• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1250-1257
• /
• 2020

The early detection of diseases is important in agriculture because diseases are major threats of reducing crop yield for farmers. The shape and color of plant leaf are changed differently according to the disease. So we can detect and estimate the disease by inspecting the visual feature in leaf. This study presents a vision-based leaf classification method for detecting the diseases of tomato crop. ResNet-50 model was used to extract the visual feature in leaf and classify the disease of tomato crop, since the model showed the higher accuracy than the other ResNet models with different depths. We propose a new ensemble approach using several DCNN classifiers that have the same structure but have been trained at different ranges in the DCNN layers. Experimental result achieved accuracy of 97.19% for PlantVillage dataset. It validates that the proposed method effectively classify the disease of tomato crop.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.278-287
• /
• 2019

Spatial information extraction is to retrieve static and dynamic aspects in natural language text by explicitly marking spatial elements and their relational words. This paper proposes a deep learning approach for spatial information extraction for Korean language using a two-step bidirectional LSTM-CRF ensemble model. The integrated model of spatial element extraction and spatial relation attribute extraction is proposed too. An experiment with the Korean SpaceBank demonstrates the better efficiency of the proposed deep learning model than that of the previous CRF model, also showing that the proposed ensemble model performed better than the single model.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.39-51
• /
• 2022

Image-based gender classification and age estimation of human are classic problems in computer vision. Most of researches in this field focus just only one task of either gender classification or age estimation and most of the reported methods for each task focus on accuracy performance and are not computationally light. Thus, running both tasks together simultaneously on low cost mobile or embedded systems with limited cpu processing speed and memory capacity are practically prohibited. In this paper, we propose a novel light-weight gender classification and age estimation method based on ensemble multitasking deep learning with light-weight processing neural network architecture, which processes both gender classification and age estimation simultaneously and in real-time even for embedded systems. Through experiments over various well-known datasets, it is shown that the proposed method performs comparably to the state-of-the-art gender classification and/or age estimation methods with respect to accuracy and runs fast enough (average 14fps) on a Jestson Nano embedded board.

• Journal of the Korean Institute of Gas
• /
• v.23 no.5
• /
• pp.52-58
• /
• 2019

In this study, we have developed a forecasting model for city- gas acceptance. City-gas corporations have to report about city-gas sale volume next year to KOGAS. So it is a important thing to them. Factors influenced city-gas have differences corresponding to usage classification, however, in city-gas acceptence, it is hard to classificate. So we have considered tha outside temperature as factor that influence regardless of usage classification and the model development was carried out. ARIMA, one of the traditional time series analysis, and LSTM, a deep running technique, were used to construct forecasting models, and various Ensemble techniques were used to minimize the disadvantages of these two methods.Experiments and validation were conducted using data from JB Corp. from 2008 to 2018 for 11 years.The average of the error rate of the daily forecast was 0.48% for Ensemble LSTM, the average of the error rate of the monthly forecast was 2.46% for Ensemble LSTM, And the absolute value of the error rate is 5.24% for Ensemble LSTM.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.9
• /
• pp.3243-3257
• /
• 2021

Deep neural networks provide excellent performance in pattern recognition, audio classification, and image recognition. It is important that they accurately recognize input data, particularly when they are used in autonomous vehicles or for medical services. In this study, we propose a data correction method for increasing the accuracy of an unknown classifier by modifying the input data without changing the classifier. This method modifies the input data slightly so that the unknown classifier will correctly recognize the input data. It is an ensemble method that has the characteristic of transferability to an unknown classifier by generating corrected data that are correctly recognized by several classifiers that are known in advance. We tested our method using MNIST and CIFAR-10 as experimental data. The experimental results exhibit that the accuracy of the unknown classifier is a 100% correct recognition rate owing to the data correction generated by the proposed method, which minimizes data distortion to maintain the data's recognizability by humans.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.1
• /
• pp.83-91
• /
• 2021

The increased turbidity in rivers during flood events has various effects on water environmental management, including drinking water supply systems. Thus, prediction of turbid water is essential for water environmental management. Recently, various advanced machine learning algorithms have been increasingly used in water environmental management. Ensemble machine learning algorithms such as random forest (RF) and gradient boosting decision tree (GBDT) are some of the most popular machine learning algorithms used for water environmental management, along with deep learning algorithms such as recurrent neural networks. In this study GBDT, an ensemble machine learning algorithm, and gated recurrent unit (GRU), a recurrent neural networks algorithm, are used for model development to predict turbidity in a river. The observation frequencies of input data used for the model were 2, 4, 8, 24, 48, 120 and 168 h. The root-mean-square error-observations standard deviation ratio (RSR) of GRU and GBDT ranges between 0.182~0.766 and 0.400~0.683, respectively. Both models show similar prediction accuracy with RSR of 0.682 for GRU and 0.683 for GBDT. The GRU shows better prediction accuracy when the observation frequency is relatively short (i.e., 2, 4, and 8 h) where GBDT shows better prediction accuracy when the observation frequency is relatively long (i.e. 48, 120, 160 h). The results suggest that the characteristics of input data should be considered to develop an appropriate model to predict turbidity.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.373-381
• /
• 2021

In this paper, we propose a classification model based on convolutional neural network(CNN) for predicting 2-year recurrence in non-small cell lung cancer(NSCLC) patients using preoperative chest CT images. Based on the region of interest(ROI) defined as the tumor internal and external area, the input images consist of an intratumoral patch, a peritumoral patch and a peritumoral texture patch focusing on the texture information of the peritumoral patch. Each patch is trained through AlexNet pretrained on ImageNet to explore the usefulness and performance of various patches. Additionally, ensemble learning of network trained with each patch analyzes the performance of different patch combination. Compared with all results, the ensemble model with intratumoral and peritumoral patches achieved the best performance (ACC=98.28%, Sensitivity=100%, NPV=100%).

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.641-651
• /
• 2023

Malicious hate speech and gender bias comments are common in online communities, causing social problems in our society. Gender bias and hate speech detection has been investigated. However, it is difficult because there are diverse ways to express them in words. To solve this problem, we attempted to detect malicious comments in a Korean hate speech dataset constructed in 2020. We explored bidirectional encoder representations from transformers (BERT)-based deep learning models utilizing hyperparameter tuning, data sampling, and logits ensembles with a label distribution. We evaluated our model in Kaggle competitions for gender bias, general bias, and hate speech detection. For gender bias detection, an F1-score of 0.7711 was achieved using an ensemble of the Soongsil-BERT and KcELECTRA models. The general bias task included the gender bias task, and the ensemble model achieved the best F1-score of 0.7166.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.4
• /
• pp.197-204
• /
• 2020

The ImageNet dataset is a large scale dataset and contains various natural scene images. In this paper, we propose a convolutional neural network (CNN)-based weighted ensemble technique for the ImageNet classification task. First, in order to fuse several models, our technique uses weights for each model, unlike the existing average-based ensemble technique. Then we propose an algorithm that automatically finds the coefficients used in later ensemble process. Our algorithm sequentially selects the model with the best performance of the validation set, and then obtains a weight that improves performance when combined with existing selected models. We applied the proposed algorithm to a total of 13 heterogeneous models, and as a result, 5 models were selected. These selected models were combined with weights, and we achieved 3.297% Top-5 error rate on the ImageNet test dataset.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.313-315
• /
• 2021

Timely and accurate diagnosis of lung diseases using Chest X-ray images has been gained much attention from the computer vision and medical imaging communities. Although previous studies have presented the capability of deep convolutional neural networks by achieving competitive binary classification results, their models were seemingly unreliable to effectively distinguish multiple disease groups using a large number of x-ray images. In this paper, we aim to build an advanced approach, so-called Ensemble Knowledge Distillation (EKD), to significantly boost the classification accuracies, compared to traditional KD methods by distilling knowledge from a cumbersome teacher model into an ensemble of lightweight student models with parallel branches trained with ground truth labels. Therefore, learning features at different branches of the student models could enable the network to learn diverse patterns and improve the qualify of final predictions through an ensemble learning solution. Although we observed that experiments on the well-established ChestX-ray14 dataset showed the classification improvements of traditional KD compared to the base transfer learning approach, the EKD performance would be expected to potentially enhance classification accuracy and model generalization, especially in situations of the imbalanced dataset and the interdependency of 14 weakly annotated thorax diseases.