• Korean Journal of Remote Sensing
• /
• v.34 no.5
• /
• pp.811-827
• /
• 2018

The purpose of this study is to compare machine learning algorithm and deep learning algorithm in crop classification using multi-temporal remote sensing data. For this, impacts of machine learning and deep learning algorithms on (a) hyper-parameter and (2) training sample size were compared and analyzed for Haenam-gun, Korea and Illinois State, USA. In the comparison experiment, support vector machine (SVM) was applied as machine learning algorithm and convolutional neural network (CNN) was applied as deep learning algorithm. In particular, 2D-CNN considering 2-dimensional spatial information and 3D-CNN with extended time dimension from 2D-CNN were applied as CNN. As a result of the experiment, it was found that the hyper-parameter values of CNN, considering various hyper-parameter, defined in the two study areas were similar compared with SVM. Based on this result, although it takes much time to optimize the model in CNN, it is considered that it is possible to apply transfer learning that can extend optimized CNN model to other regions. Then, in the experiment results with various training sample size, the impact of that on CNN was larger than SVM. In particular, this impact was exaggerated in Illinois State with heterogeneous spatial patterns. In addition, the lowest classification performance of 3D-CNN was presented in Illinois State, which is considered to be due to over-fitting as complexity of the model. That is, the classification performance was relatively degraded due to heterogeneous patterns and noise effect of input data, although the training accuracy of 3D-CNN model was high. This result simply that a proper classification algorithms should be selected considering spatial characteristics of study areas. Also, a large amount of training samples is necessary to guarantee higher classification performance in CNN, particularly in 3D-CNN.

• The Journal of the Convergence on Culture Technology
• /
• v.3 no.4
• /
• pp.165-169
• /
• 2017

CNN(Convolutional Nerual Network) is one of the algorithms that show superior performance in image recognition and classification among machine learning algorithms. CNN is simple, but it has a large amount of computation and it takes a lot of time. Consequently, in this paper we performed an parallel processing unit for the convolution layer, pooling layer and the fully connected layer, which consumes a lot of handling time in the process of CNN, through the SIMT(Single Instruction Multiple Thread)'s structure of GPGPU(General-Purpose computing on Graphics Processing Units).And we also expect to improve performance by reducing the number of memory accesses and directly using the output of convolution layer not storing it in pooling layer. In this paper, we use MNIST dataset to verify this experiment and confirm that the proposed CNN structure is 12.38% better than existing structure.

• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.2
• /
• pp.505-516
• /
• 2000

Cellular Neural Networks(CNN) is a nonlinear information-processing system that has a locally connected characteristic and is widely used in the real-time high speed image processing. In this paper, a practical system approach of time-multiplexing CNN implementations suitable for processing large and complex images using small CNN arrays is presented and $6\times6$ CNN hardware is designed for the processing of a large image. While previous implementations are mostly suitable for black and white applications because of the thresholded outputs, our approach is especially suitable for applications in gray image processing due to the analog nature of the state node. CNN chip is designed using a 0.65${\mu}{\textrm}{m}$ 2P2M(double poly, double metal) N-Well CMOS process technology. It contains about 15,400 devices on an area of about $1.85\times1.75$ md. The designed $6\times6$ CNN is tested for the edge detection of a large image input and it's performance is verified.

• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.39-46
• /
• 2019

In this study, before system development for the elimination of foreign fish species, we propose an algorithm to classify fish species by training fish images with CNN. The raw data for CNN learning were directly captured images for each species, Dataset 1 increases the number of images to improve the classification of fish species and Dataset 2 realizes images close to natural environment are constructed and used as training and test data. The classification performance of four CNNs are over 99.97% for dataset 1 and 99.5% for dataset 2, in particular, we confirm that the learned CNN using Data Set 2 has satisfactory performance for fish images similar to the natural environment. And among four CNNs, AlexNet achieves satisfactory performance, and this has also the shortest execution time and training time, we confirm that it is the most suitable structure to develop the system for the elimination of foreign fish species.

• Journal of Cadastre & Land InformatiX
• /
• v.48 no.2
• /
• pp.213-225
• /
• 2018

For constructing three-dimensional (3D) spatial information occlusion region problem arises in the process of taking the texture of the building. In order to solve this problem, it is necessary to investigate the automation method to automatically recognize the occlusion region, issue it, and automatically complement the texture. In fact there are occasions when it is possible to generate a very large number of structures and occlusion, so alternatives to overcome are being considered. In this study, we attempt to apply an approach to automatically create an occlusion region based on learning by patterning the blocked region using the recently emerging deep learning algorithm. Experiment to see the performance automatic detection of people, banners, vehicles, and traffic lights that cause occlusion in building walls using two advanced algorithms of Convolutional Neural Network (CNN) technique, Faster Region-based Convolutional Neural Network (R-CNN) and Mask R-CNN. And the results of the automatic detection by learning the banners in the pre-learned model of the Mask R-CNN method were found to be excellent.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.11
• /
• pp.1357-1363
• /
• 2019

In this paper, we compares the performance of the gredient descent optimizers of the Faster Region-based Convolutional Neural Network (R-CNN) model for the chromosome object detection in digital images composed of human metaphase chromosomes. In faster R-CNN, the gradient descent optimizer is used to minimize the objective function of the region proposal network (RPN) module and the classification score and bounding box regression blocks. The gradient descent optimizer. Through performance comparisons among these four gradient descent optimizers in our experiments, we found that the Adamax optimizer could achieve the mean average precision (mAP) of about 52% when considering faster R-CNN with a base network, VGG16. In case of faster R-CNN with a base network, ResNet50, the Adadelta optimizer could achieve the mAP of about 58%.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.10
• /
• pp.59-66
• /
• 1997

Neural networks has widely been be used for several practical applications such as speech, image processing, and pattern recognition. Thus, a approach to the voltage-controlled current source in areas of neural networks, the key features of CNN in locally connected only to its netighbors. Because the architecture of the interconnection elements between cells in very simple and space invariant, CNNs are suitable for VLSI implementation. In this paper, processing element of digital programmable CNN with variable template memory was implemented using CMOS circuit. CNN PE circuit was designe dto control gain for obtaining the optimal solutions in the CNN output. Performance of operation for 4*4 CNN circuit applied for fixed template and variable template analyzed with the result of simulation using HSPICE tool. As a result of simulations, the proposed variable template method verified to improve performance of operation in comparison with the fixed template method.

• Phonetics and Speech Sciences
• /
• v.8 no.2
• /
• pp.23-30
• /
• 2016

This paper describes some implementation schemes of CNN in view of mini-batch DNN training for efficient second order optimization. This uses same procedure updating parameters of DNN to train parameters of CNN by simply arranging an input image as a sequence of local patches, which is actually equivalent with mini-batch DNN training. Through this conversion, second order optimization providing higher performance can be simply conducted to train the parameters of CNN. In both results of image recognition on MNIST DB and syllable automatic speech recognition, our proposed scheme for CNN implementation shows better performance than one based on DNN.