• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.131-135
• /
• 2021

Numbers of studies related to optimization of design of organic light emitting diodes(OLED) through machine learning are increasing. We propose the generative method of the image to assess the performance of the device combining with machine learning technique. Principle parameter regarding dark spot growth mechanism of the OLED can be the key factor to determine the long-time performance. Captured images from actual device and randomly generated images at specific time and initial pinhole state are fed into the deep neural network system. The simulation reinforced by the machine learning technique can predict the device parameters accurately and faster. Similarly, the inverse design using multiple layer perceptron(MLP) system can infer the initial degradation factors at manufacturing with given device parameter to feedback the design of manufacturing process.

• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.799-810
• /
• 2021

When monitoring the structural integrity of a bridge using data collected through accelerometers, identifying the profile of the load exerted on the bridge from the vehicles passing over it becomes a crucial task. In this study, the speed and location of vehicles on the deck of a bridge is reconfigured using real-time video to implicitly associate the load applied to the bridge with the response from the bridge sensors to develop an image-based deep learning network model. Instead of directly measuring the load that a moving vehicle exerts on the bridge, the intention in the proposed method is to replace the correlation between the movement of vehicles from CCTV images and the corresponding response by the bridge with a neural network model. Given the framework of an input-output-based system identification, CCTV images secured from the bridge and the acceleration measurements from a cantilevered beam are combined during the process of training the neural network model. Since in reality, structural damage cannot be induced in a bridge, the focus of the study is on identifying local changes in parameters by adding mass to a cantilevered beam in the laboratory. The study successfully identified the change in the material parameters in the beam by using the deep-learning neural network model. Also, the method correctly predicted the acceleration response of the beam. The proposed approach can be extended to the structural health monitoring of actual bridges, and its sensitivity to damage can also be improved through optimization of the network training.

• Journal of Korea Multimedia Society
• /
• v.23 no.1
• /
• pp.31-42
• /
• 2020

During the 4th Industrial Revolution, service platforms utilizing diverse contents are emerging, and research on recommended systems that can be customized to users to provide quality service is being conducted. hybrid recommendation systems that provide high accuracy recommendations are being researched in various domains, and various filtering techniques, machine learning, and deep learning are being applied to recommended systems. However, in a recommended service environment where data must be analyzed and processed real time, the accuracy of the recommendation is important, but the computational speed is also very important. Due to high level of model complexity, a hybrid recommendation system or a Deep Learning-based recommendation system takes a long time to calculate. In this paper, a Cascade-hybrid recommended algorithm is proposed that can reduce the computational time while maintaining the accuracy of the recommendation. The proposed algorithm was designed to reduce the complexity of the model and minimize the computational speed while processing sequentially, rather than using existing weights or using a hybrid recommendation technique handled in parallel. Therefore, through the algorithms in this paper, contents can be analyzed and recommended effectively and real time through services such as SNS environments or shared economy platforms.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.129-138
• /
• 2022

Collecting and labeling sufficient training data, which is essential to deep learning-based visual inspection, is difficult for manufacturers to perform because it is very expensive. This paper presents a steel plate surface defect detection system with industrial-grade detection performance by training a small amount of steel plate surface images consisting of labeled and non-labeled data. To overcome the problem of lack of training data, we propose two data augmentation techniques: program-based augmentation, which generates defect images in a geometric way, and generative model-based augmentation, which learns the distribution of labeled data. We also propose a 4-step semi-supervised learning using pseudo labels and consistency training with fixed-size augmentation in order to utilize unlabeled data for training. The proposed technique obtained about 99% defect detection performance for four defect types by using 100 real images including labeled and unlabeled data.

• Smart Structures and Systems
• /
• v.22 no.2
• /
• pp.175-183
• /
• 2018

Time-series data often contain one of the most valuable pieces of information in many fields including manufacturing. Because time-series data are relatively cheap to acquire, they (e.g., vibration signals) have become a crucial part of big data even in manufacturing shop floors. Recently, deep-learning models have shown state-of-art performance for analyzing big data because of their sophisticated structures and considerable computational power. Traditional models for a machinery-monitoring system have highly relied on features selected by human experts. In addition, the representational power of such models fails as the data distribution becomes complicated. On the other hand, deep-learning models automatically select highly abstracted features during the optimization process, and their representational power is better than that of traditional neural network models. However, the applicability of deep-learning models to the field of prognostics and health management (PHM) has not been well investigated yet. This study integrates the "residual fitting" mechanism inherently embedded in the wavelet transform into the convolutional neural network deep-learning structure. As a result, the architecture combines a signal smoother and classification procedures into a single model. Validation results from rotor vibration data demonstrate that our model outperforms all other off-the-shelf feature-based models.

• Journal of Korea Multimedia Society
• /
• v.21 no.5
• /
• pp.626-637
• /
• 2018

Human exchanges information not only through words, but also through body gesture or hand gesture. And they can be used to build effective interfaces in mobile, virtual reality, and augmented reality. The past 2D gesture recognition research had information loss caused by projecting 3D information in 2D. Since the recognition of the gesture in 3D is higher than 2D space in terms of recognition range, the complexity of gesture recognition increases. In this paper, we proposed a real-time gesture recognition deep learning model and application in 3D space using deep learning technique. First, in order to recognize the gesture in the 3D space, the data collection is performed using the unity game engine to construct and acquire data. Second, input vector normalization for learning 3D gesture recognition model is processed based on deep learning. Thirdly, the SELU(Scaled Exponential Linear Unit) function is applied to the neural network's active function for faster learning and better recognition performance. The proposed system is expected to be applicable to various fields such as rehabilitation cares, game applications, and virtual reality.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.428-442
• /
• 2022

A reliable automatic passenger counting (APC) system is a key point in transportation related to the efficient scheduling and management of transport routes. In this study, we introduce a lightweight head detection network using deep learning applicable to an embedded system. Currently, object detection algorithms using deep learning have been found to be successful. However, these algorithms essentially need a graphics processing unit (GPU) to make them performable in real-time. So, we modify a Tiny-YOLOv3 network using certain techniques to speed up the proposed network and to make it more accurate in a non-GPU environment. Finally, we introduce an APC system, which is performable in real-time on embedded systems, using the proposed head detection algorithm. We implement and test the proposed APC system on a Samsung ARTIK 710 board. The experimental results on three public head datasets reflect the detection accuracy and efficiency of the proposed head detection network against Tiny-YOLOv3. Moreover, to test the proposed APC system, we measured the accuracy and recognition speed by repeating 50 instances of entering and 50 instances of exiting. These experimental results showed 99% accuracy and a 0.041-second recognition speed despite the fact that only the CPU was used.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.264-272
• /
• 2022

Human-robot cooperative tasks are increasingly required in our daily life with the development of robotics and artificial intelligence technology. Interactive reinforcement learning strategies suggest that robots learn task by receiving feedback from an experienced human trainer during a training process. However, most of the previous studies on Interactive reinforcement learning have required an extra feedback input device such as a mouse or keyboard in addition to robot itself, and the scenario where a robot can interactively learn a task with human have been also limited to virtual environment. To solve these limitations, this paper studies training strategies of robot that learn table balancing tasks interactively using deep reinforcement learning with human's facial expression feedback. In the proposed system, the robot learns a cooperative table balancing task using Deep Q-Network (DQN), which is a deep reinforcement learning technique, with human facial emotion expression feedback. As a result of the experiment, the proposed system achieved a high optimal policy convergence rate of up to 83.3% in training and successful assumption rate of up to 91.6% in testing, showing improved performance compared to the model without human facial expression feedback.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.613-617
• /
• 2021

According to the growth of the service industry, stresses from emotional labor workers have been emerging as a social problem, thereby so-called the Emotional Labor Protection Act was implemented in 2018. However, insufficient substantial protection systems for emotional workers emphasizes the necessity of a digital stress management system. Thus, in this paper, we suggest a stress detection system for customer service representatives based on deep learning facial expression recognition. This system consists of a real-time face detection module, an emotion classification FER module that deep-learned big data including Korean emotion images, and a monitoring module that only visualizes stress levels. We designed the system to aim to monitor stress and prevent mental illness in emotional workers.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.31-36
• /
• 2020

This research study designed a location image collecting technology. It provides the exact location information of an image which is not given in the photo to the user. Deep learning technology analysis and collects the images. The purpose of this service system is to provide the exact place name, location and the various information of the place such as nearby recommended attractions when the user upload the image photo to the service system. Suggested system has a deep learning model that has a size of 25.3MB, and the model repeats the learning process 50 times with a total of 15,266 data, performing 93.75% of the final accuracy. This system can also be linked with various services potentially for further development.