• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.145-155
• /
• 2002

In content-based image retrieval (CBIR), most conventional approaches assume a linear relationship between different features and require users themselves to assign the appropriate weights to each feature. However, the linear relationship assumed between the features is too restricted to accurately represent high-level concepts and the intricacies of human perception. In this paper, a neural network-based image retrieval (NNIR) model is proposed. It has been developed based on a human-computer interaction approach to CBIR using a radial basis function network (RBFN). By using the RBFN, this approach determines the nonlinear relationship between features and it allows the user to select an initial query image and search incrementally the target images via relevance feedback so that more accurate similarity comparison between images can be supported. The experiment was performed to calculate the level of recall and precision based on a database that contains 1,015 images and consists of 145 classes. The experimental results showed that the recall and level of the proposed approach were 93.45% and 80.61% respectively, which is superior than precision the existing approaches such as the linearly combining approach, the rank-based method, and the backpropagation algorithm-based method.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.10
• /
• pp.851-856
• /
• 2015

This study aimed to develop a sensory feedback system which could measure force and temperature for the user of myoelectric prosthetic hands. The Sensory measurement module consisted of a force sensing resistor to measure forces and non-contact infrared temperature sensor. These sensors were attached on the fingertips of the myoelectric prosthetic hand. The module was validated by using standard weights corresponding to external force and a Peltier module. Sensory transmission module consisted of four vibration motors. Eight vibration patterns were generated by combining motion of each vibration motor and were dependent on kinds and/or magnitude. The module was verified by using standard weigts and water at varying temperatures. There were correlations of force and temperature between the sensory measurement module and standard weight and water. Additionally, exact vibration patterns were generated, indicating the efficacy of the sensory feedback system for the myoelectric prosthetic hand.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.1
• /
• pp.39-49
• /
• 2013

This paper presents a method of improving the performance of a day-ahead 24-h load curve and peak load forecasting. The next-day load curve is forecasted using radial basis function (RBF) neural network models built using the best design parameters. To improve the forecasting accuracy, the load curve forecasted using the RBF network models is corrected by the weighted sum of both the error of the current prediction and the change in the errors between the current and the previous prediction. The optimal weights (called "gains" in the error correction) are identified by differential evolution. The peak load forecasted by the RBF network models is also corrected by combining the load curve outputs of the RBF models by linear addition with 24 coefficients. The optimal coefficients for reducing both the forecasting mean absolute percent error (MAPE) and the sum of errors are also identified using differential evolution. The proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange. Simulation results reveal satisfactory forecasts: 1.230% MAPE for daily peak load and 1.128% MAPE for daily load curve.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.14 no.6
• /
• pp.77-83
• /
• 2015

This paper is a study of the functions required for the system to quantify the closest target weight by combining several random weights such as chips, snacks, fruits, and vegetables. The multi-head weigher is designed for high-performance applications requiring increased production rates and tight accuracy tolerances. This combination system has 12 heads considered in the form of a rectangular array of $2{\times}6$ or $3{\times}4$. Channel combination can usually occur between 1 and n, and the frequency was the highest with two or three combinations. Experimental result of a combination system for a total target weight was measured at the range from 100g to 500g by increments of 50g, and the average success rate was about 70%. The average elapsed time was about 1.7 seconds, which means it can be used for the packaging of agricultural products with a variety of items.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1993.10a
• /
• pp.1254-1263
• /
• 1993

Representing knowledge uncertainty , aggregating evidence confidences , and propagation uncertainties are three key elements that effect the ability of a rule-based expert system to represent domains with uncertainty . Fuzzy set theory provide a good mathematical tool for representing the vagueness associated with a variable when , as the condition of a rule , it only partially corresponds to the input data. However, the aggregation of ANDed and Ored confidences is not as simple as the intersection and union operators defined for fuzzy set membership. There is, in fact, a certain degree of compensation that occurs when an expert aggregates confidences associated with compound evidence . Further, expert often consider individual evidences to be varying importance , or weight , in their support for a conclusion. This paper presents a flexible approach for evaluating evidence and conclusion confidences. Evidences may be represented as fuzzy or nonfuzzy variables with as associat d degree of certainty . different weight can also be associated degree of certainty. Different weights can also be assigned to the individual condition in determining the confidence of compound evidence . Conclusion confidence is calculated using a modified approach combining the evidence confidence and a rule strength. The techniques developed offer a flexible framework for representing knowledge and propagating uncertainties. This framework has the potention to reflect human aggregation of uncertain information more accurately than simple minimum and maximum operator do.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.715-722
• /
• 2016

In this paper, by applying the linear least squared error algorithm, we derive an estimation technique for three dimensional target location when a number of radars are used in detecting a target. The proposed technique is then enhanced by combining GPS information and by assigning variable weights to information sources. The enhanced performance of proposed techniques is confirmed via simulation. It is also observed from simulation results that the performance is robust to the uncertainty of information.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.1
• /
• pp.26-31
• /
• 2010

We proposed a new directional edge based interpolation, DEBI, by combining two weighted directional information to reduce blurred edges and annoying artifacts. Four isotropic gradient masks are employed in defining edge directions and they are proven to hold a first order derivative relation with respect to a rotating coordinate. Two minimum gradients among four absolute directional results are shown to be sufficient to describe slant edges efficiently. Compared with widely used bilinear and bicubic interpolation methods, the proposed algorithm results in a noticeable improvement along edge area.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.4
• /
• pp.1188-1202
• /
• 2012

In this paper, we propose a new multi-scale connected coherence tree algorithm (MCCTA) by improving the connected coherence tree algorithm (CCTA). In contrast to many multi-scale image processing algorithms, MCCTA works on multiple scales space of an image and can adaptively change the parameters to capture the coarse and fine level details. Furthermore, we design a Multi-scale Connected Coherence Tree algorithm plus Spectral graph partitioning (MCCTSGP) by combining MCCTA and Spectral graph partitioning in to a new framework. Specifically, the graph nodes are the regions produced by CCTA and the image pixels, and the weights are the affinities between nodes. Then we run a spectral graph partitioning algorithm to partition on the graph which can consider the information both from pixels and regions to improve the quality of segments for providing image segmentation. The experimental results on Berkeley image database demonstrate the accuracy of our algorithm as compared to existing popular methods.

• Journal of the Semiconductor & Display Technology
• /
• v.13 no.2
• /
• pp.23-28
• /
• 2014

For the reconstruction of three-dimensional (3D) shape of microscopic objects through shape from focus (SFF) methods, usually a single focus measure operator is employed. However, it is difficult to compute accurate depth map using a single focus measure due to different textures, light conditions and arbitrary object surfaces. Moreover, real images with diverse types of illuminations and contrasts lead to the erroneous depth map estimation through a single focus measure. In order to get better focus measurements and depth map, we have combined focus measure operators by using genetic algorithm. The resultant focus measure is obtained by weighted sum of the output of various focus measure operators. Optimal weights are obtained using genetic algorithm. Finally, depth map is obtained from the refined focus volume. The performance of the developed method is then evaluated by using both the synthetic and real world image sequences. The experimental results show that the proposed method is more effective in computing accurate depth maps as compared to the existing SFF methods.

• International Journal of Knowledge Content Development & Technology
• /
• v.9 no.3
• /
• pp.23-41
• /
• 2019

This study combines the concept of degree centrality in complex network with the Term Frequency $^*$ Proportional Document Frequency ($TF^*PDF$) algorithm; the combined method, called PMCN (PDF-Modified similarity and Complex Network), constructs relationship networks among sentences for writing news summaries. The PMCN method is a multi-document summarization extension of the ideas of Bun and Ishizuka (2002), who first published the $TF^*PDF$ algorithm for detecting hot topics. In their $TF^*PDF$ algorithm, Bun and Ishizuka defined the publisher of a news item as its channel. If the PDF weight of a term is higher than the weights of other terms, then the term is hotter than the other terms. However, this study attempts to develop summaries for news items. Because the $TF^*PDF$ algorithm summarizes daily news, PMCN replaces the concept of "channel" with "the date of the news event", and uses the resulting chronicle ordering for a multi-document summarization algorithm, of which the F-measure scores were 0.042 and 0.051 higher than LexRank for the famous d30001t and d30003t tasks, respectively.