• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.463-472
• /
• 2000

In this paper, we consider the problem of realizing associative memories via cellular neural network(CNN). After introducing qualitative properties of the CNN model, we formulate the synthesis of CNN that can store given binary vectors with optimal performance as a constrained optimization problem. Next, we observe that this problem's constraints can be transformed into simple inequalities involving linear matrix inequalities(LMIs). Finally, we reformulate the synthesis problem as a generalized eigenvalue problem(GEVP), which can be efficiently solved by recently developed interior point methods. Proposed method can be applied to both space varying template CNNs and space-invariant template CNNs. The validity of the proposed approach is illustrated by design examples.

• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1356-1364
• /
• 2016

This paper proposes a novel aesthetic photo recomposition method using a deep convolutional neural network (DCNN). Previous recomposition approaches define the aesthetic score of photo composition based on the distribution of salient objects, and enhance the photo composition by maximizing the score. These methods suffer from heavy computational overheads, and often fail to enhance the composition because their optimization depends on the performance of existing salient object detection algorithms. Unlike previous approaches, we address the photo recomposition problem by utilizing DCNN, which shows remarkable performance in object detection and recognition. DCNN is used to iteratively predict cropping directions for a given photo, thus generating an aesthetically enhanced photo in terms of composition. Experimental results and user study show that the proposed framework can automatically crop the photo to follow specific composition guidelines, such as the rule of thirds.

• Journal of Korean Association for Spatial Structures
• /
• v.20 no.2
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.

• Journal of the Korea Convergence Society
• /
• v.9 no.8
• /
• pp.33-39
• /
• 2018

In the Internet of Things (IoT) era, objects are connected to each other by wired and wireless networks, and information is exchanged whenever necessary. Channel and network environments change over time; thus, a carrier sensing function that identifies whether signals containing information are present in the channel is essential. The carrier sensing circuit of a wireless communication system determines the receiver sensitivity, and the receiver sensitivity is closely related to the service coverage and service quality of the system. As the receiver sensitivity decreases, the service coverage increases but it becomes sensitive to noise. However, as the receiver sensitivity increases, the service coverage decreases but it becomes insensitive to the noise. Therefore, carrier sensing design and optimization are very important from the viewpoint of the receiver sensitivity and noise sensitivity. This paper proposes an effective carrier sensing technique from the viewpoint of the receiver sensitivity for the long range IoT.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.6
• /
• pp.620-628
• /
• 2010

Small satellites can be used for various space research and scientific or educational purposes due to advantages in small size, low-cost, and rapid development. Small Satellites have many advantages of application to Responsive Space. Compared to traditional larger satellites, however, Small satellites have many constraints due to limitations in size. Therefore, it is difficult to expect high performance. To approach maximum capability with minimal size, weight, and cost, standard modular platform of Small satellites is necessary. Modularity supports plug-and-play architecture. The result is Small satellites that can be combined quickly and reliably using plug-and-play mechanisms. For communication between modules, standard bus interface is needed. Controller Area Network(CAN) protocol is considered optimum data bus for modular Small satellite. CAN can be applied to data communication with high reliability. Hence, design optimization and simplification can also be expected. For ease of assembly and integration, modular design can be considered. This paper proposes development method for standardized modular Small satellites, and describes design of data interface based on CAN and a method of testing for modularity.

• The Journal of the Korea Contents Association
• /
• v.17 no.7
• /
• pp.93-100
• /
• 2017

Recently, demands for high-performance flash-based storage devices (i.e., flash SSD) have rapidly grown in social network services, cloud computing, super-computing, and enterprise storage systems. The industry and academic communities made the NVMe specification for high-performance storage devices, and NVMe-based flash SSDs can be now obtained in the market. In this article, we evaluate performance of NoSQL databases that social network services and cloud computing services heavily adopt by using NVMe-based flash SSDs. To this end, we use NVMe SSD that Samsung Electronics recently developed, and the SSD used in this study has performance up to 3.5GB/s for sequential read/write operations. We use WiredTiger for NoSQL databases, and it is a default storage engine for MongoDB. Our experimental results show that log processing in NoSQL databases is a major overhead when high-performance NVMe-based flash SSDs are used. Furthermore, we optimize components of log processing and optimized WiredTiger show up to 15 times better performance than original WiredTiger.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.152-167
• /
• 2016

This paper investigates the simultaneous wireless information and power transfer (SWIPT) for two-hop orthogonal frequency division multiplexing (OFDM) decode-and-forward (DF) relay network, where a relay harvests energy from radio frequency signals transmitted by a source and then uses the harvested energy to assist information transmission from the source to its destination. The power splitting receiver is considered at the relay. To explore the performance limit of such a SWIPT-enabled system, a resource allocation (RA) optimization problem is formulated to maximize the achievable information rate of the system, where the power allocation, the subcarrier pairing and the power splitting factor are jointly optimized. As the problem is non-convex and there is no known solution method, we first decompose it into two separate subproblems and then design an efficient RA algorithm. Simulation results demonstrate that our proposed algorithm can achieve the maximum achievable rate of the system and also show that to achieve a better system performance, the relay node should be deployed near the source in the SWIPT-enabled two-hop OFDM DF relay system, which is very different from that in conventional non-SWIPT system where the relay should be deployed at the midpoint of the line between the source and the destination.

• The KIPS Transactions:PartC
• /
• v.14C no.7
• /
• pp.597-602
• /
• 2007

In conventional cooperative communication data rate is 1/2 than non cooperative protocols. In this paper, we propose a full data rate DF (Decode and Forward) cooperative transmission scheme. Proposed scheme is based on time division multiplexing (TDM) channel access. When DF protocol has full data rate, it can not obtain diversity gain under the pairwise error probability (PEP) view point. If it increases time slot to obtain diversity gain, then data rate is reduced. The proposed algorithm uses orthogonal frequency and constellation rotation to obtain both full data rate and diversity order 2. Moreover, performance is analyzed according to distance and optimized components that affect the system performance by using computer simulation. The simulation results revealed that the cooperation can save the network power up to 7dB over direct transmission and 5dB over multi-hop transmission at BER of $10^{-2}$. Besides, it can improve date rate of system compared with the conventional DF protocol.

• Journal of Communications and Networks
• /
• v.12 no.6
• /
• pp.568-576
• /
• 2010

The paper presents a control architecture aimed at implementing bandwidth optimization combined with call admission control (CAC) over a digital video broadcasting (DVB) return channel satellite terminal (RCST) under quality of service (QoS) constraints. The approach can be applied in all cases where traffic flows, coming from a terrestrial portion of the network, are merged together within a single DVB flow, which is then forwarded over the satellite channel. The paper introduces the architecture of data and control plane of the RCST at layer 2. The data plane is composed of a set of traffic buffers served with a given bandwidth. The control plane proposed in this paper includes a layer 2 resource manager (L2RM), which is structured into decision makers (DM), one for each traffic buffer of the data plane. Each DM contains a virtual queue, which exactly duplicates the corresponding traffic buffer and performs the actions to compute the minimum bandwidth need to assure the QoS constraints. After computing the minimum bandwidth through a given algorithm (in this view the paper reports some schemes taken in the literature which may be applied), each DM communicates this bandwidth value to the L2RM, which allocates bandwidth to traffic buffers at the data plane. Real bandwidth allocations are driven by the information provided by the DMs. Bandwidth control is linked to a CAC scheme, which uses current bandwidth allocations and peak bandwidth of the call entering the network to decide admission. The performance evaluation is dedicated to show the efficiency of the proposed combined bandwidth allocation and CAC.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1295-1301
• /
• 2019

In this paper, we propose a novel method of denoising human motion using a bidirectional recurrent neural network (BRNN) with an attention mechanism. The corrupted motion captured from a single 3D depth sensor camera is automatically fixed in the well-established smooth motion manifold. Incorporating an attention mechanism into BRNN achieves better optimization results and higher accuracy than other deep learning frameworks because a higher weight value is selectively given to a more important input pose at a specific frame for encoding the input motion. Experimental results show that our approach effectively handles various types of motion and noise, and we believe that our method can sufficiently be used in motion capture applications as a post-processing step after capturing human motion.