to estimate the time-history seismic response of bridge structures. The proposed deep neural network was trained using structural and ground motion parameters. The performance of the seismic response prediction algorithm showed the similar phase and magnitude to those of the time-history analysis in a single-degree-of-freedom system that exhibits nonlinear behavior as a main structural element. Then, the proposed algorithm was expanded to predict the seismic response and fragility prediction of a bridge system. The proposed deep neural network reasonably predicted the nonlinear seismic behavior of piers and bearings for approximately 93% and 87% of the test dataset, respectively. The results of the study also demonstrated that the proposed algorithm can be utilized to assess the seismic fragility of bridge components and system.

• Journal of Advanced Navigation Technology
• /
• v.19 no.6
• /
• pp.484-491
• /
• 2015

Aerial scene is greatly increased by the introduction and supply of the image due to the growth of digital optical imaging technology and development of the UAV. It has been used as the extraction of ground properties, classification, change detection, image fusion and mapping based on the aerial image. In particular, in the image analysis and utilization of deep learning algorithm it has shown a new paradigm to overcome the limitation of the field of pattern recognition. This paper presents the possibility to apply a more wide range and various fields through the segmentation and classification of aerial scene based on the Deep learning(ConvNet). We build 4-classes image database consists of Road, Building, Yard, Forest total 3000. Each of the classes has a certain pattern, the results with feature vector map come out differently. Our system consists of feature extraction, classification and training. Feature extraction is built up of two layers based on ConvNet. And then, it is classified by using the Multilayer perceptron and Logistic regression, the algorithm as a classification process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.10
• /
• pp.1300-1306
• /
• 2018

The purpose of this study is to see possibility of Char2Vec as alternative of Word2Vec that most famous word embedding model in Sentence Similarity Measure Problem by Deep-Learning. In experiment, we used the Siamese Ma-LSTM recurrent neural network architecture for measure similarity two random sentences. Siamese Ma-LSTM model was implemented with tensorflow. We train each model with 200 epoch on gpu environment and it took about 20 hours. Then we compared Word2Vec based model training result with Char2Vec based model training result. as a result, model of based with Char2Vec that initialized random weight record 75.1% validation dataset accuracy and model of based with Word2Vec that pretrained with 3 million words and phrase record 71.6% validation dataset accuracy. so Char2Vec is suitable alternate of Word2Vec to optimize high system memory requirements problem.