• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.91-99
• /
• 2024

Collision avoidance system is important to improve the robustness and functional safety of autonomous vehicles. This paper proposes an object-level distance estimation method to develop a collision avoidance system, and it is applied to golfcarts utilized in country club environments. To improve the detection accuracy, we continually trained an object detection model based on pseudo labels generated by a pre-trained detector. Moreover, we propose object-aware depth estimation (OADE) method which trains a depth model focusing on object regions. In the OADE algorithm, we generated dense depth information for object regions by utilizing detection results and sparse LiDAR points, and it is referred to as object-aware LiDAR projection (OALP). By using the OALP maps, a depth estimation model was trained by backpropagating more gradients of the loss on object regions. Experiments were conducted on our custom dataset, which was collected for the travel distance of 22 km on 54 holes in three country clubs under various weather conditions. The precision and recall rate were respectively improved from 70.5% and 49.1% to 95.3% and 92.1% after the continual learning with pseudo labels. Moreover, the OADE algorithm reduces the absolute relative error from 4.76% to 4.27% for estimating distances to obstacles.

• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.58-67
• /
• 2020

In this paper, we propose a data-driven-based beam selection scheme for massive multiple-input and multiple-output (MIMO) systems in ultra-dense networks (UDN), which is capable of addressing the problem of high computational cost of conventional coordinated beamforming approaches. We consider highly dense small-cell scenarios with more small cells than mobile stations, in the millimetre-wave band. The analog beam selection for hybrid beamforming is a key issue in realizing millimetre-wave UDN MIMO systems. To reduce the computation complexity for the analog beam selection, in this paper, two deep neural network models are used. The channel samples, channel gains, and radio frequency beamforming vectors between the access points and mobile stations are collected at the central/cloud unit that is connected to all the small-cell access points, and are used to train the networks. The proposed machine-learning-based scheme provides an approach for the effective implementation of massive MIMO system in UDN environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4255-4269
• /
• 2019

This paper proposes an image generation method using a Multi Discriminator Generative Adversarial Net (MDGAN) as a next generation 2D game sprite creation technique. The proposed GAN is an Autoencoder-based model that receives three areas of information-color, shape, and animation, and combines them into new images. This model consists of two encoders that extract color and shape from each image, and a decoder that takes all the values of each encoder and generates an animated image. We also suggest an image processing technique during the learning process to remove the noise of the generated images. The resulting images show that 2D sprites in games can be generated by independently learning the three image attributes of shape, color, and animation. The proposed system can increase the productivity of massive 2D image modification work during the game development process. The experimental results demonstrate that our MDGAN can be used for 2D image sprite generation and modification work with little manual cost.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1029-1035
• /
• 2019

In recent years, artificial intelligence (AI) services have become one of the most essential parts to extend human capabilities in various fields such as face recognition for security, weather prediction, and so on. Various learning algorithms for existing AI services are utilized, such as classification, regression, and deep learning, to increase accuracy and efficiency for humans. Nonetheless, these services face many challenges such as fake news spread on social media, stock selection, and volatility delay in stock prediction systems and inaccurate movie-based recommendation systems. In this paper, various algorithms are presented to mitigate these issues in different systems and services. Convolutional neural network algorithms are used for detecting fake news in Korean language with a Word-Embedded model. It is based on k-clique and data mining and increased accuracy in personalized recommendation-based services stock selection and volatility delay in stock prediction. Other algorithms like multi-level fusion processing address problems of lack of real-time database.

• Smart Structures and Systems
• /
• v.32 no.2
• /
• pp.111-121
• /
• 2023

This study proposes an automated assembly performance evaluation method for prefabricated steel structures (PSSs) using machine learning methods. Assembly component images were segmented using a modified version of the receptive field pyramid. By factorizing channel modulation and the receptive field exploration layers of the convolution pyramid, highly accurate segmentation results were obtained. After completing segmentation, the positions of the bolt holes were calculated using various image processing techniques, such as fuzzy-based edge detection, Hough's line detection, and image perspective transformation. By calculating the distance ratio between bolt holes, the assembly performance of the PSS was estimated using the k-nearest neighbors (kNN) algorithm. The effectiveness of the proposed framework was validated using a 3D PSS printing model and a field test. The results indicated that this approach could recognize assembly components with an intersection over union (IoU) of 95% and evaluate assembly performance with an error of less than 5%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.421-422
• /
• 2021

국내·외 기업들의 기술을 보호하고자 매년 100만개의 특허가 출원되고 있다. 등록된 특허 수가 증가될수록 전문가의 판단만으로 원하는 기술 분야의 유효한 특허문서를 선별하는 것은 효율적이지 않으며 객관적인 결과를 기대하기 어려워진다. 본 연구에서는 유효 특허문서 분류 정확성과 전문가의 업무 효율성을 제고하고자 비지도학습 모델인 잠재 디리클레 할당 알고리즘(Latent Dirichlet Allocation, LDA)과 딥러닝을 활용하여 자동 특허문서 분류 시스템을 제안하고자 한다.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.109-116
• /
• 2020

With the advent of high-speed railways, railways are one of the most frequently used means of transportation at home and abroad. In addition, in terms of environment, carbon dioxide emissions are lower and energy efficiency is higher than other transportation. As the interest in railways increases, the issue related to railway safety is one of the important concerns. Among them, visual abnormalities occur when various obstacles such as animals and people suddenly appear in front of the railroad. To prevent these accidents, detecting rail tracks is one of the areas that must basically be detected. Images can be collected through cameras installed on railways, and the method of detecting railway rails has a traditional method and a method using deep learning algorithm. The traditional method is difficult to detect accurately due to the various noise around the rail, and using the deep learning algorithm, it can detect accurately, and it combines the two algorithms to detect the exact rail. The proposed algorithm determines the accuracy of railway rail detection based on the data collected.

• Korean Journal of Construction Engineering and Management
• /
• v.22 no.5
• /
• pp.73-85
• /
• 2021

This study proposes an efficient management direction for Korean construction accident cases through a deep learning-based text data classification model. A deep learning model was developed, which categorizes five categories of construction accidents: fall, electric shock, flying object, collapse, and narrowness, which are representative accident types of KOSHA. After initial model tests, the classification accuracy of fall disasters was relatively high, while other types were classified as fall disasters. Through these results, it was analyzed that 1) specific accident-causing behavior, 2) similar sentence structure, and 3) complex accidents corresponding to multiple types affect the results. Two accuracy improvement experiments were then conducted: 1) reclassification, 2) elimination. As a result, the classification performance improved with 185.7% when eliminating complex accidents. Through this, the multicollinearity of complex accidents, including the contents of multiple accident types, was resolved. In conclusion, this study suggests the necessity to independently manage complex accidents while preparing a system to describe the situation of future accidents in detail.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.141-148
• /
• 2021

This paper presents a method to detect zebra-crossing using deep learning which combines SegNet and ResNet. For the blind, a safe crossing system is important to know exactly where the zebra-crossings are. Zebra-crossing detection by deep learning can be a good solution to this problem and robotic vision-based assistive technologies sprung up over the past few years, which focused on specific scene objects using monocular detectors. These traditional methods have achieved significant results with relatively long processing times, and enhanced the zebra-crossing perception to a large extent. However, running all detectors jointly incurs a long latency and becomes computationally prohibitive on wearable embedded systems. In this paper, we propose a model for fast and stable segmentation of zebra-crossing from captured images. The model is improved based on a combination of SegNet and ResNet and consists of three steps. First, the input image is subsampled to extract image features and the convolutional neural network of ResNet is modified to make it the new encoder. Second, through the SegNet original up-sampling network, the abstract features are restored to the original image size. Finally, the method classifies all pixels and calculates the accuracy of each pixel. The experimental results prove the efficiency of the modified semantic segmentation algorithm with a relatively high computing speed.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.