• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.12
• /
• pp.2324-2328
• /
• 2010

In this paper we proposed a new algorithm that can reduce the open-loop pitch estimation time of G.723.1. The time domain cross-correlation method is simple but has long processing time by recursive multiplication. For reduction of processing time, we use the method that compute the cross-correlation by multiplying the Fourier value of speech by it's complex conjugate. Also, we can reduce the processing time by omitting the bit-reversing of FFT and IFFT for time-frequency domain transform. As a result, the processing time of improved hybrid domain cross-correlation algorithm is reduced by 67.37% of conventional time domain cross-correlation.

• Journal of Korea Multimedia Society
• /
• v.14 no.7
• /
• pp.866-871
• /
• 2011

In this paper, an improved method of hand detecting and hand gesture recognition is proposed, it can be applied in different illumination condition and complex background. We use Adaptive Skin Threshold (AST) to detect the areas of hand. Then the result of hand detection is used to hand recognition through the improved HMM algorithm. At last, we design a simple program using the result of hand recognition for recognizing "stone, scissors, cloth" these three kinds of hand gesture. Experimental results had proved that the hand and gesture can be detected and recognized with high average recognition rate (92.41%) and better than some other methods such as syntactical analysis, neural based approach by using our approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5497-5512
• /
• 2016

An improved optimal weights based on parallel interference cancellation algorithm has been proposed to cancel for interference induced by multi-user access satellite to ground uplink system. Due to differences in elevation relative motion between the user and the satellite, as well as access between users, resulting in multi-user access interference (Multi-user Access Interference, MUI), which significantly degrade system performance when multi-user access. By steepest gradient method, it obtained based on the MMSE criterion, parallel interference cancellation adjust optimal weights to obtain the maximum SINR. Compared to traditional parallel interference cancellation (Parallel Interference Cancellation, PIC) algorithm or serial interference cancellation ( Successive interference Cancellation, SIC), the accuracy of which is not high and too many complex iterations, we establish the multi-user access to the satellite to ground up link system to demonstrate that the improved WPIC algorithm could be provided with high accuracy and relatively low number of iterations.

• Journal of Information Processing Systems
• /
• v.17 no.5
• /
• pp.892-904
• /
• 2021

An image semantic segmentation model is proposed based on improved ENet network in order to achieve the low accuracy of image semantic segmentation in complex environment. Firstly, this paper performs pruning and convolution optimization operations on the ENet network. That is, the network structure is reasonably adjusted for better results in image segmentation by reducing the convolution operation in the decoder and proposing the bottleneck convolution structure. Squeeze-and-excitation (SE) module is then integrated into the optimized ENet network. Small-scale targets see improvement in segmentation accuracy via automatic learning of the importance of each feature channel. Finally, the experiment was verified on the public dataset. This method outperforms the existing comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU) values. And in a short running time, the accuracy of the segmentation and the efficiency of the operation are guaranteed.

• Structural Engineering and Mechanics
• /
• v.70 no.5
• /
• pp.513-524
• /
• 2019

This study proposed an improved particle swarm optimization (IPSO) method ensemble with kriging model for model updating. By introducing genetic algorithm (GA) and grouping strategy together with elite selection into standard particle optimization (PSO), the IPSO is obtained. Kriging metamodel serves for predicting the structural responses to avoid complex computation via finite element model. The combination of IPSO and kriging model shall provide more accurate searching results and obtain global optimal solution for model updating compared with the PSO, Simulate Annealing PSO (SimuAPSO), BreedPSO and PSOGA. A plane truss structure and ASCE Benchmark frame structure are adopted to verify the proposed approach. The results indicated that the hybrid of kriging model and IPSO could serve for model updating effectively and efficiently. The updating results further illustrated that IPSO can provide superior convergent solutions compared with PSO, SimuAPSO, BreedPSO and PSOGA.

• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1479-1494
• /
• 2020

As an important part of image processing, image demosaicking has been widely researched. It is especially necessary to propose an efficient interpolation algorithm with good visual quality and performance. To improve the limitations of residual interpolation (RI), based on RI algorithm, minimalized-Laplacian RI (MLRI), and iterative RI (IRI), this paper focuses on adaptive RI (ARI) and proposes an improved ARI (IARI) algorithm which obtains more distinct R, G, and B colors in the images. The proposed scheme fully considers the brightness information and edge information of the image. Since the ARI algorithm is not completely adaptive, IARI algorithm executes ARI algorithm twice on R and B components according to the directional difference, which surely achieves an adaptive algorithm for all color components. Experimental results show that the improved method has better performance than other four existing methods both in subjective assessment and objective assessment, especially in the complex edge area and color brightness recovery.

• Journal of Engineering Education Research
• /
• v.20 no.6
• /
• pp.68-75
• /
• 2017

This study has a purpose to analyse changes in perception and image about engineering and technology of students who participated in the engineering camp. To achieve this objective, the questions were as follows. 1) What about participants' image difference for engineering before and after participating the engineering camp 2) What about participants' image difference for technology before and after participating the engineering camp. For this study, the program was progressed from Aug in 2017 and the data was collected from 88 students, middle school seniors and high school freshmen. The results of this study were as follows: First, secondary students perceived 'valuable(6.74)', 'meaningful(6.73)', 'rich(6.40)', 'collaborative(6.42)', 'nice(6.22)' as high image rank of the positive response for engineering. On the other hand, 'complex(3.59)', 'labored(3.80)', 'hard(4.66)', 'dangerous(4.48)', 'cold(4.86)' were perceived as low image rank of the negative response for engineering. We can realize that they generally has the image that engineering is valuable, meaningful and nice but also labored, complex and hard. The students who participated in the engineering camp showed the greatest difference in 'complex - simple' and 'dangerous - safe' engineering categories before and after the camp, followed by 'cold - hot', 'labored - easy', and 'hard - soft', respectively. Second, secondary students perceived 'meaningful(6.58)', 'valuable(6.55)', 'wide(6.38)', 'nice(6.37)', 'strong(6.25)' as high image rank of the positive response for technology. On the other hand, 'complex(3.85)', 'labored(3.93)', 'hard(4.62)', 'dangerous(4.72)', 'cold(5.05)' were perceived as low image rank of the negative response for technology. The students who participated in the engineering camp had the big change in 'hard - soft' technology category before and after the camp, followed by 'complex - simple', 'labored - easy', 'theoretical - practical' and 'dangerous - safe', respectively. We can see that the negative images for technology which were complex, labored, dangerous, theoretical was improved with positive image such as simple, easy, safe and practical, after conducting the engineering camp. In conclusion, both image recognitions for engineering and technology have improved after the camp. It means that interesting and entertaining engineering-technology program can boost interests in engineering and technology which felt difficult, so that images about them can be turned out positive. Also, it is possible to reduce avoidance of natural science and engineering subjects, as part of the purpose of training creative talents in science and engineering, so it can be said that the engineering camp is highly meaningful because it can lead students into the field of science and engineering.

• Journal of the Optical Society of Korea
• /
• v.20 no.6
• /
• pp.653-662
• /
• 2016

An optimized multilayer superlens is designed, using a rigorous and efficient approach based on the method of moments (MoM) in conjunction with a simulated annealing (SA) algorithm. For the MoM solution, fast evaluation of closed-form Green's functions (GFs) in the spatial domain is performed by applying the complex-image (CI) technique, which obviates the time-consuming numerical evaluation of Sommerfeld integrals. The imaging capability of the superlens is examined with the correlation coefficient; results show that using circular polarization for the incident wave can improve this coefficient. To validate the proposed method, finite-element-based simulations are exploited, which reveal the method's accuracy and computational efficiency. Simulation results indicate that the designed structure is capable of producing two-dimensional sub-diffraction-limited images in the visible range, which may make it more versatile for practical applications. Finally, as a considerable finding, it is demonstrated for the proposed design that using circularly polarized illumination provides improved super-resolving performance, compared to linearly polarized illumination.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.5
• /
• pp.1935-1944
• /
• 2018

With the increase of the production of energy from renewable, it becomes important to look at techniques to store this energy. Therefore, a single winding bearingless flywheel motor (SWBFM) specially for flywheel energy storage system is introduced. For the control system of SWBFM, coupling between the torque and the suspension subsystems exists inevitably. It is necessary to build a reasonable radial force mathematical model to precisely control SWBFM. However, SWBFM has twelve independently controlled windings which leads to high-order matrix transformation and complex differential calculation in the process of mathematical modeling based on virtual displacement method. In this frame, a Maxwell tensor modeling method which is no need the detailed derivation and complex theoretical computation is present. Moreover, it possesses advantages of universality, accuracy, and directness. The fringing magnetic path is improved from straight and circular lines to elliptical line and the rationality of elliptical line is verified by virtual displacement theory according to electromagnetic torque characteristics. A correction function is taken to increase the model accuracy based on finite element analysis. Simulation and experimental results show that the control system of SWBFM with radial force mathematical model based on Maxwell tensor method is feasible and has high precision.

• Communications for Statistical Applications and Methods
• /
• v.30 no.5
• /
• pp.501-516
• /
• 2023

Knowledge distillation (KD) refers to extracting knowledge from a large and complex model (teacher) and transferring it to a relatively small model (student). This can be done by training the teacher model to obtain the activation function values of the hidden or the output layers and then retraining the student model using the same training data with the obtained values. Recently, relational KD (RKD) has been proposed to extract knowledge about relative differences in training data. This method improved the performance of the student model compared to conventional KDs. In this paper, we propose a new method for RKD by introducing a new loss function for RKD. The proposed loss function is defined using the area difference between the teacher model and the student model in a specific hidden layer, and it is shown that the model can be successfully compressed, and the generalization performance of the model can be improved. We demonstrate that the accuracy of the model applying the method proposed in the study of model compression of audio data is up to 1.8% higher than that of the existing method. For the study of model generalization, we demonstrate that the model has up to 0.5% better performance in accuracy when introducing the RKD method to self-KD using image data.