• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.451-457
• /
• 2018

We propose an automatic detection and classification system of sewer damage database based on artificial intelligence and deep learning. In order to optimize the performance, we implemented a robust system against various environmental variations such as illumination and shadow changes. In our proposed system, a crack detection and damage classification method using a deep learning based Convolutional Neural Network (CNN) is implemented. For optimal results, 9,941 CCTV images with $256{\times}256$ pixel resolution were used for machine learning on the damaged area based on the CNN model. As a result, the recognition rate of 98.76% was obtained. Total of 646 images of $720{\times}480$ pixel resolution were extracted from various sewage DB for performance evaluation. Proposed system presents the optimal recognition rate for the automatic detection and classification of damage in the sewer DB constructed in various environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1704-1720
• /
• 2020

Recognizing food from photographs presents many applications for machine learning, computer vision and dietetics, etc. Recent progress of deep learning techniques accelerates the recognition of food in a great scale. We build a hierarchical structure composed of deep CNN to recognize and classify food from photographs. We build a dataset for Korean food of 18 classes, which are further categorized in 4 major classes. Our hierarchical recognizer classifies foods into four major classes in the first step. Each food in the major classes is further classified into the exact class in the second step. We employ DenseNet structure for the baseline of our recognizer. The hierarchical structure provides higher accuracy and F1 score than those from the single-structured recognizer.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.33-39
• /
• 2019

In this paper, we propose deep convolutional neural network(CNN) with bottleneck structure which improves the performance of earthquake classification. In order to address all possible forms of earthquakes including micro-earthquakes and artificial-earthquakes as well as large earthquakes, we need a representation and classifier that can effectively discriminate seismic waveforms in adverse conditions. In particular, to robustly classify seismic waveforms even in low snr, a deep CNN with 1x1 convolution bottleneck structure is proposed in raw seismic waveforms. The representative experimental results show that the proposed method is effective for noisy seismic waveforms and outperforms the previous state-of-the art methods on domestic earthquake database.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.651-658
• /
• 2021

In this paper, we propose methods for character recognition and classification for table items through deep learning. First, table areas are detected in a document image through CNN. After that, table areas are separated by separators such as vertical lines. The text in document is recognized through a neural network combined with CNN and RNN. To correct errors in the character recognition, multiple candidates for the recognized result are provided for a sentence which has low recognition accuracy.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.2
• /
• pp.61-72
• /
• 2020

Recently, researches that are using deep learning technology in various fields are being conducted. The fields include geographic map processing. In this paper, I propose a method to infer where the map area included in the image is. The proposed method generates and learns images including a map, detects map areas from input images, extracts character strings belonging to those map areas, and converts the extracted character strings into coordinates through geocoding to infer the coordinates of the input image. Faster R-CNN was used for learning and map detection. In the experiment, the difference between the center coordinate of the map on the test image and the center coordinate of the detected map is calculated. The median value of the results of the experiment is 0.00158 for longitude and 0.00090 for latitude. In terms of distance, the difference is 141m in the east-west direction and 100m in the north-south direction.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.166-175
• /
• 2023

Reinforcement learning can be applied to a wide variety of problems. However, the fundamental limitation of reinforcement learning is that it is difficult to derive an answer within a given time because the problems in the real world are too complex. Then, with the development of neural network technology, research on deep reinforcement learning that combines deep learning with reinforcement learning is receiving lots of attention. In this paper, two types of neural networks are combined with reinforcement learning and their characteristics were compared and analyzed with existing value-based reinforcement learning algorithms. Two types of neural networks are FNN and CNN, and existing reinforcement learning algorithms are SARSA and Q-learning.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.644-645
• /
• 2021

In this paper, we propose a hardware structure of a watermarking processor based on deep learning technology to protect the intellectual property rights of ultra-high resolution digital images and videos. We propose an optimization methodology to implement a deep learning-based watermarking algorithm in hardware.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.10-11
• /
• 2021

As concrete is used in many construction works, the use of aggregates is increasing. However, supply and demand of high-quality aggregates has become difficult recently, and although circular aggregates that recycle construction waste are used, the performance of concrete, such as liquidity and strength, are being reduced due to defective aggregates. As a result, quality tests such as sieve analysis test are conducted, but a lot of waste occurs such as time and manpower. To solve this problem, this study was conducted to measure the assembly rate of fine aggregate, which accounts for about 35% of the concrete volume, using Deep Learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.43-50
• /
• 2021

Recently, researches and projects of companies based on artificial intelligence have been actively carried out. Various services and systems are being grafted with artificial intelligence technology. They become more intelligent. Accordingly, interest in deep learning, one of the techniques of artificial intelligence, and people who want to learn it have increased. In order to learn deep learning, deep learning theory with a lot of knowledge such as computer programming and mathematics is required. That is a high barrier to entry to beginners. Therefore, in this study, we designed and implemented a web-based deep learning platform called DeepBlock, which enables beginners to implement basic models of deep learning such as DNN and CNN without considering programming and mathematics. The proposed DeepBlock can be used for the education of students or beginners interested in deep learning.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.375-390
• /
• 2024

Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.