• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.343-350
• /
• 2020

In the era of the Fourth Industrial Revolution in the digital revolution is taking place, various attempts have been made to provide various contents in a digital environment. In this paper, agent-recruitment service system based on collaborative deep learning is proposed for the intelligent head hunting service. The service system is improved from previous research [7] using collaborative deep learning for more reliable recommendation results. The Collaborative deep learning is a hybrid recommendation algorithm using "Recurrent Neural Network(RNN)" specialized for exponential calculation, "collaborative filtering" which is traditional recommendation filtering methods, and "KNN-Clustering" for similar user analysis. The proposed service system can expect more reliable recommendation results than previous research and showed high satisfaction in user survey for verification.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2003.06a
• /
• pp.179-184
• /
• 2003

HLA-RTI is middleware for the distribute simulation that developed in the US Department of Defense. This provides fast accomplishment speed and reliability than distribute simulation Middleware by transfer. However, DDM(Data Distribution Management) service is used as data filtering technology in the existing HLA-RTI. As for this, the problem that network traffic increases in data exchange between the mobility simulation objects is generated. it proposes applying agent technology to the mobility simulation object in order to solve these problems in this paper in this. And this paper applies that to practical simulation and analyzes performance between each data filtering technology with comparison.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.400-409
• /
• 2003

Collaborative filtering (CF) recommendation is a knowledge sharing technology for distribution of opinions and facilitating contacts in network society between people with similar interests. The main concerns of the CF algorithm are about prediction accuracy, speed of response time, problem of data sparsity, and scalability. In general, the efforts of improving prediction algorithms and lessening response time are decoupled. We propose a three-step CF recommendation model which is composed of profiling, inferring, and predicting steps while considering prediction accuracy and computing speed simultaneously. This model combines a CF algorithm with two machine learning processes, SOM (Self-Organizing Map) and CBR (Case Based Reasoning) by changing an unsupervised clustering problem into a supervised user preference reasoning problem, which is a novel approach for the CF recommendation field. This paper demonstrates the utility of the CF recommendation based on SOM cluster-indexing CBR with validation against control algorithms through an open dataset of user preference.

• Educational Technology International
• /
• v.6 no.1
• /
• pp.65-79
• /
• 2005

In a widely distributed environment, many occasions arise when people need to filter informationwith email clients. The existing information agents such as Maxims and Message Assistant have capabilities of filtering email messages either by an autonomous agent or by user-defined rules. FlexMA, a variation of FAMES (Flexible Asynchronous Messaging System) is proposed as an information filtering agent. Agents in our system can be scaled up to adapt user's various demands by controlling messages delivered among heterogeneous email clients. Several functionalities are split into each agent in terms of component configuration with the addition of multiple agents'cooperation and negotiation. User-defined rules are collected and executed by these agents in a semi-autonomous manner. This paper demonstrates how this design is feasible in a flexible message system.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.175-186
• /
• 1999

Detecting the features of significant patterns from their own historical data is so much crucial to good performance specially in time-series forecasting. Recently, a new data filtering method (or multi-scale decomposition) such as wavelet analysis is considered more useful for handling the time-series that contain strong quasi-cyclical components than other methods. The reason is that wavelet analysis theoretically makes much better local information according to different time intervals from the filtered data. Wavelets can process information effectively at different scales. This implies inherent support fer multiresolution analysis, which correlates with time series that exhibit self-similar behavior across different time scales. The specific local properties of wavelets can for example be particularly useful to describe signals with sharp spiky, discontinuous or fractal structure in financial markets based on chaos theory and also allows the removal of noise-dependent high frequencies, while conserving the signal bearing high frequency terms of the signal. To date, the existing studies related to wavelet analysis are increasingly being applied to many different fields. In this study, we focus on several wavelet thresholding criteria or techniques to support multi-signal decomposition methods for financial time series forecasting and apply to forecast Korean Won / U.S. Dollar currency market as a case study. One of the most important problems that has to be solved with the application of the filtering is the correct choice of the filter types and the filter parameters. If the threshold is too small or too large then the wavelet shrinkage estimator will tend to overfit or underfit the data. It is often selected arbitrarily or by adopting a certain theoretical or statistical criteria. Recently, new and versatile techniques have been introduced related to that problem. Our study is to analyze thresholding or filtering methods based on wavelet analysis that use multi-signal decomposition algorithms within the neural network architectures specially in complex financial markets. Secondly, through the comparison with different filtering techniques' results we introduce the present different filtering criteria of wavelet analysis to support the neural network learning optimization and analyze the critical issues related to the optimal filter design problems in wavelet analysis. That is, those issues include finding the optimal filter parameter to extract significant input features for the forecasting model. Finally, from existing theory or experimental viewpoint concerning the criteria of wavelets thresholding parameters we propose the design of the optimal wavelet for representing a given signal useful in forecasting models, specially a well known neural network models.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.8
• /
• pp.149-156
• /
• 2010

As following the development of the USN technology, sensor node used in sensor network has capability of quick data process and storage to support efficient network configuration is enabled. In addition, tree-based structure was transformed to cluster in the construction of sensor network. However, query processing based on existing tree structure could be inefficient under the cluster-based network. In this paper, we suggest energy efficient query processing mechanism using filtering through data attribute classification in cluster-based sensor network. The suggestion mechanism use advantage of cluster-based network so reduce energy of query processing and designed more intelligent query dissemination. And, we prove excellence of energy efficient side with MATLab.

• Journal of the Korea Society for Simulation
• /
• v.18 no.4
• /
• pp.1-8
• /
• 2009

The distributed war-game simulation system has been used to represent the virtual battlefield environment. In order to produce a simulation result, simulators connected from a network transfer messages with location information of simulated objects to a central simulation server. This network traffic is an immediate cause of system performance degradation. Therefore, the paper proposes a system to manage and control network traffic generated from distributed war-game simulation. The proposed system determines the moving distance of simulated objects and filters location messages by a distance threshold which is controlled according to system conditions like network traffic and location error. And, the system predicts the next location of simulated objects to minimize location error caused by message filtering. Experimental results demonstrate that the proposed system is effective to control the network traffic of distributed war-game simulation systems and reduce the location error of simulated objects.

• Journal of KIISE:Databases
• /
• v.32 no.4
• /
• pp.372-382
• /
• 2005

Aggregation such as computing an average value of data measured in each sensor commonly occurs in many applications of sensor networks. Since sensor networks consist of low-cost nodes with limited battery power, reducing energy consumption must be considered in order to achieve a long network lifetime. Reducing the amount of messages exchanged is the most important for saving energy. Earlier work has demonstrated the effectiveness of in-network data aggregation and data filtering for minimizing the amount of messages in sensor networks. In this paper, we propose an adaptive error adjustment scheme that is simpler, more effective and efficient than previous work. The proposed scheme is based on self-adjustment in each sensor node. We show through various experiments that our scheme reduces the network traffic significantly, and performs better than existing methods.

• Journal of the Korea Society for Simulation
• /
• v.17 no.3
• /
• pp.27-34
• /
• 2008

Wireless sensor networks are comprised of sensor nodes with resource-constrained hardware. Nodes in the sensor network without adequate protection may be compromised by adversaries. Such compromised nodes are vulnerable to the attacks like false reports injection attacks and false data injection attacks on legitimate reports. In false report injection attacks, an adversary injects false report into the network with the goal of deceiving the sink or the depletion of the finite amount of energy in a battery powered network. In false data injection attacks on legitimate reports, the attacker may inject a false data for every legitimate report. To address such attacks, the probabilistic voting-based filtering scheme (PVFS) has been proposed by Li and Wu. However, each cluster head in PVFS needs additional transmission device. Therefore, this paper proposes a fuzzy logic-based false report detection method (FRD) to mitigate the threat of these attacks. FRD employs the statistical en-route filtering scheme as a basis and improves upon it. We demonstrate that FRD is efficient with respect to the security it provides, and allows a tradeoff between security and energy consumption, as shown in the simulation.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.141-150
• /
• 2007

This paper proposes how to reduce the amount of data transmitted in each sensor and cluster head in order to lengthen the lifetime of sensor network. The most important factor of reducing the sensor's energy dissipation is to reduce the amount of messages transmitted. This paper proposed is to classify the node's cluster state into 6 categories in order to reduce both the number and amount of data transmission: Initial, Cluster Head, Cluster Member, Non-transmission Cluster Head, Non-transmission Cluster Member, and Sleep. This should increase the efficiency of filtering and decrease the inaccuracy of the data compared to the methods which enlarge the filter width to do more filtering. This method is much more efficient and effective than the previous work. We show through various experiments that our scheme reduces the network traffic significantly and increases the network's lifetime than existing methods.