• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.191-204
• /
• 2018

To combat the adverse impact imposed by illumination variation in the face recognition process, an effective and feasible algorithm is proposed in this paper. Firstly, an enhanced local texture feature is presented by applying the central symmetric encode principle on the fused component images acquired from the wavelet decomposition. Then the proposed local texture features are combined with Deep Belief Network (DBN) to gain robust deep features of face images under severe illumination conditions. Abundant experiments with different test schemes are conducted on both CMU-PIE and Extended Yale-B databases which contain face images under various illumination condition. Compared with the DBN, LBP combined with DBN and CSLBP combined with DBN, our proposed method achieves the most satisfying recognition rate regardless of the database used, the test scheme adopted or the illumination condition encountered, especially for the face recognition under severe illumination variation.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.6
• /
• pp.401-406
• /
• 2017

This paper presents the performance assessment of several key algorithms conducted for amphibian species sound classification. Firstly, 9 target species including endangered species are defined and a database of their sounds is built. For performance assessment, three feature vectors such as MFCC (Mel Frequency Cepstral Coefficient), RCGCC (Robust Compressive Gammachirp filterbank Cepstral Coefficient), and SPCC (Subspace Projection Cepstral Coefficient), and three classifiers such as GMM(Gaussian Mixture Model), SVM(Support Vector Machine), DBN-DNN(Deep Belief Network - Deep Neural Network) are considered. In addition, i-vector based classification system which is widely used for speaker recognition, is used to assess for this task. Experimental results indicate that, SPCC-SVM achieved the best performance with 98.81 % while other methods also attained good performance with above 90 %.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.146-154
• /
• 2020

Negative emotion causes stress and lack of attention concentration. The classification of negative emotion is important to recognize risk factors. To classify emotion status, various methods such as questionnaires and interview are used and it could be changed by personal thinking. To solve the problem, we acquire multi modal bio-signals such as electrocardiogram (ECG), skin temperature (ST), galvanic skin response (GSR) and extract features. The neural network (NN), the deep neural network (DNN), and the deep belief network (DBN) is designed using the multi modal bio-signals to analyze emotion status. As a result, the DBN based on features extracted from ECG, ST and GSR shows the highest accuracy (93.8%). It is 5.7% higher than compared to the NN and 1.4% higher than compared to the DNN. It shows 12.2% higher accuracy than using only single bio-signal (GSR). The multi modal bio-signal acquisition and the deep learning classifier play an important role to classify emotion.

• Smart Structures and Systems
• /
• v.29 no.5
• /
• pp.729-746
• /
• 2022

In this paper, a nonlinear structural model updating methodology based on the Deep Belief Network (DBN) is proposed. Firstly, the instantaneous parameters of the vibration responses are obtained by the discrete analytical mode decomposition (DAMD) method and the Hilbert transform (HT). The instantaneous parameters are regarded as the independent variables, and the nonlinear model parameters are considered as the dependent variables. Then the DBN is utilized for approximating the nonlinear mapping relationship between them. At last, the instantaneous parameters of the measured vibration responses are fed into the well-trained DBN. Owing to the strong learning and generalization abilities of the DBN, the updated nonlinear model parameters can be directly estimated. Two nonlinear shear-type structure models under two types of excitation and various noise levels are adopted as numerical simulations to validate the effectiveness of the proposed approach. The nonlinear properties of the structure model are simulated via the hysteretic parameters of a Bouc-Wen model and a Giuffré-Menegotto-Pinto model, respectively. Besides, the proposed approach is verified by a three-story shear-type frame with a piezoelectric friction damper (PFD). Simulated and experimental results suggest that the nonlinear model updating approach has high computational efficiency and precision.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2180-2197
• /
• 2019

With the proliferation of the Android malicious applications, malware becomes more capable of hiding or confusing its malicious intent through the use of code obfuscation, which has significantly weaken the effectiveness of the conventional defense mechanisms. Therefore, in order to effectively detect unknown malicious applications on the Android platform, we propose DroidVecDeep, an Android malware detection method using deep learning technique. First, we extract various features and rank them using Mean Decrease Impurity. Second, we transform the features into compact vectors based on word2vec. Finally, we train the classifier based on deep learning model. A comprehensive experimental study on a real sample collection was performed to compare various malware detection approaches. Experimental results demonstrate that the proposed method outperforms other Android malware detection techniques.

• Nuclear Engineering and Technology
• /
• v.53 no.1
• /
• pp.148-163
• /
• 2021

Timely fault identification is important for safe and reliable operation of the electric valve system. Many research works have utilized different data-driven approach for fault diagnosis in complex systems. However, they do not consider specific characteristics of critical control components such as electric valves. This work presents an integrated shallow-deep fault diagnostic model, developed based on signals extracted from DN50 electric valve. First, the local optimal issue of particle swarm optimization algorithm is solved by optimizing the weight search capability, the particle speed, and position update strategy. Then, to develop a shallow diagnostic model, the modified particle swarm algorithm is combined with support vector machine to form a hybrid improved particle swarm-support vector machine (IPs-SVM). To decouple the influence of the background noise, the wavelet packet transform method is used to reconstruct the vibration signal. Thereafter, the IPs-SVM is used to classify phase imbalance and damaged valve faults, and the performance was evaluated against other models developed using the conventional SVM and particle swarm optimized SVM. Secondly, three different deep belief network (DBN) models are developed, using different acoustic signal structures: raw signal, wavelet transformed signal and time-series (sequential) signal. The models are developed to estimate internal leakage sizes in the electric valve. The predictive performance of the DBN and the evaluation results of the proposed IPs-SVM are also presented in this paper.

• Smart Media Journal
• /
• v.5 no.3
• /
• pp.35-41
• /
• 2016

In this paper, we propose hand-gesture signal recognition based on EPS(Electronic Potential Sensor) using Deep learning model. Extracted signals which from Electronic field based sensor, EPS have much of the noise, so it must remove in pre-processing. After the noise are removed with filter using frequency feature, the signals are reconstructed with dimensional transformation to overcome limit which have just one-dimension feature with voltage value for using convolution operation. Then, the reconstructed signal data is finally classified and recognized using multiple learning layers model based on deep learning. Since the statistical model based on probability is sensitive to initial parameters, the result can change after training in modeling phase. Deep learning model can overcome this problem because of several layers in training phase. In experiment, we used two different deep learning structures, Convolutional neural networks and Recurrent Neural Network and compared with statistical model algorithm with four kinds of gestures. The recognition result of method using convolutional neural network is better than other algorithms in EPS gesture signal recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.5
• /
• pp.423-431
• /
• 2016

In general LPR(License Plate Recognition) in outdoor image is not so simple differently from in the image captured from manmade environment, because of geometric shape distortion and large illumination changes. this paper proposes three techniques for LPR in outdoor images captured from CCTV. At first, a serially connected multi-stage Adaboost LP detector is proposed, in which different complementary features are used. In the proposed detector the performance is increased by the Haar-like Adaboost LP detector consecutively connected to the MB-LBP based one in serial manner. In addition the technique is proposed that makes image processing easy by the prior determination of LP type, after correction of geometric distortion of LP image. The technique is more efficient than the processing the whole LP image without knowledge of LP type in that we can take the appropriate color to gray conversion, accurate location for separation of text/numeric character sub-images, and proper parameter selection for image processing. In the proposed technique we use DBN(Deep Belief Network) to achieve a robust character recognition against stroke loss and geometric distortion like slant due to the incomplete image processing.

• Smart Media Journal
• /
• v.6 no.3
• /
• pp.41-48
• /
• 2017

Event detection using social media has been widespread since social network services have been an active communication channel for connecting with others, diffusing news message. Especially, the real-time characteristic of social media has created the opportunity for supporting for real-time applications/systems. Social network such as Twitter is the potential data source to explore useful information by mining messages posted by the user community. This paper proposed a novel system for temporal event detection by analyzing social data. As a result, this information can be used by first responders, decision makers, or news agents to gain insight of the situation. The proposed approach takes advantages of deep learning methods that play core techniques on the main tasks including informative data identifying from a noisy environment and temporal event detection. The former is the responsibility of Convolutional Neural Network model trained from labeled Twitter data. The latter is for event detection supported by Recurrent Neural Network module. We demonstrated our approach and experimental results on the case study of earthquake situations. Our system is more adaptive than other systems used traditional methods since deep learning enables to extract the features of data without spending lots of time constructing feature by hand. This benefit makes our approach adaptive to extend to a new context of practice. Moreover, the proposed system promised to respond to acceptable delay within several minutes that will helpful mean for supporting news channel agents or belief plan in case of disaster events.