• Journal of Korea Water Resources Association
• /
• v.37 no.6
• /
• pp.449-460
• /
• 2004

The purpose of this study is to test the applicability of neuro-fuzzy system for monthly dam inflow forecasts by using weather forecasting information. The neuro-fuzzy algorithm adopted in this study is the ANFIS(Adaptive neuro-fuzzy Inference System) in which neural network theory is combined with fuzzy theory. The ANFIS model can experience the difficulties in selection of a control rule by a space partition because the number of control value increases rapidly as the number of fuzzy variable increases. In an effort to overcome this drawback, this study used the subtractive clustering which is one of fuzzy clustering methods. Also, this study proposed a method for converting qualitative weather forecasting information to quantitative one. ANFIS for monthly dam inflow forecasts was tested in cases of with or without weather forecasting information. It can be seen that the model performances obtained from the use of past observed data and future weather forecasting information are much better than those from past observed data only.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.3
• /
• pp.639-647
• /
• 2011

In this paper, we introduce a design methodology of data-centroid Radial Basis Function neural networks with extended polynomial function. The two underlying design mechanisms of such networks involve K-means clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on K-means clustering method for efficient processing of data and the optimization of model was carried out using PSO. In this paper, as the connection weight of RBF neural networks, we are able to use four types of polynomials such as simplified, linear, quadratic, and modified quadratic. Using K-means clustering, the center values of Gaussian function as activation function are selected. And the PSO-based RBF neural networks results in a structurally optimized structure and comes with a higher level of flexibility than the one encountered in the conventional RBF neural networks. The PSO-based design procedure being applied at each node of RBF neural networks leads to the selection of preferred parameters with specific local characteristics (such as the number of input variables, a specific set of input variables, and the distribution constant value in activation function) available within the RBF neural networks. To evaluate the performance of the proposed data-centroid RBF neural network with extended polynomial function, the model is experimented with using the nonlinear process data(2-Dimensional synthetic data and Mackey-Glass time series process data) and the Machine Learning dataset(NOx emission process data in gas turbine plant, Automobile Miles per Gallon(MPG) data, and Boston housing data). For the characteristic analysis of the given entire dataset with non-linearity as well as the efficient construction and evaluation of the dynamic network model, the partition of the given entire dataset distinguishes between two cases of Division I(training dataset and testing dataset) and Division II(training dataset, validation dataset, and testing dataset). A comparative analysis shows that the proposed RBF neural networks produces model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• The Journal of the Korea Contents Association
• /
• v.16 no.10
• /
• pp.608-616
• /
• 2016

The Smith-Watrman (SW) algorithm is a local alignment algorithm which is one of important operations in DNA sequence analysis. The SW algorithm finds the optimal local alignment with respect to the scoring system being used, but it has a problem to demand long execution time. To solve the problem of SW, some methods to perform SW in distributed and parallel manner have been proposed. The ADAM which is a distributed and parallel processing framework for DNA sequence has parallel SW. However, the parallel SW of the ADAM does not consider that the SW is a dynamic programming method, so the parallel SW of the ADAM has the limit of its performance. In this paper, we propose a method to enhance the parallel SW of ADAM. The proposed parallel SW (PSW) is performed in two phases. In the first phase, the PSW splits a DNA sequence into the number of partitions and assigns them to multiple nodes. Then, the original Smith-Waterman algorithm is performed in parallel at each node. In the second phase, the PSW estimates the portion of data sequence that should be recalculated, and the recalculation is performed on the portions in parallel at each node. In the experiment, we compare the proposed PSW to the parallel SW of the ADAM to show the superiority of the PSW.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.157-165
• /
• 2020

Aiming at the development of neural network and self-driving data set, it is also an idea to improve the performance of network model to detect moving objects by dividing the data set. In Darknet network framework, the YOLOv4 (You Only Look Once v4) network model was used to train and test Udacity data set. According to 7 proportions of the Udacity data set, it was divided into three subsets including training set, validation set and test set. K-means++ algorithm was used to conduct dimensional clustering of object boxes in 7 groups. By adjusting the super parameters of YOLOv4 network for training, Optimal model parameters for 7 groups were obtained respectively. These model parameters were used to detect and compare 7 test sets respectively. The experimental results showed that YOLOv4 can effectively detect the large, medium and small moving objects represented by Truck, Car and Pedestrian in the Udacity data set. When the ratio of training set, validation set and test set is 7:1.5:1.5, the optimal model parameters of the YOLOv4 have highest detection performance. The values show mAP50 reaching 80.89%, mAP75 reaching 47.08%, and the detection speed reaching 10.56 FPS.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.17 no.6 s.109
• /
• pp.562-573
• /
• 2006

It is required to reduce the peak-to-average power ratio(PAPR) in an orthogonal frequency division multiplexing system or a multicarrier system. And it is needed to eliminate the transmission of the side information in the Partial Transmit Sequences. So, in this paper, a new technique is proposed, where the subcarriers used for the multiple signal representation are only utilized for the reduction of PAPR to eliminate the burden of transmitting the side information. That is, it is proposed by taking the modified minimization criteria of partial transmit sequences scheme instead of using the convex optimization or the fast algorithm of tone reservation(TR) technique As the result of simulation, the PAPR reduction capability of the proposed method is improved by 3.2 dB dB, 3.4 dB, 3.6 dB with M=2, 4, 8(M is the number of partition in the so-called partial transmit reduction sequences(PTRS)), when the iteration number of fast algorithm of TR is 10 and the data rate loss is 5 %. But it is degraded in the capability of PAPR reduction by 3.4 dB, 3.1 dB, 2.2 dB, comparing to the TR when the data rate loss is 20 %. Therefore, the proposed method is outperformed the TR technique with respect to the complexity and PAPR reduction capability when M=2.

• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.282-289
• /
• 2008

Although there were some technological developments in improving the collaborative filtering, they have yet to fully reflect the actual relation of the items. In this paper, we propose the recommendation system using associative web document classification by word frequency and ${\alpha}$-cut to address the short comings of the collaborative filtering. The proposed method extracts words from web documents through the morpheme analysis and accumulates the weight of term frequency. It makes associative rules and applies the weight of term frequency to its confidence by using Apriori algorithm. And it calculates the similarity among the words using the hypergraph partition. Lastly, it classifies related web document by using ${\alpha}$-cut and calculates similarity by using adjusted cosine similarity. The results show that the proposed method significantly outperforms the existing methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.181-189
• /
• 2013

In this paper, we introduce the fuzzy neural network based on the individual input space to design the pattern recognizer. The proposed networks configure the network by individually dividing each input space. The premise part of the networks is independently composed of the fuzzy partition of individual input spaces and the consequence part of the networks is represented by polynomial functions. The learning of fuzzy neural networks is realized by adjusting connection weights of the neurons in the consequent part of the fuzzy rules and it follows a back-propagation algorithm. In addition, in order to optimize the parameters of the proposed network, we use real-coded genetic algorithms. Finally, we design the optimized pattern recognizer using the experimental data for pattern recognition.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.75-83
• /
• 2007

Multithreaded model is an effective parallel system in that it can reduce the long memory reference latency time and solve the synchronization problems. When compiling the non-strict functional programs for the multithreaded parallel machine, the most important thing is to find an set of sequentially executable instructions and to partitions them into threads. The existing partitioning algorithm partitions the condition of conditional expression, true expression and false expression into the basic blocks and apply local partitioning to these basic blocks. We can do the better partitioning if we modify the definition of the thread and allow the branching within the thread. The branching within the thread do not reduce the parallelism, do not increase the number of synchronization and do not violate the basic rule of the thread partitioning. On the contrary, it can lengthen the thread and reduce the number of synchronization. In the paper, we enhance the method of the partition of threads by combining the three basic blocks into one of two blocks.

• Journal of Broadcast Engineering
• /
• v.15 no.5
• /
• pp.617-630
• /
• 2010

At 37th VCEG meeting in Jan. 2009, Toshiba proposed Quadtree-based Adaptive Loop Filter (QALF). The basic concept of QALF is to apply Wiener filter to decoded image after the conventional deblocking filter and to represent the filter on/off flag data for each basic filtering unit in a more efficient way of quadtree structure. QALF could enhance the compression performance of around more than 9%, but the structure of one filter for a decoded frame leaves room for further improvement in the sense that optimal filter for one region of a frame could quite different from the optimal filter for other parts of a picture. This paper proposes multiple adaptive loop filters for better utilization of local characteristics of decoded frame to optimize the region-based Wiener filters. Additional filters, proposed in this paper, cover separate spatial area of each decoded frame according to the performance of previously designed filter(s) to provide the flexibility of rate-distortion based selection of the number of filters.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.164-167
• /
• 2005

Recently, STC techniques have been considered to be candidate to support multimedia services in the next generation mobile radio communications and have been developed the many communications systems in order to achieve the high data rates. In this paper, we propose the Trellis-Coded Differential Space Time Modulation system with multiple symbol detection. The Trellis-code performs the set partition with unitary group codes. The Viterbi decoder containing new branch metrics is introduced in order to improve the bit error rate (BER) in the differential detection of the unitary differential space time modulation. Also, we describe the Viterbi algorithm in order to use this branch metrics. Our study shows that such a Viterbi decoder improves BER performance without sacrificing bandwidth and power efficiency.