• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.22 no.2
• /
• pp.115-123
• /
• 2018

This paper discusses extended Kalman filter method for solving learning problems of multilayered neural networks. A lot of learning algorithms for deep layered network are sincerely suffered from complex computation and slow convergence because of a very large number of free parameters. We consider an efficient learning algorithm for deep neural network. Extended Kalman filter method is applied to parameter estimation of neural network to improve convergence and computation complexity. We discuss how an efficient algorithm should be developed for neural network learning by using Extended Kalman filter.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.23-30
• /
• 2021

Sentiment Analysis has become very important field of research because posting of reviews is becoming a trend. Supervised, unsupervised and semi supervised machine learning methods done lot of work to mine this data. Feature engineering is complex and technical part of machine learning. Deep learning is a new trend, where this laborious work can be done automatically. Many researchers have done many works on Deep learning Convolutional Neural Network (CNN) and Long Shor Term Memory (LSTM) Neural Network. These requires high processing speed and memory. Here author suggested two models simple & bidirectional deep leaning, which can work on text data with normal processing speed. At end both models are compared and found bidirectional model is best, because simple model achieve 50% accuracy and bidirectional deep learning model achieve 99% accuracy on trained data while 78% accuracy on test data. But this is based on 10-epochs and 40-batch size. This accuracy can also be increased by making different attempts on epochs and batch size.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.12
• /
• pp.1772-1781
• /
• 2017

In this study, the design methodology for alleviating the overfitting problem of Polynomial Neural Networks(PNN) is realized with the aid of two kinds techniques such as L2 regularization and Sum of Squared Coefficients (SSC). The PNN is widely used as a kind of mathematical modeling methods such as the identification of linear system by input/output data and the regression analysis modeling method for prediction problem. PNN is an algorithm that obtains preferred network structure by generating consecutive layers as well as nodes by using a multivariate polynomial subexpression. It has much fewer nodes and more flexible adaptability than existing neural network algorithms. However, such algorithms lead to overfitting problems due to noise sensitivity as well as excessive trainning while generation of successive network layers. To alleviate such overfitting problem and also effectively design its ensuing deep network structure, two techniques are introduced. That is we use the two techniques of both SSC(Sum of Squared Coefficients) and $L_2$ regularization for consecutive generation of each layer's nodes as well as each layer in order to construct the deep PNN structure. The technique of $L_2$ regularization is used for the minimum coefficient estimation by adding penalty term to cost function. $L_2$ regularization is a kind of representative methods of reducing the influence of noise by flattening the solution space and also lessening coefficient size. The technique for the SSC is implemented for the minimization of Sum of Squared Coefficients of polynomial instead of using the square of errors. In the sequel, the overfitting problem of the deep PNN structure is stabilized by the proposed method. This study leads to the possibility of deep network structure design as well as big data processing and also the superiority of the network performance through experiments is shown.

• Journal of Sensor Science and Technology
• /
• v.30 no.5
• /
• pp.290-294
• /
• 2021

Experts have designed popular and successful model architectures, which, however, were not the optimal option for different scenarios. Despite the remarkable performances achieved by deep neural networks, manually designed networks for classification tasks are the backbone of object detection. One major challenge is the ImageNet pre-training of the search space representation; moreover, the searched network incurs huge computational cost. Therefore, to overcome the obstacle of the pre-training process, we introduce a network adaptation technique using a pre-trained backbone model tested on ImageNet. The adaptation method can efficiently adapt the manually designed network on ImageNet to the new object-detection task. Neural architecture search (NAS) is adopted to adapt the architecture of the network. The adaptation is conducted on the MobileNetV2 network. The proposed NAS is tested using SSDLite detector. The results demonstrate increased performance compared to existing network architecture in terms of search cost, total number of adder arithmetics (Madds), and mean Average Precision(mAP). The total computational cost of the proposed NAS is much less than that of the State Of The Art (SOTA) NAS method.

• Journal of Sensor Science and Technology
• /
• v.30 no.1
• /
• pp.20-24
• /
• 2021

The electrocardiogram (ECG) is one of the most extensively employed signals used to diagnose and predict cardiovascular diseases (CVDs). In recent years, several deep learning (DL) models have been proposed to improve detection accuracy. Among these, deep neural networks (DNNs) are the most popular, wherein the features are extracted automatically. Despite the increment in classification accuracy, DL models require exorbitant computational resources and power. This causes the mapping of DNNs to be slow; in addition, the mapping is challenging for a wearable device. Embedded systems have constrained power and memory resources. Therefore full-precision DNNs are not easily deployable on devices. To make the neural network faster and more power-efficient, spiking neural networks (SNNs) have been introduced for fewer operations and less complex hardware resources. However, the conventional SNN has low accuracy and high computational cost. Therefore, this paper proposes a new binarized SNN which modifies the synaptic weights of SNN constraining it to be binary (+1 and -1). In the simulation results, this paper compares the DL models and SNNs and evaluates which model is optimal for ECG classification. Although there is a slight compromise in accuracy, the latter proves to be energy-efficient.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.917-924
• /
• 2018

Recently, researches using LBP and SVM have been performed as one of the image - based methods for facial emotion recognition. LBP, introduced by Ojala et al., is widely used in the field of image recognition due to its high discrimination of objects, robustness to illumination change, and simple operation. In addition, CS(Center-Symmetric)-LBP was used as a modified form of LBP, which is widely used for face recognition. In this paper, we propose a method to detect four facial expressions such as expressionless, happiness, surprise, and anger using deep neural network. The validity of the proposed method is verified using accuracy. Based on the existing LBP feature parameters, it was confirmed that the method using the deep neural network is superior to the method using the Adaboost and SVM classifier.

• ETRI Journal
• /
• v.43 no.5
• /
• pp.881-890
• /
• 2021

Photoplethysmography (PPG) is a noninvasive technique that can be used to conveniently measure heart rate (HR) and thus obtain relevant health-related information. However, developing an automated PPG system is difficult, because its waveforms are susceptible to motion artifacts and between-patient variation, making its interpretation difficult. We use deep neural network (DNN) filters to mimic the cognitive ability of a human expert who can distinguish the features of PPG altered by noise from various sources. Systolic (S), onset (O), and first derivative peaks (W) are recognized by three different DNN filters. In addition, the boundaries of uninformative regions caused by artifacts are identified by two different filters. The algorithm reliably derives the HR and presents recognition scores for the S, O, and W peaks and artifacts with only a 0.7-s delay. In the evaluation using data from 11 patients obtained from PhysioNet, the algorithm yields 8643 (86.12%) reliable HR measurements from a total of 10 036 heartbeats, including some with uninformative data resulting from arrhythmias and artifacts.

• Journal of Korea Multimedia Society
• /
• v.21 no.11
• /
• pp.1244-1253
• /
• 2018

The color of traffic light is sensitive to various illumination conditions. Especially it loses the hue information when oversaturation happens on the lighting area. This paper proposes a traffic light recognition method robust to these illumination variations. The method consists of two steps of traffic light detection and recognition. It just uses the intensity and saturation in the first step of traffic light detection. It delays the use of hue information until it reaches to the second step of recognizing the signal of traffic light. We utilized a deep learning technique in the second step. We designed a deep convolutional neural network(DCNN) which is composed of three convolutional networks and two fully connected networks. 12 video clips were used to evaluate the performance of the proposed method. Experimental results show the performance of traffic light detection reporting the precision of 93.9%, the recall of 91.6%, and the recognition accuracy of 89.4%. Considering that the maximum distance between the camera and traffic lights is 70m, the results shows that the proposed method is effective.

• Journal of Sensor Science and Technology
• /
• v.30 no.1
• /
• pp.15-19
• /
• 2021

Image processing is one of the major techniques that are used for computer vision. Nowadays, researchers are using machine learning and deep learning for the aforementioned task. In recent years, digit recognition tasks, i.e., automatic meter recognition approach using electric or water meters, have been studied several times. However, two major issues arise when we talk about previous studies: first, the use of the deep learning technique, which includes a large number of parameters that increase the computational cost and consume more power; and second, recent studies are limited to the detection of digits and not storing or providing detected digits to a database or mobile applications. This paper proposes a system that can detect the digital number of meter readings using a lightweight deep neural network (DNN) for low power consumption and send those digits to an Android mobile application in real-time to store them and make life easy. The proposed lightweight DNN is computationally inexpensive and exhibits accuracy similar to those of conventional DNNs.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.119-128
• /
• 2022

Recently, due to the development of related technologies for autonomous vehicles, driving work is changing more safely. However, the development of support technologies for level 5 full autonomous driving is still insufficient. That is, even in the case of an autonomous vehicle, the driver needs to drive through forward attention while driving. In this paper, we propose a method to monitor driving tasks by recognizing driver behavior. The proposed method uses pre-trained deep convolutional neural network models to recognize whether the driver's face or body has unnecessary movement. The use of pre-trained Deep Convolitional Neural Network (DCNN) models enables high accuracy in relatively short time, and has the advantage of overcoming limitations in collecting a small number of driver behavior learning data. The proposed method can be applied to an intelligent vehicle safety driving support system, such as driver drowsy driving detection and abnormal driving detection.