• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.441-446
• /
• 2020

In this paper, we propose the α-Feature Map Scaling (α-FMS) method which extends the FMS method that was designed to enhance the discriminative power of feature maps of deep neural networks in Speaker Verification (SV) systems. The FMS derives a scale vector from a feature map and then adds or multiplies them to the features, or sequentially apply both operations. However, the FMS method not only uses an identical scale vector for both addition and multiplication, but also has a limitation that it can only add a value between zero and one in case of addition. In this study, to overcome these limitations, we propose α-FMS to add a trainable parameter α to the feature map element-wise, and then multiply a scale vector. We compare the performance of the two methods: the one where α is a scalar, and the other where it is a vector. Both α-FMS methods are applied after each residual block of the deep neural network. The proposed system using the α-FMS methods are trained using the RawNet2 and tested using the VoxCeleb1 evaluation set. The result demonstrates an equal error rate of 2.47 % and 2.31 % for the two α-FMS methods respectively.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.703-712
• /
• 2019

Single image Super-Resolution (SISR) aims to generate a visually pleasing high-resolution image from its degraded low-resolution measurement. In recent years, deep learning - based super - resolution methods have been actively researched and have shown more reliable and high performance. A typical method is WaveletSRNet, which restores high-resolution images through wavelet coefficient learning based on feature maps of images. However, there are two disadvantages in WaveletSRNet. One is a big processing time due to the complexity of the algorithm. The other is not to utilize feature maps efficiently when extracting input image's features. To improve this problems, we propose an efficient single image super resolution method, named RDB-WaveletSRNet. The proposed method uses the residual dense block to effectively extract low-resolution feature maps to improve single image super-resolution performance. We also adjust appropriated growth rates to solve complex computational problems. In addition, wavelet packet decomposition is used to obtain the wavelet coefficients according to the possibility of large scale ratio. In the experimental result on various images, we have proven that the proposed method has faster processing time and better image quality than the conventional methods. Experimental results have shown that the proposed method has better image quality by increasing 0.1813dB of PSNR and 1.17 times faster than the conventional method.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.59-70
• /
• 2018

In order to provide stable district heat supplying service to the certain limited residential area, it is the most important to forecast the short-term future demand more accurately and produce and supply heat in efficient way. However, it is very difficult to develop a universal heat demand forecasting model that can be applied to general situations because the factors affecting the heat consumption are very diverse and the consumption patterns are changed according to individual consumers and regional characteristics. In particular, considering all of the various variables that can affect heat demand does not help improve performance in terms of accuracy and versatility. Therefore, this study aims to develop a demand forecasting model using deep learning based on only limited information that can be acquired in real time. A demand forecasting model was developed by learning the artificial neural network of the Tensorflow using past data consisting only of the outdoor temperature of the area and date as input variables. The performance of the proposed model was evaluated by comparing the accuracy of demand predicted with the previous regression model. The proposed heat demand forecasting model in this research showed that it is possible to enhance the accuracy using only limited variables which can be secured in real time. For the demand forecasting in a certain region, the proposed model can be customized by adding some features which can reflect the regional characteristics.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.50-53
• /
• 2022

Recently, there have been cases in which counterfeit foreign ships have entered and left domestic ports several times. Vessels have a ship-specific serial number given by the International Maritime Organization (IMO) to identify the vessel, and IMO marking is mandatory on all ships built since 2004. In the case of airports and ports, which are representative logistics platforms, a security system is essential, but it is difficult to establish a security system at a port and there are many blind spots, which can cause security problems due to insufficient security systems. In this paper, a port security system is designed using deep learning object recognition and OpenCV. The security system process extracts the IMO number of the ship after recognizing the object when entering the ship, determines whether it is the same ship through feature point matching for ships with entry records, and stores the ship image and IMO number in the entry/exit DB for the first arrival vessel. Through the system of this paper, port security can be strengthened by improving the efficiency and system of port logistics by increasing the efficiency of port management personnel and reducing incidental costs caused by unauthorized entry.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.2
• /
• pp.343-350
• /
• 2022

It is worth verifying the effectiveness of data integration between data with different features. This study investigated whether the data integration affects the accuracy of deep neural network (DNN), and which integration method shows the best improvement. This study used two different public datasets. One public dataset was taken in an actual farm in India. And another was taken in a laboratory environment in Korea. Leaf images were selected from two different public datasets to have five classes which includes normal and four different types of plant diseases. DNN used pre-trained VGG16 as a feature extractor and multi-layer perceptron as a classifier. Data were integrated into three different ways to be used for the training process. DNN was trained in a supervised manner via the integrated data. The trained DNN was evaluated by using a test dataset taken in an actual farm. DNN shows the best accuracy for the test dataset when DNN was first trained by images taken in the laboratory environment and then trained by images taken in the actual farm. The results show that data integration between plant images taken in a different environment helps improve the performance of deep neural networks. And the results also confirmed that independent use of plant images taken in different environments during the training process is more effective in improving the performance of DNN.

• Economic and Environmental Geology
• /
• v.56 no.5
• /
• pp.533-545
• /
• 2023

In this study, an investigation was conducted on the features, events, and processes (FEP) that could impact the long-term safety of the natural barriers constituting high-level radioactive waste geological repositories. The FEP list was developed utilizing the IFEP list 3.0 provided by the Nuclear Energy Agency (NEA) as foundational data, supplemented by geological investigations and research findings from leading countries in this field. A total of 49 FEPs related to the performance of the natural barrier were identified. For each FEP, detailed definitions, classifications, impacts on long-term safety, significance in domestic conditions, and feasibility of quantification were provided. Moreover, based on the compiled FEP list, three scenarios that could affect the long-term safety of the disposal facility were developed. Geological factors affecting the performance of the natural barrier in each scenario were selected and their relationships were visualized. The constructed FEP list and the visualization of interrelated factors in various scenarios are anticipated to provide essential information for selecting and organizing factors that must be considered in the development of mathematical models for quantitatively evaluating the long-term safety of deep geological repositories. In addition, these findings could be effectively utilized in establishing criteria related to the key performance of natural barriers for the confirmation of repository sites.

• Information Systems Review
• /
• v.23 no.3
• /
• pp.51-75
• /
• 2021

Global e-commerce websites offer personalized recommendation services to gain sustainable competitiveness. Existing studies have offered personalized recommendation services using quantitative preferences such as ratings. However, offering personalized recommendation services using only quantitative data has raised the problem of decreasing recommendation performance. For example, a user gave a five-star rating but wrote a review that the user was unsatisfied with hotel service and cleanliness. In such cases, has problems where quantitative and qualitative preferences are inconsistent. Recently, a growing number of studies have considered review data simultaneously to improve the limitations of existing personalized recommendation service studies. Therefore, in this study, we identify review and rating mismatches and build a new user profile to offer personalized recommendation services. To this end, we use deep learning algorithms such as CNN, LSTM, CNN + LSTM, which have been widely used in sentiment analysis studies. And extract sentiment features from reviews and compare with quantitative preferences. To evaluate the performance of the proposed methodology in this study, we collect user preference information using real-world hotel data from the world's largest travel platform TripAdvisor. Experiments show that the proposed methodology in this study outperforms the existing other methodologies, using only existing quantitative preferences.

• KIPS Transactions on Software and Data Engineering
• /
• v.13 no.1
• /
• pp.35-49
• /
• 2024

Video captioning technology, as a significant outcome of the integration between computer vision and natural language processing, has emerged as a key research direction in the field of artificial intelligence. This technology aims to achieve automatic understanding and language expression of video content, enabling computers to transform visual information in videos into textual form. This paper provides an initial analysis of the research trends in deep learning-based video captioning and categorizes them into four main groups: CNN-RNN-based Model, RNN-RNN-based Model, Multimodal-based Model, and Transformer-based Model, and explain the concept of each video captioning model. The features, pros and cons were discussed. This paper lists commonly used datasets and performance evaluation methods in the video captioning field. The dataset encompasses diverse domains and scenarios, offering extensive resources for the training and validation of video captioning models. The model performance evaluation method mentions major evaluation indicators and provides practical references for researchers to evaluate model performance from various angles. Finally, as future research tasks for video captioning, there are major challenges that need to be continuously improved, such as maintaining temporal consistency and accurate description of dynamic scenes, which increase the complexity in real-world applications, and new tasks that need to be studied are presented such as temporal relationship modeling and multimodal data integration.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.3
• /
• pp.281-301
• /
• 2024

The power cable tunnels which are part of the underground transmission line project, are constructed using the shield TBM method. The disc cutter among the shield TBM components plays an important role in breaking rock mass. Efficient tunnel construction is possible only when appropriate replacement occurs as the wear limit is reached or damage such as uneven wear occurs. A study was conducted to determine the wear conditions of disc cutter using a deep learning algorithm based on real-time measurement data of wear and rotation speed. Based on the results of full-scaled tunnelling tests, it was confirmed that measurement data was obtained differently depending on the wear conditions of disc cutter. Using real-time measurement data, an algorithm was developed to determine disc cutter wear characteristics based on a convolutional neural network model. Distributional patterns of data can be learned through CNN filters, and the performance of the model that can classify uniform wear and uneven wear through these pattern features.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3598-3614
• /
• 2020

With the increase of motor vehicles and tourism demand, some traffic problems gradually appear, such as traffic congestion, safety accidents and insufficient allocation of traffic resources. Facing these challenges, a model of Spatio-Temporal Dilated Convolutional Network (STDGCN) is proposed for assistance of extracting highly nonlinear and complex characteristics to accurately predict the future traffic flow. In particular, we model the traffic as undirected graphs, on which graph convolutions are built to extract spatial feature informations. Furthermore, a dilated convolution is deployed into graph convolution for capturing multi-scale contextual messages. The proposed STDGCN integrates the dilated convolution into the graph convolution, which realizes the extraction of the spatial and temporal characteristics of traffic flow data, as well as features of road occupancy. To observe the performance of the proposed model, we compare with it with four rivals. We also employ four indicators for evaluation. The experimental results show STDGCN's effectiveness. The prediction accuracy is improved by 17% in comparison with the traditional prediction methods on various real-world traffic datasets.