• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.5
• /
• pp.69-79
• /
• 2010

In the current cloud environments, the applications are executed on the remote cloud server, and they also utilize computing resources of the remote cloud server such as physical memory and CPU. Therefore, if remote server is exposed to security threat, every applications in remote server can be victim by several security-attacks. Especially, despite many advantages, both individuals and businesses often have trouble to start the cloud services according to the malicious administrator of the cloud server. We propose a security-enhanced local process executing scheme resolving vulnerability of current cloud computing environments. Since secret data is stored in the local, we can protect secret data from security threats of the cloud server. By utilizing computing resource of local computer instead of remote server, high-secure processes can be set free from vulnerability of remote server.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.640-645
• /
• 2021

The deep learning based end-to-end TTS system consists of Text2Mel module that generates spectrogram from text, and vocoder module that synthesizes speech signals from spectrogram. Recently, by applying deep learning technology to the TTS system the intelligibility and naturalness of the synthesized speech is as improved as human vocalization. However, it has the disadvantage that the inference speed for synthesizing speech is very slow compared to the conventional method. The inference speed can be improved by applying the non-autoregressive method which can generate speech samples in parallel independent of previously generated samples. In this paper, we introduce FastSpeech, FastSpeech 2, and FastPitch as Text2Mel technology, and Parallel WaveGAN, Multi-band MelGAN, and WaveGlow as vocoder technology applying non-autoregressive method. And we implement them to verify whether it can be processed in real time. Experimental results show that by the obtained RTF all the presented methods are sufficiently capable of real-time processing. And it can be seen that the size of the learned model is about tens to hundreds of megabytes except WaveGlow, and it can be applied to the embedded environment where the memory is limited.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.160-168
• /
• 2022

In this paper, we propose a 3D mesh reconstruction method from a single image using deep learning and a sphere shape transformation method. The proposed method has the following originality that is different from the existing method. First, the position of the vertex of the sphere is modified to be very similar to the 3D point cloud of an object through a deep learning network, unlike the existing method of building edges or faces by connecting nearby points. Because 3D point cloud is used, less memory is required and faster operation is possible because only addition operation is performed between offset value at the vertices of the sphere. Second, the 3D mesh is reconstructed by covering the surface information of the sphere on the modified vertices. Even when the distance between the points of the 3D point cloud created by correcting the position of the vertices of the sphere is not constant, it already has the face information of the sphere called face information of the sphere, which indicates whether the points are connected or not, thereby preventing simplification or loss of expression. can do. In order to evaluate the objective reliability of the proposed method, the experiment was conducted in the same way as in the comparative papers using the ShapeNet dataset, which is an open standard dataset. As a result, the IoU value of the method proposed in this paper was 0.581, and the chamfer distance value was It was calculated as 0.212. The higher the IoU value and the lower the chamfer distance value, the better the results. Therefore, the efficiency of the 3D mesh reconstruction was demonstrated compared to the methods published in other papers.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.422-429
• /
• 2022

A light sensor chip requires a small capacity eFuse (electrical fuse) OTP (One-Time Programmable) memory IP (Intellectual Property) to trim analog circuits or set initial values of digital registers. In this paper, 128-bit eFuse OTP IP is designed using only 3.3V MV (Medium Voltage) devices without using 1.8V LV (Low-Voltage) logic devices. The eFuse OTP IP designed with 3.3V single MOS devices can reduce a total process cost of three masks which are the gate oxide mask of a 1.8V LV device and the LDD implant masks of NMOS and PMOS. And since the 1.8V voltage regulator circuit is not required, the size of the illuminance sensor chip can be reduced. In addition, in order to reduce the number of package pins of the illumination sensor chip, the VPGM voltage, which is a program voltage, is applied through the VPGM pad during wafer test, and the VDD voltage is applied through the PMOS power switching circuit after packaging, so that the number of package pins can be reduced.

• 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.

• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.453-462
• /
• 2022

In this paper, the artificial intelligence (AI) technology used in the medical image analysis field was analyzed through a literature review. Literature searches were conducted on PubMed, ResearchGate, Google and Cochrane Review using the key word. Through literature search, 114 abstracts were searched, and 98 abstracts were reviewed, excluding 16 duplicates. In the reviewed literature, AI is applied in classification, localization, disease detection, disease segmentation, and fit degree of registration images. In machine learning (ML), prior feature extraction and inputting the extracted feature values into the neural network have disappeared. Instead, it appears that the neural network is changing to a deep learning (DL) method with multiple hidden layers. The reason is thought to be that feature extraction is processed in the DL process due to the increase in the amount of memory of the computer, the improvement of the calculation speed, and the construction of big data. In order to apply the analysis of medical images using AI to medical care, the role of physicians is important. Physicians must be able to interpret and analyze the predictions of AI algorithms. Additional medical education and professional development for existing physicians is needed to understand AI. Also, it seems that a revised curriculum for learners in medical school is needed.

• Geophysics and Geophysical Exploration
• /
• v.25 no.3
• /
• pp.109-119
• /
• 2022

The computational efficiency of reverse time migration (RTM) based on numerical modeling is not secured due to the high-frequency band of several hundred Hz or higher for data acquired through a three-dimensional (3D) ultra-high-resolution (UHR) seismic survey. Therefore, this study develops an RTM program to derive high-quality 3D geological structures using UHR seismic data. In the traditional 3D RTM program, an excitation amplitude technique that stores only the maximum amplitude of the source wavefield and a domain-limiting technique that minimizes the modeling area where the source and receivers are located were used to significantly reduce memory usage and calculation time. The program developed through this study successfully derived a 3D migration image with a horizontal grid size of 1 m for the 3D UHR seismic survey data obtained from the Korea Institute of Geoscience and Mineral Resources in 2019, and geological analysis was conducted.

• Journal of Advanced Navigation Technology
• /
• v.27 no.3
• /
• pp.306-313
• /
• 2023

Realistic and graphics-based virtual reality content is based on 360-degree videos, and viewport extraction through the viewer's intention or automatic recommendation function is essential. This paper designs a viewport extraction system based on multiple object tracking in 360-degree videos and proposes a parallel computing structure necessary for multiple viewport extraction. The viewport extraction process in 360-degree videos is parallelized by composing pixel-wise threads, through 3D spherical surface coordinate transformation from ERP coordinates and 2D coordinate transformation of 3D spherical surface coordinates within the viewport. The proposed structure evaluated the computation time for up to 30 viewport extraction processes in aerial 360-degree video sequences and confirmed up to 5240 times acceleration compared to the CPU-based computation time proportional to the number of viewports. When using high-speed I/O or memory buffers that can reduce ERP frame I/O time, viewport extraction time can be further accelerated by 7.82 times. The proposed parallelized viewport extraction structure can be applied to simultaneous multi-access services for 360-degree videos or virtual reality contents and video summarization services for individual users.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.295-303
• /
• 2023

As the cloud computing market grows, a variety of cloud services are now reliably delivered. Administrative agencies and public institutions of South Korea are transferring all their information systems to cloud systems. It is essential to develop security solutions in advance in order to safely operate cloud services, as protecting cloud services from misuse and malicious access by insiders and outsiders over the Internet is challenging. In this paper, we propose a zero trust model for cloud storage services that store sensitive data. We then verify the effectiveness of the proposed model by operating a cloud storage service. Memory, web, and network forensics are also performed to track access and usage of cloud users depending on the adoption of the zero trust model. As a cloud storage service, we use Amazon S3(Simple Storage Service) and deploy zero trust techniques such as access control lists and key management systems. In order to consider the different types of access to S3, furthermore, we generate service requests inside and outside AWS(Amazon Web Services) and then analyze the results of the zero trust techniques depending on the location of the service request.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.