• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.159-166
• /
• 2023

The COI gene is a sequence of approximately 650 bp at the 5' terminal of the mitochondrial Cytochrome c Oxidase subunit I (COI) gene. As an effective DeoxyriboNucleic Acid (DNA) barcode, it is widely used for the taxonomic identification and evolutionary analysis of species. We created a CNN-LSTM hybrid model by combining the gene features partially extracted by the Long Short-Term Memory ( LSTM ) network with the feature maps obtained by the CNN. Compared to K-Means Clustering, Support Vector Machines (SVM), and a single CNN classification model, after training 278 samples in a training set that included 15 genera from two orders, the CNN-LSTM hybrid model achieved 94% accuracy in the test set, which contained 118 samples. We augmented the training set samples and four genera into four orders, and the classification accuracy of the test set reached 100%. This study also proposes calculating the cosine similarity between the training and test sets to initially assess the reliability of the predicted results and discover new species.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.859-868
• /
• 2004

We propose a method of selecting initial training examples for active learning so that it can reach high accuracy faster with fewer further queries. Our method is based on the assumption that an active learner can reach higher performance when given an initial training set consisting of diverse and typical examples rather than similar and special ones. To obtain a good initial training set, we first cluster examples by using k-means clustering algorithm to find groups of similar examples. Then, a representative example, which is the closest example to the cluster's centroid, is selected from each cluster. After these representative examples are labeled by querying to the user for their categories, they can be used as initial training examples. We also suggest a method of using the centroids as initial training examples by labeling them with categories of corresponding representative examples. Experiments with various text data sets have shown that the active learner starting from the initial training set selected by our method reaches higher accuracy faster than that starting from randomly generated initial training set.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.705-712
• /
• 2013

Active learning aims to improve the performance of a classification model by repeating the process to select the most helpful unlabeled data and include it to the training set through labelling by expert. In this paper, we propose a method for active learning based on hierarchical agglomerative clustering using Ward's linkage. The proposed method is able to construct a training set actively so as to include at least one sample from each cluster and also to reflect the total data distribution by expanding the existing training set. While most of existing active learning methods assume that an initial training set is given, the proposed method is applicable in both cases when an initial training data is given or not given. Experimental results show the superiority of the proposed method.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.53-60
• /
• 2012

Nearest-neighbor classification predicts the class of an input data with the most frequent class among the near training data of the input data. Even though nearest-neighbor classification doesn't have a training stage, all of the training data are necessary in a predictive stage and the generalization performance depends on the quality of training data. Therefore, as the training data size increase, a nearest-neighbor classification requires the large amount of memory and the large computation time in prediction. In this paper, we propose a prototype selection algorithm that predicts the class of test data with the new set of prototypes which are near-boundary training data. Based on Tomek links and distance metric, the proposed algorithm selects boundary data and decides whether the selected data is added to the set of prototypes by considering classes and distance relationships. In the experiments, the number of prototypes is much smaller than the size of original training data and we takes advantages of storage reduction and fast prediction in a nearest-neighbor classification.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.57-58
• /
• 2022

Concrete mix design is used as essential data for the quality of concrete, analysis of structures, and stable use of sustainable structures. However, since most of the formulation design is established based on the experience of experts, there is a lack of data to base it on. are suffering Accordingly, in this study, the purpose of this study is to build a predictive model to use the concrete mixing factor as basic data for calculation using the DNN technique. As for the data set for DNN model learning, OPC and ternary concrete data were collected according to the presence or absence of admixture, respectively, and the model was separated for OPC and ternary concrete, and training was carried out. In addition, by varying the number of hidden layers of the DNN model, the prediction performance was evaluated according to the model structure. The higher the number of hidden layers in the model, the higher the predictive performance for the prediction of the mixing elements except for the compressive strength factor set as the output value, and the ternary concrete model showed higher performance than the OPC. This is expected because the data set used when training the model also affected the training.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.24 no.4
• /
• pp.362-370
• /
• 2004

In this work, the collapse moment due to wall-thinning defects is estimated by using fuzzy neural networks. The developed fuzzy neural networks have been applied to the numerical data obtained from the finite element analysis. Principal component analysis is used to preprocess the input signals into the fuzzy neural network to reduce the sensitivity to the input change and the fuzzy neural networks are trained by using the data set prepared for training (training data) and verified by using another data set different (independent) from the training data. Also, two fuzzy neural networks are trained for two data sets divided into the two classes of extrados and intrados defects, which is because they have different characteristics. The relative 2-sigma errors of the estimated collapse moment are 3.07% for the training data and 4.12% for the test data. It is known from this result that the fuzzy neural networks are sufficiently accurate to be used in the wall-thinning monitoring of elbows.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.3
• /
• pp.300-310
• /
• 2022

A vast amount of labeled data is required for deep neural network training. A typical strategy to improve the performance of a neural network given a training data set is to use data augmentation technique. The goal of this work is to offer a novel image augmentation method for improving object detection accuracy. An object in an image is removed, and a similar object from the training data set is placed in its area. An in-painting algorithm fills the space that is eliminated but not filled by a similar object. Our technique shows at most 2.32 percent improvements on mAP in our testing on a military vehicle dataset using the YOLOv4 object detector.

• Structural Engineering and Mechanics
• /
• v.74 no.4
• /
• pp.559-565
• /
• 2020

This paper intends to progress models to accurately estimate the behavior of fresh concrete under vibration using artificial neural networks (ANNs). To this end, behavior of a full scale precast concrete mold was investigated numerically. Experimental study was carried out under vibration with the use of a computer-based data acquisition system. In this study measurements were taken at three points using two vibrators. Transducers were used to measure time-dependent lateral displacements at these points on mold while both mold is empty and full of fresh concrete. Modeling of empty and full mold was made using ANNs. Benefiting ANNs used in this study for modeling fresh concrete, mold design can be performed. For the modeling of ANNs: Experimental data were divided randomly into two parts such as training set and testing set. Training set was used for ANN's learning stage. And the remaining part was used for testing the ANNs. Finally, ANN modeling was compared with measured data. The comparisons show that the experimental data and ANN results are compatible.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.157-165
• /
• 2020

Aiming at the development of neural network and self-driving data set, it is also an idea to improve the performance of network model to detect moving objects by dividing the data set. In Darknet network framework, the YOLOv4 (You Only Look Once v4) network model was used to train and test Udacity data set. According to 7 proportions of the Udacity data set, it was divided into three subsets including training set, validation set and test set. K-means++ algorithm was used to conduct dimensional clustering of object boxes in 7 groups. By adjusting the super parameters of YOLOv4 network for training, Optimal model parameters for 7 groups were obtained respectively. These model parameters were used to detect and compare 7 test sets respectively. The experimental results showed that YOLOv4 can effectively detect the large, medium and small moving objects represented by Truck, Car and Pedestrian in the Udacity data set. When the ratio of training set, validation set and test set is 7:1.5:1.5, the optimal model parameters of the YOLOv4 have highest detection performance. The values show mAP50 reaching 80.89%, mAP75 reaching 47.08%, and the detection speed reaching 10.56 FPS.

• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.14-20
• /
• 2018

The purpose of training a convolutional neural network (CNN) is to obtain weight factors that give high classification accuracies. The initial values of hyper-parameters affect the training results, and it is important to train a CNN with a suitable hyper-parameter set of a learning rate, a batch size, the initialization of weight factors, and an optimizer. We investigate the effects of a single hyper-parameter while others are fixed in order to obtain a hyper-parameter set that gives higher classification accuracies and requires shorter training time using a proposed VGG-like CNN for training since the VGG is widely used. The CNN is trained for four datasets of CIFAR10, CIFAR100, GTSRB and DSDL-DB. The effects of the normalization and the data transformation for datasets are also investigated, and a training scheme using merged datasets is proposed.