• ETRI Journal
• /
• v.44 no.3
• /
• pp.462-475
• /
• 2022

Although researchers have proposed numerous techniques for speech emotion recognition, its performance remains unsatisfactory in many application scenarios. In this study, we propose a speech emotion recognition model based on a genetic algorithm (GA)-decision tree (DT) fusion of deep and acoustic features. To more comprehensively express speech emotional information, first, frame-level deep and acoustic features are extracted from a speech signal. Next, five kinds of statistic variables of these features are calculated to obtain utterance-level features. The Fisher feature selection criterion is employed to select high-performance features, removing redundant information. In the feature fusion stage, the GA is is used to adaptively search for the best feature fusion weight. Finally, using the fused feature, the proposed speech emotion recognition model based on a DT support vector machine model is realized. Experimental results on the Berlin speech emotion database and the Chinese emotion speech database indicate that the proposed model outperforms an average weight fusion method.

• Applied Microscopy
• /
• v.50
• /
• pp.23.1-23.9
• /
• 2020

We propose an effective deep learning model to denoise scanning transmission electron microscopy (STEM) image series, named Noise2Atom, to map images from a source domain 𝓢 to a target domain 𝓒, where 𝓢 is for our noisy experimental dataset, and 𝓒 is for the desired clear atomic images. Noise2Atom uses two external networks to apply additional constraints from the domain knowledge. This model requires no signal prior, no noise model estimation, and no paired training images. The only assumption is that the inputs are acquired with identical experimental configurations. To evaluate the restoration performance of our model, as it is impossible to obtain ground truth for our experimental dataset, we propose consecutive structural similarity (CSS) for image quality assessment, based on the fact that the structures remain much the same as the previous frame(s) within small scan intervals. We demonstrate the superiority of our model by providing evaluation in terms of CSS and visual quality on different experimental datasets.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.45-59
• /
• 2023

In this paper, to optimize the average delay and power allocation (PA) for system users, we propose a resource scheduling scheme for wireless networks based on Cyclic Prefix Orthogonal Frequency Division Multiplexing (CP-OFDM) according to the first fifth-generation standards. For delay minimization, we solve a throughput maximization problem that considers CPOFDM systems with carrier aggregation (CA). Regarding PA, we consider an approach that involves maximizing goodput using an effective signal-to-noise ratio. An algorithm for jointly solving delay minimization through computation of required user rates and optimizing the power allocated to users is proposed to compose the resource allocation approach. In wireless network simulations, we consider a scenario with the following capabilities: CA, 256-Quadrature Amplitude Modulation, millimeter waves above 6 GHz, and a radio frame structure with 120 KHz spacing between the subcarriers. The performance of the proposed resource allocation algorithm is evaluated and compared with those of other algorithms from the literature using computational simulations in terms of various Quality of Service parameters, such as the throughput, delay, fairness index, and loss rate.

• Journal of the Korean Society of Safety
• /
• v.38 no.2
• /
• pp.23-29
• /
• 2023

This study analyzed the fire status of a rubber product manufacturing factory based on 19 years of fire data. Through the analysis of the current state of fire, electrical fires accounted for 58.19%, and among electrical fires, motor fires were the highest at 26.21%. For the motor fire occurrence process, the curing process accounted for the highest rate of 51.9%. Therefore, the installation environment was investigated for the motor in the curing process, and it was confirmed that the motor's maximum ambient temperature exceeded 40℃. In particular, in the case of the motor for curing operation, the motor was installed in a separate motor room, so the average indoor temperature was 48.10℃ and the motor frame's maximum temperature was 72.80℃. In this study, the risk of motor fire was confirmed through a field survey, and a safety management plan was derived by finding a process with high fire risk and conducting an experiment on the motor's installation environment and electrical characteristics in that process.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.43.1-43.1
• /
• 2019

In this study, we apply a deep learning model to denoising solar magnetograms. For this, we design a model based on conditional generative adversarial network, which is one of the deep learning algorithms, for the image-to-image translation from a single magnetogram to a denoised magnetogram. For the single magnetogram, we use SDO/HMI line-of-sight magnetograms at the center of solar disk. For the denoised magnetogram, we make 21-frame-stacked magnetograms at the center of solar disk considering solar rotation. We train a model using 7004 paris of the single and denoised magnetograms from 2013 January to 2013 October and test the model using 1432 pairs from 2013 November to 2013 December. Our results from this study are as follows. First, our model successfully denoise SDO/HMI magnetograms and the denoised magnetograms from our model are similar to the stacked magnetograms. Second, the average pixel-to-pixel correlation coefficient value between denoised magnetograms from our model and stacked magnetogrmas is larger than 0.93. Third, the average noise level of denoised magnetograms from our model is greatly reduced from 10.29 G to 3.89 G, and it is consistent with or smaller than that of stacked magnetograms 4.11 G. Our results can be applied to many scientific field in which the integration of many frames are used to improve the signal-to-noise ratio.

• Journal of the Korean Society of Radiology
• /
• v.12 no.5
• /
• pp.669-675
• /
• 2018

This study aimed to investigate the difference of X-ray exposure by comparing and analyzing entrance surface dose and absorbed dose according to the frame change in coronary angiography using an X-ray machine. Moreover, appropriate frame selection measures for examination, including the effect of frame change on the image quality, were sought by measuring and analyzing the SNR and CNR of the image through image J. The study was conducted on 30 patients (19 males and 11 females) who underwent CAG at this hospital from June 2017 to October 2017. In regard to the patients, their age range was 49-82 years (mean of $65{\pm}9$ years), body weight was 45-91 kg (mean of $67{\pm}8.9kg$), height was 150-179cm (mean of $165.1{\pm}8.9kg$), and BMI was 19.5-30.5(mean of $24.5{\pm}2.9$). For the entrance surface dose and absorbed dose, air kerma value and DAP were obtained and analyzed retrospectively. The SNR and CNR were measured and analyzed through imageJ, and the result values were derived by applying the values to the formula. As for the statistical analyses, the correlations between the entrance surface dose and absorbed dose, and between the SNR and CNR were analyzed by using the SPSS statistical program. The relationship between the entrance surface dose and absorbed dose was not statistically significant for both 10 f/s and 15 f/s (p>0.05). In terms of the relationship between the SNR and CNR, the SNR ($3.374{\pm}2.1297$) and CNR ($0.234{\pm}0.2249$) in 10 f/s were $1.43{\pm}0.4861$ and $0.132{\pm}0.0555$ lower, respectively, than the SNR ($4.929{\pm}2.8532$) and CNR ($0.391{\pm}0.3025$) in 15 f/s, which were not statistically significant (p>0.05). In the correlation analysis, statistically significant results were obtained among the BMI, air kerma, and DAP; between air kerma and DAP; and between SNR and CNR (p<0.001, p<0.001). In conclusion, there was no significant difference between the entrance surface dose and absorbed dose even when the images were taken by changing the frame from 10 f/s to 15 f/s at the time of the coronary angiography. SNR and CNR increased at 15 f/s than at 10 f/s, but they were not statistically significant. Therefore, this study suggests that the concern of the patient and practitioner regarding image quality degradation, as well as the problem of X-ray exposure caused by imaging at 10 f/s and 15 f/s, may be reduced.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.7
• /
• pp.49-53
• /
• 2016

Recently, the use of signal compression methods to improve the efficiency of wireless networks have increased. In particular, the MPC system was used in the pitch extraction method and the excitation source of voiced and unvoiced to reduce the bit rate. In general, the MPC system using an excitation source of voiced and unvoiced would result in a distortion of the synthesis speech waveform in the case of voiced and unvoiced consonants in a frame. This is caused by normalization of the synthesis speech waveform in the process of restoring the multi-pulses of the representation segment. This paper presents an ACFBD-MPC (Amplitude Compensation Frequency Band Division-Multi Pulse Coding) using amplitude compensation in a multi-pulses each pitch interval and specific frequency to reduce the distortion of the synthesis speech waveform. The experiments were performed with 16 sentences of male and female voices. The voice signal was A/D converted to 10kHz 12bit. In addition, the ACFBD-MPC system was realized and the SNR of the ACFBD-MPC estimated in the coding condition of 8kbps. As a result, the SNR of ACFBD-MPC was 13.6dB for the female voice and 14.2dB for the male voice. The ACFBD-MPC improved the male and female voice by 1 dB and 0.9 dB, respectively, compared to the traditional MPC. This method is expected to be used for cellular telephones and smartphones using the excitation source with a low bit rate.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.63-77
• /
• 1994

This paper describes the real-time system which, through analyzing a sequence of images, can extract motional information on a moving object and can contol servo equipment to always locate the moving object at the center of an image frame. An image is a vast amount of two-dimensional signal, so it takes a lot of time to analyze the whole quantity of a given image. Especially, the time needed to load pixels from a memory to processor increase exponentially as the size of an image increases. To solve such a problem and track a moving object in real-time, this paper addresses how to selectively search the spatial and time domain. Based on the selective search of spatial and time domain, this paper suggests various types of techniques which are essential in implementing a real-time tracking system. That is, this paper describes how to detect an entrance of a moving object in the field of view of a camera and the direction of the entrance, how to determine the time interval of adjacent images, how to determine nonstationary areas formed by a moving object and calculated velocity and position information of a moving object based on the determined areas, how to control servo equipment to locate the moving object at the center of an image frame, and how to properly adjust time interval(${\Delta}$t) to track an object taking variable speed.

• Microbiology and Biotechnology Letters
• /
• v.40 no.4
• /
• pp.348-355
• /
• 2012

In the present study, we investigated the overexpression and characterization of bovine pancreatic (bp)- DNase I in Saccharomyces cerevisiae and Pichia pastoris. The bp-DNase I gene was fused in frame with the GAL10 promoter, $MF{\alpha}$, and GAL7 terminator sequences, resulting in the plasmid, pGAL-$MF{\alpha}$-DNaseI (6.4 kb). Also, the bp-DNase I gene was fused in frame with the AOX1 promoter, $MF{\alpha}$, and AOX1 terminator sequences, resulting in the plasmid, pPEXI (8.8 kb). The recombinant plasmids, pGAL-$MF{\alpha}$-DNaseI and pPEXI were introduced into S. cerevisiae and P. pastoris host cells, respectively. When the transformed yeast cells were cultured at $30^{\circ}C$ for 48 h in galactose or methanol medium, bp-DNase I was overexpressed and the most of activity was found in the extracellular fraction. P. pastoris transformant activity showed 45.5 unit/mL in the culture medium at 48 h cultivation, whereas S. cerevisiae transformant revealed 37.7 unit/mL in the extracellular fraction at 48 h cultivation. The enzymatic characteristics, such as DNA cleavage and half life were investigated. Treatment of the recombinant DNase I from P. pastoris induced degradation of the calf thymus DNA within 1 minute, and this DNA degradation rate was higher than that of commercial bp-DNase I (SIGMA) and the recombinant DNase I from S. cerevisiae.

• The Journal of the Convergence on Culture Technology
• /
• v.3 no.3
• /
• pp.7-19
• /
• 2017

Korean standard poetry with a fixed form are Rated Sijo. These Rated Sijos can be found in the 24 number of Gosijos. Then, why should Korean standard poetry be Rated Sijo? This is because only the Rated Sijo has a fixed form frame. Rated Sijo naturally tailored by a rigid framework is the best representation of Koreans' unique breath and temperament. Also, Rated Sijo is superior to general sijo or poem in terms of literary therapeutic utility for human body. If Haiku omits the end of narrative with the rated number of sounds and invites different imaginations to each reader, the Rated Sijo presents a certain frame to the direction of the human's rated signal by constructing the essence of the narrative with the rated number of sounds. Thus, the Rated Sijo suggests the way of human harmony and communication by inducing different imagination of readers cooperating in a certain direction. So, the famous poem of Korea, Rated Sijo, presents our future as a framework of literature that can contribute to the improvement of human communication and quality of life. Therefore, research to preserve and develop the value of the Rated Sijo should now be initiated and continued.