• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.676-677
• /
• 2022

In this paper, we propose a new method based on a deep learning model with an optimized dynamic decay learning rate and improved model structure to achieve fast and accurate classification of fashion clothing images. Experiments are performed using the model proposed in the Fashion-MNIST dataset and compared with methods of CNN, LeNet, LSTM and BiLSTM.

• Journal of Advanced Information Technology and Convergence
• /
• v.8 no.2
• /
• pp.119-127
• /
• 2018

Training a very large deep neural network can be painfully slow and prone to overfitting. Many researches have done for overcoming the problem. In this paper, a combination of early stopping and ADAM based deep neural network was presented. This form of deep network is useful for handling the big data because it automatically stop the training before overfitting occurs. Also generalization ability is better than pure deep neural network model.

• Journal of Multimedia Information System
• /
• v.8 no.3
• /
• pp.175-182
• /
• 2021

Oral cancer is ranked second most diagnosed cancer among Indian population and ranked sixth all around the world. Oral cancer is one of the deadliest cancers with high mortality rate and very less 5-year survival rates even after treatment. It becomes necessary to detect oral malignancies as early as possible so that timely treatment may be given to patient and increase the survival chances. In recent years deep learning based frameworks have been proposed by many researchers that can detect malignancies from medical images. In this paper we have proposed a deep learning-based framework which detects oral cancer from histopathology images very efficiently. We have designed our model to split the color channels and extract deep features from these individual channels rather than single combined channel with the help of Efficient NET B3. These features from different channels are fused by using feature fusion module designed as a layer and placed before dense layers of Efficient NET. The experiments were performed on our own dataset collected from hospitals. We also performed experiments of BreakHis, and ICML datasets to evaluate our model. The results produced by our model are very good as compared to previously reported results.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.1
• /
• pp.23-30
• /
• 2019

As deep learning with the network-based algorithms evolve, artificial intelligence is rapidly growing around the world. Among them, finance is expected to be the field where artificial intelligence is most used, and many studies have been done recently. The existing financial strategy using deep-run is vulnerable to volatility because it focuses on stock price forecasts for a single stock. Therefore, this study proposes to construct ETF products constructed through portfolio methods by calculating the stocks constituting funds by using deep learning. We analyze the performance of the proposed model in the KOSPI 100 index. Experimental results showed that the proposed model showed improved results in terms of returns or volatility.

• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.777-783
• /
• 2022

Even though several deep learning-based methods have been applied in the field of acoustic source localization, the previous works have only been conducted using the two-dimensional representation of the beamforming maps, particularly with the planar array system. While the acoustic sources are more required to be localized in a spherical microphone array system considering that we live and hear in the 3D world, the conventional 2D equirectangular map of the spherical beamforming map is highly vulnerable to the distortion that occurs when the 3D map is projected to the 2D space. In this study, a 3D deep learning approach is proposed to fulfill accurate source localization via distortion-free 3D representation. A target function is first proposed to obtain 3D source distribution maps that can represent multiple sources' positional and strength information. While the proposed target map expands the source localization task into a point-wise prediction task, a PointNet-based deep neural network is developed to precisely estimate the multiple sources' positions and strength information. While the proposed model's localization performance is evaluated, it is shown that the proposed method can achieve improved localization results from both quantitative and qualitative perspectives.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.695-700
• /
• 2021

The Faster RCNN-based shellfish recognition algorithm is introduced for shellfish recognition studies that currently do not have any deep learning-based algorithms in a practical setting. The original feature extraction module is replaced by DenseNet, which fuses multi-level feature data and optimises the NMS algorithm, network depth and merging method; overcoming the omission of shellfish overlap, multiple shellfish and insufficient light, effectively solving the problem of low shellfish classification accuracy. In the complexifier test environment, the test accuracy was improved by nearly 4%. Higher testing accuracy was achieved compared to the original testing algorithm. This provides favourable technical support for future applications of the improved Faster RCNN approach to seafood quality classification.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.113-117
• /
• 2023

As sputter equipment becomes more complex, it becomes increasingly difficult to understand the parameters that affect the thickness uniformity of thin metal film deposited by sputter. To address this issue, we verified a deep learning model that can predict complex relationships. Specifically, we trained the model to predict the height of 36 magnets based on the thickness of the material, using Support Vector Machine (SVM), Multilayer Perceptron (MLP), 1D-Convolutional Neural Network (1D-CNN), and 2D-Convolutional Neural Network (2D-CNN) algorithms. After evaluating each model, we found that the MLP model exhibited the best performance, especially when the dataset was constructed regardless of the thin film material. In conclusion, our study suggests that it is possible to predict the sputter equipment source using film thickness data through a deep learning model, which makes it easier to understand the relationship between film thickness and sputter equipment.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.2854-2863
• /
• 2023

Objective: To present a hybrid approach that incorporates a constrained beam-hardening estimator (CBHE) and deep learning (DL)-based post-refinement for metal artifact reduction in dental cone-beam computed tomography (CBCT). Methods: Constrained beam-hardening estimator (CBHE) is derived from a polychromatic X-ray attenuation model with respect to X-ray transmission length, which calculates associated parameters numerically. Deep-learning-based post-refinement with an artifact disentanglement network (ADN) is performed to mitigate the remaining dark shading regions around a metal. Artifact disentanglement network (ADN) supports an unsupervised learning approach, in which no paired CBCT images are required. The network consists of an encoder that separates artifacts and content and a decoder for the content. Additionally, ADN with data normalization replaces metal regions with values from bone or soft tissue regions. Finally, the metal regions obtained from the CBHE are blended into reconstructed images. The proposed approach is systematically assessed using a dental phantom with two types of metal objects for qualitative and quantitative comparisons. Results: The proposed hybrid scheme provides improved image quality in areas surrounding the metal while preserving native structures. Conclusion: This study may significantly improve the detection of areas of interest in many dentomaxillofacial applications.

• Korea Trade Review
• /
• v.46 no.6
• /
• pp.191-209
• /
• 2021

In this paper, various time series analysis models and machine learning models are presented for long-term prediction of export growth rate, and the prediction performance is compared and reviewed by RMSE and MAE. Export growth rate is one of the major economic indicators to evaluate the economic status. And It is also used to predict economic forecast. The export growth rate may have a negative (-) value as well as a positive (+) value. Therefore, Instead of using the ReLU function, which is often used for time series prediction of deep learning models, the PReLU function, which can have a negative (-) value as an output value, was used as the activation function of deep learning models. The time series prediction performance of each model for three types of data was compared and reviewed. The forecast data of long-term prediction of export growth rate was deduced by three forecast methods such as a fixed forecast method, a recursive forecast method and a rolling forecast method. As a result of the forecast, the traditional time series analysis model, ARDL, showed excellent performance, but as the time period of learning data increases, the performance of machine learning models including LSTM was relatively improved.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.45-51
• /
• 2021

With the development of deep learning, semantic segmentation methods are being studied in various fields. There is a problem that segmenation accuracy drops in fields that require accuracy such as medical image analysis. In this paper, we improved PSPNet, which is a deep learning based segmentation method to minimized the loss of features during semantic segmentation. Conventional deep learning based segmentation methods result in lower resolution and loss of object features during feature extraction and compression. Due to these losses, the edge and the internal information of the object are lost, and there is a problem that the accuracy at the time of object segmentation is lowered. To solve these problems, we improved PSPNet, which is a semantic segmentation model. The multi-scale attention proposed to the conventional PSPNet was added to prevent feature loss of objects. The feature purification process was performed by applying the attention method to the conventional PPM module. By suppressing unnecessary feature information, eadg and texture information was improved. The proposed method trained on the Cityscapes dataset and use the segmentation index MIoU for quantitative evaluation. As a result of the experiment, the segmentation accuracy was improved by about 1.5% compared to the conventional PSPNet.