• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.51-62
• /
• 2021

Plant disease is one of the issues that can create losses in the production and economy of the agricultural sector. Early detection of this disease for finding solutions and treatments is still a challenge in the sustainable agriculture field. Currently, image processing techniques and machine learning methods have been applied to detect plant diseases successfully. However, the effectiveness of these methods still needs to be improved, especially in multiclass plant diseases classification. In this paper, a convolutional neural network with a batch normalization-based deep learning approach for classifying plant diseases is used to develop an automatic diagnostic assistance system for leaf diseases. The significance of using deep learning technology is to make the system be end-to-end, automatic, accurate, less expensive, and more convenient to detect plant diseases from their leaves. For evaluating the proposed model, an experiment is conducted on a public dataset contains 20654 images with 15 plant diseases. The experimental validation results on 20% of the dataset showed that the model is able to classify the 15 plant diseases labels with 96.4% testing accuracy and 0.168 testing loss. These results confirmed the applicability and effectiveness of the proposed model for the plant disease detection task.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.17-23
• /
• 2018

We proposed a LSTM-based RNN model that can effectively perform the automatic spacing characteristics. For those long or noisy sentences which are known to be difficult to handle within Neural Network Learning, we defined a proper input data format and decoding data format, and added dropout, bidirectional multi-layer LSTM, layer normalization, and attention mechanism to improve the performance. Despite of the fact that Sejong corpus contains some spacing errors, a noise-robust learning model developed in this study with no overfitting through a dropout method helped training and returned meaningful results of Korean word spacing and its patterns. The experimental results showed that the performance of LSTM sequence-to-sequence model is 0.94 in F1-measure, which is better than the rule-based deep-learning method of GRU-CRF.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.07a
• /
• pp.260-260
• /
• 2004

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12B
• /
• pp.2447-2454
• /
• 1999

This paper proposes a N-APPEM(Nonlinear A Posteriori Probability Estimation Method) with a frame normalization method to conventional classification network to increase speech recognition ability. It also tests the recognition ability of the classification and prediction neural networks for the Korean isolated digits. From the experimental results, the prediction network with MLP(Multi-Layer Perceptron) achieves the highest recognition ability of 98.0%. The prediction requires very complicated networks increased linearly with the number of incoming speech categories. However, the classification network with the N-APPEM and the normalization improves the recognition ability up to 85.5% with a sin81e network, which is almost 12.0% improvement.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.232-240
• /
• 2022

To fulfill user expectations, the rapid evolution of software techniques and approaches has necessitated reliable and flawless software operations. Aging prediction in the software under operation is becoming a basic and unavoidable requirement for ensuring the systems' availability, reliability, and operations. In this paper, an improved evolutionary computing-driven extreme learning scheme (ECD-ELM) has been suggested for object-oriented software aging prediction. To perform aging prediction, we employed a variety of metrics, including program size, McCube complexity metrics, Halstead metrics, runtime failure event metrics, and some unique aging-related metrics (ARM). In our suggested paradigm, extracting OOP software metrics is done after pre-processing, which includes outlier detection and normalization. This technique improved our proposed system's ability to deal with instances with unbalanced biases and metrics. Further, different dimensional reduction and feature selection algorithms such as principal component analysis (PCA), linear discriminant analysis (LDA), and T-Test analysis have been applied. We have suggested a single hidden layer multi-feed forward neural network (SL-MFNN) based ELM, where an adaptive genetic algorithm (AGA) has been applied to estimate the weight and bias parameters for ELM learning. Unlike the traditional neural networks model, the implementation of GA-based ELM with LDA feature selection has outperformed other aging prediction approaches in terms of prediction accuracy, precision, recall, and F-measure. The results affirm that the implementation of outlier detection, normalization of imbalanced metrics, LDA-based feature selection, and GA-based ELM can be the reliable solution for object-oriented software aging prediction.

• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.525-538
• /
• 2020

A practical animal face classification system that classifies animals in image and video data is considered as a pivotal topic in machine learning. In this research, we are proposing a novel method of fully connected dual Deep Convolutional Neural Network (DCNN), which extracts and analyzes image features on a large scale. With the inclusion of the state of the art Batch Normalization layer and Exponential Linear Unit (ELU) layer, our proposed DCNN has gained the capability of analyzing a large amount of dataset as well as extracting more features than before. For this research, we have built our dataset containing ten thousand animal faces of ten animal classes and a dual DCNN. The significance of our network is that it has four sets of convolutional functions that work laterally with each other. We used a relatively small amount of batch size and a large number of iteration to mitigate overfitting during the training session. We have also used image augmentation to vary the shapes of the training images for the better learning process. The results demonstrate that, with an accuracy rate of 92.0%, the proposed DCNN outruns its counterparts while causing less computing costs.

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.900-904
• /
• 1991

In this paper, our study for the recognition of Hand-written Korean characters, Arabic numbers and alphabets by neural netwoks. This System extracts feature of character by using the MESH feature point of handwritten character, Arabic numbers and alphabets. To reduce the input image data, features are extracted from each input images. A MLP(multi-layer perceptron) with one hidden layer was trained with a modified BEP(back error propagation) algorithm. This method extracts feature sets of the characters directly from the scanner and can enhance computation speed without using the special preprocesses such as size normalization, smoothing, and thinning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.423-430
• /
• 2013

Recently, the personal identification technologies using vein pattern of back of the hand, palm, and finger have been developed actively because it has the advantage that the vein blood vessel in the body is impossible to damage, make a replication and forge. However, it is difficult to extract clearly the vein region from captured vein images through common image prcessing based region segmentation method, because of the light scattering and non-uniform internal tissue by skin layer and inside layer skeleton, etc. Especially, it takes a long time for processing time and makes a discontinuity of blood vessel just in a image because it has non-uniform illumination due to use a locally different adaptive threshold for the binarization of acquired finger-vein image. To solve this problem, we propose illumination normalization based fast method for extracting the finger-vein region. The proposed method has advantages compared to the previous methods as follows. Firstly, for remove a non-uniform illumination of the captured vein image, we obtain a illumination component of the captured vein image by using a low-pass filter. Secondly, by extracting the finger-vein path using one time binarization of a single threshold selection, we were able to reduce the processing time. Through experimental results, we confirmed that the accuracy of extracting the finger-vein region was increased and the processing time was shortened than prior methods.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.1
• /
• pp.114-123
• /
• 2018

This paper concerns a design and learning method of softmax function neural networks based on K-means clustering. The partial discharge data Information is preliminarily processed through simulation using an Epoxy Mica Coupling sensor and an internal Phase Resolved Partial Discharge Analysis algorithm. The obtained information is processed according to the characteristics of the pattern using a Motor Insulation Monitoring System program. At this time, the processed data are total 4 types that void discharge, corona discharge, surface discharge and slot discharge. The partial discharge data with high dimensional input variables are secondarily processed by principal component analysis method and reduced with keeping the characteristics of pattern as low dimensional input variables. And therefore, the pattern classifier processing speed exhibits improved effects. In addition, in the process of extracting the partial discharge data through the MIMS program, the magnitude of amplitude is divided into the maximum value and the average value, and two pattern characteristics are set and compared and analyzed. In the first half of the proposed partial discharge pattern classifier, the input and hidden layers are classified by using the K-means clustering method and the output of the hidden layer is obtained. In the latter part, the cross entropy error function is used for parameter learning between the hidden layer and the output layer. The final output layer is output as a normalized probability value between 0 and 1 using the softmax function. The advantage of using the softmax function is that it allows access and application of multiple class problems and stochastic interpretation. First of all, there is an advantage that one output value affects the remaining output value and its accompanying learning is accelerated. Also, to solve the overfitting problem, L2-normalization is applied. To prove the superiority of the proposed pattern classifier, we compare and analyze the classification rate with conventional radial basis function neural networks.

• Knowledge Management Research
• /
• v.22 no.4
• /
• pp.27-40
• /
• 2021

Click-Through Rate (CTR) prediction is a key function that determines the ranking of candidate items in the recommendation system and recommends high-ranking items to reduce customer information overload and achieve profit maximization through sales promotion. The fields of natural language processing and image classification are achieving remarkable growth through the use of deep neural networks. Recently, a transformer model based on an attention mechanism, differentiated from the mainstream models in the fields of natural language processing and image classification, has been proposed to achieve state-of-the-art in this field. In this study, we present a method for improving the performance of a transformer model for CTR prediction. In order to analyze the effect of discrete and categorical CTR data characteristics different from natural language and image data on performance, experiments on embedding regularization and transformer normalization are performed. According to the experimental results, it was confirmed that the prediction performance of the transformer was significantly improved when the L2 generalization was applied in the embedding process for CTR data input processing and when batch normalization was applied instead of layer normalization, which is the default regularization method, to the transformer model.