• The Journal of the Acoustical Society of Korea
• /
• v.24 no.7
• /
• pp.410-415
• /
• 2005

Recently, most of the speaker verification systems are based on the pattern recognition approach method. And performance of the pattern-classifier depends on how to classify a variety of speakers' feature parameters. In order to classify feature parameters efficiently and effectively, it is of great importance to enlarge variations between speakers and effectively measure distances between feature parameters. Therefore, this paper would suggest the positively mixed model scheme that can enlarge inter-speaker variation by searching the individual model with world model at the same time. During decision procedure, we can maximize inter-speaker variation by using the proposed mixed model scheme. We also make use of a symbol probability weighting function in this system so as to reduce vector quantization errors by measuring symbol probability derived from the distance rate of between the world codebook and individual codebook. As the result of our experiment using this method, we could halve the Detection Cost Function (DCF) of the system from $2.37\%\;to\;1.16\%$.

• Journal of Korea Multimedia Society
• /
• v.12 no.9
• /
• pp.1333-1341
• /
• 2009

Tactical path-finding in computer games is path-finding where a path is selected by considering not only basic elements such as the shortest distance or the minimum time spend but also tactical information of surroundings when deciding character's moving trajectory. One way to include tactical information in path-finding is to represent a heuristic function as a sum of tactical quality multiplied by a weighting factor which is.. determined based on the degree of its importance. The choice of weighting factors for tactics is very important because it controls search performance and the characteristic of paths found. In this paper. we propose a method for improving a heuristic function by adjusting weights based on the difference between paths on examples given by a level designer and paths found during the search process based on the CUITent weighting factors. The proposed method includes the search algorithm modified to detect search errors and learn heuristics and the perceptron-like weight updating formular. Through simulations it is demonstrated how different paths found by tactical path-finding are from those by traditional path-finding. We analyze the factors that affect the performance of learning and show the example applied to the real game environments.

• Nuclear Engineering and Technology
• /
• v.50 no.4
• /
• pp.589-598
• /
• 2018

To maintain safety and reliability of reactors, redundant sensors are usually used to measure critical variables and estimate their averaged time-dependency. Nonhealthy sensors can badly influence the estimation result of the process variable. Since online condition monitoring was introduced, the online cross-calibration method has been widely used to detect any anomaly of sensor readings among the redundant group. The cross-calibration method has four main averaging techniques: simple averaging, band averaging, weighted averaging, and parity space averaging (PSA). PSA is used to weigh redundant signals based on their error bounds and their band consistency. Using the consistency weighting factor (C), PSA assigns more weight to consistent signals that have shared bands, based on how many bands they share, and gives inconsistent signals of very low weight. In this article, three approaches are introduced for improving the PSA technique: the first is to add another consistency factor, so called trend consistency (TC), to include a consideration of the preserving of any characteristic edge that reflects the behavior of equipment/component measured by the process parameter; the second approach proposes replacing the error bound/accuracy based weighting factor ($W^a$) with a weighting factor based on the Euclidean distance ($W^d$), and the third approach proposes applying $W^d$, TC, and C, all together. Cold neutron source data sets of four redundant hydrogen pressure transmitters from a research reactor were used to perform the validation and verification. Results showed that the second and third modified approaches lead to reasonable improvement of the PSA technique. All approaches implemented in this study were similar in that they have the capability to (1) identify and isolate a drifted sensor that should undergo calibration, (2) identify a faulty sensor/s due to long and continuous missing data range, and (3) identify a healthy sensor.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.4
• /
• pp.370-381
• /
• 2021

This paper presented an efficient transceiver structure of multiband Frequency Shift Keying (FSK) signals with direct sequence spread spectrum for maintaining covertness and performance. In aspect to covertness, direct sequence spread spectrum method, which multiplying by Pseudo Noise (PN) codes whose rate is much higher than that of data sequence, is employed. In aspect to performance, in order to overcome performance degradation caused by multipath and Doppler spreading, we applied multiband, turbo equalization, and weighting algorithm are applied. Based on the simulation results, by applying 4 number of multiband and number of chips are 8 and 32, experiments were conducted in a lake with a distance of moving from 300 m to 500 m between the transceivers. we confirmed that the performance was improved as the number of bands and chips are increased. Furthermore, the performance of multiband was improved when the proposed weighting algorithm was applied.

• Journal of information and communication convergence engineering
• /
• v.20 no.1
• /
• pp.22-30
• /
• 2022

The reinforcement learning algorithm has proven its potential in solving sequential decision-making problems under uncertainties, such as finding paths to route data packets in wireless sensor networks. With reinforcement learning, the computation of the optimum path requires careful definition of the so-called reward function, which is defined as a linear function that aggregates multiple objective functions into a single objective to compute a numerical value (reward) to be maximized. In a typical defined linear reward function, the multiple objectives to be optimized are integrated in the form of a weighted sum with fixed weighting factors for all learning agents. This study proposes a reinforcement learning -based routing protocol for wireless sensor network, where different learning agents prioritize different objective goals by assigning weighting factors to the aggregated objectives of the reward function. We assign appropriate weighting factors to the objectives in the reward function of a sensor node according to its hop-count distance to the sink node. We expect this approach to enhance the effectiveness of multi-objective reinforcement learning for wireless sensor networks with a balanced trade-off among competing parameters. Furthermore, we propose SDN (Software Defined Networks) architecture with multiple controllers for constant network monitoring to allow learning agents to adapt according to the dynamics of the network conditions. Simulation results show that our proposed scheme enhances the performance of wireless sensor network under varied conditions, such as the node density and traffic intensity, with a good trade-off among competing performance metrics.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.367-372
• /
• 2001

This paper proposes a hierachically structured navigation algorithm for multiple mobile robots under unknown dynamic environment. The proposed algorithm consists of three basic parts as follows. The first part based on the fuzzy rule generates the turning angle and moving distance of the robot for goal approach without obstacles. In the second part, using both fuzzy and neural network, the angle and distance of the robot to avoid collision with dynamic and static obstacles are obtained. The final adjustment of the weighting factor based on fuzzy rule for moving and avoiding distance of the robots is provided in the third stage. Some simulation results show the effectiveness of the proposed algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.180-185
• /
• 2003

This paper proposes an intelligent navigation algorithm for multiple mobile robots under unknown dynamic environment. The proposed algorithm consists of three basic parts as follows. The first part based on the fuzzy rule generates the turning angle and moving distance of the robot for goal approach without obstacles. In the second part, using both fuzzy and neural network, the angle and distance of the robot to avoid collision with dynamic and static obstacles are obtained. The final adjustment of the weighting factor based on fuzzy rule for moving and avoiding distance of the robots is provided in the third stage. The experiments which demonstrate the performance of the proposed intelligent controller is described.

• Animal Systematics, Evolution and Diversity
• /
• v.15 no.1
• /
• pp.11-25
• /
• 1999

Two problematic subgenera of Tomoceridae (Collembola, Insecta) were investigated for their phylogenetic relationships based on morphological characters and allozyme study from three relevant species. Different dendrograms were obtained obtained between morphological and allozyme studies. The morphological data did not give rise to any result distinctive enough to separate the two subgenera whereas the allozyme analysis produced a clear separation by the high genetic distance value. They were consistent, however, whether given rise to by using distance or cladistic methods and also whether character weighting or unweighting approaches employed in the morphological character analysis. As a consequence, it is strongly suggested that any prominent morphological trait might work as a good taxonomical character when supported by a strong genetic divergence as evidenced by allozyme analysis for instance.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.44 no.4
• /
• pp.85-98
• /
• 2002

The purpose of this study is to develop a land use planning model (LUPM) which can be applied to development of rural villages considering their spatial expansion. The LUPM finds out and allocates the new built site required for the improvement of existing villages. in the development of LUPM, CA (cellular automata) and land suitability analysis methods were applied combinedly. The model uses basically numerical data of CIS based on grid data. Agglomerated settlement, as a type of village for simulation, was adopted. Probability of land use change for optimizing development area was calculated by the six criteria: slope. drainage characteristic, direction of slope, as absolute suitability of grid itself, distance from road. distance from stream and distance from the village center, as relative probability by neighborhood cells. Weighting values of these criteria were quantified by AHP (analytic hierarchy process) method, which is one of MCE(multi-criteria evaluation) method. The algorithm of the model was verified by three example villages: an isolation village, a village with horizontal road, and a village with nodal point of cross road

• Journal of Welding and Joining
• /
• v.16 no.3
• /
• pp.55-63
• /
• 1998

Among the position sensing methods available, the arc sensor which utilizes the electrical signal obtained from the welding arc itself is one of the most prevalently used methods, because it has an advantage that no particular sensing device is necessary and real-time sensing of a groove position is possible directly under the arc. The authors have already developed a seam tracking system that contains a new arc sensor algorithm, which uses the relative welding current variation according to the tip-to-workpiece distance in GMA welding. In this study a torch height control algorithm for automatic weld seam tracking was proposed for completing the previous system, which uses an on-off control technique. To implement the torch height control algorithm during weld seam tracking the system parameters which include 2nd averaging range, weighting factor for 2nd moving averaging, and Z-directional basic compensation distance were determined by experimental analysis. Finally the two different height control methods, one is simple on-off control and the other on-off control using a reference current value , were compared in their tracking abilities.