• Science of Emotion and Sensibility
• /
• v.20 no.4
• /
• pp.101-112
• /
• 2017

We investigated the neural representation of reward probability recognition and its neural connectivity with other regions of the brain. Using functional magnetic resonance imaging (fMRI), we used a simple guessing task with different probabilities of obtaining rewards across trials to assay local and global regions processing reward probability. The results of whole brain analysis demonstrated that lateral prefrontal cortex, inferior parietal lobe, and postcentral gyrus were activated during probability-based decision making. Specifically, the higher the expected value was, the more these regions were activated. Fronto-parietal connectivity, comprising inferior parietal regions and right lateral prefrontal cortex, conjointly engaged during high reward probability recognition compared to low reward condition, regardless of whether the reward information was extrinsically presented. Finally, the result of a regression analysis identified that cortico-subcortical connectivity was strengthened during the high reward anticipation for the subjects with higher cognitive impulsivity. Our findings demonstrate that interregional functional involvement is involved in valuation based on reward probability and that personality trait such as cognitive impulsivity plays a role in modulating the connectivity among different brain regions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.5
• /
• pp.915-920
• /
• 2007

Using the existing algorithms that estimate the background noise, the detection probability for the week tonals is low and for the even week tonals, there is a limit not detected. Therefore it is required to algorithms which can improve the performance of the tonal extraction. Recently, many researches using artificial neural networks in sonar signal processing are performed. We propose a neural network with double feedback that can remove automatically the background noise and detect the even week tonals buried in background noise, therefore not detected by growing the week tonals lastingly for a certain time. For the real underwater target, experiments for the tonal extraction are performed by using the existing algorithms that estimate the background noise and the proposed neural network. As a result of the experiment, a method using the proposed neural network showed the better performance of the tonal extraction in comparison with the existing algorithms.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.1019-1029
• /
• 2020

In this paper, we propose a novel knowledge distillation algorithm to create an compressed deep ensemble network coupled with the combined use of local and global features of face images. In order to transfer the capability of high-level recognition performances of the ensemble deep networks to a single deep network, the probability for class prediction, which is the softmax output of the ensemble network, is used as soft target for training a single deep network. By applying the knowledge distillation algorithm, the local feature informations obtained by training the deep ensemble network using facial subregions of the face image as input are transmitted to a single deep network to create a so-called compressed ensemble DCNN. The experimental results demonstrate that our proposed compressed ensemble deep network can maintain the recognition performance of the complex ensemble deep networks and is superior to the recognition performance of a single deep network. In addition, our proposed method can significantly reduce the storage(memory) space and execution time, compared to the conventional ensemble deep networks developed for face recognition.

• Journal of the Institute of Convergence Signal Processing
• /
• v.1 no.1
• /
• pp.1-6
• /
• 2000

In this paper, the hybrid system of HMM and neural network is proposed and show better recognition rate of the post-process procedure which minimizes the process error of recognition than that of HMM(Hidden Markov Model) only used. After the HMM training by training data, testing data that are not taken part in the training are sent to HMM. The output probability from HMM output by testing data is used for the training data of the neural network, post processor. After neural network training, the hybrid system is completed. This hybrid system makes the recognition rate improvement of about $4.5\%$ in MLP and about $2\%$ in RBFN and gives the solution to training time of conventional hybrid system and to decrease of the recognition rate due to the lack of training data in real-time speech recognition system.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1653-1661
• /
• 2022

In this study, the classification of cold water and normal water based on Geo-Kompsat 2A images was performed. Daily mean surface temperature products provided by the National Meteorological Satellite Center (NMSC) were used, and convolution neural network (CNN) deep learning technique was applied as a classification algorithm. From 2019 to 2022, the cold water occurrence data provided by the National Institute of Fisheries Science (NIFS) were used as the cold water class. As a result of learning, the probability of detection was 82.5% and the false alarm ratio was 54.4%. Through misclassification analysis, it was confirmed that cloud area should be considered and accurate learning data should be considered in the future.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.348-358
• /
• 2022

Software fault prediction is a method to compute fault in the software sections using software properties which helps to evaluate the quality of software in terms of cost and effort. Recently, several software fault detection techniques have been proposed to classifying faulty or non-faulty. However, for such a person, and most studies have shown the power of predictive errors in their own databases, the performance of the software is not consistent. In this paper, we propose a hybrid soft computing technique for SFP based on optimal feature extraction and classification (HST-SFP). First, we introduce the bat induced butterfly optimization (BBO) algorithm for optimal feature selection among multiple features which compute the most optimal features and remove unnecessary features. Second, we develop a layered recurrent neural network (L-RNN) based classifier for predict the software faults based on their features which enhance the detection accuracy. Finally, the proposed HST-SFP technique has the more effectiveness in some sophisticated technical terms that outperform databases of probability of detection, accuracy, probability of false alarms, precision, ROC, F measure and AUC.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.10
• /
• pp.1894-1899
• /
• 1994

In this paper, a new identification method is proposed for unknown digitally modulated input signals. The proposed identification method is implemented using a self-organized neural network which is based on the characteristic features of the symbol magnitude; the number of symbol magnitude levels, amplitude probability density and adjacent symbol magnitude ratio. The proposed method was performed for 5 QAM signals. The simulation results show that the self-organized neural network can accurately recognize all kinds of patterns even at SNR 8dB. The proposed method can be applied to the intelligent communication system on ISDN and multi-point polling networks.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.4
• /
• pp.117-130
• /
• 2005

It is effective and desirable for a proper customer relationship management or marketing to focus on the specific customers rather than a number of non specific customers. This study forecasts the prospective purchasers with high probability to purchase a specific product. Artificial Neural Network( ANN) can classily the characteristics of the prospective purchasers but ANN has a limitation in comprehending of outputs. ANN is integrated into IRANN with IR of decision tree program C5.0 to comprehend and analyze the outputs of ANN. We compare and analyze the accuracy of ANN, IR, and IRANN each other.

• Ocean Systems Engineering
• /
• v.7 no.4
• /
• pp.319-328
• /
• 2017

Higher prediction efficacy is a very challenging task in any field of engineering. Due to global warming, there is a considerable increase in the global sea level. Through this work, an attempt has been made to find the sea level variability due to climate change impact at Haldia Port, India. Different statistical downscaling techniques are available and through this paper authors are intending to compare and illustrate the performances of three regression models. The models: Wavelet Neural Network (WNN), Minimax Probability Machine Regression (MPMR), Feed-Forward Neural Network (FFNN) are used for projecting the sea level variability due to climate change at Haldia Port, India. Model performance indices like PI, RMSE, NSE, MAPE, RSR etc were evaluated to get a clear picture on the model accuracy. All the indices are pointing towards the outperformance of WNN in projecting the sea level variability. The findings suggest a strong recommendation for ensembled models especially wavelet decomposed neural network to improve projecting efficiency in any time series modeling.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.352-368
• /
• 2021

Sign-in point of interest (POI) are extremely sparse in location-based social networks, hindering recommendation systems from capturing users' deep-level preferences. To solve this problem, we propose a content-aware POI recommendation algorithm based on a convolutional neural network. First, using convolutional neural networks to process comment text information, we model location POI and user latent factors. Subsequently, the objective function is constructed by fusing users' geographical information and obtaining the emotional category information. In addition, the objective function comprises matrix decomposition and maximisation of the probability objective function. Finally, we solve the objective function efficiently. The prediction rate and F1 value on the Instagram-NewYork dataset are 78.32% and 76.37%, respectively, and those on the Instagram-Chicago dataset are 85.16% and 83.29%, respectively. Comparative experiments show that the proposed method can obtain a higher precision rate than several other newer recommended methods.