• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.11a
• /
• pp.417-426
• /
• 2000

This study suggests integrated neural network models for Interest rate forecasting using change-point detection, classifiers, and classification functions based on structural change. The proposed model is composed of three phases with tee-staged learning. The first phase is to detect successive and appropriate structural changes in interest rare dataset. The second phase is to forecast change-point group with classifiers (discriminant analysis, logistic regression, and backpropagation neural networks) and their. combined classification functions. The fecal phase is to forecast the interest rate with backpropagation neural networks. We propose some classification functions to overcome the problems of two-staged learning that cannot measure the performance of the first learning. Subsequently, we compare the structured models with a neural network model alone and, in addition, determine which of classifiers and classification functions can perform better. This article then examines the predictability of the proposed classification functions for interest rate forecasting using structural change.

• The Journal of Information Technology and Database
• /
• v.2 no.2
• /
• pp.71-85
• /
• 1995

Many research results conducted by neural network researchers have claimed that the classification accuracy of neural networks is superior to, or at least equal to that of conventional methods. However, in series of neural network classifications, it was found that the classification accuracy strongly depends on the characteristics of training data set. Even though there are many research reports that the classification accuracy of neural networks can be different, depending on the composition and architecture of the networks, training algorithm, and test data set, very few research addressed the problem of classification accuracy when the basic assumption of data monotonicity is violated, In this research, development project of automated credit evaluation system is described. The finding was that arrangement of training data is critical to successful implementation of neural training to maintain monotonicity of the data set, for enhancing classification accuracy of neural networks.

• Journal of Biomedical Engineering Research
• /
• v.16 no.2
• /
• pp.157-166
• /
• 1995

The Electroencephalogram (EEG) and evoked potential (EP) t;ave widely been used for study of brain functions. The EEG and EP signals acquired from multi-channel electrodes placed on the head surface are often interfered by other relatively large physiological signals such as electromyogram (EMG) or electroculogram (EOG). Since these artifact-affected EEG signals degrade EEG mapping, the removal of the artifact-affected EEGs is one of the key elements in neuro-functional mapping. Conventionally this task has been carried out by human experts spending lots of examination time. In this paper a neural-network based classification is proposed to replace or to reduce human expert's efforts and time. From experiments, the neural-network based classification performs as good as human experts : variation of decisions between the neural network and human expert appears even smaller than that between human experts.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.1
• /
• pp.197-208
• /
• 2016

In this paper, we propose a method based on a convolutional neural network which is one of the deep neural network. So, we convert a malware code to malware image and train the convolutional neural network. In experiment with classify 9-families, the proposed method records a 96.2%, 98.7% of top-1, 2 error rate. And our model can classify 27 families with 82.9%, 89% of top-1,2 error rate.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.7
• /
• pp.70-78
• /
• 1992

In this paper, an approach for 3-D object segmentation and classification, which is based on eigen-values of polynomial function as their surface features, using neural network is proposed. The range images of 3-D objects are classified into surface primitives which are homogeneous in their intrinsic eigenvalue properties. The misclassified regions due to noise effect are merged into correct regions satisfying homogeneous constraints of Hopfield neural network. The proposed method has advantage of processing both segmentation and classification simultaneously.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.229-232
• /
• 2008

A Neural network classification of human activity data is presented. The data acquisition system involves a tri-axial accelerometer in wireless sensor network environment. The wireless ad-hoc system has the advantage of small size, convenience for wearability and cost effectiveness. The system can further improve the range of user mobility with the inclusion of ad-hoc environment. The classification is based on the frequencies of the involved activities. The most significant Fast Fourier coefficients, of the acceleration of the body movement, are used for classification of the daily activities like, Rest walk and Run. A supervised learning approach is used. The work presents classification accuracy with the available fast batch training algorithms i.e. Levenberg-Marquardt and Resilient back propagation scheme is used for training and calculation of accuracy.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• The Journal of Korea Robotics Society
• /
• v.17 no.2
• /
• pp.133-141
• /
• 2022

This paper introduces model compression algorithms which make a deep neural network smaller and faster for embedded systems. The model compression algorithms can be largely categorized into pruning, quantization and knowledge distillation. In this study, gradual pruning, quantization aware training, and knowledge distillation which learns the activation boundary in the hidden layer of the teacher neural network are integrated. As a large deep neural network is compressed and accelerated by these algorithms, embedded computing boards can run the deep neural network much faster with less memory usage while preserving the reasonable accuracy. To evaluate the performance of the compressed neural networks, we evaluate the size, latency and accuracy of the deep neural network, DenseNet201, for image classification with CIFAR-10 dataset on the NVIDIA Jetson Xavier.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.2 s.16
• /
• pp.23-33
• /
• 2000

On this study, Among the classification methods of land cover using satellite imagery, we compared the classification accuracy of Neural Network Classifier and that of Maximum Likelihood Classifier which has the characteristics of parametric and non-parametric classification method. In the assessment of classification accuracy, we analyzed the classification accuracy about testing area as well as training area that many analysts use generally when assess the classification accuracy. As a result, Neural Network Classifier is superior to Maximum Likelihood Classifier as much as 3% in the classification of training data. When ground reference data is used, we could get poor result from both of classification methods, but we could reach conclusion that the classification result of Neural Network Classifier is superior to the classification result of Maximum Likelihood Classifier as much as 10%.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.23-29
• /
• 2020

This paper presents an approach for dynamic hand gesture recognition by using algorithm based on 3D Convolutional Neural Network (3D_CNN), which is later extended to 3D Residual Networks (3D_ResNet), and the neural network based key frame selection. Typically, 3D deep neural network is used to classify gestures from the input of image frames, randomly sampled from a video data. In this work, to improve the classification performance, we employ key frames which represent the overall video, as the input of the classification network. The key frames are extracted by SegNet instead of conventional clustering algorithms for video summarization (VSUMM) which require heavy computation. By using a deep neural network, key frame selection can be performed in a real-time system. Experiments are conducted using 3D convolutional kernels such as 3D_CNN, Inflated 3D_CNN (I3D) and 3D_ResNet for gesture classification. Our algorithm achieved up to 97.8% of classification accuracy on the Cambridge gesture dataset. The experimental results show that the proposed approach is efficient and outperforms existing methods.