• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.148-154
• /
• 2021

With the advent of context-aware computing, many attempts were made to understand emotions. Among these various attempts, Speech Emotion Recognition (SER) is a method of recognizing the speaker's emotions through speech information. The SER is successful in selecting distinctive 'features' and 'classifying' them in an appropriate way. In this paper, the performances of SER using neural network models (e.g., fully connected network (FCN), convolutional neural network (CNN)) with Mel-Frequency Cepstral Coefficients (MFCC) are examined in terms of the accuracy and distribution of emotion recognition. For Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset, by tuning model parameters, a two-dimensional Convolutional Neural Network (2D-CNN) model with MFCC showed the best performance with an average accuracy of 88.54% for 5 emotions, anger, happiness, calm, fear, and sadness, of men and women. In addition, by examining the distribution of emotion recognition accuracies for neural network models, the 2D-CNN with MFCC can expect an overall accuracy of 75% or more.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1464-1480
• /
• 2019

Robust tracking of infrared (IR) pedestrian targets with various backgrounds, e.g. appearance changes, illumination variations, and background disturbances, is a great challenge in the infrared image processing field. In the paper, we address a new tracking method for IR pedestrian targets via multi-feature local sparse representation (SR), which consists of three important modules. In the first module, a multi-feature local SR model is constructed. Considering the characterization of infrared pedestrian targets, the gray and edge features are first extracted from all target templates, and then fused into the model learning process. In the second module, an effective tracker is proposed via the learned model. To improve the computational efficiency, a sliding window mechanism with multiple scales is first used to scan the current frame to sample the target candidates. Then, the candidates are recognized via sparse reconstruction residual analysis. In the third module, an adaptive dictionary update approach is designed to further improve the tracking performance. The results demonstrate that our method outperforms several classical methods for infrared pedestrian tracking.

• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.273-275
• /
• 2022

Deep Learning is used nowadays in Nuclei segmentation. While recent developments in theory and open-source software have made these tools easier to implement, expert knowledge is still required to choose the exemplary model architecture and training setup. We compare two popular segmentation frameworks, U-Net and Mask-RCNN, in the nuclei segmentation task and find that they have different strengths and failures. we compared both models aiming for the best nuclei segmentation performance. Experimental Results of Nuclei Medical Images Segmentation using U-NET algorithm Outperform Mask R-CNN Algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1042-1047
• /
• 2004

Voltage control is an essential part of the electric energy transmission and distribution system to maintain proper voltage limit at the consumer's terminal. Besides the generating units that provide the basic voltage control, there are many additional voltage-controlling agents e.g., shunt capacitors, shunt reactors, static VAr compensators, regulating transformers mentioned in [1], [2]. The most popular one, among all those agents for controlling voltage levels at the distribution and transmission system, is the on-load tap changer transformer. It serves two functions-energy transformation in different voltage levels and the voltage control. Artificial Neural Network (ANN) has been realized as a convenient tool that can be used in controlling the on load tap changer in the distribution transformers. Usage of the ANN in this area needs suitable training and testing data for performance analysis before the practical application. This paper briefly describes a procedure of processing the data to train an Artificial Neural Network (ANN) to control the tap changer operating decision of parallel transformers for a closed primary bus. The data set are used to train a two layer ANN using three different neural net learning algorithms, namely, Standard Backpropagation [3], Bayesian Regularization [4] and Scaled Conjugate Gradient [5]. The experimental results are presented including performance analysis.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.17 no.1
• /
• pp.109-115
• /
• 2021

The number of freshmen at universities is decreasing due to the recent decline in the school-age population, and the survival of many universities is threatened. To overcome this situation, universities are seeking ways to use big data within the school to improve the quality of education. A study on the prediction of dropout students is a representative case of using big data in universities. The dropout prediction can prepare a systematic management plan by identifying students who will drop out of school due to reasons such as dropout or expulsion. In the case of actual on-campus data, a large number of missing values are included because it is collected and managed by various departments. For this reason, it is necessary to construct a model by effectively reflecting the missing values. In this study, we propose a university student dropout prediction model based on eXtreme Gradient Boost that can be applied to data with many missing values and shows high performance. In order to examine the practical applicability of the proposed model, an experiment was performed using data from C University in Chungbuk. As a result of the experiment, the prediction performance of the proposed model was found to be excellent. The management strategy of dropout students can be established through the prediction results of the model proposed in this paper.

• Journal of Ginseng Research
• /
• v.32 no.4
• /
• pp.341-346
• /
• 2008

In the present study, we assessed the effects of white ginseng and red ginseng extract on the learning and memory impairments induced by scopolamine. The cognition-enhancing effect of ginseng extracts was investigated using the Morris water maze and Y-maze test. Drug-induced amnesia was induced by treating animals with scopolamine (2 mg/kg, i.p.), an antagonist of muscarinic acetylcholine (ACh) receptor. Tacrine was used a positive control. Ginseng extract (200 mg/kg, p.o.), tacrine (10 mg/kg, p.o.) administration significantly reduced the escape latency during training in the Morris water maze (p<0.05). At the probe trial session, scopolamine significantly increased the escape latency on day 5 in comparison with control (p<0.01). The effect of ginseng extracts on spontaneous alternation in Y-maze was similar to that of scopolamine treated group. In addition, numbers of arm entries were similar in all experimental groups. Moreover, red ginseng extract significantly inhibited acetylcholinesterase activity in the cortex and serum (p<0.05). Brain ACh contents of ginseng extract treated groups increased more than that of scopolamine group, which did not show statistically significant. These results suggest that ginseng extract may be useful for the treatment of cognitive impairment.

• International Journal of Automotive Technology
• /
• v.4 no.4
• /
• pp.181-191
• /
• 2003

Since the nonlinearity and uncertainties which inherently exist in vehicle system need to be considered in active suspension control law design, this paper proposes a new control strategy for active vehicle suspension systems by using a combined control scheme, i.e., respectively using a genetic algorithm (GA) based self-tuning PID controller and a fuzzy logic controller in two loops. In the control scheme, the PID controller is used to minimize vehicle body vertical acceleration, the fuzzy logic controller is to minimize pitch acceleration and meanwhile to attenuate vehicle body vertical acceleration further by tuning weighting factors. In order to improve the adaptability to the changes of plant parameters, based on the defined objectives, a genetic algorithm is introduced to tune the parameters of PID controller, the scaling factors, the gain values and the membership functions of fuzzy logic controller on-line. Taking a four degree-of-freedom nonlinear vehicle model as example, the proposed control scheme is applied and the simulations are carried out in different road disturbance input conditions. Simulation results show that the present control scheme is very effective in reducing peak values of vehicle body accelerations, especially within the most sensitive frequency range of human response, and in attenuating the excessive dynamic tire load to enhance road holding performance. The stability and adaptability are also showed even when the system is subject to severe road conditions, such as a pothole, an obstacle or a step input. Compared with conventional passive suspensions and the active vehicle suspension systems by using, e.g., linear fuzzy logic control, the combined PID and fuzzy control without parameters self-tuning, the new proposed control system with GA-based self-learning ability can improve vehicle ride comfort performance significantly and offer better system robustness.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.22-28
• /
• 2010

Adaboost is well known for a representative learner as one of the kernel methods. Adaboost which is based on the statistical learning theory shows good generalization performance and has been applied to various pattern recognition problems. However, Adaboost is basically to deal with a two-class classification problem, so we cannot solve directly a multi-class problem with Adaboost. One-Vs-All and Pair-Wise have been applied to solve the multi-class classification problem, which is one of the multi-class problems. The two methods above are ones of the output coding methods, a general approach for solving multi-class problem with multiple binary classifiers, which decomposes a complex multi-class problem into a set of binary problems and then reconstructs the outputs of binary classifiers for each binary problem. However, two methods cannot show good performance. In this paper, we propose the method to solve a multi-target classification problem by using radial basis function of Adaboost weak classifier.

• Geomechanics and Engineering
• /
• v.37 no.3
• /
• pp.223-241
• /
• 2024

Evaluating the performance of Tunnel Boring Machines (TBMs) stands as a pivotal juncture in the domain of hard rock mechanized tunneling, essential for achieving both a dependable construction timeline and utilization rate. In this investigation, three advanced artificial neural networks namely, gated recurrent unit (GRU), back propagation neural network (BPNN), and simple recurrent neural network (SRNN) were crafted to prognosticate TBM-rate of penetration (ROP). Drawing from a dataset comprising 1125 data points amassed during the construction of the Alborze Service Tunnel, the study commenced. Initially, five geomechanical parameters were scrutinized for their impact on TBM-ROP efficiency. Subsequent statistical analyses narrowed down the effective parameters to three, including uniaxial compressive strength (UCS), peak slope index (PSI), and Brazilian tensile strength (BTS). Among the methodologies employed, GRU emerged as the most robust model, demonstrating exceptional predictive prowess for TBM-ROP with staggering accuracy metrics on the testing subset (R² = 0.87, NRMSE = 6.76E-04, MAD = 2.85E-05). The proposed models present viable solutions for analogous ground and TBM tunneling scenarios, particularly beneficial in routes predominantly composed of volcanic and sedimentary rock formations. Leveraging forecasted parameters holds the promise of enhancing both machine efficiency and construction safety within TBM tunneling endeavors.