• Journal of IKEEE
• /
• v.20 no.4
• /
• pp.351-360
• /
• 2016

Recently, machine learning algorithms, especially deep learning-based algorithms, have been receiving attention due to its high classification performance. Among the algorithms, Convolutional Neural Network(CNN) is known to be efficient for image processing tasks used for Advanced Driver Assistance Systems(ADAS). However, it is difficult to achieve real-time processing for CNN in vehicle embedded software environment due to the repeated operations contained in each layer of CNN. In this paper, we propose a hardware accelerator which enhances the execution time of CNN by parallelizing the repeated operations such as convolution. Xilinx ZC706 evaluation board is used to verify the performance of the proposed accelerator. For $36{\times}36$ input images, the hardware execution time of CNN is 2.812ms in 100MHz clock frequency and shows that our hardware can be executed in real-time.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.1
• /
• pp.60-65
• /
• 2018

In this paper, a covariance matrix and modulogram are proposed for realizing amphibian sound classification using CNN (Convolutional Neural Network). First of all, a database is established by collecting amphibians sounds including endangered species in natural environment. In order to apply the database to CNN, it is necessary to standardize acoustic signals with different lengths. To standardize the acoustic signals, covariance matrix that gives distribution information and modulogram that contains the information about change over time are extracted and used as input to CNN. The experiment is conducted by varying the number of a convolutional layer and a fully-connected layer. For performance assessment, several conventional methods are considered representing various feature extraction and classification approaches. From the results, it is confirmed that convolutional layer has a greater impact on performance than the fully-connected layer. Also, the performance based on CNN shows attaining the highest recognition rate with 99.07 % among the considered methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.309-316
• /
• 2020

We predict the mortality of the elderly patients visiting the emergency department who are over 65 years old using Feed Forward Neural Network (FFNN) and Convolutional Neural Network (CNN) respectively. Medical data consist of 99 features including basic information such as sex, age, temperature, and heart rate as well as past history, various blood tests and culture tests, and etc. Among these, we used random forest to select features by measuring the importance of features in the prediction of mortality. As a result, using the top 80 features with high importance is best in the mortality prediction. The performance of the FFNN and CNN is compared by using the selected features for training each neural network. To train CNN with images, we convert medical data to fixed size images. We acquire better results with CNN than with FFNN. With CNN for mortality prediction, F1 score and the AUC for test data are 56.9 and 92.1 respectively.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1168-1177
• /
• 2019

In order to diagnose and prevent Alzheimer's Disease (AD), it is becoming increasingly important to develop a CAD(Computer-aided Diagnosis) system for AD diagnosis, which provides effective treatment for patients by analyzing 3D MRI images. It is essential to apply powerful deep learning algorithms in order to automatically classify stages of Alzheimer's Disease and to develop a Alzheimer's Disease support diagnosis system that has the function of detecting hippocampus and CSF(Cerebrospinal fluid) which are important biomarkers in diagnosis of Alzheimer's Disease. In this paper, for AD diagnosis, we classify a given MRI data into three categories of AD, mild cognitive impairment, and normal control according by applying 3D brain MRI image to the Faster R-CNN model and detect hippocampus and CSF in MRI image. To do this, we use the 2D MRI slice images extracted from the 3D MRI data of the Faster R-CNN, and perform the widely used majority voting algorithm on the resulting bounding box labels for classification. To verify the proposed method, we used the public ADNI data set, which is the standard brain MRI database. Experimental results show that the proposed method achieves impressive classification performance compared with other state-of-the-art methods.

• The Journal of the Korea Contents Association
• /
• v.18 no.11
• /
• pp.447-454
• /
• 2018

This paper proposes a depth image generation algorithm of stereo images using a deep learning model composed of a CNN (convolutional neural network). The proposed algorithm consists of a feature extraction unit which extracts the main features of each parallax image and a depth learning unit which learns the parallax information using extracted features. First, the feature extraction unit extracts a feature map for each parallax image through the Xception module and the ASPP(Atrous spatial pyramid pooling) module, which are composed of 2D CNN layers. Then, the feature map for each parallax is accumulated in 3D form according to the time difference and the depth image is estimated after passing through the depth learning unit for learning the depth estimation weight through 3D CNN. The proposed algorithm estimates the depth of object region more accurately than other algorithms.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.134-142
• /
• 2019

As the development of internet of energy (IoE) technologies and spread of various electronic devices have diversified patterns of energy consumption, the reliability of demand prediction has decreased, causing problems in optimization of power generation and stabilization of power supply. In this study, we propose a deep learning method, 1-Dimention-Convolution and Bidirectional Long Short-Term Memory (1D-ConvBLSTM), that combines a convolution neural network (CNN) and a Bidirectional Long Short-Term Memory(BLSTM) for highly reliable demand forecasting by effectively extracting the energy consumption pattern. In experimental results, the demand is predicted with the proposed deep learning method for various number of learning iterations and feature maps, and it is verified that the test data is predicted with a small number of iterations.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.605-610
• /
• 2020

Software Defined Networking (SDN) is setting the standard for the management of networks due to its scalability, flexibility and functionality to program the network. The Distributed Denial of Service (DDoS) attack is most widely used to attack the SDN controller to bring down the network. Different methodologies have been utilized to detect DDoS attack previously. In this paper, first the dataset is obtained by Kaggle with 84 features, and then according to the rank, the 20 highest rank features are selected using Permutation Importance Algorithm. Then, the datasets are trained and tested with Convolution Neural Network (CNN) classifier model by utilizing deep learning techniques. Our proposed solution has achieved the best results, which will allow the critical systems which need more security to adopt and take full advantage of the SDN paradigm without compromising their security.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.20-29
• /
• 2021

In the Industry 4.0 era, artificial intelligence has attracted considerable interest for learning mass data to improve the accuracy of forecasting and classification. On the other hand, the current method of detecting anomalies relies on traditional statistical methods for a limited amount of data, making it difficult to detect accurate anomalies. Therefore, this paper proposes an artificial intelligence-based anomaly detection methodology to improve the prediction accuracy and identify new data patterns. In particular, data were collected and analyzed from the point of view that sensor data collected at vehicle idle could be used to detect abnormalities. To this end, a sensor was designed to determine the appropriate time length of the data entered into the forecast model, compare the results of idling data with the overall driving data utilization, and make optimal predictions through a combination of various sensor data. In addition, the predictive accuracy of artificial intelligence techniques was presented by comparing Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) as the predictive methodologies. According to the analysis, using idle data, using 1.5 times of the data for the idling periods, and using CNN over LSTM showed better prediction results.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.179-188
• /
• 2022

There have been many successful researches on a bearing fault diagnosis based on Deep Learning, but there is still a critical issue of the data distribution difference between training data and test data from their different working conditions causing performance degradation in applying those methods to the machines in the field. As a solution, a data adaptation method has been proposed and showed a good result, but each and every approach is strictly limited to a specific applying scenario or presupposition, which makes it still difficult to be used as a real-world application. Therefore, in this study, we have proposed a method that, using a data transformation with MFCCs and a simple CNN architecture, can perform a robust diagnosis on a target domain data without an additional learning or tuning on the model generated from a source domain data and conducted an experiment and analysis on the proposed method with the CWRU bearing dataset, which is one of the representative datasests for bearing fault diagnosis. The experimental results showed that our method achieved an equal performance to those of transfer learning based methods and a better performance by at least 15% compared to that of an input transformation based baseline method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.3
• /
• pp.99-103
• /
• 2021

Recently, convolutional neural networks (CNNs) have been widely utilized due to their outstanding performance in various computer vision fields. However, due to their computational-intensive and high memory requirements, it is difficult to deploy CNNs on hardware platforms that have limited resources, such as mobile devices and IoT devices. To address these limitations, a neural network compression research is underway to reduce the size of neural networks while maintaining their performance. This paper proposes a CNN compression technique that dynamically adjusts the thresholds of pruning, one of the neural network compression techniques. Unlike the conventional pruning that experimentally or heuristically sets the thresholds that determine the weights to be pruned, the proposed technique can dynamically find the optimal thresholds that prevent accuracy degradation and output the light-weight neural network in less time. To validate the performance of the proposed technique, the LeNet was trained using the MNIST dataset and the light-weight LeNet could be automatically obtained 1.3 to 3 times faster without loss of accuracy.