• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.135-144
• /
• 2021

Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1938-1943
• /
• 2005

Network human-robot interface is an important research topic. In home application, users access the robotic system directly via voice, gestures or through the network. Users explore a system by using the services provided by this system and to some extend users are enable to participate in a service as partners. A service may be provided by a robot, a group of robots or robots and other network connected systems (distributed sensors, information systems, etc). All these services are done in the network environment, where uncertainty such as the unstable network connection, the availability of the partners in a service, exists. Moreover, these services are controlled by several users, accessing at different time by different methods. Our research aimed at solving this problem to provide a high available level, flexible coordination system. In this paper, a multi-agent framework is proposed. This framework is validated by using our new concept of slave agents, a responsive multi-agent environment, a virtual directory facilitator (VDF), and a task allocation system using contract net protocol. Our system uses a mixed model between distributed and centralized model. It uses a centralized agent management system (AMS) to control the overall system. However, the partners and users may be distributed agents connected to the center through agent communication or centralized at the AMS container using the slave agents to represent the physical agents. The system is able to determine the task allocation for a group of robot working as a team to provide a service. A number of experiments have been conducted successfully in our lab environment using Issac robot, a PDA for user agent and a wireless network system, operated under our multi agent framework control. The experiments show that this framework works well and provides some advantages to existing systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2325-2349
• /
• 2014

Network virtualization technology plays a key role in cloud computing, which serves as an effective approach for provisioning a flexible and highly adaptable shared substrate network to satisfy the demands of various applications or services. Recently, the problem of mapping a virtual network (VN) onto a substrate network has been addressed by various algorithms. However, these algorithms are typically efficient for unicast service-oriented virtual networks, and generally not applicable to multicast service-oriented virtual networks (MVNs). Furthermore, the survivable MVN mapping (SMVNM) problem that considers the survivability of MVN has not been studied and is also the focus of this work. In this research, we discuss SMVNM problem under regional failures in the substrate network and propose an efficient algorithm for solving this problem. We first propose a framework and formulate the SMVNM problem with the objective of minimizing mapping cost by using mixed integer linear programming. Then we design an efficient heuristic to solve this problem and introduce several optimizations to achieve the better mapping solutions. We validate and evaluate our framework and algorithms by conducting extensive simulations on different realistic networks under various scenarios, and by comparing with existing approaches. Our simulation experiments and results show that our approach outperforms existing solutions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.7
• /
• pp.2892-2913
• /
• 2016

Network virtualization promises to play a dominant role in shaping the future Internet by overcoming the Internet ossification problem. However, due to the injecting of additional virtualization layers into the network architecture, several new security risks are introduced by the network virtualization. Although traditional protection mechanisms can help in virtualized environment, they are not guaranteed to be successful and may incur high security overheads. By performing the virtual network (VN) embedding in a security-aware way, the risks exposed to both the virtual and substrate networks can be minimized, and the additional techniques adopted to enhance the security of the networks can be reduced. Unfortunately, existing embedding algorithms largely ignore the widespread security risks, making their applicability in a realistic environment rather doubtful. In this paper, we attempt to address the security risks by integrating the security factors into the VN embedding. We first abstract the security requirements and the protection mechanisms as numerical concept of security demands and security levels, and the corresponding security constraints are introduced into the VN embedding. Based on the abstraction, we develop three security-risky modes to model various levels of risky conditions in the virtualized environment, aiming at enabling a more flexible VN embedding. Then, we present a mixed integer linear programming formulation for the VN embedding problem in different security-risky modes. Moreover, we design three heuristic embedding algorithms to solve this problem, which are all based on the same proposed node-ranking approach to quantify the embedding potential of each substrate node and adopt the k-shortest path algorithm to map virtual links. Simulation results demonstrate the effectiveness and efficiency of our algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.1
• /
• pp.14-24
• /
• 2002

In this paper, a design of the pulsewidth-modulation(PWM) neural network with both retrieving and learning function is proposed. In the designed PWM neural system, the input and output signals of the neural network are represented by PWM signals. In neural network, the multiplication is one of the most commonly used operations. The multiplication and summation functions are realized by using the PWM technique and simple mixed-mode circuits. Thus, the designed neural network only occupies the small chip area. By applying some circuit design techniques to reduce the nonideal effects, the designed circuits have good linearity and large dynamic range. Moreover, the delta learning rule can easily be realized. To demonstrate the learning capability of the realized PWM neural network, the delta learning nile is realized. The circuit with one neuron, three synapses, and the associated learning circuits has been designed. The HSPICE simulation results on the two learning examples on AND function and OR function have successfully verified the function correctness and performance of the designed neural network.

• Journal of Wetlands Research
• /
• v.7 no.2
• /
• pp.121-132
• /
• 2005

To classify the surface sedimentary facies using IKONOS image collected over Hwangdo tidal flat in Cheonsu Bay, the optical reflectance was compared for characterizing various sedimentary environments such as grain size, tidal channel pattern and area ratio of surface remnant water. The intertidal DEM (Digital Elevation Model) was generated by echo-sounder for analyzing the relationship between IKONOS image and sedimentary environments including topography. The boundary of the optical reflectance between mud-mixed facies and sand facies was distinct, and discrimination of the associated sandbar feature was also possible. The mud-mixed facies coupled with intricate tidal channels is confined to the relatively hi호 topography of Hwangdo tidal flat. The boundary between mud and mixed flat was indistinct in IKONOS optical reflectance but it would have a difference in the area ratio of surface remnant water. The dark area in the image represented the well developed sand facies having a lot of surface remnant water due to the relatively low surface topography. The overall accuracy of characterizing the surface sediment facies by maximum likelihood classification method was 86.2 %. These results demonstrate that high spatial resolution satellite imagery such as IKONOS coupled with knowledge of grain size, surface remnant water and tidal channel network can be effectively used to characterize the surface sedimentary facies (mud, mixed and sand) network of the tidal flat environments.

• Journal of the Korean Institute of Educational Facilities
• /
• v.24 no.6
• /
• pp.19-26
• /
• 2017

The aim of this study is to suggest an improvement of BTL in Educational Facilities applying the concept of n-BPPP(non-Benefits Public-Private Partnerships). The research is based on four of ninety-nine completed projects of Mixed-use Educational Facilities since 2001. Ninety-nine projects are analyzed and categorized to the typology of architectural program. The architectural programs planned are uniform in function, such as gym, swimming pool, library, info-center, parking etc. The public parking is a main program in the BTL projects, where district offices are involved as partner. The difference between BTL and n-BPPP for educational facilities is the business units. The n-BPPP concerns in regional or district units in order to expand public infrastructure facilities based on the network of schools and local community. And the fund for n-BPPP does not come from the government but from the investors. The economic interest is to reinvest on the maintenance of the facilities. The benefits of n-BPPP will be not only for the Governments in terms of social welfare budgets but also for local residents and students in terms of a variety of high-quality public services. The concept of n-BPPP can be an alternative way for the Mixed-use Educational Facilities.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.23 no.4
• /
• pp.105-113
• /
• 2017

Purpose: While Japan undergoes super aged society, Japanese Elderly Facilities are trying to keep elderly residents from social isolation and expand regional interaction. Methods: This study analyzes regional linkage characteristics through 8 cases of Aichi-Elderly Facilities which realize regional interaction and symbiosis(life together) between various generations by visiting. Result: 1) Most researched facilities except SO provide and share opportunity for interaction with community and residents through space for regional interaction including cafe and various programs and interactive settings. 2) The facility which seeks regional linkage through Mixed-use of facilities can devide into (1) Mixed-use of facilities easy to found, (2) Addition of housing function (NM, SM, DM) and (3) Mixed-use with different facilities(HY, GM) 3) The characteristics of interaction and symbiosis between generations are (1) to adopt concept of life together to have interaction possibility with young generation and children: most studied facilities except SO (2) to establish elderly residence into facility to have interaction(FE, SM, GM) or place family room or single room into elderly residence (NM, DM, BN) (3) to disperse small facilities into community (FE) or facility or community realizing symbiosis through various facility arrangement (SM, GM). 4) Therefore, this study can categorize (1) Program network, (2) Temporary interaction, (3) Symbiosis residence, (4) Symbiosis community according to characteristics which regional linkage has. Implication: Regional Linkage is an important concept to improve social interaction in community-based facilities. It is a thought-provoking concept to Korean elderly facilities because Korean facilities are still far from a city and in isolated environment.

• Proceedings of the KSR Conference
• /
• 2005.05a
• /
• pp.1105-1108
• /
• 2005

In oder to develope a train system for parcel service of high speed railway, which had been proposed for the operation of a high speed train, its conceptual design was build. Through this system, we are able to expect the fulfillment of customer needs for high speed rail market segments, and enhancement for cost-effective rail network operation of the mixed traffic on infrastructure cost-reduction in national logistics.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.178-180
• /
• 2007

In this paper, a real-time transmission algorithm based on IEEE 802.15.4 is proposed. The superframe of IEEE 802.15.4 is applied to the transmission method of real-time mixed data (periodic data, sporadic data, and non real-time message). The simulation results show the real-time performance of sporadic data is improved by using the proposed transmission algorithm.