• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.5
• /
• pp.102-108
• /
• 2011

Support vector machines are well known for their outstanding performance in pattern recognition fields. One example of their applications is music/speech classification for a standardized codec such as 3GPP2 selectable mode vocoder. In this paper, we propose a novel scheme that improves the speech/music classification of support vector machines based on the second-order conditional maximum a priori. While conventional support vector machine optimization techniques apply during training phase, the proposed technique can be adopted in classification phase. In this regard, the proposed approach can be developed and employed in parallel with conventional optimizations, resulting in synergistic boost in classification performance. According to experimental results, the proposed algorithm shows its compatibility and potential for improving the performance of support vector machines.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1E
• /
• pp.14-21
• /
• 1995

This paper presents a parallel sorting algorithm suitable for the SIMD multiprocessor. The algorithm finds pivots for partitioning the data into ordered subsets. The data can be evenly distributed to be sorted since it uses the probability theory. For n data elements to be sorted on p processors, when $n{\geq}p^2$, the algorithm is shown to be asymptotically optimal. In practice, sorting 8 million data items on 64 processors achieved a 48.43-fold speedup, while the PSRS required a 44.4-fold speedup. On a variety of shared and distributed memory machines, the algorithm achieved better than half-linear speedups.

• International Journal of Aeronautical and Space Sciences
• /
• v.4 no.1
• /
• pp.34-44
• /
• 2003

An advanced aeroelastic analysis using a computational structural dynamics (CSD), finite element method (FEM) and computational fluid dynamics (CFD) is presented in this Paper. A general aeroelastic analysis system is originally developed and applied to realistic design problems in the transonic flow region, where strong shock wave interactions exist. The present computational approach is based on the modal-based coupled nonlinear analysis with the matched-point concept and adopts the high-speed parallel processing technique on the low-cost network based PC-clustered machines. It can give very accurate and useful engineering data on the structural dynamic design of advanced flight vehicles. For the nonlinear unsteady aerodynamics in high transonic flow region, Euler equations using the unstructured grid system have been applied to easily consider complex configurations. It is typically shown that the advanced numerical approach can give very realistic and practical results for design engineers and safe flight tests. One can find that the present study conducts a virtual flutter flight test which are usually very dangerous in reality.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.7
• /
• pp.251-257
• /
• 2014

The Viterbi algorithm(VA) is used to estimate the state transition of discrete-time finite state machine(FSM) that is in an uncorrelated noisy environment. This paper modified the Hamming Network to estimate the state transitions in the finite state machines, and proposed state-parallel and block-parallel Viterbi decoder. The modified Hamming Network(mHN) can perform the decoding of convolutional codes correctly as conventional Viterbi decoder. Furthermore, the complexities of the proposed Viterbi decoder are reduced approximately 10% less than conventional Viterbi decoder, and the processing times are improved approximately 40% more than conventional Viterbi decoder.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.6
• /
• pp.1838-1855
• /
• 2008

The manufacturing industry seeks for improvements in efficiency at the manufacturing process. This paper presents a method for effective real time dispatching for parallel machines with multi product that minimizes mean tardiness and maximizes the quality of the product. What is shown in this paper is that using the Rolling Horizon Tabu search method in the real time dispatching process, mean tardiness can be reduced to the minimum. The effectiveness of the method presented in this paper has been examined in the simulation and compared with other dispatching methods. In fact, using this method manufacturing companies can increase profits and improve customer satisfaction as well.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1185-1201
• /
• 2018

This paper presents a sensorless direct torque control (DTC) combined with sliding mode approach (SM) and space vector modulation (SVM) to achieve mainly a high performance and reduce torque and flux ripples of a parallel-connected two five-phase permanent magnet synchronous machine (PMSM) drive system. In order to increase the proposed drive robustness and decrease its complexity and cost, the rotor speeds, rotor positions, fluxes as well as torques are estimated by using a sliding mode observer (SMO) scheme. The effectiveness of the proposed sliding mode observer in conjunction with the sliding mode control based DTC is confirmed through the application of different load torques for wide speed range operation. Comparison between sliding mode control and proportional integral (PI) control based DTC of the proposed two-motor drive is provided. The obtained speeds, torques and fluxes responses follow their references; even in low and reverse speed operations, load torques changes, and machines parameters variations. Simulation results confirm also that, the ripples of the torques and fluxes are reduced more than 3.33% and 16.66 %, respectively, and the speed overshoots and speed drops are reduced about 99.85% and 92.24%, respectively.

• Journal of the Korean Society of Safety
• /
• v.19 no.1
• /
• pp.66-71
• /
• 2004

This paper describes that the improved effects on the ignition limit are studied by parallel safety components for propane-air 5.25vol.% mixture gas in low voltage inductive circuits. The experimental devices are used in the IEC type spark ignition test apparatus. The improved effects on the ignition limit are respectively obtained as the maximum rising rate of 650%, 1,080% by composing parallel circuits between inductance and safety components (condenser and diode) as compared with disconnecting inductance with the safety components. The more values of inductance the higher improved effects of ignition limit rise. This improving method for the ignition limit is not concerned with the safety components. Diode appears to effect greatly better than condenser. It is considered that the result can be used for not only data for researches and development of intrinsically safe explosion-proof machines which are applied equipment and detectors used in hazardous areas but also for data for its equipment tests.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.7
• /
• pp.1702-1710
• /
• 2009

In this paper, we propose a problem space based search(PSBS) algorithm to solve parallel machine scheduling problem considering rework probabilities. For each pair of a machine and a job type, rework probability of each job on a machine can be known through historical data acquisition. Neighborhoods are generated by perturbing four problem data vectors (processing times, due dates, setup times, and rework probabilities) and evaluated through the efficient dispatching heuristic (EDDR). The proposed algorithm is measured by maximum lateness and the number of reworked jobs. We show that the PSBS algorithm is considerably improved from the result obtained by EDDR.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.270-278
• /
• 2023

We propose a container orchestration system for process workloads that combines the potential of big data and machine learning technologies to integrate enterprise process-centric workloads. This proposed system analyzes big data generated from industrial automation to identify hidden patterns and build a machine learning prediction model. For each machine learning case, training data is loaded into a data store and preprocessed for model training. In the next step, you can use the training data to select and apply an appropriate model. Then evaluate the model using the following test data: This step is called model construction and can be performed in a deployment framework. Additionally, a visual hierarchy is constructed to display prediction results and facilitate big data analysis. In order to implement parallel computing of PCA in the proposed system, several virtual systems were implemented to build the cluster required for the big data cluster. The implementation for evaluation and analysis built the necessary clusters by creating multiple virtual machines in a big data cluster to implement parallel computation of PCA. The proposed system is modeled as layers of individual components that can be connected together. The advantage of a system is that components can be added, replaced, or reused without affecting the rest of the system.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.771-788
• /
• 2019

Deep learning techniques such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) show superior performance in text classification than traditional approaches such as Support Vector Machines (SVMs) and Naïve Bayesian approaches. When using CNNs for text classification tasks, word embedding or character embedding is a step to transform words or characters to fixed size vectors before feeding them into convolutional layers. In this paper, we propose a parallel word-level and character-level embedding approach in CNNs for text classification. The proposed approach can capture word-level and character-level patterns concurrently in CNNs. To show the usefulness of proposed approach, we perform experiments with two English and three Korean text datasets. The experimental results show that character-level embedding works better in Korean and word-level embedding performs well in English. Also the experimental results reveal that the proposed approach provides better performance than traditional CNNs with word-level embedding or character-level embedding in both Korean and English documents. From more detail investigation, we find that the proposed approach tends to perform better when there is relatively small amount of data comparing to the traditional embedding approaches.