• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.7
• /
• pp.191-198
• /
• 2021

Since the size of training dataset become large and the model is getting deeper to achieve high accuracy in deep learning, the deep neural network training requires a lot of computation and it takes too much time with a single node. Therefore, distributed deep learning is proposed to reduce the training time by distributing computation across multiple nodes. In this study, we propose hybrid allreduce strategy that considers the characteristics of each layer and communication and computational overlapping technique for synchronization of distributed deep learning. Since the convolution layer has fewer parameters than the fully-connected layer as well as it is located at the upper, only short overlapping time is allowed. Thus, butterfly allreduce is used to synchronize the convolution layer. On the other hand, fully-connecter layer is synchronized using ring all-reduce. The empirical experiment results on PyTorch with our proposed scheme shows that the proposed method reduced the training time by up to 33% compared to the baseline PyTorch.

• Journal of the Korea Convergence Society
• /
• v.10 no.6
• /
• pp.7-14
• /
• 2019

In this paper, we propose a Cascade Classifier face detection method using the Haar-like feature, which is complemented by the Flood Fill algorithm for lossy areas due to illumination and shadow in YCbCr color space extraction. The Cascade Classifier using Haar-like features can generate noise and loss regions due to lighting, shadow, etc. because skin color extraction using existing YCbCr color space in image only uses threshold value. In order to solve this problem, noise is removed by erosion and expansion calculation, and the loss region is estimated by using the Flood Fill algorithm to estimate the loss region. A threshold value of the YCbCr color space was further allowed for the estimated area. For the remaining loss area, the color was filled in as the average value of the additional allowed areas among the areas estimated above. We extracted faces using Haar-like Cascade Classifier. The accuracy of the proposed method is improved by about 4% and the detection rate of the proposed method is improved by about 2% than that of the Haar-like Cascade Classifier by using only the YCbCr color space.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_2
• /
• pp.1179-1192
• /
• 2018

In order to detect the Antarctic Polar Front (PF) among the main fronts in the Southern Ocean, this study is based on the combinations of satellite-based sea surface temperature (SST) and height (SSH) observations. For accurate PF detection, we classified the signals as front or non-front grids based on the Bayesian decision theory from daily SST and SSH datasets, and then spatio-temporal synthesis has been performed to remove primary noises and to supplement geographical connectivity of the front grids. In addition, sea ice and coastal masking were employed in order to remove the noise that still remains even after performing the processes and morphology operations. Finally, we selected only the southernmost grids, which can be considered as fronts and determined as the monthly PF by a linear smoothing spline optimization method. The mean positions of PF in this study are very similar to those of the PFs reported by the previous studies, and it is likely to be well represents PF formation along the bottom topography known as one of the major influences of the PF maintenance. The seasonal variation in the positions of PF is high in the Ross Sea sector (${\sim}180^{\circ}W$), and Australia sector ($120^{\circ}E-140^{\circ}E$), and these variations are quite similar to the previous studies. Therefore, it is expected that the detection approach for the PF position applied in this study and the final composite have a value that can be used in related research to be carried out on the long term time-scale.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.100-109
• /
• 2019

Maintainability indicates the extent to which maintenance can be done easily and quickly. The consideration of maintainability is crucial to reduce the operation and support costs of weapon systems, but if the maintainability is evaluated after the prototype production is done and necessitates design changes, it may increase the cost and delay the schedule. The evaluation should verify whether maintenance work can be performed, and support the designers in developing a design to improve maintainability. In previous studies, the maintainability index was calculated using the graph theory at the early design phase, but evaluation accuracy appeared to be limited. Analyzing the methods of evaluating the maintainability using fuzzy logic and 3D modeling indicate that the design of a system with good maintainability should be done in an integrated manner during the whole system life cycle. This paper proposes a method to evaluate maintainability using SysML-based modeling and simulation technique and fuzzy logic. The physical design structure with maintainability attributes was modeled using SysML 'bdd' diagram, and the maintainability was represented by an AHP matrix for maintainability attributes. We then calculated the maintainability using AHP-based weighting calculation and fuzzy logic through the use of SysML 'par' diagram that incorporated MATLAB. The proposed maintainability model can be managed efficiently and consistently, and the state of system design and maintainability can be analyzed quantitatively, thereby improving design by early identifying the items with low maintainability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.5
• /
• pp.550-558
• /
• 2019

As the scale of the Internet of Things (IoT) environment grows and develops day by day, the information collected and shared through IoT devices becomes increasingly diverse and more common. However, because IoT devices have limitations on computing power and a low power capacity due to their miniaturized size, it is difficult to apply security technologies like encryption and authentication that have been directly applied in the previous Internet environment, making the IoT vulnerable to security threats. Because of this weakness, important information that needs to be delivered safely and accurately is exposed to the threat of malicious exploitation, such as data forgery, data leakage, and infringement of personal information. In order to overcome this threat, various security studies are being actively conducted to compensate for the weaknesses in IoT environment devices. In particular, since various devices interact, and share and communicate information collected in the IoT environment, each device should be able to communicate with reliability. With regard to this, various studies have been carried out on techniques for device authentication. This study examines the limitations and problems of the authentication techniques that have been studied thus far, and proposes technologies that can certify IoT devices for safe communication between reliable devices in the Internet environment.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.1-9
• /
• 2021

In this paper, we propose a training algorithm of support vector machine (SVM) with a sensitive variable. Although machine learning models enable automatic decision making in the real world applications, regulations prohibit sensitive information from being used to protect privacy. In particular, the privacy protection of the legally protected attributes such as race, gender, and disability is compulsory. We present an efficient least square SVM (LSSVM) training algorithm using a fully homomorphic encryption (FHE) to protect a partial sensitive attribute. Our framework posits that data owner has both non-sensitive attributes and a sensitive attribute while machine learning service provider (MLSP) can get non-sensitive attributes and an encrypted sensitive attribute. As a result, data owner can obtain the encrypted model parameters without exposing their sensitive information to MLSP. In the inference phase, both non-sensitive attributes and a sensitive attribute are encrypted, and all computations should be conducted on encrypted domain. Through the experiments on real data, we identify that our proposed method enables to implement privacy-preserving sensitive LSSVM with FHE that has comparable performance with the original LSSVM algorithm. In addition, we demonstrate that the efficient sensitive LSSVM with FHE significantly improves the computational cost with a small degradation of performance.

• Journal of Internet Computing and Services
• /
• v.20 no.5
• /
• pp.95-104
• /
• 2019

Various kinds of devices are used for the Internet of Things (IoT) service, and IoT devices mainly use communication technology that uses the frequency of the unlicensed band. There are several types of communication technology in the unlicensed band, but WiFi is most commonly used. Devices used for IoT services vary in computing resources from devices with limited capabilities to smartphones and provide services over wireless networks such as WiFi. Most IoT devices can't perform complex operations for network control, thus they choose a WiFi access point (AP) based on signal strength. This causes a decrease in IoT service efficiency. In this paper, an intelligent AP system that can efficiently control the WiFi connection of the IoT devices is implemented. Based on the network information measured by the IoT device, the access point learns using a feed forward neural network algorithm, and predicts a network connection state to control the WiFi connection. By controlling the WiFi connection at the AP, the service efficiency of the IoT device can be improved.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.9 no.4
• /
• pp.11-22
• /
• 1999

Least-mean-square(LMS) adaptive filters have proven to be extremely useful in a number of signal processing tasks. However LMS adaptive filter suffer from a slow rate of convergence for a given steady-state mean square error as compared to the behavior of recursive least squares adaptive filter. In this paper an efficient signal interference control technique is introduced to improve the convergence speed of LMS algorithm with tap weighted vectors updating which were controled by reusing data which was abandoned data in the Adaptive transversal filter in the scheme with data recycling buffers. The computer simulation show that the character of convergence and the value of MSE of proposed algorithm are faster and lower than the existing LMS according to increasing the step-size parameter $\mu$ in the experimentally computed. learning curve. Also we find that convergence speed of proposed algorithm is increased by (B+1) time proportional to B which B is the number of recycled data buffer without complexity of computation. Adaptive transversal filter with proposed data recycling buffer algorithm could efficiently reject ISI of channel and increase speed of convergence in avoidance burden of computational complexity in reality when it was experimented having the same condition of LMS algorithm.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.11 no.1
• /
• pp.13-23
• /
• 2001

This paper implemented into hardware SEED which is the KOREA standard 128-bit block cipher. First, at the respect of hardware implementation, we compared and analyzed SEED with AES finalist algorithms - MARS, RC6, RIJNDAEL, SERPENT, TWOFISH, which are secret key block encryption algorithms. The encryption of SEED is faster than MARS, RC6, TWOFISH, but is as five times slow as RIJNDAEL which is the fastest. We propose a SEED hardware architecture which improves the encryption speed. We divided one round into three parts, J1 function block, J2 function block J3 function block including key mixing block, because SEED repeatedly executes the same operation 16 times, then we pipelined one round into three parts, J1 function block, J2 function block, J3 function block including key mixing block, because SEED repeatedly executes the same operation 16 times, then we pipelined it to make it more faster. G-function is implemented more easily by xoring four extended 4 byte SS-boxes. We tested it using ALTERA FPGA with Verilog HDL. If the design is synthesized with 0.5 um Samsung standard cell library, encryption of ECB and decryption of ECB, CBC, CFB, which can be pipelined would take 50 clock cycles to encrypt 384-bit plaintext, and hence we have 745.6 Mbps assuming 97.1 MHz clock frequency. Encryption of CBC, OFB, CFB and decryption of OFB, which cannot be pipelined have 258.9 Mbps under same condition.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.14 no.5
• /
• pp.109-119
• /
• 2004

The home network environment can be defined as a network environment, connecting digital home devices such as computer systems, digital appliances, and mobile devices. In this kind of home network environments, there will be numerous local/remote interactions to monitor and control the home network devices and the home gateway. Such an environment may result in communication bottleneck. By applying the mobile agents that can migrate among the computing devices autonomously and work on behalf of the user, remote interactions and network traffics can be reduced enormously. The mobile agent authentication is necessary to apply mobile agent concept to the home network environments, as a prerequisite technology for authorization or access control to the home network devices and resources. The existing mobile agent systems have mainly used the public key based authentication scheme, which is not suitable to the home network environments, composed of digital devices of limited computation capability. In this paper, we propose a shared key based mobile agent authentication scheme for single home domain and expand the scheme to multiple domain environments with the public key based authentication scheme. Application of the shared key encryption scheme to the single domain mobile agent authentication enables to authenticate the mobile agent with less overhead than the public key based authentication scheme.